This paper is focused on two topics very relevant in water distribution networks (WDNs): vulnerability assessment and the optimal placement of water quality sensors. The main novelty element of this paper is to represent the data of the problem, in this case all objects in a graph underlying a water distribution network, as discrete probability distributions. For vulnerability (and the related issue of re-silience) the metrics from network theory, widely studied and largely adopted in the water research community, reflect connectivity expressed as closeness centrality or, betweenness centrality based on the average values of shortest paths between all pairs of nodes. Also network efficiency and the related vulnerability measures are related to average of inverse distances. In this paper we propose a different approach based on the discrete probability distribution, for each node, of the node-to-node distances. For the optimal sensor placement, the elements to be represented as dis-crete probability distributions are sub-graphs given by the locations of water quality sensors. The objective functions, detection time and its variance as a proxy of risk, are accordingly represented as a discrete e probability distribution over contamination events. This problem is usually dealt with by EA algorithm. We’ll show that a probabilistic distance, specifically the Wasserstein (WST) distance, can naturally allow an effective formulation of genetic operators. Usually, each node is associated to a scalar real number, in the optimal sensor placement considered in the literature, average detection time, but in many applications, node labels are more naturally expressed as histograms or probability distributions: the water demand at each node is naturally seen as a histogram over the 24 hours cycle. The main aim of this paper is twofold: first to show how different problems in WDNs can take advantage of the representational flexibility inherent in WST spaces. Second how this flexibility translates into computational procedures.

Unmanned Aerial Vehicles (UAVs) in particular multirotors are becoming the {\it de facto} tool for aerial sensing and remote inspection. In large industrial facilities, a UAV can transmit an online video stream to inspect difficult to access structures, such chimneys, deposits and towers. However, the communication range is limited, constraining the UAV operation range. This limitation can be overcome with relaying UAVs placed between the source UAV and the control station, creating a line of communication links. In this work we assume the use of a digital data packet network technology, namely WiFi, and tackle the problem of defining the exact placement for the relaying UAVs that creates an end-to-end channel with maximal delivery of data packets. We consider asymmetric communication links and we show an increase as large as $15$\% in end-to-end packet delivery ratio when compared to an equidistant placement. We also discuss the deployment of such a network and propose a fully distributed method that converges to the global optimal relay positions taking, on average, 1.4 the time taken by a centralized method.

Blade Health Monitoring (BHM) is often necessary in power plants and in aviation to prevent excessive blade vibration and cracks. This article proposes a network of blade tip timing sensors operated in a distributed BHM system. A number of cooperating agents is implemented in smart conditioning units which can autonomously operate in an adverse environment and communicate with other nodes via a serial interface. The project uses special versions of reduced instruction set chips that are able to operate near the hot section of the engine. Due to the limited number of types of microprocessors available in the extended temperature range grading, it was necessary to fully utilize the limited hardware resources and implement preemptive multitasking. For this purpose, a custom operating system and communication protocol were designed. The protocol hosts the middle layer which hides the implementation of the distributed system. The presented architecture ensures the sufficient computational capacity in individual nodes of the network operated in adverse conditions. It is scalable and resistant to transmission errors.

Eddy current testing can be used to interrogate steels but it is hampered by the lift-off distance of the sensor. Previously, the lift-off point of intersection (LOI) feature has been found for the pulsed eddy current (PEC) testing. In this paper, a lift-off invariant inductance (LII) feature is proposed for the multi-frequency eddy current (MEC) testing, which merely targets the ferromagnetic steels. That is, at a certain working frequency, the measured inductance signal is found nearly immune to the lift-off distance of the sensor. Such working frequency and inductance are termed as the lift-off invariant frequency (LIF) and LII. Through simulations and experimental measurements of different steels under the multi-frequency manner, the LII has been verified to be merely related to the sensor parameters and independent of different steels. By referring to the LIF of the test piece and using an iterative inverse solver, one of the steel properties (either the electrical conductivity or magnetic permeability) can be reconstructed with a high accuracy.

Drug repositioning (also called drug repurposing) is a strategy for identifying new therapeutic targets for existing drugs. This approach is of great importance in pharmacology as it is a faster and cheaper way to develop new medical treatments. In this paper, we present, to our knowledge, the first application of multiplex-heterogeneous network embedding to drug repositioning. Network embedding learns the vector representations of nodes, opening the whole machine learning toolbox for a wide variety of applications including link prediction, node labelling or clustering. So far, the application of network embedding for drug repositioning focused on heterogeneous networks. Our approach for drug repositioning is based on multiplex-heterogeneous network embedding. Such method allows the richness and complexity of multiplex and heterogeneous networks to be projected in the same vector space. In other words, multiplex-heterogeneous networks aggregate different multi-omics data in the same network representation. We validate the approach on a task of link prediction and on a case study for SARS-CoV2 drug repositioning. Experimental results show that our approach is highly robust and effective for finding new drug-target associations.

Utilization of Bidirectional Reflectance Distribution Function (BRDF) model parameters obtained from the multi-angular remote sensing is one of the approaches for the retrieval of vegetation structural information. In this research, the potential of multi-angular vegetation indices, formulated by the combination of multi-spectral reflectance from different view angles, for the retrieval of forest above ground biomass was assessed. This research was implemented in the New England region with the availability of a high quality forest inventory database. The multi-angular vegetation indices were generated by the simulation of the Moderate Resolution Imaging Spectroradiometer (MODIS) BRDF/Albedo Model Parameters Product (MCD43A1 Version 6) based BRDF parameters. The effects of seasonal (spring, summer, autumn, and winter) composites of the multi-angular vegetation indices on above ground biomass, angular relationship of the spectral reflectance with above ground biomass, and the interrelationships between the multi-angular vegetation indices were analyzed. Among the existing multi-angular vegetation indices, only the Nadir BRDF-adjusted NDVI ( and Hot-spot incorporated NDVI ( showed significant relationship (more than 50%) with the above ground biomass. This research proposed two more sensitive vegetation structural indices, Fore-scattering Back-scattering NDVI and Vegetation Structure Index (VSI). The Fore-scattering Back-scattering NDVI showed higher sensitivity (R² = 0.62, RMSE = 52.46) towards the above ground biomass than existing multi-angular vegetation indices. Furthermore, the VSI performed in the most efficient way explaining 64% variation of the above ground biomass, suggesting that the right choice of the spectral channel and observation geometry should be considered for improving the estimates of the above ground biomass. In addition, the right choice of seasonal data (summer) was found to be important for estimating the forest biomass while other seasonal data were either insensitive or pointless. The promising results shown by the VSI suggest that it could be an appropriate candidate for monitoring vegetation structure from the multi-angular satellite remote sensing.

This study suggests a novel cooperative multi-simplex algorithm that generalizes a local search optimizer to design a novel global search heuristic algorithm. The proposed algorithm exploits the vertex sharing strategy to enhance the search abilities of the working simplexes. The vertex sharing among the simplexes is carried out through cooperative step that is based on fitness of the underlying simplex. The proposed algorithm is applied to solve some systems of nonlinear equations by transforming them to optimization problems. Comparative analysis of results shows that the proposed method is practical and effective.

Exploiting the linguistic knowledge of the source language for neural machine translation (NMT) has recently achieved impressive performance on many large-scale language pairs. However, since the Turkish→English machine translation task is low-resource and the source-side Turkish is morphologically-rich, there are limited resources of bilingual corpora and linguistic information available to further improve the NMT performance. Focusing on the above issues, we propose a multi-source NMT approach that models the word feature in parallel to external linguistic features by using two separate encoders to explicitly incorporate linguistic knowledge into the NMT model. We extend the word embedding layer of the knowledge-based encoder to accommodate for each word’s linguistic annotations in the context. Moreover, we share all parameters across encoders to enhance the representation ability of the NMT model on the source language. Experimental results show that our proposed approach achieves substantial improvements of up to 2.4 and 1.1 BLEU scores in Turkish→English and English→Turkish machine translation tasks, respectively, which points to a promising way to utilize the source-side linguistic knowledge for the low-resource NMT.

The next generation of wireless and mobile networks will have to handle a significant increase in traffic load compared to the actual one. This situation calls for novel ways to increase spectral efficiency. Therefore in this paper, we propose a wireless spectrum hypervisor architecture that abstracts a radio frequency (RF) front-end into a configurable number of virtual RF front-ends. The proposed architecture has the ability to enable flexible spectrum access in existing wireless and mobile networks, which is a challenging task due to the limited spectrum programmability, $i.e.$, the capability a system has to change the spectral properties of a given signal to fit an arbitrary frequency allocation. The main goal of the proposed approach is to improve spectral efficiency by efficiently using vacant gaps in congested spectrum-bandwidths or adopting network densification through infrastructure sharing. We demonstrate mathematically how our proposed approach works and present several simulation results proving its functionality and efficiency. Additionally, we designed and implemented an open-source and free proof of concept prototype of the proposed architecture, which can be used by researchers and developers to run experiments or extend the concept to other applications. We present several experimental results used to validate the proposed prototype. We demonstrate that the prototype can easily handle up to 12 concurrent physical layers.

The highest efficiency solar cell won in the efficiency race does not always give the most excellent annual energy yield in the real world solar condition that the spectrum is ever-changing. The study of the radiative coupling of the concentrator solar cells implied that the efficiency could increase by the recycle of the radiative recombination generated by the surplus current in upper junction. Such configuration is called by a super-multi-junction cell. We expanded the model in the concentrator solar cell to non-concentrating installation. It was shown that this super-multi-junction cell configuration was found robust and can keep the maximum potential efficiency (50 % in realistic spectrum fluctuation) up to 10 junctions. The super-multi-junction cell is also robust in the bandgap engineering of each junction. Therefore, the future multi-junction may not be needed to tune the bandgap for matching the standard solar spectrum, as well as relying upon artificial technologies like ELO (Epitaxial lift-off), wafer-bonding, mechanical-stacking, and reverse-growth, but merely uses up-right and lattice-matching growth technologies. We have two challenging techniques; one is the optical cap layer that may be the directional photon coupling layer in the application of the photonics technologies, and another is the high-quality epitaxial growth with almost 100 % of the radiative efficiency.

Multi-receiver encryption enables a sender to encrypt a message and transmit the ciphertext to a set of authorized users, while no one out this group of authorized users can decrypt the message. Multi-receiver encryption is of great importance in many sectors such as broadcast communication, cloud computing, wireless communications, networking applications, e-voting, lottery, and medical applications. This paper proposes an efficient multi-receiver public key encryption scheme based on Lucas sequences. The results of the computational analysis show that, projected scheme is better against renown attacks and prevailing anonymous multireceiver algorithms

Recently, torrential rain and drought have occurred in close temporal proximity and for similar durations due to changes in the spatiotemporal patterns of rainfall owing to climate change. In particular, when a drought occurs, it tends to be prolonged, making it necessary to improve the operation of multi-purpose dams that not only control flooding but also serve as water supplies. In this study, standard water volume lines and action plans by response stage were improved so that water could be stored in advance of a drought instead of reservoir operation criteria set based on data from the past. The minimum water demand by use (domestic water, industrial water, and agricultural water) was also calculated. The improved reservoir operation criteria were applied to multi-purpose dams in the Nakdong River Basin, and their effects were analyzed by calculating additionally secured water volumes. In the future, in case of lowered water volumes in multi-purpose dams owing to a drought, the application of these improved reservoir operation criteria is expected to contribute to water supply stability by delaying entry into the drought stage, and minimizing the damages caused by limited water supplies.

Accurate and timely rainfall prediction enhances productivity and can aid proper planning in sectors such as agriculture, health, transport and water resources. This study is aimed at improving rainfall prediction using ensemble methods. It first assesses the performance of six convective schemes (Kain–Fritsch (KF); Betts–Miller–Janji´c (BMJ); Grell–Fretas (GF); Grell 3D ensemble (G3); New–Tiedke (NT) and Grell–Devenyi (GD)) using the root mean square error (RMSE) and mean error (ME) focusing on the March–May 2013 rainfall period over Uganda. 18 ensemble members are generated from the three best performing convective schemes (i.e. KF, GF & G3). The performance of three ensemble methods (i.e. ensemble mean (EM); ensemble mean analogue (EMA) and multi–member analogue ensemble (MAEM)) is also analyzed using the RMSE and ME. The EM presented a smaller RMSE compared to individual schemes (EM:10.02; KF:23.96; BMJ:26.04; GF:25.85; G3:24.07; NT:29.13 & GD:26.27) and a better bias (EM:-1.28; KF:-1.62; BMJ:-4.04; GF:-3.90; G3:-3.62; NT:-5.41 & GD:-4.07). The EMA and MAEM presented 13 out of 21 stations & 17 out of 21 stations respectively with smaller RMSE compared to EM thus demonstrating additional improvement in predictive performance. The MAEM is a new approach proposed and described in the study.

With the increasing demand for precise condition monitoring and diagnosis of gas-insulated switchgears (GIS), it has become a challenge to improve the detection sensitivity of partial discharge (PD) induced in the GIS spacer. This paper deals with the elimination of the capacitive component from the phase resolved partial discharge (PRPD) signal generated in GIS spacer based on the discrete wavelet transform. Three types of typical insulation defects were simulated using PD cells. The single PD pulses were detected and were further used to determine the optimal mother wavelet. As a result, the bior6.8 was selected to decompose the PD signal into 8 levels and the signal energy at each level was calculated. The decomposed components related with capacitive disturbance were discarded whereas those associated with PD were de-noised by a threshold and a thresholding function. Finally, the PRPD signals were reconstructed using the de-noised components.

The evaluation of spatial planning results, or outcomes, has been rather neglected by scholars and practitioners. The causes of this neglect are linked to the characteristics of the planning systems in use or difficulties in quantifying results. To advance the state of the art of outcome evaluation, this paper focuses on assessing the implementation of national spatial planning objectives in urban landscapes, through the use of an evaluation framework that makes use of spatially explicit information. The framework is built on four dimensions which reflect the main domains of spatial planning: efficient built-up development, conservation of agricultural land, landscape preservation, and human perception. Indicators capable of capturing landscape changes in both time and space are used to verify degree of conformance between adopted objectives and actual development patterns. We make use of spatially explicit data and assess whether and where landscape changes occurred, by integrating the framework into a multi-criteria analysis. In the present study, the framework is tested in two study areas in Switzerland and Romania, and the results are interpreted from the perspective of spatial planning approaches in the two countries. The efficiency and utility of the framework is demonstrated by its ability to provide valuable information facilitating improvement in the performance of planning processes, such as identifying where the implementation of objectives is less effective, and the domains of spatial planning that are affected. Our findings highlight that the distance between objectives and outcomes can be attributed to differences in countries’ spatial planning approaches, particularly regarding landscape preservation and management. Our study provides valuable insights for the integration of time series of spatial data into the evaluation procedure.

The evolving multiphase induction generators (MPIG) with more than three phases are receiving prominence in high power generation systems. This paper aims at the development of a comprehensive model of the wind turbine driven seven-phase induction generator (7PIG) along with necessary the power electronic converters and controller for grid interface. The dynamic model of the system is developed in Maltlab/Simulink. Synchronous reference frame phase-locked loop (SRFPLL) system is incorporated for grid synchronization. The modeling aspects are detailed and the system response is observed for various wind velocities. The effectiveness of seven phase induction generator is demonstrated with the fault tolerant capability and high output power with reduced phase current when compared to conventional 3-phase wind generation scheme. The response of the PLL is analyzed and the results are presented.

Intelligent systems are driven by the latest technological advances in so different areas as sensing, embedded systems, wireless communications or context recognition. This paper focuses on some of those areas. Concretely, the paper deals with wireless communications issues on embedded systems. More precisely, the paper combines the multi-hop networking with Bluetooth technology and a quality of service (QoS) metric, the latency. Bluetooth is a radio license free worldwide communication standard that makes low power multi-hop wireless networking available. It establishes piconets (point-to-point and point-to-multipoint links) and scatternets (multi-hop networks). As a result, many Bluetooth nodes can be interconnected to set up ambient intelligent networks. Then, this paper presents the results of the investigation on multi-hop latency with park and sniff Bluetooth low power modes conducted over the hardware test bench previously implemented. In addition, the empirical models to estimate the latency of multi-hop communications over Bluetooth Asynchronous Connectionless Links (ACL) in park and sniff mode are given. The designers of devices and networks for intelligent systems will benefit from the estimation of the latency in Bluetooth multi-hop communications that the models provide.

Marine renewable energy is emerging as one of the fast-growing industry in the last decades, as modern society pushes for technologies that can convert energy contained from winds, waves, tides and stream flows. The implementation of renewable energy technologies impose high demands on both structural and environmental engineering, as the energy converters have to work under extreme conditions where parameters such as sea-bottom configuration, water transparency and depth, sea-states and prevailing winds are harsh. Constant monitoring of the marine environment is crucial in order to keep this sector reliable. Active acoustics is becoming a standard tool to collect multi-dimensional data from physical, geological and biological properties of the marine environment. The Div. of Electricity of Uppsala University have been developing an environmental monitoring platform based on sonar systems. This platform aims to monitor the installation, operation and decommissioning of marine renewable energy converters. The focus will be given the observations of behaviors of marine animals in vicinity of energy converters but also structural inspection and monitoring of MRETs. This paper describes how this multifunctional environmental monitoring platform come to existence from the design to the deployment phase.

In any document, graphical elements like tables, figures, and formulas contain essential information. The processing and interpretation of such information require specialized algorithms. Off-the-shelf OCR components cannot process this information reliably. Therefore, an essential step in document analysis pipelines is to detect these graphical components. It leads to a high-level conceptual understanding of the documents that makes digitization of documents viable. Since the advent of deep learning, the performance of deep learning-based object detection has improved many folds. In this work, we outline and summarize the deep learning approaches for detecting graphical page objects in the document images. Therefore, we discuss the most relevant deep learning-based approaches and state-of-the-art graphical page object detection in document images. This work provides a comprehensive understanding of the current state-of-the-art and related challenges. Furthermore, we discuss leading datasets along with the quantitative evaluation. Moreover, it discusses briefly the promising directions that can be utilized for further improvements.

Tree species composition is an important key element for biodiversity and sustainable forest management, and hyperspectral data provide detailed spectral information, which can be used for tree species classification. There are two main challenges for using hyperspectral imagery: a) Hughes phenomena, meaning by increasing the number of bands in hyperspectral imagery, the number of required classification samples would increase exponentially, and b) in a more complex environment, such as riparian mixed forest, focusing on spectral variability per pixel may not be adequate for definability of tree species. Therefore, the focus of this study is to assess spectral-spatial dimensionality reduction of airborne hyperspectral imagery by using minim noise fraction (MNF) transformation, and object-based image analysis (OBIA). An airborne prism experiment (APEX) hyperspectral imagery was used. A study area was a riparian mixed forest located along the Salzach river, and six tree species including Picea abies, Populus (canadensis and balsamifera), Fraxinus excelsior, Alnus incana, and Salix alba were selected. A machine learning algorithm random forest (RF) was used to train and apply a prediction model for classification. Using a spectral dimensionality reduced APEX, a pixel-level classification was also done. According to a confusion matrix, the object-level classification of MNF-derived components achieved the overall accuracy of 85 %, and kappa coefficient of 0.805. The performance of classes according to producer’s accuracy varied between 80% for Fraxinus excelsior, Alnus incana, and Populus canadensis to 90% for Salix alba and Picea abies. Comparison the results to a pixel-level classification, showed a better performance of object-level classification (an overall accuracy of 63% and Kappa coefficient of 0.559 were achieved for pixel-level classification). The performance of classes using pixel-based classification varied 45 % for Alnus incana to 80% for Picea abies. In general, Spectral-spatial complexity reduction using MNF transformation and object-level classification yielded a statistically satisfactory results.

Miscanthus holds a great potential in the frame of the bioeconomy and yield prediction can help improving Miscanthus logistic supply chain. Breeding programs in several countries are attempting to produce high-yielding Miscanthus hybrids better adapted to different climates and end-uses. Multispectral images acquired from unmanned aerial vehicles (UAVs) in Italy and in the UK in 2021 and 2022 were used to investigate the feasibility of high-throughput phenotyping (HTP) of novel Miscanthus hybrids for yield prediction and crop traits estimation. An intercalibration procedure was performed using simulated data from the PROSAIL model to link vegetation indices (VIs) derived from two different multispectral sensors. Random forest algorithm estimated with good accuracy yield traits (light interception, plant height, green leaf biomass and standing biomass) using VIs time series and predicted yield using peak descriptor derived from VIs time series with 2.3 Mg DM ha-1 of RMSE. The study demonstrates the potential of UAVs multispectral in HTP applications and in yield prediction for providing important information needed to increase sustainable biomass production.

Solidification microstructure is formed under high cooling rates and temperature gradients in powder-based additive manufacturing. In this study, a non-equilibrium multi-phase field method (MPFM), which was based on a finite interface dissipation model proposed by Steinbach et. al., coupled with a CALPHAD database was developed for a multicomponent Ni alloy. A qua-si-equilibrium MPFM was also developed for comparison. Two-dimensional equiaxed micro-structural evolution for the Ni (Bal.)–Al–Co–Cr–Mo–Ta–Ti–W–C alloy was performed at various cooling rates. The temperature–γ fraction profiles obtained under 10^5 K/s using non- and qua-si-equilibrium MPFMs were in good agreement with each other. Over 10^6 K/s, the differences between non- and quasi-equilibrium methods grew as the cooling rate increased. The non-equilibrium solidification was strengthened over a cooling rate of 10^6 K/s. Colum-nar-solidification microstructural evolution was performed under cooling rates from 5×10^5 K/s to 1×10^7 K/s at various temperature gradient values under the constant interface velocity (0.1 m/s). The results showed that as the cooling rate increased, the cell space decreased in both methods, and the non-equilibrium MPFM agreed well with experimental measurements. Our results show that the non-equilibrium MPFM can simulate solidification microstructure in powder bed fusion additive manufacturing.

Several studies in computer vision have examined specular removal, which is crucial for object detection and recognition. This research has traditionally been divided into two tasks: specular highlight removal, which focuses on removing specular highlights on object surfaces, and reflection removal, which deals with specular reflections occurring on glass surfaces. In reality, however, both types of specular effects often coexist, making it a fundamental challenge that has not been adequately addressed. Recognizing the necessity of integrating specular components handled in both tasks, we constructed a Specular-Light (S-Light) DB for training single-image-based deep learning models. Moreover, considering the absence of benchmark datasets for quantitative evaluation, the Multi-Scale Normalized Cross Correlation (MS-NCC) metric, which considers the correlation between specular and diffuse components, was introduced to assess the learning outcomes.

Deep learning classification is the state-of-the-art of machine learning approach. Earlier work proves that the deep convolutional neural network has successfully and brilliantly in different applications such as images or video data. Recognizing and clarifying the remote sensing aspect of the earth's surface and exploit land cover and land use (LCLU). First, this article summarized the remote sensing emerging application and challenges for deep learning methods. Second, we propose four approaches to learn efficient and effective CNNs to transfer image representation on the ImageNet dataset to recognize LCLU datasets. We use VGG16, Inception-ResNet-V2, Inception-V3, and DenseNet201 models to extract features from the EACC dataset. We use pre-trained CNNs on ImageNet to extract features. For feature selection we proposed principal component analysis (PCA) to improve accuracy and speed up the model. We train our model by multi-layer perceptron (MLP) as a classifier. Lastly, we apply the multi-granularity encoding ensemble model. We achieve an overall accuracy of 92.3% for the nine-class classification problem. This work will help remote sensing scientists understand deep learning tools and apply them in large-scale remote sensing challenges

The World Health Organization has developed the Integrated Care of Older People (ICOPE) strategy, a program based on the measurement of intrinsic capacity (IC) as “the composite of all physical and mental attributes on which an individual can draw”. Multicomponent interventions appear to be the more effective approach to enhance IC and to prevent frailty and dependence, being adapted physical activity is the preventive intervention that has shown more evidence in the treatment of frailty and risk of falls. The present study aims to describe the development of a multi-domain group-based intervention addressed to frail older people living in the community aimed to improve and/or maintain intrinsic capacity by means of promoting physical activity, healthy nutrition, and psychological wellbeing in frail older people. We used the GUIDED checklist to describe the development process of AMICOPE (Aptitude Multi-domain group-based intervention to improve and/or maintain IC in frail Older PEople). The intervention was built upon the ICOPE framework and it is described with Template for Intervention Description and Replication (TIDieR) guidelines and it includes dietary advice, cognitive stimulation strategies, medication review, goal setting, and activities to strengthen social support and manage depressive symptoms, as well as strength, balance and flexibility exercise using the Vivifrail program. The study represents the first stage of the UK Medical Research Council framework for developing and evaluating a complex intervention. The next step should be carrying out a feasibility study for the AMICOPE intervention, and in a later stage, assessing the effectiveness in a randomized controlled trial.

The study aims to elaborate a neural model and algorithm for optimising hardness and porosity of coatings and thus ensure that they have superior cavitation erosion resistance. Al2O3-13wt.%TiO2 ceramic coatings were deposited onto 316L stainless steel by atmospheric plasma spray (ASP). The coatings were prepared with different values of two spray process parameters: the stand-off distance and torch velocity. Microstructure, porosity and microhardness of the coatings were examined. Cavitation erosion tests were conducted in compliance with the ASTM G32 standard. Artificial neural networks (ANN) were employed to elaborate the model, and the multi-objectives genetic algorithm (MOGA) was used to optimise both properties and cavitation erosion resistance of the coatings. Results were analysed with Matlab software by Neural Network Toolbox and Global Optimization Toolbox. The fusion of artificial intelligence methods (ANN+MOGA) is essential for future selection of thermal spray process parameters, especially for the design of ceramic coatings with specified functional properties. Selection of these parameters is a multicriteria decision problem. The proposed method made it possible to find a Pareto front, i.e. trade-offs between several conflicting objectives – maximising the hardness and cavitation erosion resistance of Al2O3-13%TiO2 coatings and, at the same time, minimizing their porosity.

Tables in the document image are one of the most important entities since they contain crucial information. Therefore, accurate table detection can significantly improve information extraction from tables. In this work, we present a novel end-to-end trainable pipeline, HybridTabNet, for table detection in scanned document images. Our two-stage table detector uses the ResNeXt-101 backbone for feature extraction and Hybrid Task Cascade (HTC) to localize the tables in scanned document images. Moreover, we replace conventional convolutions with deformable convolutions in the backbone network. This enables our network to detect tables of arbitrary layouts precisely. We evaluate our approach comprehensively on ICDAR-13, ICDAR-17 POD, ICDAR-19, TableBank, Marmot, and UNLV. Apart from the ICDAR-17 POD dataset, our proposed HybridTabNet outperforms earlier state-of-the-art results without depending on pre and post-processing steps. Furthermore, to investigate how the proposed method generalizes unseen data, we conduct an exhaustive leave-one-out-evaluation. In comparison to prior state-of-the-art results, our method reduces the relative error by 27.57% on ICDAR-2019-TrackA-Modern, 42.64% on TableBank (Latex), 41.33% on TableBank (Word), 55.73% on TableBank (Latex + Word), 10% on Marmot, and 9.67% on UNLV dataset. The achieved results reflect the superior performance of the proposed method.

Pieron's and Chocholle’s seminal psychophysical work predicts that human response time to information relative to visual contrast and/or sound frequency decreases when contrast intensity or sound frequency increases. The goal of this study is to bring to the fore the ability of individuals to use visual contrast intensity and sound frequency in combination for faster perceptual decisions of relative depth (“nearer”) in planar (2D) object configurations on the basis of physical variations in luminance contrast. Computer controlled images with two abstract patterns of varying contrast intensity, one on the left and one on the right, preceded or not by a pure tone of varying frequency, were shown to healthy young humans in controlled experimental sequences. Their task (two-alternative forced-choice) was to decide as quickly as possible which of two patterns, the left or the right one, in a given image appeared to “stand out as if it were nearer” in terms of apparent (subjective) visual depth. The results show that the combinations of varying relative visual contrast with sounds of varying frequency exploited here produced an additive effect on choice response times in terms of facilitation, where a stronger visual contrast combined with a higher sound frequency produced shorter forced-choice response times. This new effect is predicted by cross-modal audio-visual probability summation.

The Onion Route Network (also called TOR) is by far the most efficient and widely used anonymity platform with millions of users daily and an expanding size and capacities. Since its public deployment in 2002, the Onion Routing network (also known as TOR) has maintained its leading position and dozens of propositions aiming to improve its performance and enhance the security (anonymity and privacy) have been made. Given the significance of this research area, this work seek to contribute into the improvement of TOR by investigating and testing revolutionary cryptographic and routing mechanism. This work is justified by the current TOR vulnerability and observed weaknesses, and set the challenging aim of covering these security flaws by proposing the relevant security and performances improvement such as the authenticated-encryption for onion construction, the lightened onion encapsulation approach and the secured circuit selection and cell routing mechanisms. The obtained results from implementing the proposed improvements and testing them into a TOR-like simulation platform permit to validate not only, the performances and security contributions brought by the improvement, but also the suitability of their potential implementation into the real TOR network.

The option of decarbonizing urban freight transport using Battery Electric Vehicle (BEV) seems promising.However, there is currently a strong debate whether Fuel Cell Electric Vehicle (FCEV) might be the bettersolution. The question arises as to how a fleet of FCEV influences the operating cost, the Greenhouse Gas(GHG) emissions and primary energy demand in comparison to BEVs and to Internal Combustion EngineVehicle (ICEV). To investigate this, we simulate the urban food retailing as a representative share of urbanfreight transport using a multi-agent transport simulation software. Synthetic routes as well as fleet size andcomposition are determined by solving a Vehicle Routing Problem (VRP). We compute the operating costsusing a total cost of ownership (Total Cost of Ownership (TCO)) analysis and the use phase emissions as wellas primary energy demand using the Well To Wheel (WTW) approach. While a change to BEV results in 17 -23% higher costs compared to ICEV, using FCEVs leads to 22 - 57% higher costs. Assuming today’s electricitymix, we show a GHG emission reduction of 25% compared to the ICEV base case when using BEV. Currenthydrogen production leads to a GHG reduction of 33% when using FCEV which however cannot be scaled tolarger fleets. Using current electricity in electrolysis will increase GHG emission by 60% compared to the basecase. Assuming 100% renewable electricity for charging and hydrogen production, the reduction from FCEVsrises to 73% and from BEV to 92%. The primary energy requirement for BEV is in all cases lower and forhigher compared to the base case. We conclude that while FCEV have a slightly higher GHG savings potentialwith current hydrogen, BEV are the favored technology for urban freight transport from an economic andecological point of view, considering the increasing shares of renewable energies in the grid mix.

The lumpy skin disease virus (LSDV) is an animal virus and a member of the Poxviridae family, which causes lumpy skin disease (LSD) in livestock animals like cows and buffaloes. LSD is an important transboundary disease of economic importance that was first discovered in 1929 in Zambia. LSDV has been prevalent in African countries, where several outbreaks have been reported previously. However, the virus has spread rapidly across the Middle East in the past two decades, reaching Russia and, recently, the Asian subcontinent. With the unprecedented cluster outbreaks reported across Asian countries, LSDV is certainly undergoing an epidemiological shift and expanding its geographical footprint globally. The recent LSD outbreaks have gained attention from global regulatory authorities and raised serious concerns among epidemiologists and veterinary researchers. Although there is no dearth of knowledge about LSDV, the disease lacks networked global surveillance and management, consequently making the current statistics deficient, fragmented, and unreliable. Hence, recurrent LSD outbreaks seriously threaten the global livestock industry. This review provides recent insights into LSDV by augmenting latest literature associated with its epidemiology, pathogenesis, transmission, currently-available intervention strategies, and economic implications on the dairy industries. The review also critically examines the changing epidemiological footprint of LSD and speculates on the possible reasons contributing to the ongoing multi-country LSD outbreak.

In Ultra-wideband (UWB)-based wireless ranging or distance measurement, differentiation between line-of-sight~(LOS), non-line-of-sight~(NLOS), and multi-path (MP) conditions are important for precise indoor localization. This is because the accuracy of the reported measured distance in UWB ranging systems is directly affected by the measurement conditions (LOS, NLOS or MP). However, the major contributions in literature only address the binary classification between LOS and NLOS in UWB ranging systems. The MP condition is usually ignored. In fact, the MP condition also has a significant impact on the ranging errors of the UWB compared to the direct LOS measurement results. Though, the magnitudes of the error contained in MP conditions are generally lower than completely blocked NLOS scenarios. This paper addresses machine learning techniques for identification of the mentioned three classes (LOS, NLOS, and MP) in the UWB indoor localization system using an experimental data-set. The data-set was collected in different conditions at different scenarios in indoor environments. Using the collected real measurement data, we compare three machine learning (ML) classifiers, i.e., support vector machine (SVM), random forest (RF) based on an ensemble learning method, and multilayer perceptron (MLP) based on a deep artificial neural network, in terms of their performance. The results show that applying ML methods in UWB ranging systems are effective in identification of the above-mentioned three classes. In specific, the overall accuracy reaches up to 91.9% in the best-case scenario and 72.9% in the worst-case scenario. Regarding the F1-score, it is 0.92 in the best-case and 0.69 in the worst-case scenario. For reproducible results and further exploration, we (will) provide the publicly accessible experimental research data discussed in this paper at PUB - Publications at Bielefeld University. The evaluations of the three classifiers are conducted using the open-source python machine learning library scikit-learn.

This paper investigates the leader-following H∞ consensus of fractional-order multi-agent systems (FOMASs) under input saturation via the output feedback. Based on the bounded real lemma for FOSs, the sufficient conditions of H∞ consensus for FOMASs are provided in α∈0,1 and 1,2, respectively. Furthermore, the iterative linear matrix inequalities (ILMIs) approaches are applied for solving quadratic matrix inequalities (QMIs). The ILMI algorithms show a method to derive initial values and transform QMIs into LMIs. Mathematical tools are employed to transform the input saturation issue into optimal solution of LMIs for estimating stable regions. The ILMI algorithms avoid the conditional constraints on matrix variables during the LMIs construction and reduce conservatism. The approach does not disassemble the entire MASs by transformations to the Laplacian matrix, instead adopting a holistic analytical perspective to obtain gain matrices. In the end, numerical examples are conducted to validate the efficiency of the approach.

Cancer cells display elevated reactive oxygen species (ROS) and altered redox status, Here based on these characteristics, we develop a multi-drug delivery platform AMB@PDAP-Fe (APPF), from magnetotactic bacterium AMB-1 and realize MRI-visualized tumor microenvironment-responsive photothermal-chemodynamic therapy. The Fe3+ in PDAP-Fe is reduced by the GSH at tumor site and is released in the form of highly active Fe2+, which catalyzes the generation of ROS through Fenton reaction and inhibits tumor growth. At the same time, the significant absorption of the mineralized magnetosomes in AMB-1 cells in the NIR region enable them to efficiently convert near-infrared light into heat energy for photothermal therapy (PTT), to which PDAP also contributes. The heat generated in the PTT process accelerates the process of Fe2+ release, thereby achieving an enhanced Fenton reaction in tumor microenvironment. In addition, the magnetosomes in AMB-1 are used as MRI contrast agent, and the curing process is visualized. This tumor microenvironment-responsive MTB-based multi-drug delivery platform displays a potency to combat tumor and demonstrates the utility and practicality of understanding the cooperative molecular mechanism when designing multi-drug combination therapies.

Light can interfere like a wave in a multi-path experiment, but it also has particle properties when interacting with matter. In a closer look, the interference pattern is created by many individual detections ("clicks"), which do not all occur simultaneously. An established assumption is therefore that a single light particle is capable of interfering with itself by superimposing all possibilities to get from the source to the detector. This is in stark contrast to our experience with macroscopic objects, which always "decide" in favour of only one of the alternative paths.In 2010, Jin et al. (Ref. 15) described an event-based model which allowed the authors to show that an interference pattern consisting of clicks can arise in a multi-path experiment even if photons, like macroscopic objects, only follow one path. To do this, photons must be able to transmit the information about their travelling duration to the detector and the detector must have a basic memory. A threshold function uses the message of several light quanta to decide whether a single detection is initiated, which is not the evidence for a single photon. In this "proof of principle", the authors do not claim that the detector function is a realistic one.In the present paper, this detector is replaced by a material consisting of ionizable molecules whose interaction with light takes place according to a modified version of Einstein's radiation laws. Based on this, a photon pair interaction mediated by matter takes place, which in a multi-path experiment generates an interference pattern of clicks at the detector, even if an arbitrary amount of time elapses between the individual detections. In the present model an interference pattern with minima that have less than half the intensity of the maxima is the result of a peculiar behaviour of the detector: In this case, the entirety of its electrons must be described as a unit (a “field”) with many equidistant energy levels. The results of a simulation are presented which enable the model to be tested in experiments.

Light can interfere like a wave in a multi-path experiment, but it also has particle properties when interacting with matter. In a closer look, the interference pattern is created by many individual detections ("clicks"), which do not all occur simultaneously. An established assumption is therefore that a single light particle is capable of interfering with itself by superimposing all possibilities to get from the source to the detector. This is in stark contrast to our experience with macroscopic objects, which always "decide" in favour of only one of the alternative paths.In 2010, Jin et al. (Ref. 15) described an event-based model which allowed the authors to show that an interference pattern consisting of clicks can arise in a multi-path experiment even if photons, like macroscopic objects, only follow one path. To do this, photons must be able to transmit the information about their travelling duration to the detector and the detector must have a basic memory. A threshold function uses the message of several light quanta to decide whether a single detection is initiated, which is not the evidence for a single photon. In this "proof of principle", the authors do not claim that the detector function is a realistic one.In the present paper, this detector is replaced by a material consisting of ionizable molecules whose interaction with light takes place according to a modified version of Einstein's radiation laws. Based on this, a photon pair interaction mediated by matter takes place, which in a multi-path experiment generates an interference pattern of clicks at the detector, even if an arbitrary amount of time elapses between the individual detections. In the present model an interference pattern with minima that have less than half the intensity of the maxima is the result of a peculiar behaviour of the detector: In this case, the entirety of its electrons must be described as a unit (a “field”) with many equidistant energy levels. The results of a simulation are presented which enable the model to be tested in experiments.

In order to improve real-time performance of gesture recognition by micro-Doppler map of mmWave Radar, the point cloud based gesture recognition for mmWave Radar is proposed in this paper.Two steps are carried out for mmWave Radar based gesture recognition. The first step is to estimate the point cloud of the gestures by 3D-FFT and the peak grouping. The second step is to train the TRANS-CNN model by combining the multi-head self-attention and the 1D-convolutional network, so as to extract the features in the point cloud data at a deeper level to categorize the gestures. In the experiments, TI mmWave Radar sensor IWR1642 is used as benchmark to evaluate the feasibility of the proposed approach. The results show that the accuracy of the gesture recognition reaches 98.5%. In order to prove the effectiveness of our approach, a simply 2Tx2Rx Radar sensor is developed in our lab and the accuracy of recognition reaches 97.1%. The results show that our proposed gesture recognition approach achieves the best performance in real-time with limited training data, in comparison with the existing methods.

In recent years, the viability of employing multi-agent reinforcement learning technology for adaptive traffic signal control has been extensively validated. However, owing to restricted communication among agents and the partial observability of the traffic environment, the process of mapping road network states to actions encounters numerous challenges. To address this problem, this paper proposes a multi-agent deep reinforcement learning model with an emphasis on communication content (CMARL). The model decouples the complex relationships between multi-signal agents through centralized training and decentralized execution. Specifically, we first pass the traffic state through an improved deep neural network to achieve the extraction of high-dimensional semantic information and the learning of the communication matrix. Then the agents selectively interact with each other based on the learned communication matrix and generate the final state features. Finally, the features are inputted to the QMIX network to achieve the final action selection. We compare the CMARL model with 6 other baseline algorithms in real traffic networks. The results show that CMARL can significantly reduce vehicle congestion, and run stably in various scenarios.

Stochastic modelling of geometrically imperfect steel frame structures requires inputs of statistical values of the imperfection parameters, in some cases also with suitably selected mutual correlations between these input parameters. The paper presents a verification study of two stochastic methods to directly model the initial global geometrical imperfections of the steel frame structures. The stochastic input values of geometrical imperfections are derived from the tolerance criteria of the corresponding European Standard. Two advanced stochastic methods have been developed, referred as #RSS (random story sway) and #RSP (random story position). These methods are verified using random sampling simulations. This study provides useful provisions for the advanced numerical analyses of multi-story steel frames of various geometries. The proposed methods are verified for equidistant story heights and for structures of up to 24 stories, hence might be used for the most types of the standard steel frame structures.

We propose a new hierarchy of the vector derivative nonlinear Schr{\"o}dinger equations and consider the simplest multiphase solutions of this hierarchy. The study of the simplest solutions of these equations led to the following results. First, the three-leaf spectral curves $\Gamma=\{(\mu,\lambda)\}$ of the simplest multiphase solutions have a quite simple symmetry. They are invariant with respect to holomorphic involution $\tau$. The type of this involution depends on the genus of the spectral curve. Or the involution has the form $\tau:(\mu,\lambda)\to(\mu,-\lambda)$, or $\tau:(\mu,\lambda)\to(-\mu,-\lambda)$. The presence of symmetry leads to the fact that the dynamics of the solution is determined not by the entire spectral curve $\Gamma$, but by its factor $\Gamma/\tau$, which has a smaller genus. Secondly, it turned out that the dynamics of the two-component vector $\bp=(p_1,p_2)^t$ is determined, first of all, by the dynamics of its length $\abs{\bp}$. Independent equations determine the dependence of the direction of the vector $\bp$ from its length. In cases where the direction of the vector $\bp$ is fixed, the corresponding spectral curve splits into separate components. In conclusion, we note that, as in the case of the Manakov system, the equation of the spectral curve is invariant with respect to the orthogonal transformation of the vector solutions. I.e., the solution can be found from the spectral curve up to the orthogonal transformation. This fact indicates that the spectral curve does not depend on the individual components of the solution, but on their symmetric functions. Thus, the spectral data of multiphase solutions have two symmetries. These symmetries make it difficult to reconstruct signals from their spectral data. The work contains examples illustrating these statements.

This paper investigated reliability modeling for systems subject to dependent competing risks considering that the variation of failure threshold is not considered in most studies on competing failure reliability. Firstly, the variation of degradation quantity under shocks was analyzed, and the variation of threshold was considered on this basis. Secondly, the cumulative degradation under the influence of the random shock process was analyzed. The attractive property of copula is symmetry. Then, A linear Wiener process model is applied to model performance degradation failure, and a multi-performance-degradation correlated-competition model based on a Copula function is constructed, which considers the correlated competition between multiperformance degradation failures. Lastly, the micromotor system is used to analyze the applicability of the proposed model for bivariate instances. demonstrating the rationality and effectiveness of the proposed model.

Is it possible that the addition of wild-growing flowers with anti-inflammatory applications can improve the antioxidant properties of rapeseed and multifloral honey? The study objective was a comparative analysis of two honey varieties enriched by flowers of six plant species, based on the content of the antioxidant capacity as well as total flavonoids and phenolic content. Experiments demonstrated that at each level of enrichment there was an improvement in antioxidant properties compared to honey of both varieties without additives, especially in the case of dried flowers. Primula veris L. and Pulmonaria officinalis L. improved the antioxidant properties and phenolic content most effectively in honey at all levels of enrichment. Rapeseed-type honey produces a better matrix for the incorporation of natural plant metabolites into honey. The content of biologically active substances in honey enriched with flowers gives hope for new applications of health-promoting substances contained in wild plants.

Fabry-Pérto (FP) cavity is the essential component of ultra-stable laser (USL) for gravitational wave detection, which couples multi-physic (Optical/Thermal/Mechanics) fields and requires ultra-high precision. To satisfy the requirements of precise and efficient design, a multi-physic coupling optimization method for fixing cubic FP cavity based on data learning is proposed. A multi-physic model for the cubic FP cavity is established and the performance is obtained by finite element analysis. The key performance indices (V, wF, wF) and key design variables (d, l, F) are determined considering the features of the FP cavity. The 49 sets of data by orthogonal experiment are acquired for the establishment and comparison of different data learning models (NN, RSF, KRG). The result turns out that the neural network has the best performance. Based on NSGA-II, the Pareto optimal front is obtained and the optimal combination of design variables is finally determined as {5,32,250}. The performance after optimization has proven to be a great improvement, of which the displacement under the fixing force and vibration test are decreased by more than 60%. The optimization strategy can not only help the design of the FP cavity but also enlighten other optimization fields.

Fine-tuning is an important technique in transfer learning that has achieved significant success in tasks that lack training data. However, as it is difficult to extract effective features for single-source domain fine-tuning when the data distribution difference between the source and the target domain is large, we propose a transfer learning framework based on multi-source domain called adaptive multi-source domain collaborative fine-tuning to address this issue. This approach utilizes multiple source domain models for collaborative fine-tuning, thereby improving the model's feature extraction capability in the target task. Specifically, this approach employs an adaptive multi-source domain layer selection strategy to customize appropriate layer fine-tuning schemes for the target task among multiple source domain models. The objective is to extract more efficient features. Furthermore, a novel multi-source domain collaborative loss function is designed to facilitate the precise extraction of target data features by each source domain model. Simultaneously, it works towards minimizing the output difference among various source domain models, thereby enhancing the adaptability of the source domain model to the target data. In order to validate the effectiveness of the proposed the adaptive multi-source domain collaborative fine-tuning framework, it is analyzed and compared with the most widely used fine-tuning methods by applying them to seven publicly available visual categorization datasets commonly employed in transfer learning. Experimental results demonstrate that, in comparison with the existing fine-tuning approaches, our method not only enhances the accuracy of feature extraction in the model but also provides precise layer fine-tuning schemes for the target task, resulting in state-of-the-art performance.

The narrow parking space will result in difficulties in path planning and spot turning caused by sudden changes and discontinuities in path curvature. To address the problem, this paper investigates the performance of three path planning algorithms and proposes a path optimization algorithm. First, the narrow parking space is defined based on single-step parking of the arc-line combination parking algorithm. Second, to compare the arc-line combination algorithm, Hybrid A* algorithm, and particle swarm optimization parking algorithm under different narrow parking spaces, a multi-objective evaluation function is proposed, including three evaluation indicators, namely, the path length, the number of positive and negative conversions of vehicle speed, and the smoothness of the path. Their performance is compared by simulation conducted in MATLAB, the results show that the Hybrid A* algorithm is the better than others for narrow parking spaces. Third, to smooth the planning path, a path optimization algorithm based on the cubic B-spline curve and gradient descent is proposed. Finally, the simulation is conducted between the proposed algorithm and Hybrid A* algorithm, the result shows that the proposal can effectively eliminate the curvature mutation point and constrain the path curvature to meet the requirements of a smooth path.

This work aims to describe the dielectric behaviours of four main tissues in the human forearm using mathematical modelling, including fat, muscle, blood, and bone. Determining the electrical response of multiple tissues can help develop physiological monitoring of an organ or a body’s section by filtering out the impedance contributions from the surrounding tissues to blood flow-induced impedance variations. Multi-frequency bioimpedance analysis (MF-BIA) was initially performed using the finite element method (FEM) with a 3D forearm model followed by a pilot study to characterise the response of actual forearm tissues from 1 kHz to 349 kHz. Both the simulation and experimental results were fitted to a single-dispersion Cole model (SDCM) and a multi-dispersion Cole model (MDCM) to determine the Cole parameters for each tissue. The correlation analysis and Bland-Altman plot indicated a good fit between raw and fitted impedance values using both SDCM and MDCM. Overall, MDCM exhibited better performance in fitting and estimation of the Cole parameters with correlation coefficient (R2) of 0.99 and 0.97, root mean squared error (RMSE) of 0.09 Ω and 0.14 Ω, and mean difference (mean±standard deviation) of 0.00±0.09 Ω and -0.03±0.14 Ω for the real part and imaginary part of impedance, respectively.

This work aims to produce a cartographic model that identifies areas with a greater probability of finding karstic caves - the endokarst potential - in the northern sector of Santo António Plateau (Estremadura Limestone Massif, Central Portugal). Geological, topographic, hydrogeological, and vegetation cover data were collected, processed, and integrated into a spatial database using a geographic information system (GIS). The location of known cave entrances in the study area was also identified from the records of local public institutions and speleological teams. Four conditioning factors were extracted from the collected data, including lithostratigraphic units, fracture density, relief energy, and land cover. In a multi-criteria decision-making analysis framework, each previously chosen conditioning factor and respective classes/categories were weighted using the analytic hierarchy process (AHP). With an agreement of 81.9%, the results of the cartographic model constructed in GIS seem to be promising, considering that the entrances of the known caves are mainly located in areas classified as having high to very high endokarst potential. This prototype of the endokarst potential map for the study area can be used in strategic and operational environmental planning (at least on a local scale), as it can assist decision-makers, competent authorities, and local speleological teams in a more accurate and thoughtful definition of the areas that should be investigated, providing a substantial reduction in times and costs field prospecting.

Wheat and barley are among the primary food resources of the world population; therefore, their growth and observation are essential in farms to enhance food security worldwide. On top of that, careful observation of the product is essential to find solutions for the issues faced during their production and to reduce the impacts of weather changes. With the advancement of Remote Sensing technology, the observation and estimation process has increased. In this study, numbers of spectral vegetation indices was used along with canopy biophysical properties ( LAI ) and biochemical properties (chlorophyll), there calculated from (Landsat 8 and Sentinel-2) satellite data. The wheat and barley samples were collected before were be ready for harvest, and a relation with the vegetarian indices was established using the Multi-Linear Regression module, in which the equations used in predicting the harvest were developed and used to create a graph for expected harvest. The result indicated that there is a strong relationship between the vegetation indices of Sentinel-2 and Landsat images and the actual grain yield with R² of 0.77 and 0.71, respectively. The results show that the strongest correlation is observed between the LAI data obtained from Sentinel data and cereal yield data, with an R² 0.68, and the highest correlation for the indices of Landsat images is observed in the NDWI with R² 0.59 and the lowest degree of error was in the root mean square error (RMSE) for the Sentinel-2 and Landsat 8 with 0.57 and 1.54. In addition, this study also showed that the least relationship for grain yield prediction was observed between the NDRI for Sentinel-2 (R² 0.1) and SAVI for Landsat image (R² 0.47).

Deep convolutional neural networks (CNNs) have been widely used in various medical imaging tasks. However, due to the intrinsic locality of convolution operation, CNNs generally cannot model long-range dependencies well, which are important for accurately identifying breast cancer from unregistered multi-view mammograms. This motivates us to leverage the architecture of Vision Transformers to capture long-range relationships of multiple mammograms from the same patient. For this purpose, we employ local Transformer blocks to separately learn patch relationships within a specific view (CC/MLO) of one side (right/left) of mammogram. The outputs from different views and sides are concatenated and fed into global Transformer blocks, to jointly learn patch relationships between two different views of the left and right breasts. To evaluate the proposed model, we retrospectively assembled a dataset involving 949 sets of CC and MLO view mammograms, which include 470 malignant cases and 479 normal or benign cases. We trained and evaluated the model using a five-fold cross-validation method. Without any arduous preprocessing steps (e.g., optimal window cropping, chest wall or pectoral muscle removal, two-view image registration, etc.), our two-view Transformer-based model achieves lesion classification accuracy of 77.0% and area under ROC curve (AUC = 0.814), outperforming state-of-the-art multi-view CNNs by 3.1% and 3%, respectively. Meanwhile, the new two-view model improves mammographic case classification accuracies of two single-view models by 7.4% (CC) and 4.5% (MLO), respectively. The promising results unveil the great potential of using Transformers to develop high-performing computer-aided diagnosis (CADx) schemes of mammography.

In this paper, we propose, implement, and test two novel downlink LTE scheduling algorithms. The implementation and testing of these algorithms were in Matlab, and they are based on the use of Reinforcement Learning, more specifically, the Qlearning technique for scheduling two types of users. The first algorithm is called a Collaborative scheduling algorithm, and the second algorithm is called a Competitive scheduling algorithm. The first type of the scheduled users is the Primary Users, and they are the licensed subscribers that pay for their service. The second type of the scheduled users is the Secondary Users, and they could be unlicensed subscribers that dont pay for their service, device to device communications, or sensors. Each user whether it is a primary or secondary is considered as an agent. In the Collaborative scheduling algorithm, the primary user agents will collaborate in order to make a joint scheduling decision about allocating the resource blocks to each one of them, then the secondary user agents will compete among themselves to use the remaining resource blocks. In the Competitive scheduling algorithm, the primary user agents will compete among themselves over the available resources, then the secondary user agents will compete among themselves over the remaining resources. Experimental results show that both scheduling algorithms converged to almost ninety percent utilization of the spectrum, and provided fair shares of the spectrum among users.

We provide methodology and numerical results for the Hattendorff differential equa- tion for the continuous time evolution of the variance of L(j)t , the loss at time t random variable for a multi-state process, given that the state at time t is j.

The testing requirements of the active phased array antennas are very different from those of traditional passive antennas, due to its beam steering capability. Usually, each beam profile of the active phased array needs a separate radiation pattern test, which makes the overall testing time extremely long. Thus the traditional antenna test method can no longer meet the efficiency and cost requirements of new active phased array antennas test. In this paper, a fast test method tailored for phased array antennas is proposed that offers significantly reduced testing time at the expense of slight sacrifice of the accuracy. Using the simulated element pattern in array and ideal port excitation, the beam profile in any direction can be predicted by testing only a certain beam profile. Through theoretical derivation and experiments, the effectiveness of the method is verified, and the testing efficiency of the phased array antenna is demonstrated to be improved by ten times or even more.

This paper proposes a linear eddy-current feature to determine the radius of a metallic ball in a non-contact manner. An electromagnetic eddy-current sensor with two coils is placed co-axially to the metal ball during measurement. It is well known that the distance between the sensor and test piece (i.e. lift-off) affects eddy-current signals. In this paper, it is found that the peak frequency feature of inductance spectrum is linear to the lift-off spacing between the centre of coil and ball. Besides, the slope of peak frequencies versus lift-offs is linked to the radius of ball. The radius of metallic balls is retrieved from the experimental and embedded analytical result of the slope. Measurements have been carried out on 6 metallic balls with different radii. The radius of the metallic ball can be retrieved with an error of less than 2 %.

Open domain question answering (OpenQA) tasks have been recently attracting more and more attention from the natural language processing (NLP) community. In this work, we present the first free-form multiple-choice OpenQA dataset for solving medical problems, MedQA, collected from the professional medical board exams. It covers three languages: English, simplified Chinese, and traditional Chinese, and contains 12,723, 34,251, and 14,123 questions for the three languages, respectively. We implement both rule-based and popular neural methods by sequentially combining a document retriever and a machine comprehension model. Through experiments, we find that even the current best method can only achieve 36.7%, 42.0%, and 70.1% of test accuracy on the English, traditional Chinese, and simplified Chinese questions, respectively. We expect MedQA to present great challenges to existing OpenQA systems and hope that it can serve as a platform to promote much stronger OpenQA models from the NLP community in the future.

This study aims to develop a performance evaluation system that can facilitate performance evaluation at region, hospital, and department levels to enable better cost management for sustainable development. A multi-level system of performance evaluation informs a hierarchical assessment of cost management from regions to hospitals to departments using diagnosis-related group (DRGs). Various metrics are developed employing the variances between targets and actuals where targets are determined from two perspectives: benchmarking using external regional prices and change management using internal data. Targets for the latter are statistically based and specifically incorporate variability. The model is applied to two hospitals, twenty departments, nine DRGs and 1071 inpatients. The analyses indicate that the approach can provide a practical evaluation tool that allows for particular characteristics at multiple levels. The system provides macro-micro and external-internal perspectives in performance, enabling high-level variances to be decomposed thereby identifying sources of performance variability and financial impact.

This paper presents an unsupervised feature selection method for multi-dimensional histogram-valued data. We define a multi-role measure, called the compactness, based on the concept size of given objects and/or clusters described by a fixed number of equal probability bin-rectangles. In each step of clustering, we agglomerate objects and/or clusters so as to minimize the compactness for the generated cluster. This means that the compactness plays the role of a similarity measure between objects and/or clusters to be merged. To minimize the compactness is equivalent to maximize the dis-similarity of the generated cluster, i.e., concept, against the whole concept in each step. In this sense, the compactness plays the role of cluster quality. We also show that the average compactness of each feature with respect to objects and/or clusters in several clustering steps is useful as feature effectiveness criterion. Features having small average compactness are mutually covariate, and are able to detect geometrically thin structure embedded in the given multi-dimensional histogram-valued data. We obtain thorough understandings of the given data by the visualization using dendrograms and scatter diagrams with respect to the selected informative features. We illustrate the effectiveness of the proposed method by using an artificial data set and real histogram-valued data sets.

Wound infections evidently appeared in times of World War I that accounted a significant mortality and morbidity rate among injured soldiers. Currently, around 11 million people worldwide require medical treatment for wound infections and 300,000 die every year due to untreated wound infection. The extensive use of antibiotics to treat wound infection leads to emerging new microbial strains that are resistant to many antibiotics. There is a growing concern on the emergence and re-emergence of drug-resistant pathogens such as multi-resistant bacterial strains. Hence, the development of new antimicrobial compounds or the modification of those that already exist to improve antibacterial activity is a high priority area of research. During the past few decades, nanotechnology has arisen with new promising technology for synthesis of nanobiomaterials. Metallic nanoparticles (NPs) are considered as new alternative treatment with superior antibacterial activity. In this study, new formulation of titanium oxide (TiO2) NPs with different sizes were synthesized and characterized. Genotoxicity, mutagenicity and antibacterial activities of TiO2 NPs against the causative agents of wound infection were investigated. Antibacterial activity of TiO2 NPs was conducted against three ATCC ® bacterial strains: methicillin-resistant Staphylococcus aureus (MRSA), Escherichia coli and Pseudomonas aeruginosa. The results clearly illustrate a superior antibacterial activity of all newly formulated TiO2 NPs against the most causative agents of wound infection. Most of our TiO2 NPs showed non-genotoxic and non-mutagenic results at the maximum concentrations. Findings of this study will enhance the future of the therapeutic strategies against the resistant pathogenic strains that cause wound infections.

The small satellite market continues to grow year after year. A compound annual growth rate of 17% is estimated during the period between 2020 and 2025. Low-cost satellites can send a vast amount of images to be post-processed at the ground to improve the quality and extract detailed information. In this domain lies the resolution enhancement task, where a low-resolution image is converted to a higher resolution automatically. Deep learning approaches to Super-Resolution (SR) reached the state-of-the-art in multiple benchmarks; however, most of them were studied in a single-frame fashion. With satellite imagery, multi-frame images can be obtained at different conditions giving the possibility to add more information per image and improve the final analysis. In this context, we developed and applied to the PROBA-V dataset of multi-frame satellite images a model that recently topped the European Space Agency’s Multi-frame Super Resolution (MFSR) competition. The model is based on proven methods that worked on 2D images tweaked to work on 3D: the Wide Activation Super Resolution (WDSR) family. We show that with a simple 3D CNN residual architecture with WDSR blocks and a frame permutation technique as data augmentation better scores can be achieved than with more complex models. Moreover, the model requires few hardware resources, both for training and evaluation, so it can be applied directly from a personal laptop.

The aim of this research is forwarded for assessment of provision possibilities of the multi-componential and heterogeneous services in the fast-changing topology of cargo transportation processes. The mobile intelligent services in nowadays transport means require the development of complex infrastructure for multi-compositional service support. Our objectives are related to the investigation in data-transfer capabilities for heterogeneous service support, by offering some improvements for developing the infrastructure of transportation of vehicles by helping in the administration of transport processes. This research aims to develop an approach for assessment of infrastructure for sustainable management of cargo transportation processes by roads. Such assessment is multi-layered by including the management possibilities of cargo transportation logistic processes and electronic (smart, mobile) services by implementing of nowadays innovative software and hardware of information communication technologies (ICT). Special attention is paid for road safety, more environment cleanable, and paperless management by assessing the integration of potentials and prospects of wireless, vehicle Ad-hoc communication networks (VANET), and other communication possibilities. Some requirements are revealed for such type of infrastructure for the provision of heterogeneous services. The results of the development of infrastructure demonstrate the capacities of the potential of wireless networks for the provision of high-level of multi-component, heterogeneous services.

Enhancing the effectiveness of search and rescue operation at sea is always a duty of utmost importance of the coastal states. The search area for distressed objects can be determined by using Monte Carlo simulation, combined with the Median-Filter. Once the search area has been identified, the success of search and rescue operations depends on the sweeping ability of search and rescue vessel at the probability area of the distress object with the minimum time. This is the important element to the success of the search and rescue operation as it minimizes the risk and cost for Search and rescue team. In this article, the authors study and propose the use of Bacterial Foraging Optimization Algorithm (BFOA) to calculate the optimal search and co-ordination route for many search and rescue vessels in Vietnam sea. The simulation results show that it is quite consistent with reality and BFOA can be effectively applied to determine a quick search.

In this paper, a multi-mode waveguide-based optical resonator is proposed for an integrated optical refractive index sensor. Conventional optical resonators have been studied for single-mode waveguide-based resonators to enhance the performance, but mass production is limited owing to the high fabrication costs of nano-scale structures. To overcome this problem, we designed an S-bend resonator based on a micro-scale multi-mode waveguide. In general, multi-mode waveguides cannot be utilized as optical resonators, because of a performance degradation resulting from modal dispersion and an output transmission with multi-peaks. Therefore, we exploited the mode discrimination phenomenon using the bending loss, and the resulting S-bend resonator yielded an output transmission without multi-peaks. This phenomenon is utilized to remove higher-order modes efficiently using the difference in the effective refractive index between the higher-order and fundamental modes. As a result, the resonator achieved a Q-factor and sensitivity of 2.3x10³ and 52 nm/RIU, respectively, using the variational finite-difference time-domain method. These results show that the multi-mode waveguide-based S-bend resonator with a wide line width can be utilized as a refractive index sensor.

Software defect prediction is an important means to guarantee software quality. Because there are no sufficient historical data within a project to train the classifier, cross-project defect prediction (CPDP) has been recognized as a fundamental approach. However, traditional defect prediction methods using feature attributes to represent samples, which can not avoid negative transferring, may result in poor performance model in CPDP. This paper proposes a multi-source cross-project defect prediction method based on dissimilarity space ( DM-CPDP). This method first uses the density-based clustering method to construct the prototype set with the cluster center of samples in the target set. Then, the arc-cosine kernel is used to form the dissimilarity space, and in this space the training set is obtained with the earth mover’s distance (EMD) method. For the unlabeled samples converted from the target set, the KNN algorithm is used to label those samples. Finally, we use TrAdaBoost method to establish the prediction model. The experimental results show that our approach has better performance than other traditional CPDP methods.

This study aims to understand the current state of research in urban resilience and to open a discussion about multi-level perspectives for this concept. Starting with the history of the concept of resilience, we identify three main stages in resilience concept’s evolution: conceptualization, contextualization and operationalization. Confusion occurs between sustainability and resilience, therefore we clearly separate these two concepts by creating conceptual maps. Such maps also underline the specificities of urban and regional resilience discourses. We illustrate that urban resilience research, operating within intra-urban processes, is oriented towards natural disasters, while regional resilience research, operating mostly within inter-urban processes, is oriented towards economic shocks. We show that these two approaches to resilience – urban and regional – are complementary, and we propose to integrate them into a multi-level perspective. By combining these two discourses, we propose a multi-level approach to urban resilience that takes into account both top-down and bottom-up resistance processes. In the discussion section, we propose to take the panarchy perspective as a theoretical framework for multi-level urban resilience, that explains the interactions between different levels through adaptive cycles, relationships between which can help to explain urban resilience.

Geometric Akaike Information Criteria (G-AICs) for generalized noise-level dependent crystallographic symmetry classifications of two-dimensional (2D) images that are more or less periodic in either two or one dimensions as well as Akaike weights for multi-model inferences and predictions are reviewed. Such novel classifications do not refer to a single crystallographic symmetry class exclusively in a qualitative and definitive way. Instead, they are quantitative, spread over a range of crystallographic symmetry classes, and provide opportunities for inferences from all classes (within the range) simultaneously. The novel classifications are based on information theory and depend only on information that has been extracted from the images themselves by means of maximal likelihood approaches so that these classifications are objective. This is in stark contrast to the common practice whereby arbitrarily set thresholds or null hypothesis tests are employed to force crystallographic symmetry classifications into apparently definitive/exclusive states, while the geometric feature extraction results on which they depend are never definitive in the presence of generalized noise, i.e. in all real world applications. Thus, there is unnecessary subjectivity in the currently practiced ways of making crystallographic symmetry classifications, which can be overcome by the approach outlined in this review.

The paper investigates some similarity measures in interval bipolar neutrosophic environment for multi-attribute decision making problems. At first, we define Hamming and Euclidean distances measures between interval bipolar neutrosophic sets and establish their basic properties. We also propose two similarity measures based on the Hamming and Euclidean distance functions. Using maximum and minimum operators, we define new similarity measures and prove their basic properties. Using the proposed similarity measures, we propose a novel multi attribute decision making strategy in interval bipolar neutrosophic set environment. Lastly, we solve an illustrative example of multi attribute decision making and present comparison analysis to show the feasibility, applicability and effectiveness of the proposed strategy.

Sensitivity to weather conditions, and specially to clouds, is a severe limiting factor to the use of optical remote sensing for Earth monitoring applications. A possible alternative, is to resort to weather-insensitive synthetic aperture radar (SAR) images. However, in many real-world applications, critical decisions are made based on some informative spectral features, such as water, vegetation or soil indices, which cannot be extracted from SAR images. In the absence of optical sources, these data must be estimated. The current practice is to perform linear interpolation between data available at temporally close time instants. In this work, we propose to estimate missing spectral features through data fusion and deep-learning. Several sources of information are taken into account - optical sequences, SAR sequences, DEM - so as to exploit both temporal and cross-sensor dependencies. Based on these data, and a tiny cloud-free fraction of the target image, a compact convolutional neural network (CNN) is trained to perform the desired estimation. To validate the proposed approach, we focus on the estimation of the normalized difference vegetation index (NDVI), using coupled Sentinel-1 and Sentinel-2 time-series acquired over an agricultural region of Burkina Faso from May to November 2016. Several fusion schemes are considered, causal and non-causal, single-sensor or joint-sensor, corresponding to different operating conditions. Experimental results are very promising, showing a significant gain over baselines methods according to all performance indicators.

Abstract: This study aimed to assess the agronomic performance and yield stability of elite white yam (Dioscorea rotundata) genotypes across diverse Nigerian environments. Twenty-five genotypes were evaluated at three locations in two consecutive growing seasons, 2022 and 2023. The genotypes were assessed for their agronomic performance, tuber yield and related traits using various analytical tools such as AMMI (Additive main effects and multiplicative interaction) and MTSI (Multi-trait stability index). The AMMI analysis revealed significant differences among the genotypes and across the environ-ments for all traits (p

Multi-criteria decision analysis (MCDA), one of the prevalent branches of operations research, aims to design mathematical and computational tools for selecting the best alternative among several choices with respect to specific criteria. In the cloud, MCDA based online brokers uses customer specified criteria to rank different service providers. However, subjected to limited domain knowledge, the customer may exclude relevant or include irrelevant criterion, which could result in suboptimal ranking of service providers. To deal with such misspecification, this research proposes a model, which uses notion of factor analysis from the domain of unsupervised machine learning. The model is evaluated using two quality-of-service (QoS) based datasets. The first dataset i.e., feedback from customers, was compiled using leading review websites such as Cloud Hosting Reviews, Best Cloud Computing Providers, and Cloud Storage Reviews and Ratings. The second dataset i.e., feedback from servers, was generated from cloud brokerage architecture that was emulated using high performance computing (HPC) cluster at University of Luxembourg (HPC @ Uni.lu). The simulation runs in a stable cloud environment i.e. when uncertainty is low, shows that online broker (equipped with the proposed model) produces optimized ranking of service providers as compared to other brokers. This is due the fact that proposed model assigns priorities to criteria objectively (using machine learning) rather than using priorities based on subjective judgments of the customer. This research will benefit potential cloud customers that view insufficient domain knowledge as a limiting factor for acquisition of web services in the cloud.

This study examines the DCMA concerning the future risk of the water security status. We considered three risk factors: population growth, economic growth, and natural water supply demand differences. In the risk analysis part, we consulted with experts from several sectors including academia, Non-Governmental Organization (NGOs), and industry, to predict that the probability of future water stresses in high, medium, and low scenarios are 0.73, 0.24, and 0.03, respectively. In the decision analysis part, we adopted two Multiple Criteria Decision Analysis (MCDA) approaches that include Multiple Attribute Value Theory (MAVT) and Analytic Hierarchy Process (AHP) methods to evaluate the best alternative decision to alleviate future water stresses in the DCMA. The sensitivity analysis demonstrates the best option closely connects to the weighting scheme of the criteria considered in the framework. This study provides a valuable risk and decision analysis framework to analyze the water security status associated with the future water supply and demand gap decrease caused by three risk factors: population growth, climate change, and natural water supply.

The Multi-Level Model (=MLM) was suggested by A. Levichev as a description of quarks and gluons. The review recalls MLM-terminology while MLM-findings (for quarks and leptons) are compared to the theoretical and experimental data as accepted by the Standard Model (=SM). MLM is based on Segal’s compact space-time U(2) and on the sequence of embeddings: U(2) into U(3), U(2) into U(4), etc. These groups were called the levels (of matter): U(2) - the 0th (that is, our mundane world), U(3) - the 1st, U(4) - the 2nd, etc. Such a convention matches the SM-quarks' generations list. Each SM-quark is viewed either as a sunken proton, or as a captured proton. The MLM-proton is elementary and indestructible (hence no need for confinement). For MLM-quarks, in terms of the notion of a ruling group, flavor and color are defined mathematically. The number of colors (and of flavors) is level-dependent. For levels U(3) through U(6) the correspondence with the SM-quarks is established. Three new quarks and two new leptons are predicted. The SM-puzzle of quark and lepton generations is solved. Using the Han-Nambu scheme, the notion of the quark’s electric charge is expressed in terms of color charges. The original part of the review suggests studying the proton’s properties (like mass, shape and inner pressure) on the ba-sis of its wave function.

Intestinal failure (IF) is characterized by a critical reduction of functional gut mass below the minimum needed for optimal growth in children. It requires parenteral nutrition (PN) and home-PN (HPN) which is challenging in terms of meeting nutritional needs according to age, growth velocity, clinical situation, and rapid changes in fluid and electrolyte requirements. Due to these complex requirements, age-adapted multi-chamber bags (MCBs) are important additions to the nutrition armamentarium. The launch of composite fish oil (FO)-containing intravenous lipid emulsions (ILEs) heralded the development of MCBs containing these ILEs in combination with a crystalline amino acids solution (CAAS) adapted for pediatric use. The safety and efficacy of lipid and amino acid components in this context have been widely documented in numerous published studies. This manuscript includes a review of the articles published in PubMed, Embase, and Google Scholar until June 2022, exploring studies in the age groups from term infants to children and adolescents. Preterm infants with their highly specific demands are not included. It aims to offer an overview of the clinical experience regarding the use of a composite FO-based ILE and a specific CAAS developed

Piezoelectric ultrasonic motors (USMs) are actuators that use ultrasonic frequency piezoelectric vibration generated waves to transform electrical energy into rotary or translating motion. USMs are paid more attention because they offer distinct qualities over traditional magnet-coil-based motors, such as miniaturization, great accuracy, speed, non-magnetic nature, silent operation, straightforward construction, broad temperature operations, and adaptability. This review study focuses on the principle of USMs and their classifications, characterization, fabrication methods, applications, and future challenges. Firstly, the classifications of USMs, especially, standing wave, traveling wave, hybrid mode, multi degree of freedom USMs are summarized, and their respective functioning principles are explained. Secondly, the finite element modelling analysis for design and performance predictions, the conventional and nano/micro fabrication methods, and, the various characterization methods are presented. Thirdly, their advantages, such as high accuracy, small size, and silent operation and their benefits over conventional motors for the different specific applications are examined. In addition, the substantial contributions to a variety of tech-nical fields like surgical robots, industrial, aerospace, and biomedical applications are introduced. Finally, their future prospects and challenges in USMs development, with an emphasis on downsizing, increasing efficiency, and new materials are outlined.

Advancements in Parametric Design, Generative Design, and automation in Building Information Modelling (BIM) have opened new opportunities for architects and engineers working on complex buildings, such as offices. These developments allow designers to enhance their designs, increase project efficiency, improve performance, and reduce project time and costs. To address conflicting objectives that arise during the design process, genetic algorithms with multi-objective optimization (MOO) have been employed in architectural design. The GENIUS project aims to optimize building shape, apertures, and shading systems in the concept and design stages, with a focus on energy and daylight performance. The project integrates BIM and visual programming tools with Artificial Intelligence techniques like Genetic Algorithms and RBFOpt model-based optimization. Optimization algorithms are used to identify the best solutions that meet all design objectives, helping architects optimize their designs and achieve desired outcomes. The workflow was tested on a case study of a large office building, with MOO focused on maximizing daylight performance using Spatial Daylight Autonomy metric and minimizing energy consumption using Energy Use Intensity metric. The project provides architects with a method to improve their designs using Algorithm Aided Design tools, which help identify the best solutions for complex design problems.

This paper presents work done as part of a transformation effort towards a greener and more sustainable Aluminium manufacturing plant. The effort includes reducing the carbon footprint by minimising waste and increasing operational efficiency. The contribution of this work includes the reduction of waste through the implementation of autonomous, real-time quality measurement and classification at an Aluminium casthouse. Data is collected from the MV20/20 which uses ultrasound pulses to detect molten Aluminium inclusions, which degrade the quality of the metal and cause subsequent metal waste. The sensor measures cleanliness, inclusion counts and distributions from 20 - 160 microns. The contribution of this work is in the development of business analytics to implement condition-based monitoring through anomaly detection, and to classify inclusion types for samples that failed. For anomaly detection, multivariate K-Means and DBSCAN algorithms are compared as they have been proven to work in a wide range of datasets. For classification, a two-stage classifier is implemented. The first stage classifies the success or failure of the sample, while the second stage classifies the inclusion responsible for the failed sample. The algorithms considered include logistic regression, support vector machine, multi-layer perceptron and radial basis function network. The multi-layer perceptron offers the best performance using k-fold cross-validation, and is further tuned using grid search to explore the possibility of an even better performance. The results reveal that the model has achieved a global maximum in performance. Recommendations include the integration of additional sensor systems and the improvements in quality assurance practices.

The delineation of the clinical target volumes (CTVs) for radiation therapy is time-consuming, requires intensive training and shows high inter-observer variability. Supervised deep learning methods depend heavily on consistent training data, thus state-of-the-art research focuses on making CTV labels more homogeneous and strictly bounding them to current standards. International consensus expert guidelines standardize CTV delineation by conditioning the extension of the clinical target volume on surrounding anatomical structures. Training strategies that directly following the construction rules given in the expert guidelines or the possibility to quantify the conformance of manually drawn contours with the guidelines are still missing. 71 anatomical structures that are relevant for CTV delineation in head and neck cancer patients according to the expert guidelines were segmented on 104 CT scans to assess the possibility to automate their segmentation by state-of-the-art deep learning methods. nnU-Net models were trained to automatically segment those 71 structures on planning CT scans. We report the DICE, HD and sDICE for 71 + 5 anatomical structures for most of which no previous segmentation accuracies have been reported. For those structures, for that prediction values have been reported, our segmentation accuracy matched or exceeded the reported values. The predictions from our models were always better than those predicted by the TotalSegmentator. The sDICE with 2mm margin was larger than 80% for almost all structures. Individual structures with decreased segmentation accuracy are analyzed and discussed with respect to their impact on the CTV delineation following the expert guidelines. No deviation is expected to affect the rule-based automation of the CTV delineation.

As the whisky industry applies circular economy principles to maximize resource utilization and minimize environmental impact, companies become exposed to several risks, which require complex assessments to ensure reliable outcomes. This study provides an organized framework to identify, prioritize and rank various risk factors commonly observed in whisky industry through the development of an Analytical Hierarchy Process (AHP) multi-criteria analysis model. Experts from 18 small European distilleries identified five main risk criteria and nineteen sub-criteria from brainstorming workplace observations, and categorized them as: environmental (5), operational (4), technological innovation (3), food safety (3) and economical (4) risks. The Analytical Hierarchy Process (AHP) approach was used to determine the weights and ranks of the main criteria and sub-criteria based on the survey responses received from experts from each distillery. The final judgements are consistent, as indicated by consistency values (CR) of less than 0.1 for all risk criteria. Unlike traditional risk assessment methods, the AHP model effectively integrates qualitative and quantitative data, aiding strategic decision-making in the whisky industry by breaking down complex problems into manageable sub-problems. Future research directions may expand the criteria and explore additional sustainable practices.

This paper explores the effectiveness of the Non-dominated Sorting Genetic Algorithm III (NSGA-III) and traditional Mean-Variance optimization in financial portfolio management. Using a dataset comprising global financial assets, we applied both methodologies to optimize portfolios based on multiple objectives, including risk, return, skewness, and kurtosis. The findings reveal that NSGA-III outperforms the Mean-Variance method in achieving a more diverse set of Pareto-optimal portfolios. NSGA-III portfolios exhibited superior performance in balancing risk and return, demonstrated by higher Sharpe ratios, more favorable skewness, and lower kurtosis. Additionally, NSGA-III's ability to simultaneously optimize across multiple conflicting objectives highlights its robustness in navigating complex financial landscapes, offering enhanced portfolio resilience. In contrast, the Mean-Variance approach, while effective in achieving balanced risk and return, was limited in addressing higher-order moments of the return distribution. These results underscore NSGA-III's potential as a powerful tool for portfolio optimization, providing a comprehensive alternative to traditional methods in modern financial markets where multiple objectives must be considered.

Classification of pre-processed fMRI dataset using the functional connectivity(FC) based features is considered a challenging task due to high dimensional FC features set and smaller dataset size. To tackle this specific FC high dimensional features set and a smaller dataset size , We have proposed here a GAN based dataset augmenter to firstly train the GAN on the NYU Connectivity Features dataset and used the trained GAN to generate synthetic features per category and after getting sufficient number of features per category , A multi-head attention mechanism was used as a head for the classification . We name our proposed approach as "ASD-GANNet" which is End-To-End and does not require hand-crafted features as the multi-head attention mechanism focuses on the features that are more relevant . Moreover , We compared our results with the 06 available state-of-the-art techniques from the literature and Our proposed approach results using "NYU" site as a training set for generating GAN based synthetic dataset are promising. We achieved an overall 10-fold cross validation based accuracy of 82% ,sensitivity 82% and specificity 81% outperforming the available state-of-the art approaches. Sitewise comparison of our proposed approach also outperformed the the available state-of-the-art as out of the 17 sites our proposed approach has better results in the 10 sites.

Background: Locally advanced rectal cancers (10-20%) can present with infiltration into adjacent viscera. R0 resections remain the key factor for better survival. Traditionally these cases have been managed with open surgery. There are some limitations of laparoscopic surgery in these case, which can potentially be overcome by robotic surgery. Objectives: To determine the feasibility and outcome results of robotic multi-visceral resection of stage T4 rectal carcinoma. Methods: Consecutive patients having locally advanced carcinoma of rectum, who undergone robotic multi-visceral resection as the primary treatment between 2015 -2018 were included, through our database which was maintained prospectively. All perioperative and intraoperative parameters were analyzed. Patient demographics, co-morbidities, preoperative imaging, endoscopic findings, operative data, histopathology results, postoperative hospital course and procedure related postoperative adverse events were noted and analyzed. Results: Twenty-one patients with the diagnosis of nonmetastatic locally advanced rectal cancers were operated with Robotic Si/X platform. The median body mass index was 28.5 kg/m2 (range 21-42). The mean blood loss during operation was 20 ml (range 5-200), and the mean duration of surgery was 280 min (range 240-430). The median hospital stay after operation was 6 days (range 4-25 days). On postoperative histopathology, R0 resection rate was 90.5% (19/21). Conclusions: The robotic multi-visceral en-bloc resection of stage T4 rectal carcinoma is technically feasible and oncologically safe. Advanced technical skills, accurate radiological staging and careful patient selection can allow the extension of minimal access surgery to this challenging group of patients.

In order to solve the problem of fault diagnosis for CNC machine feed system under the condition of variable speed conditions, an intelligent fault diagnosis method based on multi-domain feature extraction and ensemble learning model is proposed. First, various monitoring signals including vibration signal, noise signal and current signal are collected. Then, the monitoring signals are preprocessed and the time-domain, frequency-domain and time-frequency domain feature indexes are extracted to construct a multi-dimensional mixed domain feature set. Finally, the feature set is putting into the constructed DoubleEnsemble-LightGBM model to realize the fault diagnosis of the feed system. The experimental results show that the model can achieve good diagnosis results under different working conditions for both the public data set and the feed system test bench data set, and the average overall accuracy is 91.07% and 98.06% respectively. Compared with XGBoost and other advanced ensemble learning models, the method has better accuracy. It provides technical support for the stable operation and intelligent of CNC machine tools..

Energy communities are key actors in the energy transition since they optimally interconnect renewable energy capacities with the consumers. Despite versatile objectives, they usually aim at improving the self-consumption of renewable electricity within low voltage grids to maximize revenues. In addition, energy communities are an excellent opportunity to supply renewable electricity to regional and national energy systems. However, effective price signals have to be designed to coordinate the needs of the energy infrastructure with the interests of these local stakeholders. The aim of this paper is to demonstrate the integration of energy communities at the national level with a bottom-up approach. District energy systems with a building scale resolution are modelled in a mixed integer linear programming problem. The Dantzig-Wolfe decomposition is applied to reduce the computational time. The methodology lies within the framework of renewable energy hub, characterized by a high share of photovoltaic capacities. Both investments into equipment and its operation are considered. The model is applied on a set of five typical districts and weather locations representative of the Swiss building stock. The extrapolation to the national scale revealed a heterogeneous photovoltaic potential throughout the country. Present electricity tariffs promote a maximal investment into photovoltaic panels in every region, reaching an installed capacity of 67.2 GW and generating 80 TWh per year. Since the national PV capacity needed is forecast at 15.4 GW peak, coordinated investments between local and national actors are needed to prevent dispensable expenses. An uncoordinated design is expected to increase the total costs for residential energy systems by 43.2% and curtails 48.2% of local renewable electricity.

Background Candida auris is an emerging multidrug-resistant fungal pathogen that represents a serious threat to healthcare settings currently. Objective: Its objective was to determine the prevalence of C. auris in the hospital since its initial detection in late 2019. Methods: Using an adapted risk assessment tool, we reviewed the charts. and medical files of all suspected? and confirmed cases of C. auris cases reported at King Khalid University Hospital, Riyadh between November 2019 and December 2022. Anonymized data were retrieved in a pre-established datasheet and analyzed to determine the epidemiological characteristics of C. auris infection in our facility. We established our initial prevalence by age, gender, risk factors, and according to sampling source. Results: Of the 53 confirmed cases positive for C. auris during the study period, 33 (62%) were males. Their ages ranged between 15 and 98; most positive cases occurred in 50 and above. Only one of the confirmed cases was hospital-acquired. All patients had at least one risk factor, and Urine samples yielded the greatest number of positive cases while admission to healthcare facilities constituted the highest risk in our study. Conclusion: Establishing a local prevalence could serve as our baseline/benchmark to compare with regional and international benchmarks.

This study presents a research plan that utilizes data obtained from wearable devices to identify human activities and gain insights into human behavior. We developed a model capable of classifying activities similar to human behavior and evaluated the effectiveness and generalization capabilities of this model. The data underwent initial preprocessing, including standardization and normalization. Additionally, recognizing the inherent similarities between human activity behaviors, we introduced a multi-layer classifier model. The first layer is a random forest model based on stepwise regression, which may encounter reduced accuracy for similar activities. The second layer employs a Support Vector Machine (SVM) model based on Kernel Fisher Discriminant Analysis (KFDA). KFDA is used to reduce the dimensionality of data points with potential confusion, followed by SVM for classification. The model was experimentally evaluated and applied to four benchmark datasets: UCI DSA, UCI HAR, WISDM, and IM-WSHA. The experimental results demonstrate that our approach achieved recognition accuracies of 99.71%, 98.71%, 99.12%, and 97.6% on these datasets, indicating excellent recognition performance. Furthermore, to assess the model's generalization ability, we performed K-fold cross-validation on the random forest model and utilized ROC curves for the SVM classifier. The results indicate that our multi-layer classifier model exhibits robust generalization capabilities.

Underwater robotics equipped with visual detection systems have the function of detecting un-derwater artifacts, which is of great significance to deep-sea archaeology. Underwater artifacts are located in complex environments with poor imaging conditions, and the targets have chal-lenging problems such as breakage, stacking, and sediment burial, which causes the marine cul-tural target detection failures. To solve these problems, this paper proposes an underwater cul-tural target detection algorithm based on the deformable deep aggregation network model for underwater robotics exploration. To fully extract the target feature information of underwater targets in complex environments, this paper designs a multi-scale deep aggregation network with deformable convolutional layers. Besides, the BAM attention module is designed for fea-ture optimization, which enhances the potential feature information of the target while weak-ening the background interference information. Finally, the target prediction is achieved through feature fusion at different scales. The proposed algorithm has been extensively validat-ed and analyzed on the collected underwater artifact datasets, and the precision, recall, and mAP of the algorithm have reached 93.1%, 91.4%, and 92.8%, respectively. In addition, the present al-gorithm has been practically deployed on the underwater robotics. In the deep-sea tests, the ar-tifact detection frame rate reaches up to 19 fps, which satisfies the real-time target detection。

Non-alcoholic steatohepatitis (NASH) is a complex disease resulting from chronic liver injury associated with obesity, type 2 diabetes, and inflammation. Recently, multi-target drugs have been proposed to treat complex diseases including NASH; however, their manufacturing pro-cesses remain time- and cost-intensive and inefficient. Therefore, to overcome these limitations, we developed UniStac, a novel enzyme-mediated conjugation platform for multi-specific drug development. UniStac demonstrated high conjugation yields, optimal thermal stabilities, and robust biological activities. Through such platform, we designed a tetra-specific compound, C-192, targeting Glucagon-like peptide 1 (GLP-1), Glucagon (GCG), Fibroblast growth factor 21 (FGF21), and Interleukin-1 receptor antagonist (IL-1RA) simultaneously for the treatment of NASH. The biological activity and treatment efficacy of C-192 were confirmed both in vitro and in vivo using a methionine–choline-deficient (MCD) diet-induced mouse model. C-192 exhibited profound therapeutic efficacies compared to conventional drugs, including liraglutide and dulaglutide. C-192 significantly improved alanine transaminase levels, triglyceride accumula-tion, and the non-alcoholic fatty liver disease activity score. Our results collectively provide clin-ical feasibility of UniStac for developing multi-specific drugs, and C-192 as an innovative thera-peutic opportunity for severe NASH, as it exerts synergistic effects across multiple targets.

To predict the remaining useful life (RUL) of proton exchange membrane fuel cell (PEMFC) in advance, a prediction method based on the voltage recovery model and Bayesian optimization of a multi-kernel relevance vector machine (MK-RVM) is proposed in this paper. First, the empirical mode decomposition (EMD) method was used to preprocess the data, and then the MK-RVM was used to train the model. Then, the Bayesian optimization algorithm was used to optimize the weight coefficient of the kernel function to complete the parameter update of the prediction model, and the voltage recovery model was added to the prediction model to realize the rapid and accurate prediction of the RUL of PEMFC. Finally, the method proposed in this paper was applied to the open data set of PEMFC provided by FCLAB, and the prediction accuracy of the RUL of PEMFC was obtained by 95.35%, which showed that the method had good gen-eralization ability and verified the accuracy of the prediction for the RUL of PEMFC.

Electrospinning is a simple versatile method to generate nanofibres. Remarkable progress has been made in the development of electrospinning process. The production of nanofibers is affected by many parameters, which influence the final material properties. Electrospun fibers have a wide range of applications such as energy storage and biomedical scaffolds. Polyacrylonitrile (PAN) has been widely used in the production of carbon nanofibers. PAN has received increasing interest in recent years, due to its excellent characteristics, such as spinnability, biocompatibility, and commercial viability, opening new applications in the biotechnological field. This paper provides an overview of the electrospinning process, its main parameters, and operation modes that affect nanofibers fabrication. A review of their biological applications is proposed. A focus is made on PAN fibers formation, functionalization, and application as scaffolds to allow cell growth. Overall, nanofibre scaffolds, made of stabilized PAN, appear as a powerful tool in medical applications needing controlled cell culture.

In response to reducing the energy cost of unmanned surface vehicles (USVs) while overcoming the low accuracy problem in surface target detection, a lightweight detection algorithm with multi-scale feature fusion is proposed. Based on the popular one-stage lightweight Yolov7-tiny target detection model, a lightweight extraction module is designed first by introducing the multiscale residual module to reduce the number of parameters and computational complexity while improving accuracy. The Mish and SiLU activation functions are used to enhance network feature extraction. Second, the path aggregation network employs coordinate convolution to strengthen spatial information perception. Finally, the dynamic head, which is based on the at-tention mechanism, improves the representation ability of object detection heads without any computational overhead. According to the experimental findings, the proposed model has 22.1% fewer parameters than the original model, 15% fewer GFLOPs, a 6.2% improvement in mAP@0.5, a 4.3% rise in mAP@0.5:0.95, and it satisfies the real-time criteria. According to the research, the suggested lightweight water surface detection approach includes a lighter model, a simpler computational architecture, more accuracy, and a wide range of generalizability. It performs bet-ter in a variety of difficult water surface circumstances.

This work analyzes a new indoor laboratory data set looking at early fire indicators in controlled and realistic experiments representing different incipient fire scenarios. The experiments were performed within the confines of an indoor laboratory setting using multiple distributed sensor nodes on different room positions. Each sensor node collected data of particulate matter (PM), volatile organic compounds (VOC), CO, CO2, H2, UV, air temperature and humidity in terms of a multivariate time series. These data hold immense value for researchers within the machine learning and data science communities who are keen on exploring innovative advanced statistical and machine learning techniques. They serve as a valuable resource for the development of early fire detection systems. The analysis of the collected data was carried out in dependence of the manhattan distance between the fire source and the sensor node. We found that especially larger particles (> 0.5 μm) and VOCs show a significant dependency with respect to the intensity as a function of the manhattan distance to the source. Moreover, we observed differences in the propagation behavior of VOCs, PM, and CO, which are particularly relevant in incipient fire scenarios due to the presence of strand popagation effects.

The method propose in this study for stock market multi-objective mathematical model was linear programming using simplex algorithms to optimize the portfolio in the Nigerian Stock Market. The study selected five banks from the list of operators in the market and data were gathered from the banks to have individual market performances over a period of 5years. The data collected contains: Geometric Mean of Monthly Capital Gain Yields and Annual Capital Gain Yields from which Dividend Yields (%) were deducted to arrive Actual rate of return for the banks and the expected rate of return. Furthermore, the risk of semi-absolute deviation below the expected return is reduced. The data was analysed using Python programming because of some clauses in the data gathered. At first, the data assumes integer (-or +) and random in nature. As such, Python programming is one of the software suitable for such solution since the barrier for additivity is broken. Based on the analysis, the study therefore conclude that the potential investor(s) should invest in 13 units of investment x(GTbank Plc), 3 units of First Bank Plc`s Investment (y), 450 units of Zenith bank`s investment (z), and 8 units of Wema bank`s investment (m), and no units of investment of (n) Access bank. These investment quantities will result in the Optimal profit of p= 12797.902 billion naira.

Most existing cancer therapies negatively affect normal tissue as well as cancerous tissue. A potentially effective strategy for treating cancer that precludes off-target damage and could be an option for most patients would involve targeting one or more mutations that are ubiquitous in the given patient’s tumor(s). To effect this strategy, one would employ multi-region sequencing of a patient’s primary tumor and metastases to seek out mutations that are shared between all or at least most regions. Once the target or targets are known, one would ideally rapidly generate a molecular switch for at least one of said ubiquitous mutations that can distinguish the mutated DNA, RNA, or protein from the wild-type version and subsequently trigger a therapeutic response. I propose that the therapeutic response involve the replication of an oncolytic virus or intracellular bacterium, as any mutation can theoretically be detected by a vector that enters the cell - and automatic propagation could be very helpful. Moreover, the mutation “signal” can be easily enhanced through transcriptional and translational (if the target is an intracellular protein) enhancement. Importantly, RNA may make the best target for the molecular switches in terms of amplification of the signal and ease of targeting.

Bayesian techniques for engineering problems, that rely on Gaussian process (GP) regression, are known for their ability to quantify epistemic and aleatory uncertainties and for being data efficient. The mathematical elegance of applying these methods usually comes at a high computational cost when compared to deterministic and empirical Bayesian methods. Furthermore, using these methods becomes practically infeasible in scenarios characterized by a large number of inputs and thousands of training data. The focus of this work is on enhancing Gaussian Process-based metamodeling and model calibration tasks, when the size of the training datasets is significantly large. To achieve this goal, we employ a stochastic variational inference algorithm that enables rapid statistical learning of the calibration parameters and hyperparameter tuning, while retaining the rigor of Bayesian inference. The numerical performance of the algorithm is demonstrated on multiple metamodeling and model calibration problems with thousands of training data.

Masons are often overlooked part of impact basins, but play an important role in revealing the lunar history. Previous study in masons were usually limited to gravity data. Few researches were reported on morphology features and chronology, which hampers the construction of a complete geological interpretation for the evolution of each mascons. We use multi source remote sensing data to identify the details characteristic of mascons. Result of topography, gravity and characteristic are combined to prove that a mason beside Copernicus crater is a buried peak-ring basin which is about 130km and 260km in diameter. The underground structure is of confirmed as 890m thick mare basalts by analyzing the spectral feature of the material in a geological outcrop called Copernicus H. Geology evolution analysis joint crater size-frequency distribution (CSDF) dating demonstrate that the buried basin impact event occurred in 3.6Ga. Then a hawaiian-style eruption in late Imbrian formed Sinus Aestuum Ⅰ Dark Mantling Deposit (DMD). Mare basalts filling in 3.4Ga. After that, ejecta from Copernicus impact event in about 820Ma and weathering processes cause the disappearing from lunar surface of the buried basin.

This paper presents a study on the idle vibration reduction of a diesel sport utility vehicle (SUV). To reduce idle vibration, the transmission paths of vibration from the engine to the driver seat floor were investigated with the vehicle components related to idle vibration. Furthermore, operational deflection shape (ODS) tests were conducted to visualize the vibration shapes during engine idling. Experimental modal analyses were performed to obtain the natural frequencies and mode shapes. Through the ODS and modal tests, the vibration characteristics of the diesel SUV during idling were identified. Considering these vibration characteristics, a multi-body dynamic model for the diesel SUV described by differential equations of motion was established to evaluate the idle vibration. To implement the dynamic model effectively, the equivalent stiffnesses and damping coefficients included in the model were determined experimentally or analytically. The established dynamic model was verified by comparing the natural frequencies and idle vibration levels between simulations. Using this dynamic model, we analyzed the effects of various design variables on idle vibration and obtained an optimal design for reducing the idle vibration level. Finally, we present a design guide to reduce the idle vibration for diesel SUVs.

The Vehicle Routing Problem (VRP) and its variants are found in many fields, especially logistics. In this study, we introduced an adaptive method to a complex VRP. It combines multi-objective optimization and several forms of VRPs with practical requirements for an urban shipment system. The optimizer needs to consider terrain and traffic conditions. The proposed model also considers customers' expectations, shipper considerations as goals, and the common goal like transportation cost. We offered compromise programming to approach the multi-objective problem by decomposing the original multi-objective problem into a minimized distance-based problem. We designed a hybrid version of the Genetic algorithm with the Local Search algorithm to solve the proposed problem. We evaluate the effectiveness of the proposed algorithm with the Tabu Search algorithm, the original Genetic algorithm on the tested dataset. The results show that our method is an effective decision-making tool for the multi-objective VRP and an effective solver for the new variation of VRP.

Image segmentation is a new challenge prob- lem in medical application. The use of medical imaging has become an integral part of research, as it allows us to see inside the human body without surgical intervention. Many researcher have studied brain segmentation. One stage method is used to segment the brain tissues. In this paper, we proposed the multi-stage generative ad- versarial network to solve the problem of information loss in the one-stage. We utilize the coarse-to-fine to improve brain segmentation using multi-stage generative adversar- ial networks (GAN). In the first stage, our model generated a coarse outline for (i) background and (ii) brain tissues. Then, in the second stage, the model generated outline for (i) white matter (WM), (ii) gray matter (GM) and (iii) cerebrospinal fluid (CSF). A good result can be achieved by fusing the coarse outline and refine outline. We conclude that our model is more efficient and accu- rate in practice for both infant and adult brain segmenta- tion. Moreover, we observe that multi-stage model is faster than prior models. To be more specific, the main goal of multi-stage model is to see the performance of the model in a few shot learning case where a few labeled data are available. For medical image, this proposed model can work in a wide range of image segmentation where the convolution neural networks and one-stage methods have failed.

The total lipid and protein content of the invasive caprellid amphipod Caprella scaura, from the biofouling communities of fish farm cages in the Pagasitikos Gulf were analyzed and compared among seasons. Proteins were the most abundant component (48.5 – 49.3%). Lipid content was relatively lower, with a wider range (6.7 – 34%) and showed a distinct seasonal fluctuation with high values in the winter population and a gradual decrease in spring and summer, with the lowest values in Autumn. Composition of the fatty acids profile was consistent among the seasons, with palmitic (16:0), Oleic (18:1n-9), Eicosapentanoic (20:5n-3)(EPA) and Docosahexanoic acid (22:6n-3 )(DHA) being the most abundant fatty acids. The presence of high levels of EPA and DHA fatty acids makes the species a potential candidate for use of these organisms in aquaculture.

The General Theory of Information (GTI) tells us that information is represented, processed and communicated using physical structures. The physical universe is made up of structures combining matter and energy. According to GTI, “Information is related to knowledge as energy is related to matter.” GTI also provides tools to deal with transformation of information and knowledge. We present here, the application of these tools for the design of digital autopoietic machines with higher efficiency, resiliency and scalability than the information processing systems based on the Turing machines. We discuss the utilization of these machines for building autopoietic and cognitive applications in a multi-cloud infrastructure.

The strong couplings among ecological, economic, social and technological processes explains the complexification of human-made systems, and phenomena such as globalization, climate change, the increased urbanization and inequality of human societies, the power of information, and the COVID-19 syndemics. Among complexification’s essential features are non-decomposability, asynchronous behavior, components with many degrees of freedom, increased likelihood of catastrophic events, irreversibility, nonlinear phase spaces with immense combinatorial sizes, and the impossibility of long-term, detailed prediction. Sustainability for complex systems implies enough efficiency to explore and exploit their dynamic phase spaces and enough flexibility to coevolve with their environments. This in turn means solving intractable nonlinear semi-structured dynamic multi-objective optimization problems, with conflicting, incommensurable, non-cooperative objectives and purposes, under dynamic uncertainty, restricted access to materials, energy and information, and a given time horizon, aiming at enhancing the co-evolutionary power of the Biosphere and its human subsystems. Giving the high-stakes, the need for effective, efficient, diverse solutions, their local-global, present-future effects, and their unforeseen short, medium and long-term impacts, achieving sustainable complex systems implies the need for Sustainability-designed Universal Intelligent Agents, harnessing the strong functional coupling between human, artificial and nonhuman biological intelligence in a no-zero-sum game to achieve sustainability.

Speech emotion recognition remains a heavy lifting in natural language processing. It has strict requirements to the effectiveness of feature extraction and that of acoustic model. With that in mind, a Heterogeneous Parallel Convolution Bi-LSTM model is proposed to address these challenges. It consists of two heterogeneous branches: the left one contains two dense layers and a Bi-LSTM layer, while the right one contains a dense layer, a convolution layer, and a Bi-LSTM layer. It can exploit the spatiotemporal information more effectively, and achieves 84.65%, 79.67%, and 56.50% unweighted average recall on the benchmark databases EMODB, CASIA, and SAVEE, respectively. Compared with the previous research results, the proposed model achieves better performance stably.