Mineral identification is an important part of geological analysis. Traditional identification methods rely on either the experiences of the appraisers or the various measuring instruments and the methods are either easily influenced by the experiences or need too much work. To solve the above problems, there have been studies using image recognition and intelligent algorithms to identify minerals. But the current studies can not identify many minerals, and the accuracy is low. To increase the number of identified mineral categories and the accuracy, we proposed the method that uses both the mineral images and the Mohs hardness in the deep neural networks to identify the minerals. The experimental results showed that the method can reach 94.0% Top-1 accuracy and 99.9% Top-5 accuracy for 28 common minerals. The model that combines image and Mohs hardness together can identify more minerals and increase the accuracy using less training data.

Landslides impact on human activities and socio-economic development especially in mountainous areas. This study focuses on the comparison of the prediction capability of advanced machine learning techniques for rainfall-induced shallow landslide susceptibility of Deokjeokri catchment and Karisanri catchment in South Korea. The influencing factors for landslides i.e. topographic, hydrologic, soil, forest, and geologic factors are prepared from various sources based on availability and a multicollinearity test is also performed to select relevant causative factors. The landslide inventory maps of both catchments are obtained from historical information, aerial photographs and performing field survey. In this study, Deokjeokri catchment is considered as a training area and Karisanri catchment as a testing area. The landslide inventories content 748 landslide points in training and 219 points in testing areas. Three landslide susceptibility maps using machine learning models i.e. Random Forest (RF), Extreme Gradient Boosting (XGBoost) and Deep Neural Network (DNN) are prepared and compared. The outcomes of the analyses are validated using the landslide inventory data. A receiver operating characteristic curve (ROC) method is used to verify the results of the models. The results of this study show that the training accuracy of RF is 0.757 and the testing accuracy is 0.74. Similarly, training accuracy of XGBoost is 0.756 and testing accuracy is 0.703. The prediction of DNN revealed acceptable agreement between susceptibility map and the existing landslides with training and testing accuracy of 0.855 and 0.802, respectively. The results showed that, the DNN model achieved lower prediction error and higher accuracy results than other models for shallow landslide modeling in the study area

Hydrogen is useful as a fuel and could be produced by a variety of means. One approach uses artificial photosynthesis where energy from sunlight powers the splitting of water into hydrogen and oxygen. But, biological methods for producing hydrogen has emerged strongly over the past decades. In particular, specific microorganisms could use different substrates to produce hydrogen at differing yields. Such fundamental discoveries with industrial applications thus motivated the use of metabolic engineering approaches and methodologies in enhancing biological hydrogen production through a series of enzyme over-expression, pathway debottlenecking, and gene deletion. However, such approaches heavily rely on the selection of an appropriate microbial chassis for biohydrogen production. With the proper strain in hand, use of alternative substrates may engender greater hydrogen productivities. But learning from the bioprocessing field, co-culture of two compatible microorganisms have been sought after for improving biohydrogen production. In addition, thermophilic microbes may also be useful candidates for exploiting hydrogen production from composting. Future outlook in the field looks into filling our gaps in understanding of the metabolic network that feeds into hydrogen production in different organisms. But, more importantly, problems such as reduced growth rate in engineered microbes point to fundamental issues with using genetically engineered microorganisms for improved biohydrogen production, to which clever bioprocess engineering may yield solutions.

Online transactions are becoming more popular in present situation where the globe is facing an unknown disease COVID-19. Now authorities of Countries requested peoples to use cashless transaction as far as possible. Practically it is not always possible to use it in all transactions. Since number of such cashless transactions have been increasing during lockdown period due to COVID-19, fraudulent transactions are also increasing in a rapid way. Fraud can be analysed by viewing a series of customer transactions data that was done in his/her previous transactions. Normally banks or other transaction authorities warned their customers about the transaction If any deviation is noticed by them from available patterns. These authorities think that it is possibly of fraudulent transaction. For detection of fraud during COVID-19, banks and credit card companies are applying various methods such as data mining , decision tree, rule based mining, neural network, fuzzy clustering approach and machine learning methods. These approaches is try to find out normal usage pattern of customers based on their past activities. The objective of this paper is to find out such fraud transactions during such unmanageable situation.Digital payment schemes are often threatened by fraudulent activities. Detecting fraud transaction in during money transfer may save customers from financial loss. Mobile based money transactions are focused in this paper for fraud detection. A Deep Learning (DL) framework is suggested in this paper that monitors and detects fraudulent activities. Implementing and applying recurrent neural network on PaySim generated synthetic financial dataset, deceptive transactions are identified. The proposed method is capable to detect deceptive transactions with an accuracy of 99.87%, F1-Score of 0.99 and MSE of 0.01.

We study a minimal model of the stress-driven p53 regulatory network that includes competition between active and mutant forms of the tumor-suppressor gene p53. Depending on the nature of the external stress signal, four distinct dynamical states are observed. These states can be distinguished by dierent dynamical properties and correspond to active, apoptotic, pre-malignant and cancer states. Transitions between any two of these states are found to be unidirectional and irreversible if the stress signal is either oscillatory or constant. When the signal decays exponentially, the apoptotic state vanishes, and for low stress the pre-malignant state is bounded by two critical points, allowing the system to transition reversibly from the active to the pre-malignant state. For signicantly large stress, the range of the pre-malignant state expands and the system moves to the cancerous state which is a stable attractor. This suggests that identification of the pre-malignant state may be important both for therapeutic intervention as well as for drug discovery.

HTTP/2 video streaming has caught a lot of attentions in the development of multimedia technologies over the last few years. In HTTP/2, the server push mechanism allows the server to deliver more video segments to the client within a single request in order to deal with the requests explosion problem. As a result, recent research efforts have been focusing on utilizing such a feature to enhance the streaming experience while reducing the request-related overhead. However, current works only optimize the performance of a single client, without necessary concerns of possible influences on other clients in the same network. When multiple streaming clients compete for a shared bandwidth in HTTP/1.1, they are likely to suffer from unfairness, which is defined as the inequality in their bitrate selections. For HTTP/1.1, existing works have proven that the network-assisted solutions are effective in solving the unfairness problem. However, the feasibility of utilizing such an approach for the HTTP/2 server push has not been investigated. Therefore, in this paper, a novel proxy-based framework is proposed to overcome the unfairness problem in adaptive streaming over HTTP/2 with the server push. Experimental results confirm the outperformance of the proposed framework in ensuring the fairness, assisting the clients to avoid rebuffering events and lower bitrate degradation amplitude, while maintaining the mechanism of the server push feature.

Ebolavirus has a membrane envelope decorated by trimers of a glycoprotein (GP), which is responsible for host cell attachment and membrane fusion. Therefore, GP is a primary target for antiviral drugs development. Here, this article reports the first, to my knowledge, set of structural analysis of all Ebolavirus GP structures as of March 10, 2020, and also a brief update of the structurally identified electrostatic features of the Ebolavirus GP structures in both apo (unliganded) state and also in bound states with a series of small compounds, including a variety of approved drugs. With this comprehensive set of structural analysis, this article puts forward a hypothesis of two Achilles' heels of Ebolavirus GP structure, where the formation of two interfacial salt bridges, instead of destabilizing the prefusion conformation of Ebolavirus GP, constitutes a positive contribution towards the structural rigidification of the prefusion conformation of the Ebolavirus GP structure, thereby acting against GP-mediated Ebolavirus cell entry and/or preventing fusion between the viral and endosome membranes.

Modern energy systems collect high volumes of data that can provide valuable information about energy consumption. Electric companies can now use historical data to make informed decisions on energy production by forecasting the expected demand. Many deep learning models have been proposed to deal with these type of time series forecasting problems. Deep neural networks, such as recurrent or convolutional, can automatically capture complex patterns in time series data and provide accurate predictions. In particular, Temporal Convolutional Networks (TCN) are a specialised architecture that has advantages over recurrent networks for forecasting tasks. TCNs are able to extract long-term patterns using dilated causal convolutions and residual blocks, and can also be more efficient in terms of computation time. In this work, we propose a TCN-based deep learning model to improve the predictive performance in energy demand forecasting. Two energy-related time series with data from Spain have been studied: the national electric demand, and the power demand at charging stations for electric vehicles. An extensive experimental study has been conducted, involving more than 1900 models with different architectures and parametrisations. The TCN proposal outperforms the forecasting accuracy of Long Short-Term Memory (LSTM) recurrent networks, which are considered the state-of-the-art in the field.

Over the past 150 million years, the hyperarid core of the Atacama Desert has been transformed by geologic and atmospheric conditions into one of the most unique and inhospitable landscapes on the planet. This makes it an ideal Mars analog that has been explored for decades as preliminary studies on the space life discovery. However, two heavy rainfalls that occurred in the Atacama in 2015 and 2017 provide a unique opportunity to study the response of resident extremophiles to rapid environmental change associated with excessive water and salt shock. Here we combine geochemical analyses with molecular biology to study the variations in salts and microbial communities along an aridity gradient, and to examine the reshuffling of hyperarid microbiomes before and after the two rainfall events. Analysis of microbial community composition revealed that soils within the southern desert were consistently dominated by Actinobacteria, Proteobacteria, Acidobacteria, Planctomycetes, Chloroflexi, Bacteroidetes, Gemmatimonadetes, and Verrucomicrobia; soils within the hyperarid sites were dominated by Aquificae and Deinococcus-Thermus before heavy rainfalls, while these organisms almost totally diminished after rainfall, and the hyperarid microbial consortia and metabolisms transformed to a more southern desert pattern along with increased biodiversity. Salts at the shallow subsurface were dissolved and leached down to a deeper layer, both benefitting and challenging indigenous microorganisms with the excessive input of water and ions. Microbial viability was found to change with aridity and rainfall events but correlated with elevation, pH, conductivity, chloride, nitrate, sulfate, and soil organic matters (SOM). Metagenomic functional pathways related to stressor responses also increased in post-rainfall hyperarid soils. Our findings contribute to the primary goal of Atacama Mars analog research for understanding the microbial community structure and adaptations: this study sheds light on the structure of xerophilic, halophilic, and radioresistant microbiomes in hyperarid environments, and their response to changes in water availability.

Landslides are a frequent and recurrent problem in hilly regions of India and predicting them is always a challenging task. In this paper, an attempt was made to deal with this problem using advanced physical and numerical modeling methods. Detailed understanding of the initial slope failures is very interesting, and challenging at the same time, in the design and development of wireless sensor network based on early warning of landslide monitoring. A small scale physical model was developed to assess the instability through a sensor network with variable rain fall intensity. This was achieved by increasing the simulated rain water flow intensity in different time spans (dry condition, at t=0 to t= 30 min, 0.5 mm/min at t=30 to t= 60 min, 0.75 mm/min at t=60 to t=91 min and 1 mm/min at t=91 to t= 120 min). The water level and movement in the slope was recorded by rainfall sensor, vibration sensor, soil moisture sensor and a digital camera. The following changes were observed during the slope failure: a) movement of small particles at top of the slope; b) initial failure of medium size soil particle; c) scouring of soil mass; d) whole slope collapse. The obtained results clearly indicated the superiority and effectiveness of the proposed system in providing a factor of safety for the progressive slope.

Wi-Fi tethering using a mobile device (e.g., a smartphone or a tablet) as a hotspot for other devices has become a common practice. Despite the potential benefits of Wi-Fi tethering, the open source nature of mobile operating systems (e.g., Google Android) can be abused by a selfish device to manipulate channel-access parameters to gain an unfair advantage in throughput performance. This can cause serious performance problems within a well-planned Wi-Fi network due to an unauthorized selfish or misconfigured tethering device interfering with nearby well-planned access points (APs). In this paper, we demonstrate that the selfish behavior of a tethering node that adjusts the clear channel assessment (CCA) threshold has strong adverse effects in a multi-AP network, while providing the selfish node a high throughput gain. To mitigate this problem, we present a passive online detection scheme that identifies the network condition and detects selfish tethering nodes with high accuracy by exploiting the packet loss information of on-going transmissions. To the best of our knowledge, this is the first research to consider the problem of detecting a selfish tethering node in managed Wi-Fi networks.

Extensive experimental and theoretical research over the past several decades has culminated in the understanding of the mechanisms behind nanoparticle-mediated enhancements on the mechanical properties of hydrogels. This information is not only crucial to realizing applications that directly benefit from developing hydrogels with high mechanical strength, but also to guide the development of strategies to further enhance hydrogel properties by combining different approaches. In our study, we investigated the effect of combining two approaches – addition of nanoparticles and crosslinking two different polymers (to create double-network hydrogels) – on the mechanical properties of hydrogels. Our studies revealed that these approaches may be combined to synthesize hydrogel composites with enhanced properties; however, both polymers in the double-network hydrogel must strongly interact with the nanoparticles to fully benefit from the addition of nanoparticles. Moreover, the concentration of hydrogel monomers used for the preparation of the double-network hydrogels had a significant effect on the extent of nanoparticle-mediated enhancements; double-network hydrogel nanocomposites prepared using lower monomer concentrations showed higher enhancements in elastic moduli compared to those prepared using high monomer concentrations. Collectively, these results demonstrate that the hypotheses previously developed to understand the role of nanoparticles on the mechanical properties of hydrogel nanocomposites may be extended to double-network hydrogel systems and guide the development of next generation hydrogels with extraordinary mechanical properties through a combination of orthogonal approaches.

Pedestrian detection is the core of driver assistance system, which collects the road conditions through the radars or cameras on the vehicle, judges whether there is a pedestrian in front of the vehicle, supports decisions such as raising the alarm, automatically slowing down or emergency stopping to keep pedestrians safe, and improves the security when the vehicle is moving. Suffered from weather, lighting, clothing, large pose variations and occlusion, the current pedestrian detection still has a certain distance from the practical applications. In recent years, deep networks have shown excellent performance for image detection, recognition and classification. Some researchers employed deep network for pedestrian detection and achieve great progress, but deep networks need huge computational resources which make it difficult to put into practical applications. In real scenarios of autonomous vehicle, the computation ability is limited. Thus, the shallow networks such as UDN (Unified Deep Networks) is a better choice since it performs well on consuming less computation resources. Base on UDN, this paper proposes a new deep network model named as two-stream UDN, which augments another branch for solving traditional UDN’s indistinction of the difference between trees / telegraph poles and pedestrians. The new branch accepts the upper third part of the pedestrian image as input, and the partial image has less deformation, stable features and more distinguished characters from other objects. For the proposed two-stream UDN, multi-input features including HOG feature, Sobel feature, color feature and foreground regions extracted by GrabCut segmentation algorithms are fed. Compared with the original input of UDN, the multi-input features are more conducive for pedestrian detection since the fused HOG features and significant objects are more significant for pedestrian detection. Two-stream UDN is trained through two steps: First, the two sub-networks are trained until converge; then we fuse results of the two subnets as the final result and feed it back to the two subnets to fine tune network parameters synchronously. To improve the performance, Softplus is adopted as activation function to obtain faster training speed, and positive samples are mirrored and rotated with small angle to make positive and negative samples more balanced.

In this paper, the fixed-time stabilization problem for a class of uncertain chained system is addressed by using a novel nonsingular recursive terminal sliding mode control approach. A fixed-time controller and an adaptive law are designed to guarantee the uncertain chained form system both Lyapunov stable and fixed-time convergent within the settling time. The advantage of the controller based on the sliding mode is that the settling time does not depend on the system initial state. Furthermore, we use RBF neural network to estimate the uncertainty of the system. Finally, the simulation results demonstrate the performance of the control laws.

Nowadays industrial dryers are used instead of traditional methods for drying. In designing dryers suitable for controlling the process of drying and reaching a high quality product, it is necessary to predict the instantaneous moisture loss during drying. For this purpose, ten mathematical-experimental models with a neural network model based on the kinetic data of pistachio drying are studied. The data obtained from the cabinet dryer will be evaluated at four temperatures of inlet air and different air velocities. The pistachio seeds will be placed in a thin layer on an aluminum sheet on a drying tray and weighed by a scale attached to the computer at different times. In the neural network, data are divided into three parts: educational (60%), validation (20%) and test (20%). Finally, the best mathematical-experimental model using genetic algorithm and the best neural network structure for predicting instantaneous moisture are selected based on the least squared error and the highest correlation coefficient.

In this effort we propose a data-driven learning framework for reduced order modeling of fluid dynamics. Designing accurate and efficient reduced order models for nonlinear fluid dynamic problems is challenging for many practical engineering applications. Classical projection-based model reduction methods generate reduced systems by projecting full-order differential operators into low-dimensional subspaces. However, these techniques usually lead to severe instabilities in the presence of highly nonlinear dynamics, which dramatically deteriorates the accuracy of the reduced-order models. In contrast, our new framework exploits linear multistep networks, based on implicit Adams-Moulton schemes, to construct the reduced system. The advantage is that the method optimally approximates the full order model in the low-dimensional space with a given supervised learning task. Moreover, our approach is non-intrusive, such that it can be applied to other complex nonlinear dynamical systems with sophisticated legacy codes. We demonstrate the performance of our method through the numerical simulation of a two-dimensional flow past a circular cylinder with Reynolds number Re = 100. The results reveal that the new data-driven model is significantly more accurate than standard projection-based approaches

This research describes numerical methods to analyze the absolute transport demand of cyclists and then to quantify the road network weaknesses of a city with the aim to identify infrastructure improvements in favor of cyclists. The methods are based on a combination of bicycle counts and map-matched GPS traces and are demonstrated with the city of Bologna, Italy: the dataset is based on approximately 27,500 GPS traces from cyclists, recorded over a period of one month on a volunteer basis using a smartphone application. A first method estimates absolute, city-wide bicycle flows, by scaling map-matched bicycle flows of the entire network to manual and instrumental bicycle counts of the main bikeways of the city. As there is a good correlation between the two sources of flow data, the absolute bike-flows on the entire network have been correctly estimated. A second method describes a novel link-deviation index, which quantifies for each network edge the total deviation generated for cyclists in terms of extra distances traveled with respect to the shortest possible route. The deviations are accepted by cyclists either to avoid unpleasant road attributes along the shortest route or to experience more favorable road attributes along the chosen route. The link deviation index indicates the planner which road links are contributing most to the total deviation of all cyclists – in this way, repelling and attracting road attributes for cyclists can be identified. This is why the deviation index is of practical help to prioritize bike infrastructure construction on individual road network links.

Cloud infrastructure provides computing services where computing resources can be adjusted on-demand. However, the adoption of cloud infrastructures brings concerns like reliance on the service provider network, reliability, compliance for service level agreements (SLAs), etc. Software-defined networking (SDN) is a networking concept that suggests the segregation of a network’s data plane from the control plane. This concept improves networking behavior. In this paper, we present an SDN-enabled resource-aware topology framework. The proposed framework employs SLA compliance, Path Computation Element (PCE) and shares fair loading to achieve better topology features. We also present an evaluation, showcasing the potential of our framework.

In this paper, the physical station of space network was extended in time dimension by combining the train diagram information and station technical operation standard time. At the same time, the topology of railway space-time network which considered the secondary operation process of train was constructed and an improved A* algorithm based on car flow routing was proposed to generate feasible path sets. On this basis, a dynamic car flow organization optimization model was built to simulate the railway car flow organization process under abnormal conditions, and the results of solving the model could be used to obtain the real-time quantity of cars at each station.This paper can identify the dynamic bottleneck by comparing the real-time quantity of cars with the maximum quantity of cars at the station. Finally, the feasibility of this method was analyzed and verified by a case.

Indoor scene recognition has great significance for intelligent applications such as mobile robots, location-based services (LBS) and so on. Wherever we are or whatever we do, we are under a specific scene. The human brain can easily discern a scene with a quick glance. However, for a machine to achieve this purpose, on one hand, it often requires plenty of well-annotated data which is time-consuming and labor-intensive. On the other hand, it is hard to learn effective visual representations due to large intra-category variation and inter-categories similarity of indoor scenes. To solve these problems, in this paper, we adopted an unsupervised visual representation learning method which can learn from unlabeled data with a Siamese Convolutional Neural Network (Siamese ConvNet) and graph-based constraints. Specifically, we first mined relationships between unlabeled samples with a graph structure. And then, these relationships can be used as supervision for representation learning with a Siamese network. In this method, firstly, a k-NN graph would be constructed by taking each image as a node in the graph and its k nearest neighbors are linked to form the edges. Then, with this graph, cycle consistency and geodesic distance would be considered as criteria for positive and negative pairs mining respectively. In other words, by detecting cycles in the graph, images with large differences but in the same cycle can be considered as same category (positive pairs). By computing geodesic distance instead of Euclidean distance from one node to another, two nodes with large geodesic distance can be regarded as in different categories (negative pairs). After that, visual representations of indoor scenes can be learned by a Siamese network in an unsupervised manner with the mined pairs as inputs. In order to evaluate the proposed method, we tested it on two scene-centric datasets, MIT67 and Places365. Experiments with different number of categories have been conducted to excavate the potential of proposed method. The results demonstrated that semantic visual representations for indoor scenes can be learned in this unsupervised manner. In addition, with the learned visual representations, indoor scene recognition models trained with the learned representations and a few of labeled samples can achieve competitive performance compared to the state-of-the-art approaches.

This paper presents a novel approach for semantic segmentation of building roof in dense urban environment with Deep Convolution Neural Network (DCNN) using imagery acquired by a Chinese Very High Resolution (VHR) satellite mission, i.e. GaoFen-2 (GF-2). To provide an operational end-to-end work flow for accurate build roof mapping with feature extraction as well as image segmentation, a fully convolutional DCNN with both convolutional and deconvolutional layers is designed to perform the VHR image analysis for labeling pixels. Since the diverse urban patterns and building styles in large areas, sample image data sets of building roof and non-building roof are collected over different metropolitan regions in China. We selected typical cities with dense urban environment in each metropolitan region as study areas for collecting training and test samples. High performance cluster with GPU-mounted workstations is employed to perform the model training and optimization. With the building roof samples collected over different cities, the predictive model with multiple NN layers is developed for building roof labeling. The validation of the building roof map shows that the overall accuracy(OA) and the mean Intersection Over Union( mIOU) of DCNN based segmentation are 94.67%, 0.85 respectively, while CRF-refined segmentation achieved OA of 94.69% and mIOU of 0.83. The results suggest that the proposed approach is a promising solution for building roof mapping with VHR images over large areas across different urban and building patterns. With the operational acquisition of GF2 VHR imagery, it is expected to develop an automated pipeline for operational built-up area monitoring and timely update of building roof map over large areas.

Spatial data conflation plays a fundamental role in in many aspects of modern Geographic Information Systems (GIS) research and development such as geospatial data visualization, incremental updating of databases and disaster evaluation. The primary objective of conflation is to derive valuable information based on the comparison of multiple spatial data sources of homogeneous or heterogeneous nature. This paper reviews the state of art of the concept of conflation, feature matching, the most important progresses of conflation between image and road network data, and the complexity of spatial conflation.

In this paper analyses the characteristic of EM waves propagation in structured environment to identify the signal interference by the structure, and suggests the EM waves attenuation model considering the distance and penetration loss by the structure. The range sensor based on electromagnetic(EM) waves attenuation along to the distance showed the precise distance estimation with high resolution depending on the distance. However, it is hard to use in structured environments due to the lack of consideration of the EM waves attenuation characteristics in the structured underwater environment. In this paper, EM waves propagation characteristic and signal interference effects by the structures were analyzed, and the EM waves distance-attenuation model in structured environment was suggested with sensor installation guideline. The EM waves propagation characteristics and proposed sensor model were verified by the several experiments, and the localization result in structured environment showed the more reliable performance.

Contrary to optical images, Synthetic Aperture Radar (SAR) images are in different electromagnetic spectrum where the human visual system is not accustomed to. Thus, with more and more SAR applications, the demand for enhanced high-quality SAR images has increased considerably. However, high-quality SAR images entail high costs due to the limitations of current SAR devices and their image processing resources. To improve the quality of SAR images and to reduce the costs of their generation, we propose a Dialectical Generative Adversarial Network (Dialectical GAN) to generate high-quality SAR images. This method is based on the analysis of hierarchical SAR information and the “dialectical” structure of GAN frameworks. As a demonstration, a typical example will be shown where a low-resolution SAR image (e.g., a Sentinel-1 image) with large ground coverage is translated into a high-resolution SAR image (e.g., a TerraSAR-X image). Three traditional algorithms are compared, and a new algorithm is proposed based on a network framework by combining conditional WGAN-GP (Wasserstein Generative Adversarial Network - Gradient Penalty) loss functions and Spatial Gram matrices under the rule of dialectics. Experimental results show that the SAR image translation works very well when we compare the results of our proposed method with the selected traditional methods.

Logistics Engineering has transcended over the decades into an approach for competitive benefits in organisational performance and logistics efficiency. Most industries are recognising that significant savings are available to companies that are able to ordinate and improve within their logistics operations. Companies today face great challenges because the successful supply of many products and services needs to the effective integration of logistics activities across a prolongation supply chain and an increasing geographical separation. Moreover, logistics integration approach involves both internal integration for an ordinated, unified process as well as relationships to react flexibly, changeability, and responsibility to customer's demands. In this study, by using of Fuzzy Vikor (F-Vikor), the best combination of RIR was selected and RIR Locating was done. The main aim of this paper is survey and design of the integrated operational logistics network (IOLN) and also, a proposed IOLN to integration of the Iran Khodro Co Supply Network.

Data generation using high throughput technologies has led to the accumulation of diverse types of molecular data.These data have different types (discrete,real,string etc.) and occur in various formats and sizes. Datasets including gene expression, miRNA expression, protein-DNA binding data (ChIP-Seq/ChIP-ChIP), mutation data(copy number variation, single nucleotide polymorphisms), GO annotations, protein-protein interaction and disease-gene association data are some of the commonly used genomic datasets to study biological processes. Each of them provides a unique, complementary and partly independent view of the genome and hence embed essential information about their regulatory mechanisms. In order to understand the functions of genes, proteins and analyze mechanisms arising out of their interactions, information provided by each of these datasets individually may not be sufficient. Therefore integrating these multi-omic data and inferring regulatory interactions from the integrated dataset provides a system level biological insights in predicting gene functions and their phenotypic outcomes. To study genome functionality through interaction networks, different methods have been proposed for collective mining of information from an integrated dataset. We survey here data integration approaches using state-of-the-art techniques such as network integration, Bayesian networks, regularized regression (LASSO) and multiple kernel learning methods.

Visual question answering (VQA) is receiving increasing attention from researchers in both the computer vision and natural language processing fields. There are two key components in the VQA task: feature extraction and multi-modal fusion. For feature extraction, we introduce a novel co-attention scheme by combining Sentence-guide Word Attention (SWA) and Question-guide Image Attention (QIA) in a unified framework. To be specific, the textual attention SWA relies on the semantics of the whole question sentence to calculate contributions of different question words for text representation. For the multi-modal fusion, we propose a “Cross-modal Multistep Fusion (CMF)” network to generate multistep features and achieve multiple interactions for two modalities, rather than focusing on modeling complex interactions between two modals like most current feature fusion methods. To avoid the linear increase of the computational cost, we share the parameters for each step in the CMF. Extensive experiments demonstrate that the proposed method can achieve competitive or better performance than the state-of-the-art.

Fuel gas network (FGN) synthesis is a systematic method for reducing fresh fuel consumption in a chemical plant. In this work, we address the synthesis of fuel gas network using block superstructure originally proposed for process design and intensification (Demirel et.al. [1]). Instead of a classical source-pool-sink superstructure, we consider a superstructure with multiple feed and product streams. These blocks interact with each other through direct flows that connect a block with its adjacent blocks and through jump flows that connect a block with all blocks. The blocks with feed streams are viewed as fuel sources and the blocks with product streams are regarded as fuel sinks. Addition blocks can be added as pools when there exists intermediate operations among 9 source blocks and sink blocks. These blocks can be arranged in a I × J two-dimensional grid with I = 1 for problems without pools, or I = 2 for problems with pools. J is determined by the maximum number of pools/sinks. With this representation, we formulate fuel gas network synthesis problem as a mixed-integer nonlinear (MINLP) problem to optimally design a fuel gas network with minimal total annul cost. We present a real-life case study from LNG plant to demonstrate the capability of the proposed approach.

Autonomous electronic area, territory, or space protection is getting more important. One of the areas of application of the system is to monitor the quarantine zones created during epidemics. The idea to create a system of mobile sensory units for defending quarantine zones was born during one of the phases of the Covid epidemic in 2020. The paper contains a brief technical description of a mobile sensor units and their network. This network surrounds an area of interest. The work includes a mathematical and data model of the protected area. In addition, the paper presents a method for distributing mobile sensor units in areas of interest.

Peptide-based drugs are promising anticancer candidates due to their biocompatibility, and low toxicity. Particularly, tumor homing peptides (THPs) have the ability to bind specifically to can-cer cells receptors and tumor vasculature. Despite their potential to develop antitumor drugs, there are few available prediction tools to assist the discovery of new THPs. Two webservers based on machine learning models are currently active, the TumorHPD (https://webs.iiitd.edu.in/raghava/tumorhpd) and the THPep (http://codes.bio/thpep), and more recently the SCMTHP (SCMTHP (pmlabstack.pythonanywhere.com), based on scoring card method. Herein, a novel method based on network science and similarity searching implemented in the starPep toolbox (http://mobiosd-hub.com/starpep/) is presented for THPs discovery. The approach leverages from exploring the structural space of THPs with Chemical Space Networks (CSNs) and from applying centrality measures to identify the most relevant and non-redundant THPs sequences within the CSN. Such THPs were considered as queries (Qs) for multi-query similarity searches that applies a group fusion (MAX-SIM rule) model. The resulting multi-query similarity searching models (SSMs) were validated with three benchmarking datasets of THPs/non-THPs. Predictions achieved accuracies ranged from 92.64 to 99.18% and Matthews Correlation Coefficients between 0.894-0.98, outperforming state-of-the-art predictors. The best model was applied to repurpose AMPs from the starPep database as THPs, which were subse-quently optimized for the TH activity. Finally, 54 promising THP leads were discovered, and their sequences were analyzed to encounter novel motifs. These results demonstrate the potential of CSNs and multi-query similarity searching for a rapid and accurate identification of THPs.

An effective process monitoring strategy is a requirement for meeting the challenges posed by increasingly complex products and manufacturing processes. To address these needs, this study investigates a comprehensive scheme based on classical machine learning methods, deep learning algorithms, and feature extraction and selection techniques. In a first step, a novel deep learning architecture based on convolutional neural networks (CNN) and gated recurrent units (GRU) is introduced to predict the local weld quality based on mid-wave infrared (MWIR) and near-infrared (NIR) image data. The developed technology is used to discover critical welding defects including lack of fusion (false friends), sagging and lack of penetration, and geometric deviations of the weld seam. Additional work is conducted to investigate the significance of various geometrical, statistical, and spatio-temporal features extracted from the keyhole and weld pool regions. Furthermore, the performance of the proposed deep learning architecture is compared to that of classical supervised machine learning algorithms, such as multi-layer perceptron (MLP), logistic regression (LogReg), support vector machines (SVM), decision trees (DT), random forest (RF) and k-Nearest Neighbors (kNN). Optimal hyperparameters for each algorithm are determined by an extensive grid search. Ultimately, the three best classification models are combined into an ensemble classifier that yields the highest detection rates and achieves the most robust estimation of welding defects among all classifiers studied, which is validated on previously unknown welding trials.

In the era when the market segment of Internet of Things (IoT) tops the chart in various business reports, it is apparently envisioned that the field of medicine expects to gain a large benefit from the explosion of wearables and internet-connected sensors that surround us to acquire and communicate unprecedented data on symptoms, medication, food intake, and daily-life activities impacting one’s health and wellness. However, IoT-driven healthcare would have to overcome many barriers, such as: 1) There is an increasing demand for data storage on cloud servers where the analysis of the medical big data becomes increasingly complex; 2) The data, when communicated, are vulnerable to security and privacy issues; 3) The communication of the continuously collected data is not only costly but also energy hungry; 4) Operating and maintaining the sensors directly from the cloud servers are non-trial tasks.This book chapter defined Fog Computing in the context of medical IoT. Conceptually, Fog Computing is a serviceoriented intermediate layer in IoT, providing the interfaces between the sensors and cloud servers for facilitating connectivity, data transfer, and queryable local database. The centerpiece of Fog computing is a low-power, intelligent, wireless, embedded computing node that carries out signal conditioning and data analytics on raw data collected from wearables or other medical sensors and offers efficient means to serve telehealth interventions. We implemented and tested an fog computing system using the Intel Edison and Raspberry Pi that allows acquisition, computing, storage and communication of the various medical data such as pathological speech data of individuals with speech disorders, Phonocardiogram (PCG) signal for heart rate estimation, and Electrocardiogram (ECG)-based Q, R, S detection. The book chapter ends with experiments and results showing how fog computing could lessen the obstacles of existing cloud-driven medical IoT solutions and enhance the overall performance of the system in terms of computing intelligence, transmission, storage, configurable, and security. The case studies on various types of physiological data shows that the proposed Fog architecture could be used for signal enhancement, processing and analysis of various types of bio-signals.

Aim: This study aims to analyze the structure and impact of research collaborations in colonoscopy from 2000 to 2023 by examining co-authorship networks. The goal is to understand the evolution of these networks, identify key contributors, and assess how collaborative relationships influence the field. Method: I conducted a comprehensive network analysis of co-authorship patterns using data from the Web of Science (WoS) Core Collection database. The analysis included 41,213 articles related to colonoscopy published between 2000 and 2023. Using Python (Version 3.10.5) and PyCharm (Software Version 2022.1.3), we evaluated the networks through macro-level indicators (network density, clustering coefficient, number of components, average distance) and micro-level indicators (degree centrality, closeness centrality, betweenness centrality).Result: The analysis revealed a network with increasing but still fragmented collaboration over the years. The network density showed low proportions of realized connections relative to potential ones, with a high clustering coefficient indicating tight-knit groups when collaborations occurred. The number of components remained high, reflecting a fragmented structure. Prominent researchers such as Hassan, Cesare (Italy) and Dekker, Evelien (Netherlands) consistently emerged as central figures across different periods, demonstrating significant roles in facilitating connections between various research clusters.Conclusion: The study highlights a growing but fragmented collaborative landscape in colonoscopy research. Key researchers have played central roles in connecting different parts of the network, yet there remains substantial room for further integration. Strengthening collaborations across isolated groups could enhance the cohesiveness and impact of research in this field.

In engineering practice, information data in the detection process can not be avoided by the working environment and equipment performance and other factors, resulting in unpredictable measurement errors, greatly affecting the reliability of the manufacturing system and decision-making system decision-making scientific. This paper analyzes the application characteristics of untraceable Kalman filter (UKF) and BP neural network algorithm (BPNN) in information data fusion, and tries to realize the complementary advantages of the two through the combination of UKF and BPNN (UKF+BPNN). The information data fusion algorithm based on UKF-BPNN is established to effectively fuse the information data measurement errors brought by multiple influencing factors in order to improve the detection accuracy of the information data, and the feasibility and validity of the method are verified through the application of the algorithm in the measurement of key information data of rolling bearings.

The increasing prevalence and heightened severity of extreme weather events, which are consequences of climate change, pose significant challenges to the global property insurance sector. This study examines the concurrent crises faced by insurance companies in maintaining profitability and by property owners in affording coverage, thereby necessitating a reevaluation of current insurance paradigms. We present an innovative approach that utilizes a back-propagation (BP) neural network to forecast insurance losses and guide strategic underwriting decisions in regions prone to perils. Our advanced model combines crucial factors such as the likelihood of extreme meteorological phenomena, insurance risk premiums, and capital adequacy ratios to predict impending losses and inform insurance policy formulation. Through an extensive analysis of nearly two decades of catastrophe data from the United States and New Zealand, we determine the model's effectiveness in anticipating insurance-related losses and providing strategic guidance to insurance entities. The study concludes with recommendations for insurers to enhance risk assessment, innovate products, collaborate with governments, invest in green projects, and establish dedicated climate risk management teams. The study contributes to the discourse on climate change adaptation in the insurance industry and offers practical solutions for navigating the complexities of extreme weather risk.

The complex network relationship between leaf traits and their multiple traits is closely related to the environment, and is the result of interactions between various environmental factors such as climate and soil. Based on previous work, we selected 20 P. euphratica trees along the desert riparian forest of the main stream of the Tarim River for leaf sample collection and habitat survey. We used 27 leaf traits of P. euphratica to visualize the leaf trait network (LTN). Through network structure parameters, such as edge density, diameter, average path length, and average clustering coefficient, the spatial pattern of the LTN and its relationships with 11 soil factors and 19 climatic factors were discussed using principal component analysis and correlation analysis. The results showed that: (1) there were significant differences in the parameters of the leaf trait network of P. euphratica along the main stream of the Tarim River. The variation coefficients of the diameter and average path length were the largest, respectively, whereas that of the average clustering coefficient was the smallest. (2) There were both positive and negative correlations between each parameter and soil factors, such as soil water content, total potassium, and organic matter, and climatic factors, such as isothermality, minimum temperature of the coldest month, and precipitation of the wettest month. (3) The explanatory power of climate alone on the leaf traits of P. euphratica was generally higher than that of soil factors, indicating that climatic conditions play a more decisive role in shaping the network structure of leaf traits of P. euphratica. However, regarding the influence of network modularity, the contribution of soil factors was significant, indicating that the influence of soil conditions on some LTN parameters cannot be ignored.

Speech emotion recognition (SER) is important in facilitating natural human-computer interactions. In speech sequence modelling, a vital challenge is to learn context-aware sentence expression and temporal dynamics of para-linguistic features to achieve unambiguous emotional semantic understand-ing. In previous studies, the SER method based on the single-scale cascade feature extraction module could not effectively preserve the temporal structure of speech signals in the deep layer, downgrading the sequence modeling performance. In this paper, we propose a novel multi-scale feature pyramid network to mitigate the above limitations. With the aid of the bi-directional feature fusion of the pyramid network, the emotional representation with adequate temporal semantics is obtained. Experiments on the IEMOCAP corpus demonstrate the effectiveness of the proposed methods and achieve competitive results under speaker-independent validation.

Remote sensing (RS) and Geographic Information Systems (GIS) provide significant opportunities for monitoring and managing natural resources across various temporal, spectral, and spatial resolutions. There is a critical need for natural resource managers to understand the expanding capabilities of image sources, analysis techniques, and in-situ validation methods. This article reviews a range of image analysis tools applicable to natural resource management, including agriculture, water, forests, soil, and natural hazards, and compares their functionalities. Our study highlights that Google Earth Engine (GEE) is favored for wide-area analysis due to its extensive coverage and free access. Global Mapper excels in 3D and light detection and ranging (LIDAR) data, environment for visualizing images (ENVI) specializes in multi- and hyperspectral image processing, ERDAS IMAGINE is optimal for radar data, and eCognition is used for object-based image analysis. The article emphasizes the importance of in-situ validation data, which provides essential ground truth information to calibrate and validate RS models, thereby enhancing accuracy. Understanding these tools and integrating them with in-situ validation techniques enables natural resource managers to improve their monitoring and decision-making processes, facilitating effective collaboration with RS researchers.

This study presents the Bayesian-Optimized Attentive Neural Network (BOANN), a novel approach enhancing image classification performance by integrating Bayesian optimization with channel and spatial attention mechanisms. Traditional image classification struggles with the extensive data in today's big data era. Bayesian optimization has been integrated into neural networks in recent years to enhance model generalization, while channel and spatial attention mechanisms improve feature extraction capabilities. This paper introduces a model combining Bayesian optimization with these attention mechanisms to boost image classification performance. Bayesian optimization optimizes hyperparameter selection, accelerating model convergence and accuracy; the attention mechanisms augment feature extraction. Compared to traditional deep learning models, our model utilizes attention mechanisms for initial feature extraction, followed by a Bayesian-optimized neural network. On the CIFAR-100 dataset, our model outperforms classical models in metrics such as accuracy, loss, precision, recall, and F1 score, achieving an accuracy of 77.6%. These technologies have potential for broader application in image classification and other computer vision domains.

This paper explores the use of GNN architectures, including Graph Convolutional Networks (GCNs), Graph Attention Networks (GATs), and GraphSAGE, in modeling blockchain data. A specific focus is given to their applications in cryptocurrency transaction networks, where GNNs can detect fraudulent activities and track illicit fund flows by learning from transaction patterns and network structure. Additionally, future directions for GNN research in blockchain are discussed, including scalability challenges, privacy-preserving models, and multi-chain graph analysis. Through these advancements, GNNs offer significant potential for enhancing the security, transparency, and efficiency of blockchain and cryptocurrency ecosystems. This paper also shows an example of fraud detection for Ethereum cryptocurrencies.

Bacterial structures formed from the outer membrane and the periplasm components carry biomolecules to expel cellular material and interact with other cells. These outer membrane vesicles (OMVs) can encapsulate bioactive content, which gives OMVs a high potential as alternative drug delivery vehicles or as a platform for novel vaccine development. Single-gene mutants of the hypervesiculating strain Escherichia coli JC8031 were engineered to further enhance OMV production based on metabolic network modelling and in silico gene knockout design (ΔpoxB, ΔsgbE, ΔgmhA, and ΔallD). Mutants were experimentally obtained by genome editing using CRISPR-Cas9 and tested for OMVs recovery observing an enhanced OMV production in all of them. Lipidomic analysis through LC-ESI-QTOF-MS was performed for OMVs obtained from each engineered strain and compared to the wild type E. coli JC8031 strain. The lipid profile of OMVs from the wild type E. coli JC8031 did not change significantly when compared to the mutant strains. The obtained results suggest that the vesicle production can be further improved while the obtained vesicles are not altered in their composition, allowing further study for stability and integrity for use in therapeutic settings.

Late-onset Alzheimer’s disease (LOAD) is a dementia category disease that starts after the age of 65. Progressive problems in thinking, behaviour, learning etc. are its characteristics. Due to its progressive nature, early diagnosis is crucial. A complex pathway mechanism with different risk factors is involved in LOAD progression. A comprehensive study is done on factors causing LOAD, biomarkers used for diagnosis in clinical and preclinical stage of the disease, ML (Machine Learning) techniques to identify disease stage. We reviewed research papers on clinical and preclinical diagnosis of LOAD using ML techniques from biomarker data: MRI, PET image, MMSE, Genome / Gene expression, DNA / RNA binding sites with protein, Epigenetic expression /DNA, methylation, Speech and text. We have listed improvement scope after finding the gaps and scope of using Generative AI and SMOTE (Synthetic Minority Oversampling Technique) for data augmentation. At the end, we have elaborated current use of DL (Deep Learning) and CNN (‘Convolution Neural Network’) in Alzheimer’s disease (AD) diagnosis.

This paper investigates rural mobility in the Global South using a participatory GIS approach to address the lack of mobility data. Limited rural mobility due to poor infrastructure and financial constraints hinders social and economic activities, impeding development. The study aims to explore the socio-economic impacts of limited mobility, identify software needs for data-scarce environments, and map daily mobility patterns. Fieldwork was conducted in Kenya (2022) and Nepal (2023), collecting geographic data related to mobility. The methodology included community engagement and digital mapping using the QField app for precise data collection. The study highlights the use of participatory GIS to fill data gaps, enabling more accurate mobility assessments. In Kenya, the research significantly increased the number of mapped roads and paths, providing a more realistic view of local mobility. Community engagement revealed gender-specific mobility patterns, with women facing particular challenges in daily activities. The study emphasizes the need for adaptable data models to reflect community-specific mobility needs and the integration of qualitative insights to propose effective mobility solutions. This research contributes to understanding rural mobility in the Global South and demonstrates the effectiveness of participatory GIS in overcoming data scarcity and enhancing mobility analysis.

Real time condition monitoring and precision health assessment system is a mandatory need for effective maintenance program in industrial sector. Rapid advancement in the information technology and other engineering technologies have invited more proactive attention from research and development in industrial sectors and particularly in condition monitoring of machines and related Industrial processes. In this work, drill bit condition monitoring techniques have been developed based on wavelet analysis and artificial neural networks (ANN) for automatic drill bit fault detection and classification. An experimental work has been conducted to capture the vibration signals for analysis. In this experiment, the CNC drill machine is used with high carbon steel drill bit and mild steel material as work piece. The cutting condition parameters are kept constant and the wear level is varied from 0.2 to 0.6 mm. The Data Acquisition system (DAQ) with Lab VIEW software is used to capture the vibration signals for drill bit with different wear conditions using accelerometer. The captured vibrations data are analyzed using continuous wavelet transform (CWT) with Morlet wavelet and Daubechies wavelet as a prime function. In general, the CWT coefficient is used to generate the inputs features to ANN for automatic tool condition classification, with two outputs (0, 1) for healthy and (1, 0) for faulty. The outcome of ANN showed 98% of accuracy in the wear prediction and this results show the effectiveness of the combed WT and ANN for automatic classification of tool wear conditions with high success rate.

Smart agriculture is a new way of farming that uses advanced technology. It makes a significant contribution to improving the efficiency and productivity of farming practices. Systems that use drones to monitor pests and spray pesticides greatly reduce the burden on farmers. In addition, remote sensing technology facilitates the monitoring of crop growth conditions and the early detection of diseases and pests. However, the high cost of equipment to communicate sensor data is preventing farmers from adopting sensing systems. As a result, many studies have been conducted to make the sensing system available at a low cost. Nevertheless, many farmers have not yet adopted them. Therefore, this paper proposes an agricultural sensor network system using drones and optical camera communication (OCC). The proposed system aims to achieve high-density farm sensing at low cost. The proposed system uses OCC as the communication method for sensor data. Low cost light sources such as LED panels can be used as transmitters. In addition, existing agricultural drones equipped with cameras can be used as receivers. We also propose a trajectory control algorithm for the receiving drone to efficiently collect the sensor data. The proposed system is suitable for deploying sensor networks in areas with underdeveloped infrastructure and radio silence. In this paper, we conducted a preliminary experiment at a leaf mustard farm in Kamitonda-cho, Wakayama to demonstrate the effectiveness of the proposed system using a Mavic 2 Pro drone, launched by DJI Co., Ltd.

Image captioning aims at generating meaningful verbal descriptions of a digital image. Our paper focuses on the classic encoder-decoder deep learning model that consists of several components – sub-networks, each performing a separate task that, combined, form an effective caption generator. We investigate image feature extractors, recurrent neural networks, word embedding models, and word generation layers and discuss how each component influences the captioning model’s overall performance. Our experiments are performed on the MS COCO 2014 dataset. The results help design efficient models with optimal combinations of their components.

Unmanned aerial vehicle UAV has become an important tool for emergency communication. When disaster happens, the roads in the disaster area always are seriously damaged, and theground infrastructure communication facilities are damaged. Under emergency conditions, UAV can go into key areas as communication nodes to provide communication services for users in the area.But it's difficult for UAV to cover the entire disaster area and the efficient rescue time will be delayed. Therefore, how to make the UAV accurately perceive the regional situation and deployed in the right position is worth studying. In this paper, a virtual simulation environment is established reasonably and deep reinforcement learning algorithm is used to train UAV agents. At the same time, a series of problems such as sparse reward and long training time are still not solved in the development of reinforcement learning algorithms,and the reward function is designed to improve training efficiency. First of all, we set a specific mountain emergency communication scenario, and combined with the specific application of the UAV to carry out virtual simulation, and build a virtual environment. Furthermore, an additional shaped reward function is designed to address the sparse reward problem. Through the improvement of deep Q-learning network DQN algorithm and the reward design based on potential function, the final evaluation index is improved, and the effectiveness of the algorithm is verified. The experimental results demonstrate our work can effectively shorten the training time and increase convergencerate.

In recent years, electroencephalogram (EEG) emotion recognition has emerged as a research hotspot in the field of artificial intelligence (AI). Despite advancements in EEG-based emotion recognition, room for enhancing performance persists due to EEG signal redundancy and limitations in feature extraction, leading to inefficient models and emotional information loss. To fully utilize EEG's emotional information and improve recognition accuracy while reducing computational costs, this paper proposes a Convolutional-Recurrent Hybrid Network with a dual-stream adaptive approach and an attention mechanism (CSA-SA-CRTNN). Firstly, the model utilizes a CSAM module to assign corresponding weights to EEG channels. Then, an adaptive dual-stream convolutional-recurrent network (SA-CRNN and MHSA-CRNN) is applied to extract local spatial-temporal features. After that, the extracted local features are concatenated and fed into a temporal convolutional network with a multi-head self-attention mechanism (MHSA-TCN) to capture global information. Finally, the extracted EEG information is used for emotion classification. We conducted binary and ternary classification experiments on the DEAP dataset, achieving 99.26% and 99.15% accuracy for arousal and valence in binary classification, and 97.69% and 98.05% in ternary classification, surpassing relevant algorithms. Additionally, the model's efficiency is significantly higher than other models, achieving better accuracy with lower resource consumption.

Detecting cracks in structural health monitoring is crucial for ensuring infrastructure safety and longevity. Using drones to obtain crack images and automate processing can improve the efficiency of crack detection. To address the challenges posed by the limited computing resources of edge devices in practical applications, we propose CrackScopeNet, a lightweight segmentation network model that simultaneously considers local and global crack features, suitable for deployment on drone platforms with limited computational power and memory. CrackScopeNet features a multi-scale branch to improve sensitivity to cracks of varying sizes without substantial computational overhead and a stripe-wise context attention mechanism to enhance the capture of long-range contextual information, mitigating the interference from complex backgrounds. Experimental results on CrackSeg9k dataset demonstrate that CrackScopeNet leads to a significant improvement in prediction performance, with the highest mean intersection over union (mIoU) scores reaching 82.12%, while maintaining a lightweight architecture with only 1.05M parameters and 1.58G floating point operations (FLOPs). Besides, CrackScopeNet excels in inference speed on edge devices without GPU because of its low FLOPs. CrackScopeNet contributes to the development of efficient and effective crack segmentation networks, suitable for practical structural health monitoring applications using drone platforms.

Training artificial intelligence (AI) for reasoning presents significant challenges due to the lack of clear objectives and reward functions. In structured environments such as chess and Go, objectives are well-defined, and the optimal moves can be determined through search algorithms that maximize the reward function. This clarity enables AI to learn and improve autonomously through random trials and recursive calculation of rewards, mirroring human learning processes that depend on prior experiences and state-dependent actions. However, in real-world applications, AI lacks access to direct interaction and feedback, making it difficult to define proper reward functions. This limitation is particularly evident in the training of large language models (LLMs), where the quality of the output is constrained by the training data and the absence of a dynamic reward system. Simulated environments offer some utility but are inherently limited by their design and scope. Achieving artificial general intelligence (AGI) requires AI to function and receive feedback in real-world settings, similar to human cognitive and strategic development through interactive experiences. This paper explores the critical role of clear objectives and reward functions in AI training, the limitations posed by the current lack of real-world interaction, and the implications for future advancements in AI reasoning capabilities.

Previous studies on the water-energy nexus mainly focused on the calculation and comparison of resource consumption at the national or regional level, lacking interprovincial sector-sector transfer analysis. In this study, the intensity of water and energy consumption of various sectors in China were calculated, the key nodes and paths of resource networks were identified, and countermeasures for resource conservation were proposed from the new perspective of the “dual saving” and “bidirectional saving” of water and energy. The results showed that the metallurgical industry (Me) in Jiangsu and the chemical industry (Ch) in Hebei and Jiangsu had high node strength in the water and energy network and were key sectors in China with “dual saving” effects of water and energy. The construction industry, Ch, Me in Jiangsu, electricity and hot water production and supply industry in Beijing, and Me in Hebei had high node strength in the water-related energy network and energy-related water network, significantly supporting the “bidirectional saving” effect of water and energy in China. The electrical equipment industry (El) in Jiangsu→El in Zhejiang, El in Zhejiang→El in Shanghai frequently appeared in key paths, which could effectively reduce the resource consumption of the entire network.

Rice has become the second major food among rural people. It is one of the most nutrient and low-cost food available in Asia. Rice is composed of two major subspecies as Japonica and Indica and it belongs to the Poaceae family. The World Bank predicts that rice demand will grow 51% faster than population growth in 2025. It is high time to develop a model which predicts the type of infected paddy leaf and avoids the loss of grains. In this paper, the proposed hybrid CNN model, three CNN networks with different layer properties are trained parallel. The extracted feature from these CNN networks is combined to provide the classification of the type of infected leaf. Fieldwork was carried and about 340 samples are collected from five different types of classes. The proposed hybrid model was tested with both the fieldwork dataset and also with an available dataset on the internet. The experimental results show that the proposed model outperforms the other CNN network and yields an accuracy value of 98%, a precision value of 95%, and a misclassification rate of 4% respectively.

Marine oil spills seriously threaten the coastal environment, challenge the safety of marine eco-system, and cause huge economic losses to marine fishery, aquaculture, and tourism industries. Timely and accurate oil spill monitoring and early warning can not only make the oil spill acci-dent be handled timely and effectively but also provide key information for investigating the re-sponsibility of the polluters. Polarimetric synthetic aperture radar (SAR) has shown its great po-tential in oil spill classification for its capacity to distinguish mineral oil and biogenic look-alikes. Traditional oil spill classification approaches rely on the scattering matrix elements or pre-designed scattering mechanism-based polarimetric SAR features, which limits its robustness and generalization in large-scale marine surveillance tasks. The recent development of deep learning frameworks, especially the convolutional neural network (CNN) provides a powerful tool for remote sensing image classification. However, conventional CNN only accepts re-al-valued input, which cannot efficiently analyze the polarimetric information carried by com-plex-valued SAR data. In this study, a new framework that employs the complex-valued neural network was proposed for marine oil spill detection. Sophisticated studies were designed to evaluate the contribution of the physical scattering mechanism-based features, complex-valued framework, and convolutional feature extraction structures respectively. Comparative studies were conducted on four study cases using Radarsat-2 and SIR-C fully polarimetric SAR data. The outcome of the proposed study may shed light on the development of an end-to-end marine spill classification system and enlarge its application in practical marine surveillance operations.

Accurately predicting drug-drug interactions (DDIs) is crucial for preventing adverse drug events in clinical settings. However, existing methodologies often rely on complex models built from diverse data sources, posing challenges in computational drug discovery. To address the need for precise computational methods in predicting unknown DDIs, this study introduces a novel Deep Neural Network (DNN)-based approach. By leveraging a wide range of drug-related information, including substructure, targets, side effects, pathways, and indications, our method calculates multiple drug similarities. These similarities are then synthesized using a nonlinear fusion method to extract high-level features. Subsequently, a tailored neural network is deployed for interaction prediction. Comparative evaluation against three prominent machine learning classifiers—Extreme Gradient Boosting (XGBoost), Adaptive Gradient Boosting (AdaBoost), and Light Gradient-Boosting Machine (LGBM)—using three benchmark datasets demonstrates the superior performance of DNN. It achieves outstanding accuracy, precision, recall, and F1-score metrics, all reaching 94.6% in cross-validation. Additionally, case studies involving numerous drug pairs confirm the reliability of DNN in accurately predicting unknown DDIs. These findings underscore DNN as a potent and reliable method for DDI prediction, with promising implications for drug discovery and healthcare applications.

Convolutional neural networks (CNNs) face challenges in capturing long-distance text correlations, and Bidirectional Long Short-Term Memory (BiLSTM) networks exhibit limited feature extraction capabilities for text classification of work order. To address the abovementioned problems, this work utilizes an ensemble learning approach to integrate model elements efficiently. This study presents a method for classifying work order texts using a hybrid neural network model called BERT-BiLSTM-CNN. First, use Bert for preprocessing to obtain text vector representations. Then, capture context and process sequence information through BiLSTM. Next, capture local features in the text through CNN. Finally, obtain classification results through Softmax. Through comparative analysis, the method of fusing these three models is superior to other hybrid neural network model architectures in multiple classification tasks. It has a significant effect on work order classification.

The purpose of this article is to present an IoT architecture implemented in an intelligent environment, focusing on the optimization of initial conditions and device management. A general control system was developed using an open-source platform, integrating aWi-Fi network and YAML coding to enable communication and control of the IoT architecture devices. The implementation includes actuators, sensors, and control devices that, through a graphical interface, allow the visualization of the historical record of activities and real-time measurements of connected devices. The design includes specific mechanisms and the analysis of materials through tensile tests on specimens, following the ASTM E8 standard, and deformation test simulations, in which PLA demonstrated better performance compared to materials like ABS and resin. The significance of the implemented IoT system lies in an energy saving of 58% compared to conventional structures. Additionally, the study of response times for network connections showed that using an Ethernet cable resulted in a response time of 1.21 seconds, representing a reduction of 1.65 seconds compared to the second lowest value obtained.

The volume of fluid (VOF) method is a popular technique for the direct numerical simulations of flows involving immiscible fluids. A discrete volume fraction field evolving in time represents the interface, in particular, to compute its geometric properties. The height function method (HF) is based on the volume fraction field, and its estimate of the interface curvature converges with second-order accuracy with grid refinement. Data-driven methods have been recently proposed as an alternative to computing the curvature, with particular consideration for a well-balanced input data set generation and symmetry preservation. In the present work, a two-layer feed-forward neural network is trained on an input data set generated from the height function data instead of the volume fraction field. The symmetries for rotations, reflections, and the anti-symmetry for the phase swapping have been considered to reduce the number of input parameters. The neural network, establishing a correlation between curvature and height function values, can efficiently predict the local interface curvature. We compare the trained neural network to the standard Height Function method to assess its performance and robustness.

Numerous image processing techniques (IPTs) have been employed to detect crack defects, offering an alternative to human-conducted onsite inspections. These IPTs manipulate images to extract defect features, particularly cracks in surfaces produced through Additive Manufacturing (AM). This article presents a vision-based approach that utilizes deep convolutional neural networks (CNNs) for crack detection in AM surfaces. Traditional image processing techniques face challenges with diverse real-world scenarios and varying crack types. To overcome these challenges, our proposed method leverages CNNs, eliminating the need for extensive feature extraction. Annotation for CNN training is facilitated by LabelImg without the requirement for additional IPTs. The trained CNN, enhanced by OpenCV preprocessing techniques, achieves an outstanding 99.54% accuracy on a dataset of 14,982 annotated images with resolutions of 1536 × 1103 pixels. Evaluation metrics exceeding 96% precision, 98% recall, and a 97% F1-score highlight the precision and effectiveness of the entire process.

Deep underground laboratories offer advantages for conducting high-precision observations of weak geophysical signals, benefitting from a low background noise level. It is both valuable and feasible to enhance strong, noisy ground electromagnetic (EM) field data using synchronously recorded underground EM signals, which typically exhibit a high signal-to-noise ratio. In this study, we propose an EM field reconstruction method employing a Long Short-Term Memory (LSTM) recurrent neural network with referenced deep underground EM observations. Initially, a deep learning model was developed to capture the time-varying features of underground multi-component EM fields using the LSTM recurrent neural network. Subsequently, this model was applied to process synchronously observed strong, noisy data from other conventional observation systems, such as those at surface, to achieve noise suppression through signal reconstructions. Both theoretical analysis and practical observational data suggest that the proposed method effectively suppresses noise and reconstructs clean EM signals. This method is efficient and time-saving, representing an effective approach to fully utilizing the advantages of deep underground observation data. Furthermore, this method could be extended to the processing and analysis of other geophysical data.

Artificial intelligence (AI) is a current trend in computer science, which extends itself its amazing capacities to other technologies such as mechatronics and robotics. Going beyond technological applications, the philosophy behind AI is that there is a vague and potential convergence of artificial manufacture and natural world although the limiting approach may be still very far away, but why? The implicit problem is that Darwin theory of evolution focuses on natural world where breeding conservation is the cornerstone of the existence of creature world but there is no similar concept of breeding conservation in artificial world whose things are created by human. However, after developing for a long time until now, AI issues an interesting concept of generation in which artifacts created by computer science can derive their new generations inheriting their aspects / characteristics. Such generated artifacts make us look back on offsprings by the process of breeding conservation in natural world. Therefore, it is possible to think that AI generation, which is a recent subject of AI, is a significant development in computer science as well as high-tech domain. AI generation does not help us to reach near biological evolution even in the case that AI can combine with biological technology but, AI generation can help us to extend our viewpoint about Darwin theory of evolution as well as there may exist some uncertain relationship between man-made world and natural world. Anyhow AI generation is a current important subject in AI and there are two main generative models in computer science: 1) generative model that applies large language model into generating natural language texts understandable by human and 2) generative model that applies deep neural network into generating digital content such as sound, image, and video. This technical report focuses on deep generative model (DGM) for digital content generation, which is a short summary of approaches to implement DGMs. Researchers can read this work as an introduction to DGM with easily understandable explanations.

With the advancement of technology, signal modulation types are becoming increasingly diverse and complex. The phenomenon of signal time-frequency overlap during transmission poses significant challenges for the classification and recognition of mixed signals, including poor recognition capabilities and low generality. This paper presents a recognition model for fine-grained analysis of mixed signal characteristics, proposing a Geometry Coordinate attention mechanism and introducing a low-rank bilinear pooling module to more effectively extract signal features for classification. The model employs a residual neural network as its backbone architecture and utilizes the Geometry Coordinate attention mechanism for time-frequency weighted analysis based on information geometry theory. This analysis targets multiple-scale features within the architecture, producing time-frequency weighted features of the signal. These weighted features are further analyzed through a low-rank bilinear pooling module, combined with the backbone features, to achieve fine-grained feature fusion. This results in a fused feature vector for mixed signal classification. Experiments were conducted on a simulated dataset comprising 39,600 mixed signal time-frequency plots. The model was benchmarked against a baseline using a residual neural network. The experimental outcomes demonstrated an improvement of 9% in the exact match ratio and 5% in the Hamming score. These results indicate that the proposed model significantly enhances the recognition capability and generalizability of mixed signal classification.

RNA-seq faces persistent challenges due to the ongoing expanding array of data processing workflows, none of which have yet achieved standardization to date. It is imperative to determine which method most effectively preserves biological facts. Shannon entropy serves as a tool for depicting the biological status of a system. Thus, we assessed the measurement of Shannon entropy by several RNA-seq workflow approaches, employing RPKM and median normalization on paired samples of 475 TCGA RNA-seq datasets spanning eight different cancer types with 5-year overall survival rates ranging from 30% to 98%. Our analysis revealed that the RPKM normalization coupled with a threshold of log2 fold change ≥1 for indentifying differentially expressed genes, yielded the best results with a correlation coefficient of 0.91. We propose that Shannon entropy can serve as an objective metric for refining the optimization of RNA-seq workflows.

Reliable hydrological monitoring is crucial for effective water resource management, but establishing observatories in remote areas with extreme weather presents significant challenges. This study aimed at identifying cost-effective methods for streamflow estimation in such environments. We evaluated the performance of the Soil and Water Assessment Tool (SWAT) model using various precipitation data sources: ground-based rain gauge networks with different densities (one-gauge (1RG), two-gauge (2RG), and five-gauge (5RG) configurations) and satellite-derived Integrated Multi-satellite Retrievals for GPM (IMERG) data. The study focused on the Sahafihitry catchment, a 200 km² area in northeastern Madagascar. The results demonstrated that denser rain gauge networks (5RG and 2RG) captured the spatial variability of rainfall more effectively than a single gauge or IMERG data. This translated into superior SWAT model performance. Denser networks achieved higher statistical metrics (R², slope of regression a, Nash-Sutcliffe efficiency NSE, root mean square error RMSE, Kling-Gupta efficiency KGE) indicating a better fit between simulated and observed streamflow. Specifically, 5RG: R² = 0.84, a = 0.92, NSE = 0.83, RMSE = 3.33, KGE = 0.82; 2RG: R² = 0.85, a = 0.95, NSE = 0.83, RMSE = 3.36, KGE = 0.88; 1RG: R² = 0.73, a = 0.80, NSE = 0.72, RMSE = 4.28, KGE = 0.88; IMERG: R² = 0.48, a = 0.63, NSE = 0.37, RMSE = 6.46, KGE = 0.66. Furthermore, rain gauge data outperformed IMERG in simulating both flood events and low-flow periods. While IMERG offers low cost, readily available data, its lower performance introduces significant uncertainty into hydrological modeling. In contrast, the two-gauge network (2RG) achieved satisfactory streamflow simulations and represents the most cost-effective option for establishing reliable observatories within the specific characteristics of this study area.

Keywords: standing water bodies, glacial lakes, freshwater biodiversity, eutrophication; nature conservation network

With the development of deep learning, the Super-Resolution (SR) reconstruction of microscopic images has improved significantly. However, the scarcity of microscopic images for training, the underutilization of hierarchical features in original Low Resolution (LR) images, and the high-frequency noise unrelated with the image structure generated during reconstruction process are still challenges in the Single Image Super-Resolution (SISR) field. Faced with these issues, we first collected sufficient microscopic images through Motic, a company engaged in the design and production of optical and digital microscopes, to establish a dataset. Secondly, we proposed a Residual Dense Attention Generative Adversarial Network (RDAGAN). The network comprises a generator, an image discriminator, and a feature discriminator. The generator includes a Residual Dense Block (RDB) and a Convolutional Block Attention Module (CBAM), focusing on extracting the hierarchical features of the original LR image. Simultaneously, the added feature discriminator enables the network to generate high-frequency features pertinent to the image’s structure. Finally, we conducted experimental analysis and compared our model with six classic models. Compared with the best model, our model improved PSNR and SSIM by about 1.5dB and 0.2, respectively.

Network centrality analyses have proven successful in identifying important nodes in diverse host-pathogen interactomes. The current study presents a comprehensive investigation of the human interactome and SARS-CoV-2 host targets. We first constructed a comprehensive human interactome by compiling experimentally validated protein-protein interactions (PPIs) from eight distinct sources. Additionally, we compiled a comprehensive list of 1,449 SARS-CoV-2 host proteins and analyzed their interactions within the human interactome, which identified enriched biological processes and pathways. Seven diverse topological features were employed to reveal the enrichment of SARS-CoV-2 targets in the human interactome, with Load centrality emerging as the most effective metric. Furthermore, a novel approach called CentralityCosDist was employed to predict SARS-CoV-2 targets, which proved effective in expanding the pool of predicted targets. Pathway enrichment analyses further elucidated the functional roles and potential mechanisms associated with predicted targets. Overall, this study provides valuable insights into the complex interplay between SARS-CoV-2 and the host cellular machinery, contributing to a deeper understanding of viral infection and immune response modulation.

Generative artificial intelligence (GenAI) has been developing with many incredible achievements like ChatGPT and Bard. Deep generative model (DGM) is a branch of GenAI, which is preeminent in generating raster data such as image and sound due to strong points of deep neural network (DNN) in inference and recognition. The built-in inference mechanism of DNN, which simulates and aims to synaptic plasticity of human neuron network, fosters generation ability of DGM which produces surprised results with support of statistical flexibility. Two popular approaches in DGM are Variational Autoencoders (VAE) and Generative Adversarial Network (GAN). Both VAE and GAN have their own strong points although they share and imply underline theory of statistics as well as incredible complex via hidden layers of DNN when DNN becomes effective encoding/decoding functions without concrete specifications. In this research, VAE and GAN is unified into a consistent and consolidated model called Adversarial Variational Autoencoders (AVA) in which VAE and GAN complement each other, for instance, VAE is good at generator by encoding data via excellent ideology of Kullback-Leibler divergence and GAN is a significantly important method to assess reliability of data which is realistic or fake. In other words, AVA aims to improve accuracy of generative models, besides AVA extends function of simple generative models. In methodology this research focuses on combination of applied mathematical concepts and skillful techniques of computer programming in order to implement and solve complicated problems as simply as possible.

A novel compressible real gas 1D finite volume thermofluid network modelling methodology is proposed that can be applied in the analysis of supercritical CO₂ (sCO2) power cycles. It is applied to simulate centrifugal compressor performance via a mean line approach that directly solves the mass, energy, and momentum balance equations for the discretized flow channels within the machine along with the associated loss models, component characteristics, and applicable compressible real gas equation of state. This can be integrated seamlessly with the rest of the power cycle components like pipes, valves, heat exchangers, etc., thereby eliminating the need for static performance maps and the associated difficulties to ensure similarity over the whole range of operation. This direct simulation of the internal flows also makes it possible to do integrated cycle design optimization that includes the geometry of the compressors, and to simulate fast transients for dynamic analysis. The methodology was applied to simulate well-documented air and sCO2 centrifugal compressors and compared the generated results with that of conventional thermofluid network incompressible and compressible ideal gas approaches. The results indicate that the proposed compressible real gas approach can capture the stagnation pressure changes and isentropic efficiencies with good accuracy for both cases over the whole range of mass flow rates and shaft rotational speeds. In contrast, the conventional thermofluid network incompressible and compressible ideal gas approaches are only applicable in selected regions of the fluid property regime and suffer from discretization errors and inappropriate treatment of the relationship between stagnation and static pressures. Furthermore, comparative analyses between the newly proposed approach and the traditional mechanical energy balance method are performed, showing that the latter approach needs to be discretized more finely through the compression process to correctly capture the polytropic compression path shape, whereas the former more accurately captures the stagnation pressure changes through the analyzed compressors with only a single increment per compressor component.

The administration and management of urban transport has become an urgent need, in the context of the increasing congestion problems and the environmental and economic damage, resulting from rapid urban expansion witnessed by the Algerian cities in recent times, in order to achieve prosperity and quality of urban life. It became necessary to use the tools of modern technology, which administrative and technical departments are seeking to use primarily to support ways of decision-making and actions required. Boosted by high capabilities in the statistical data and other information is stored, and coordination and tabulation, with the possibility of installation and analysis by operations. Especially against the inability of traditional methods, which have become less able to cope with the changes that led to the urban dynamic currently experienced by urban communities in our country. This research aims to employ geographic information systems in the administration and management of the urban transport network, facing both the population and the local administration of the city of Batna. Which was chosen as a model for major Algerian cities, which is suffering more than ever of transportation bottlenecks, as well as the unintended damage for these networks and other networks. Hence the importance of the subject of our research, which aims to use GIS MapInfo systems as a means to snipe (Data Capture) and storage (Data Storage) and address (Data Processing) and directed by spatial information (Spatial Data) and link them to the descriptive information (Attribute Data). To develop a modern digital data and charts the base of each of these elements of the urban service lines equipment and mechanisms, ... etc. As a tool available to those creating and carrying out urban spaces, as well as decision-makers. It was concluded that the possibilities offered by this system would facilitate the processes of monitoring and management in order to ensure the quality of the service.

Shape-shifting polymers are widely used in various fields such as intelligent switches, soft robots and sensors, which require both multiple stimulus response functions and qualified mechanical strength. In this study, a novel near infrared light (NIR) responsible shape-shifting hydrogel system was designed and fabricated, through embedding vinylsilane modified carbon nanotubes (CNTs) into particle-double network (P-DN) hydrogels by micellar copolymerization. The dispersed brittle Poly(sodium 2-acrylamido-2-methylpropane-1-sulfonate) (PNaAMPS) network of the microgels can serves as sacrificial bonds to toughen the hydrogels, and the CNTs endow it NIR photothermal conversion ability. The results show that the CNTs embedded P-DN hydrogels present excellent mechanical strength, i. e. fracture strength of 312 kPa and fracture strain of 357%. Moreover, an asymmetric bilayer hydrogel, where the active layer contains CNTs, can achieve 0°–110° bending deformation within 10 min under NIR irradiation and can realise complex deformation movement. This study provides a theoretical and experimental basis for the design and manufacture of photoresponsive soft actuators.

Background: The commonly known assumption that combinations of several herbs in one formulation can have better efficacy due to additive or synergistic effects has not been systematically studied despite some evidence supporting the synergy concept. Study aim: The study aimed to reveal the molecular interactions in situ of host cells in response to the intervention of BHP and justify the benefits of implementing BHP in clinical practice. Results: This overview provides the results of recent clinical and network pharmacology studies of botanical herbal preparations (BHP) of Rhodiola with other plants, including Ashwagandha, Green Tea, Eleutherococcus, Schisandra, Eleutherococcus, Leuzea, Caffeine, Cordyceps, Gingko, Black Cohosh, saffron, and L-carnosine. Conclusions: The most important finding from network pharmacology studies of BHP was the evidence supporting the synergistic interaction of BHP ingredients, revealing unexpected new pharmacological activities unique and specific to the new BHP. Some studies show the superior efficacy of BHP compared with mono-drugs. At the same time, some a priori-designed combinations can fail, presumably due to antagonistic interactions and crosstalk between molecular targets within molecular networks involved in the cellular and overall response of organisms on the intervention. Network pharmacology studies help predict the results of studies to discover new indications and unpredicted adverse events.

Ensuring optimal performance and reliability in rotor-bearing systems is crucial for industrial applications. Imbalance and shaft bow in these systems can lead to decreased efficiency and increased vibrations. Early detection and mitigation of a rotor’s faults are essential, and model-based fault identification has gained much attention in the manufacturing industry for years. Over the past two decades, however, the development of fault diagnosis rules with data-driven and artificial intelligence (AI) has become a trend, and in the foreseeable future, AI combined with big data will become mainstream. Nevertheless, the critical role of rotating machinery in manufacturing introduces a challenge, as the availability of fault data is often insufficient. This limitation renders the establishment of diagnostic rules using data-driven methods and AI technologies impractical. In light of these challenges, this study proposes a novel hybrid approach, that combines a physical model with machine learning (ML) techniques for the diagnosis of multi-faults (imbalance and shaft-bow demonstrated) in a Jeffcott rotor. To overcome the lack of real-world faulted, labeled datasets, a physics-based Jeffcott rotor model is first derived and then used to generate abundant fault datasets for ML. Subsequently, simulated data are employed for the training of an artificial neural network (ANN), enabling the network to learn from and analyze the vast array of generated data. The results prove that a well-trained feed-forward neural network (FNN) can accurately isolate and diagnose the imbalance and shaft-bow faults using the simulated data and the real data from the Jeffcott rotor experiment. These physics-based and ML approaches prove effective particularly for multi-fault, offering new possibilities for advanced rotor system monitoring and maintenance strategies in industrial applications.

This paper proposed an optimal tracking control scheme through adaptive dynamic programming(ADP) for a class of partially unknown discrete-time nonlinear systems based on radial basis function neural network(RBF-NN). In order to acquire the unknown system dynamics, we use two RBF-NNs, the one is used to construct the identifier, and the another is used to directly approximate the steady-state control input, where a novel adaptive law is proposed to update neural network weights. While the optimal feedback control and the cost function are derived via feedforward neural networks approximating, it is proposed to regulate the tracking error, the critic network and the actor network are then trained online to obtain the solution of the associated Hamilton–Jacobi–Bellman (HJB) equation being built under the ADP framework. Simulations verify the effectiveness of the optimal tracking control technique using the neural networks.

The speed-density or flow-density relationship is a fundamental aspect of traffic flow theory. Single-regime models often face challenges in consistently fitting empirical data under diverse traffic conditions. This paper addresses the inaccuracies of single-regime models, attributing them not only to their functional forms but also to data dispersion and sample selection bias. To mitigate these issues, the data is segmented into day and night periods, leading to the creation of separate models for each. Calibration results, conducted on data from two freeways, Tehran-Karaj and Tehran-Qom, reveal distinct challenges, with the former exhibiting high dispersion and the latter showing low dispersion. Surprisingly, single-regime models demonstrate notable effectiveness when applied to distinct day and night data. Further analysis, categorizing data into day and night, results in reduced errors (20-60% improvement in R-Square), emphasizing the potential for enhanced accuracy by considering distinct regimes. Overall, the study underscores the significance of regime-specific considerations for accurate traffic flow modeling. Upon thorough evaluation, the study highlights the superiority of the neural network Multi-layer Perceptron (MLP) over traditional models. The research discusses the implications of incorporating day and night parameters into the models, emphasizing their potential for accuracy enhancement.

Considering that cryptocurrencies are now present in practically every financial transaction because they are widely accepted as an alternate means of making payments and exchanging currencies, academics and economists have more opportunities to study cryptocurrency prices. Over the years, investors, traders and investment banks have found it difficult to predict the closing daily price of Ethereum due to its rapid price fluctuation. The daily closing price of cryptocurrency is essential to consider when trading or investing in Ethereum. This report focuses on carrying out a comparative study of the predictive capabilities of deep machine learning algorithms with a stacking ensemble modelling framework using daily historical observations of the price of Ethereum obtained from Coindesk, tweets extracted from Twitter ranging from the 1st of August 2022 to the 8th of August 2022 and other five covariates (closing price lag1, closing price lag2, noltrend, daytype and month) engineered from the closing price of Ethereum. Seven models are used to compute the forecasts for the daily closing price of Ethereum; these are the recurrent neural network, ensemble stacked recurrent neural network, gradient boosting machine, generalized linear model, distributed random forest, deep neural networks and stacked ensemble for gradient boosting machine, generalized linear model, distributed random forest and deep neural networks. The main evaluation metric used is the mean absolute error. According to MAE, RNN forecasts outperform the other model’s forecasts in this study, producing an MAE of 0.0309.

This study focuses on understanding how global auto parts companies manage innovation by analyzing keywords in CEO messages from their reports. The study involved three key phases: (1) extraction of innovation-related keywords emphasized in CEO messages, (2) comparison of innovation-related keyword usage between high-performing (upper group) and low-performing (lower group) companies, and (3) analysis of the characteristics of innovation management via internal meaning and the structural interpretation of keywords. A comparison between the upper and lower groups revealed distinct differences in the emphasized keywords. The mapping of open innovation success factors, based on keywords extracted according to eigenvector centrality, identified Provision of Resources and Governance as central to innovation management in the upper group. These findings serve as a benchmark for establishing the direction, vision, and strategy of innovation management in the lower group.

Towards smart batteries for electric vehicles (EVs) smart algorithms to control battery packs, mainly reconfigurable batteries, have to be developed. This work proposes a reinforcement learning (RL) algorithm to balance the State of Charge (SoC) of reconfigurable batteries based on the topologies half-bridge and battery modular multilevel management (BM3). As RL algorithm, Amortized Q-learning (AQL) is implemented, which allows enourmous numbers of possible configurations of the reconfigurable battery to be controlled, as well as the combination of classical controlling approach and machine learning methods. This enables safety mechanisms in control. As a neural network of the AQL a Feedforward Neuronal Network (FNN) is implemented consisting of three hidden layers. The experimental evaluation using a 12-cell hybrid cascaded multilevel converter illustrates the applicability of the method to balance the SoC and maintain the balanced state during discharge. The evaluation shows a 20.3% slower balancing compared to the classical. Nevertheless, AQL shows great potential to be applied for multiobjective optimizations as an applicable RL algorithm for control in power electronics.

The implementation of neural networks (NN) on edge devices enables local processing of wireless data but faces challenges such as high computational complexity and memory requirements when deep neural networks (DNN) are used. Shallow neural networks customized for specific problems are more efficient, requiring fewer resources, and resulting in a lower latency solution. An additional benefit of the smaller network size is that it is suitable for real-time processing on edge devices. The main concern with shallow neural networks is their accuracy performance compared to DNNs. In this paper, we demonstrate that a customized adaptive activation function (AAF) can meet the accuracy of a DNN. We designed an efficient FPGA implementation for a customized segmented spline curve neural network (SSCNN) structure to replace the traditional fixed activation function with an AAF. We compared our SSCNN with different neural network structures such as real-valued time delay neural network (RVTDNN), augmented real-valued time delay neural network (ARVTDNN), and deep neural networks with different parameters. Our proposed SSCNN implementation uses 40% fewer hardware resources and no Block RAMS compared to the DNN with similar accuracy. We experimentally validate this computationally efficient and memory-saving FPGA implementation of SSCNN for digital predistortion of RF power amplifiers using the AMD/Xilinx RFSoC ZCU111. The implemented solution uses less than 3% of the available resources. The solution also enables an increase of the clock frequency to 221.12 MHz, allowing the transmission of wide bandwidth signals.

This paper presents a customized adaptive cascaded deep learning (ACDL) model for the design and performance prediction of metasurface absorbers. A multi-resonant metasurface absorber structure is introduced, with 10 target-driven design parameters. The proposed deep learning model takes advantage of cascading several sub-deep neural network (DNN) layers with forward noise mitigation capability. The inherent appearance of sparse data is completely dealt with in this work by proposing a trained adaptive selection technique. On the basis of the findings, the prediction response is quite fast and accurate enough to retrieve the design parameters of the studied metasurface absorber and with two sized patches of 4000 and 7000 datasets. The training loss taken form the second DNN of our proposed model shows logarithmic mean squared errors of 0.039 and 0.033 when using Keras and the adaptive method, respectively, with a dataset split of 4000. On the contrary, for a dataset split of 7000, the errors are 0.049 with Keras and 0.045 with the adaptive method. On the other hand, the validation loss is evaluated using the mean square error method, which results in a loss with 4000 datasets split with the Keras method of 0.044, while it is 0.020 with the adaptive method. When extending the dataset to 7000, the validation loss with the keras splitting method is 0.0073, while it is improved, reaching 0.006 with the proposed adaptive method, and achieving a prediction accuracy of 94%. This proposed deep learning model can be deployed in the design process and synthesis of multi-resonant metasurface absorber structures. The proposed model shows its advantages of making the design process more efficient in sparse dataset handling, efficient approach in multi-resonance metasurface data pre-processing, less time consuming, and computationally valuable.

Seawater density is an important physical property in oceanography that affects the accuracy of calculations such as gravity fields and tidal potentials, and the calibration of acoustic and optical oceanographic sensors. In related studies, constant density values are frequently used, which can introduce significant errors. Therefore, this study employs a basic convolutional neural network model to construct a comprehensive model showing the seawater density distribution across the globe. The model takes into account depth, latitude, longitude, and month as inputs. Numerous real seawater datasets were used to train the model, and it has been shown that the model has an absolute mean error and root mean square error of less than 2 kg/m3 in 99% of the test set samples. The model effectively demonstrates the influence of input parameters on the distribution of seawater density. In this paper, we present a newly developed global model for distributing seawater density which is both comprehensive and accurate, surpassing previous models. The utilization of the model presented in this paper for estimating seawater density can minimize errors in theoretical ocean models and serve as a foundation for designing and analyzing ocean exploration systems.

Photovoltaic systems and wind energy systems are generally used in distributed system. However, zero-sequence and harmonic currents occur due to photovoltaic systems, and positive-sequence harmonic currents occur due to wind turbines. Thus, the sheath current in high voltage cables increases due to these currents and poor power quality in distributed generation plants. Metal parts of the cable are grounded to prevent the negative effects of sheath currents. When long high voltage cable lines are grounded with the method in the literature, high sheath current and voltage occur on the cable sheath. Therefore, the SSBLR method is designed as a new method for the distributed generation system. The SSBLR method has been optimized with prediction methods and multi-objective optimization methods to prevent negative effects of the sheath current. Pareto optimal method is used as multi-objective optimization method, and artificial neural network, hybrid artificial neural network and regression methods are used as prediction method. The most dominant result is searched using different estimation and optimization methods in pareto optimal method. When the artificial neural network-genetic algorithm hybrid method is used as a prediction method, and genetic algorithm used as optimization method, significant decreases are observed in sheath current and voltage.

This research looks into the evolving dynamics of ransomware, shifting from conventional encryption-based attacks to sophisticated data exfiltration strategies. Employing the Bidirectional Encoder Representations from Transformers (BERT) model, the study analyzes network traffic patterns to detect ransomware activities, offering new insights into their covert operations. The findings emphasize the need for advanced AI tools in cybersecurity, highlighting the significance of adapting and innovating defense strategies to counter the changing landscape of ransomware threats. The study contributes to a deeper understanding of ransomware evolution and underscores the importance of integrating AI in cybersecurity practices.

This proposed research explores a novel approach to image classification by deploying a complex-valued neural network (CVNN) on a field-programmable gate array (FPGA), specifically for classifying 2D images transformed into polar form. The aim of this research is to address the limitations of existing neural network models in terms of energy and resource efficiency, by exploring the potential of FPGA-based hardware acceleration in conjunction with advanced neural network architectures like CVNNs. The methodological innovation of this research lies in the Cartesian to polar transformation of 2D images, effectively reducing the input data volume required for neural network processing. Subsequent efforts focused on constructing a CVNN model optimized for FPGA implementation, emphasizing the enhancement of computational efficiency and overall performance. The experimental findings provide empirical evidence supporting the efficacy of the image classification system developed in this study. One of the developed models, CVNN_128, achieves an accuracy of 88.3% with an inference time of just 1.6ms and a power consumption of 4.66mW for the classification of the MNIST test dataset consists of 10,000 frames. While there is a slight concession in accuracy compared to recent FPGA implementations that achieve 94.43%, our model significantly excels in classification speed and power efficiency—surpassing existing models by more than a factor of 100. In conclusion, the paper demonstrates the substantial advantages of FPGA-implementation of CVNNs for image classification tasks, particularly in scenarios where speed, resource, and power consumption are critical. The study’s reproducible results and corresponding code are available on GitHub at the following link: https://github.com/mahmad2005/CVNNonFPGA

Seismic velocity inversion is one of the most critical issues in the field of seismic exploration and has long been the focus of numerous experts and scholars. In recent years, the advancement of machine learning technologies has infused new vitality into the research of seismic velocity inversion and yielded a wealth of research outcomes. Typically, seismic velocity inversion based on machine learning lacks control over physical processes and interpretability. Starting from wave theory and the physical processes of seismic data acquisition, this paper proposes a method for seismic velocity model inversion based on Physical Embedding Recurrent Neural Networks. Firstly, the wave equation is a mathematical representation of the physical process of acoustic waves propagating through a medium, and the finite difference method is an effective approach to solving the wave equation. With this in mind, we introduce the architecture of recurrent neural networks to describe the finite difference solution of the wave equation, realizing the embedding of physical processes into machine learning. Secondly, in seismic data acquisition, the propagation of acoustic waves from multiple sources through the medium represents a high-dimensional causal time series (wavefield snapshots), where the influential variable is the velocity model, and the received signals are the observations of the wavefield. This forms a forward modeling process as the forward simulation of the wavefield equation, and the use of error back-propagation between observations and calculations as the velocity inversion process. Through time-lapse inversion and incorporating the causal information of wavefield propagation, the non-uniqueness issue in velocity inversion is mitigated. Through mathematical derivations and theoretical model analyses, the effectiveness and rationality of the method are demonstrated. In conjunction with simulation results for complex models, the method proposed in this paper can achieve velocity inversion in complex geological structures.

Against the backdrop of the current carbon peaking and carbon neutrality policies, higher requirements have been put forward for the upgrading and construction of smart grids. Non-intrusive load monitoring (NILM) technology is a key technology for advanced measurement systems at the end of the power grid. It obtains detailed power information of the load, without the need for traditional hardware deployment. The key step to solve this problem is load decomposition and identification. This paper first utilized Long Short Term Memory-Denoising Autoencoder(LSTM-DAE) to decompose the mixed current signal on the household busbar and obtain the current signals of multiple independent loads that constituted the mixed current. Then, the obtained independent current signals were combined with voltage signals to generate multi-cycle colored Voltage-Current(VI) trajectories, which were color-coded according to the background. These colored VI trajectories with background colors formed a feature library. When the CNN network was used for load recognition, considering the influence of hyperparameters on recognition results, the BOA algorithm was used for optimization, and the optimized CNN network was employed for VI trajectory recognition. Finally, the proposed method was validated using the PLAID dataset. Experimental results showed that the proposed method exhibited better performance in load decomposition and identification.

The quickest path problem in the multistate flow networks, also known as the quickest path reliability problem (QPRP), aims at calculating the probability of transmitting a minimum of d units of flow/dat/commodity from a source node to a destination node through one single path within T units of time. Several exact and approximation algorithms have been proposed in the literature to address this problem. Most of the exact algorithms in the literature need prior knowledge of all the network’s minimal paths (MPs), which is considered a weak point. In addition to the time, the budget is always limited in real-world systems, making it an essential consideration in the analysis of systems’ performance. Hence, this study considers the QPRP under the cost constraints and provides an efficient approach based on the node-child matrix to address the problem without knowing the MPs. We show the correctness of the algorithm, compute its complexity results, illustrate it through a benchmark example, and conduct extensive experimental results on the known benchmarks and one thousand randomly generated test problems to demonstrate its practical superiority compared to the existing algorithms in the literature.

Machine Learning (ML) has proved its capabilities in different scientific and industrial fields, but it needs to be further investigated in the construction industry for practical utilization. One of the use cases of ML is delegating the structural calculation process. In this study, to discuss ML’s capabilities in performing the work of a structural designer, calculations of concrete sections based on ACI (American Concrete Institute) as a case study were selected. At first, all manual design steps and standard considerations for a concrete beam section were coded parametrically in MATLAB. After comparing with structural design references to prove the accuracy of codes in calculating shear and bending capacities, the parametric results were used as initial data (Look−up table) for training the ML operators. Regarding different types of ML techniques and as a comparison between them, in the next steps, all essential codes for Fuzzy Logic (FL), Neural Network (NN) and Adaptive Neuro-Fuzzy Inference System (ANFIS) were coded in the same platform. The performance of the three coded ML operators to replace (delegate) standard calculations compared to direct calculations was individually investigated and displayed through parametric examples. After initial examples, the influences of the number of parameters and size of the Look−up table on the accuracy of each operator were discussed. The study concluded that although all three operators can delegate the standard calculation, the precision of the results differs considerably. In case of the desirable size of the Look−up table, ANFIS operators can represent the standard calculations with a different number of parameters and entirely high precision.

The study aims to analyze the characteristic parameters of rooftop photovoltaic (PV) power generation on industrial plant buildings in the Ningxia region of China, in order to evaluate the impact of passive design characteristic parameters on the benefits of PV power generation and determine the degree of impact of different passive design characteristic parameters. The methodology involves analyzing the characteristics of existing industrial plant buildings in Ningxia, China, and conducting a series of regional studies on the parameters of plant PV power generation influencing factors. The simulation results revealed that five features, including roof form, PV panel laying pattern, PV panel laying area, azimuth angle, and PV module material, have a significant impact on PV power generation benefits of industrial plant buildings.The study further uses MATLAB 2022b to build a backpropagation neural network model with 5 neurons in the implicit layer to predict the PV power generation benefits. The model calculates the whole-life cycle power generation benefits and the whole-life cycle reduction of carbon emissions as output data. Finally, the Mean Impact Value (MIV) method is employed to select the feature parameter values one by one within their range, and the passive design feature parameters that have the greatest influence on the prediction results are identified as the PV panel laying method, the PV panel tilt angle, and the PV material parameters, respectively.

Applications of gradient method for nonlinear optimization in development of Gradient Neural Network (GNN) and Zhang Neural Network (ZNN) are investigated. Particularly, the solution of the matrix equation AXB=D which changes over time is studied using the novel GNN model, termed as GGNN(A,B,D). The GGNN model is developed applying GNN dynamics on the gradient of the error matrix used in the development of the GNN model. The convergence analysis shows that the neural state matrix of the GGNN(A,B,D) design converges asymptotically to the solution of the matrix equation AXB=D, for any initial state matrix. It is also shown that the convergence result is the least square solution which is defined depending on the selected initial matrix. A hybridization of GGNN with analogous modification GZNN of the ZNN dynamics is considered. The Simulink implementation of presented GGNN models is carried out on the set of real matrices.

We aim to map the ESG patterns of emerging-market companies from 2018 to 2021 in order to determine whether the COVID-19 pandemic exerted any influence on sustainable corporate behavior. Thus, the ESG performances were assessed by applying the Kohonen neural network for clustering purposes at three main levels: i) ESG overall, including country and sectoral perspectives; ii) ESG thematic; and iii) ESG four-folded (stakeholder, perspective, management level, and focus strategic views). Our results show that emerging-market companies focus their ESG efforts on social and governance issues rather than on environmental. However, environmental, and social behavior differ more acutely than governance behavior across clusters. The ESG pillars country-level and eleven market-based economic sectors analysis corroborate the geographic and sector dependence of ESG performance. The thematic-level analysis indicate that operational activities and community issues received more attention, which suggests that emerging-market companies address distinct ESG topics according to their particularities and competitiveness. Furthermore, our empirical findings provide evidence that the ESG behavior of companies has changed over the course of the COVID-19 pandemic. Thus, our findings are relevant to policymakers involved in regulating ESG disclosure practices, investors focused on enhancing their sustainable investment strategies, and firms engaged in improving their ESG involvement.

In August 2020, the World Health Assembly launched a global initiative to eliminate cervical cancer by 2030, setting three primary targets. One key goal is to achieve a 70% screening coverage rate for cervical cancer, primarily relying on the precise analysis of Papanicolaou (Pap) or digital Pap smears. However, the responsibility of reviewing Pap smear samples to identify potentially cancerous cells primarily falls on pathologists, a task known to be exceptionally challenging and time-consuming. This paper proposes a solution to address the shortage of pathologists for cervical cancer screening. It leverages the OpenAI-GYM API to create a deep reinforcement learning environment utilizing liquid-based Pap smear images. By employing the Proximal Policy Optimization algorithm, autonomous agents navigate Pap smear images, identifying cells with the aid of rewards, penalties, and accumulated experiences. Furthermore, the use of a pre-trained convolutional neuronal network like Res-Net54 enhances the classification of detected cells based on their potential for malignancy. The ultimate goal of this study is to develop a highly efficient, automated Papanicolaou analysis system, ultimately reducing the need for human intervention in regions with limited pathologists.

Communication infrastructures may be partially or completely destroyed due to the natural disasters, especially the disruption of a few critical network devices, leading to the collapse of communication services.To address this issue, we constructed a layered, multi-domain data transmission architecture based on a UAV-assisted resilient network. Initially, the UAV controllers perceived the network status and learning the temporal- spatial characteristics of air-to-ground networks links. Subsequently, we developed a multi-domain routing algorithm based on federated reinforcement distillation, called FedRDR, enhancing the generalization capabilities of routing decision model through the augmentation of training data samples.We conducted simulation experiments, and the results indicate that the FedRDR algorithm has an average communication data volume of approximately 45.3KB between each domain controller and server. Compared to parameter transmission through the federated reinforcement learning algorithm, FedRDR can reduce the amount of transmitted parameters by approximately 29\%. Therefore, the FedRDR routing algorithm promotes knowledge transfer, accelerates the training process of intra-domain intelligent agents, and decreases the communication data volume between domain controllers and servers.

Early spaceborne laser altimetry mission development starts in pre-phase A design, where diverse ideas are evaluated against mission science requirements. A key challenge is predicting realistic instrument performance through forward modeling at arbitrary spatial scale. Analytical evaluations compromise accuracy for speed, while radiative transfer modeling is not applicable at global scale due to computational expense. Instead of predicting arbitrary properties of a lidar measurement, we develop a baseline theory to predict only the distribution of uncertainty specifically for the terrain elevation retrieval based on terrain slope and fractional canopy cover features through a deep neural network gaussian mixture model, also known as a mixture density network (MDN). Training data was created from differencing geocorrected GEDI L2B elevation measurements with 32 independent reference lidar datasets in the contiguous U.S. from the National Ecological Observatory Network. We trained the MDN and selected hyperparameters based on regional distribution predictive capability. On average, the relative error of equivalent standard deviation of predicted regional distributions was 15.9%, with some anomalies in accuracy due to generalization and insufficient feature diversity and correlation. As an application, we predict the percent of elevation residuals of a GEDI-like lidar within a given mission threshold from 60°S to 78.25°N, which correlate to qualitative understanding of prediction accuracy and instrument performance.

The demand for high-energy-density batteries necessitates novel anode materials. Transition metal oxides (TMOs) show promise due to their high capacity, sustainability, and cost-effectiveness. However, TMO-based anodes face challenges related to expansion and conductivity. This study presents a two-step dilution crystallization method to fabricate porous ZnO nanoflowers at a moderate temperature. In-situ integration with carbon nanotube dispersants enhances conductivity and reduces agglomeration. The resulting composite anode exhibits impressive initial discharge capacity (2314.2 mAh g-1) and cycling stability (580.5 mAh g-1 over 50 cycles). This study provides a facile approach for next-generation anode materials.

This paper presents a novel approach for the recognition of multiple sclerosis (MS) using wavelet entropy and a Particle Swarm Optimization (PSO)-based neural network. MS is a complex neurological disorder with diverse clinical manifestations, often challenging to diagnose accurately. In this study, we leverage wavelet entropy (WE) as a feature extraction method to capture intricate patterns within brain imaging data. These extracted features are then employed to train a neural network model optimized through PSO to enhance classification accuracy. Experimental results on a dataset comprising MS and healthy control subjects demonstrate the effectiveness of our proposed approach, viz., WE-PSONN, which achieves a sensitivity of 91.95±1.15, a specificity of 92.36±0.88, a precision of 92.28±0.88, an accuracy of 92.16±0.90. The combination of advanced signal processing techniques and machine learning optimization holds promise for improving the early diagnosis and management of MS, offering potential benefits to both patients and healthcare providers.

Potentilla nepalensis belongs to the Rosaceae family, and has numerous therapeutic applications as potent plant-based medicine. Forty phytoconstituents (PCs) from the root and stem through n-hexane (NR and NS) and methanolic (MR and MS) extracts were identified in our earlier studies. However, the PCs affecting human genes and their roles in the body are not disclosed till now. In this study, we employed network pharmacology, molecular docking, molecular dynamics simulations (MDS), and MMGBSA methodologies. SMILES format of PCs from the PubChem used as input to DIGEP-Pred, 764 identified as the inducing genes. Their enrichment studies have shown inducing genes gene ontology descriptions, involved pathways, associated diseases, and drugs. PPI networks constructed in String DB and network topological analysing parameters done in Cytoscape v3.10 revealed three biomarkers, TP53 from MS, NR, and NS induced genes; HSPCB and Nf-kB1 from MR induced genes. From 40 PCs, two PCs 1b (MR) and 2a (MS), showed better binding scores (kcal/mol) with p53 protein of -8.6, and -8.0; three PCs 3a, (NR) 4a and 4c (NS) with HSP protein of -9.6, -8.7, and -8.2. MDS and MMGBSA revealed these complexes are stable without higher deviations with better free energy values. Biomarkers identified in this study, have a prominent role in numerous cancers. Thus, further investigations such as in-vivo and in-vitro should be done to find the molecular functions and interlaying mechanism of the identified biomarkers on numerous cancer cell lines in considering the PCs of P.nepalensis.

During the 1950s, the Gros Michel species of bananas were nearly wiped out by the incurable Fusarium Wilt, also known as Panama Disease. Originating in Southeast Asia, Fusarium Wilt is a banana pandemic that has been threatening the multi-billion-dollar banana industry worldwide. The disease is caused by a fungus that spreads rapidly throughout the soil and into the roots of banana plants. Currently, the only way to stop the spread of this disease is for farmers to manually inspect and remove infected plants as quickly as possible, whereas it is a time-consuming process. The main purpose of this study is to build a deep Convolutional Neural Network (CNN) using a transfer learning approach to rapidly identify fusarium wilt infections on banana crop leaves. We chose to use the ResNet50 architecture as the base CNN model for our transfer learning approach owing to its remarkable performance in image classification, which was demonstrated through its victory in the ImageNet competition. After its initial training and fine-tuning on a data set consisting of 300 healthy and diseased images, the CNN model achieved near-perfect accuracy of 0.99 and was fine-tuned to adapt the ResNet base model. ResNet50’s distinctive residual block structure could be the reason behind these results. To evaluate this CNN model, 500 test images, consisting of 250 diseased and healthy banana leaf images, were classified by the model. The deep CNN model was able to achieve an accuracy of 0.98 and an F-1 score of 0.98 by correctly identifying the class of 492 of the 500 images. These results show that this DCNN model outperforms existing models such as Sangeetha et al., 2023’s deep CNN model by at least 0.07 in accuracy and is a viable option for identifying Fusarium Wilt in banana crops.

Subway construction is often in a complex natural and human-machine operating environment, and that complicated setting leads to subway construction more prone to safety accidents, which can cause substantial casualties and monetary losses. Thus, it is necessary to investigate the safety risks of subway construction. The existing literature on the identification and assessment of subway construction safety risks(SCSR) is susceptible to the influence of subjective factors. Moreover, although existing studies have explored the interrelationships between different risks, these studies usually analyze the interrelationships of single risks, lack the study of risk chain transfer relationships, and fail to find out the key path of risk transfer. Therefore, this paper innovatively combines text mining, association rules and complex networks to deep mine subway construction safety incident reports and explore risk transfer process. Firstly, it uses text mining technology to identify subway construction safety risk; Then, association rules are introduced to explore the causal relationships among safety risk; Finally, the key safety risk and important transfer paths of subway construction safety accidents (SCSA) are obtained based on the complex network model. Research results show that (a) improper safety management, unimplemented safety subject responsibilities, violation of operation rules, non-perfect safety responsibilities system and insufficient safety education and training are the key safety risk in SCSA; (b) two shorter key risk transfer paths in the subway construction safety network can be obtained: insufficient safety education and training→lower safety awareness→violation of operation rules→safety accidents; insufficient safety checks or hidden trouble investigations→violation of operation rules→safety accidents; (c) in the process of risk transfer, the risk can be controlled by controlling the key nodes or cutting off the transfer path. The results of the study provide new ideas and methods for SCSR identification and influence element mining, which help safety managers propose accurate subway construction safety risk control measures.

The cities of the future are places of sustainable mobility and a continuous reduction in the amount of harmful substances entering the surrounding environment. Current emission models are mainly dedicated to fully combustion vehicles and do not fully reflect the actual emissions of vehicles in the fleet, which is becoming increasingly diverse. The increasing share of hybrid and electric vehicles is generating the need to measure emissions and energy consumption from these vehicles and to develop new emission models that are accurate. This problem mainly concerns low-emission zones in cities, where mobility planning should be based on simulation models that are based on a continuously updated database. This work concerns the proposal of a two-dimensional model of emissions from hybrid vehicles using artificial neural networks for low-emission zones. The results can be used to further develop such emission models.

Landslide is one of the most common geological disasters in China, which is characterized by suddenness and uncertainty, and it is difficult to realize accurate identification, early warning and forecasting of landslide disaster by conventional means. With the development of high-resolution remote sensing satellites and InSAR surface deformation monitoring technology, the traditional means of landslide monitoring data sources are limited, and there is a lack of effective methods to excavate the characteristics of the spatial distribution of landslide hazards and their triggering factors and other issues. In this paper, the area extending 10 km outside the VII isobar of the Gengma earthquake is taken as the study area, and 13 evaluation factors are screened out by integrating the factors of InSAR surface deformation, topography and geological environment, and the Bayesian Optimized Convolutional Neural Network (BO-CNN) is used for the evaluation of landslide susceptibility, and the BO-RF and PSO-SVM models are selected for the comparative analysis. The model accuracy evaluation was carried out by three indexes: ROC curve, AUC value and FR value, in which the ROC curves of PSO-SVM, BO-RF and BO-CNN were all close to the upper-left corner of the corner, and the AUC values were 0.9388, 0.9529, and 0.9535, respectively, and the FR value of landslide in the high susceptibility area of BO-CNN was as high as 14.9, and was higher than that of PSO-SVM and BO-RF, respectively. SVM and BO-RF model is 4.55 and 3.69 higher, the experimental results show that the BO-CNN model used in this paper has a better effect in landslide susceptibility evaluation, and the research results of the local government's disaster prevention and mitigation measures are of great significance.