The intrinsic non-linearity and complexity of suspended sediment dynamics, which are impacted by the geographical variability of basin parameters and temporal climatic patterns, make it difficult to estimate suspended sediment concentration (SSC) accurately in hydrological processes. Deep neural networks (DNNs), a cutting-edge modeling method that can capture the innate non-linearity in hydrological systems, have emerged as a solution to this problem. Using primary data on discharge, SSC, and turbidity, the long short-term memory method of DNNs was employed in this study to simulate the discharge-suspended sediment connection for the Esopus Creek, NY, USA as the first objective. To develop effective modeling strategies, multiple scenarios of feature selection, including combinations of discharge, turbidity and SSC for preceding days, were considered. Secondly, the variations in SSC and discharge between the three USGS gages along Esopus Creek that were upper stream, lower stream, and downstream, adjacent to the pourpoint were analyzed. Statistical metrics and scenarios of feature importance were used to evaluate the effectiveness of the DNN-based models. The study shows that among 24 DNN approaches feature selection is crucial in simulating the daily SSC, and discharge and presenting novel research directions for utilizing machine learning algorithms in water quality.

Training data for a deep learning (DL) neural network (NN) controller are obtained from the input and output signals of a conventional digital controller that is designed to provide the suitable control signal to a specified plant within a feedback digital control system. It is found that if the DL controller is sufficiently deep (four hidden layers), it can outperform the conventional controller in terms of settling time of the system output transient response to a unit-step reference signal. That is, the DL controller introduces a damping effect. Moreover, it does not need to be retrained to operate with a reference signal of different magnitude, or under system parameter change. Such properties make the DL control more attractive for applications that may undergo parameter variation, like sensor networks.

Face recognition is a valuable forensic tool for criminal investigators since it certainly helps in identifying individuals in scenarios of criminal activity like fugitives or child sexual abuse. It is, however, a very challenging task as it must be able to handle low-quality images of real world settings and fulfill real time requirements. Deep learning approaches for face detection have proven to be very successful but they require a large computation power and processing time. In this work, we evaluate the speed-accuracy tradeoff of three popular deep-learning-based face detectors on the WIDER Face and UFDD data sets in several CPUs and GPUs. We also develop a regression model capable to estimate the performance, both in terms of processing time and accuracy. We expect this to become a very useful tool for the end user in forensic laboratories in order to estimate the performance for different face detection options. Experimental results showed that the best speed-accuracy tradeoff is achieved with images resized to 50% of the original size in GPUs and images resized to 25% of the original size in CPUs. Moreover, performance can be estimated using multiple linear regression models with a Mean Absolute Error (MAE) of 0.113 what is very promising for the forensic field.

This comprehensive review explores the advancements in processing-in-memory (PIM) techniques for deep learning applications. It addresses the challenges faced by monolithic chip architectures and highlights the benefits of chiplet-based designs in terms of scalability, modularity, and flexibility. The review emphasizes the importance of dataflow-awareness, communication optimization, and thermal considerations in designing PIM-enabled manycore architectures. It discusses different machine learning workloads and their tailored dataflow requirements. Additionally, the review presents a heterogeneous PIM system for energy-efficient neural network training and discusses thermally efficient dataflow-aware monolithic 3D (M3D) NoC architectures for accelerating CNN inferencing. The advantages of TEFLON (Thermally Efficient Dataflow-Aware 3D NoC) over performance-optimized SFC-based counterparts are highlighted. Overall, this review provides valuable insights into the development and evaluation of chiplet and PIM architectures, emphasizing improved performance, energy efficiency, and inference accuracy in deep learning applications.

In this paper, we present a novel approach for text independent phone-to-audio alignment based on phoneme recognition, representation learning and knowledge transfer. Our method leverages a self-supervised model (wav2vec2) fine-tuned for phoneme recognition using a Connectionist Temporal Classification (CTC) loss, a dimension reduction model and a frame-level phoneme classifier trained thanks to forced-alignment labels (using Montreal Forced Aligner) to produce multi-lingual phonetic representations, thus requiring minimal additional training. We evaluate our model using synthetic native data from the TIMIT dataset and the SCRIBE dataset for American and British English, respectively. Our proposed model outperforms the state-of-the-art (charsiu) in statistical metrics and has applications in language learning and speech processing systems. We leave experiments on other languages for future work but the design of the system makes it easily adaptable to other languages.

A common spinal condition, spondylolisthesis is the presence of a relative back or forth displacement between the upper and lower vertebra due to one vertebra being oriented away from the smooth curvature of a normal spine. Aging-related illnesses such as degenerative spondylolisthesis are especially burdensome on social welfare and health-care systems in an aging society, especially radiologists and clinical physicians. Therefore, we proposed a computer aided diagnosis algorithm, named LumbarNet, for vertebral slippage detection on clinical X-ray images. Collaborating with i) a P-grade, ii) a piecewise slope detection scheme, and iii) a dynamic shift detection routine, LumbarNet was thus specialized for analyzing complex structural patterns in lumbar spine X-ray images and outcompeted other U-Net based methods. Extensive experiments on lumbar spine X-ray images in standard clinical practices showed that LumbarNet achieved a mean intersection over union value of 0.88 in vertebral region detection and an accuracy of 88.83% in vertebral slippage detection.

Moving object detection plays a crucial role in various applications, particularly in traffic surveillance and collision warning systems. However, the high cost of training and slow detection pose significant challenges to the practicality and real-time performance of existing methods. These challenges hinder the practicality and real-time performance of existing methods. The need for a reliable and efficient moving object detection system prompts the search for cost-effective strategies. Enhancing detection speed without sacrificing accuracy is crucial for real-time applications. Overcoming these challenges is essential to advance the field of moving object detection and improve its applicability in various domains. This paper presents a comprehensive review of the literature on moving object detection, proposes novel strategies to overcome the challenges of high training costs and slow detection. The study emphasizes the importance of reliable speed monitoring systems and advancements in control systems to enhance driver assistance on urban highways. Each frame in the dataset undergoes YOLOv6 processing to detect and classify objects, generating bounding box predictions and class probabilities. Optical flow, specifically the Lucas-Kanade method, is then utilized to compute motion vectors between consecutive frames. These motion vectors facilitate object tracking across frames, enabling refined bounding box positions and improving overall object tracking accuracy. The results demonstrate the effectiveness of the proposed technique in reducing training costs, improving detection speed, and maintaining a high level of accuracy when compared to existing methods. The paper concludes by summarizing the findings and highlighting the potential of the proposed strategy for precise and reliable moving object recognition in real-world traffic scenarios

Understanding surfactant self-assembly in deep eutectic solvents (DES) is important to their potential use in industrial formulations. We have recently reported the formation of a fracto-eutectogel comprising SDS fractal aggregates at a concentration as low as 1.6 wt% in glyceline (a DES comprising glycerol and choline chloride) at room temperature. The building units of the fractals consisted of multilayers of self-assembled SDS lamellae arranged in a dendritic pattern. Here we report that this fractal phase transitions into a fluid phase above a critical gelation temperature, TCG ~ 45 oC, evident from polarized light microscopy (PLM) observations. Small-angle neutron scattering (SANS) reveals that this phase transition is underpinned by the nanoscopic morphological transformation of the SDS lamellae into cylindrical micelles at T > TGC. Fitting SANS profiles confirms that the morphology of the micelles is SDS-concentration (cSDS) dependent at T > TGC: cylindrical at cSDS > 0.6 wt% and spherical at cSDS = 0.6 wt%. At cSDS < 0.6 wt%, only isotropic scattering was observed in the SANS profiles. Such SDS self-assembly behaviors contrast with those we have previously observed in glycerol, which we attribute to the presence of ions (i.e. choline chloride) in glyceline. Our findings have general implications to surfactant self-assembly in DES, solvents that are rich in hydrogen bonding and ions.

Human-elephant conflict poses serious conservation challenge in Asia and Africa. We deployed an AI-based camera-alert system in a conflict hotspot in West Bengal, India that accurately detected elephants near villages (266 events) and transmitted real-time alerts ( = 42 seconds). Among detections of separate age and sex classes, lone adult bulls were the most prone to conflict. Real-time alerts permitted rapid response by field personnel to prevent conflict at the site ( = 18.2, SD = 12.4 min to arrival). Frequent detections of humans (33,217 events) on elephant trails highlighted the value of real-time alerts. Four human fatalities and five serious injuries occurred in the study area over a two-year period prior, but none during the study (2023-2024) after deploying the AI-alerting system. Loss of lives and livelihoods underscore the urgency of applying this approach to other elephant ranges and adapting AI models to other conflict-pronespecies to promote coexistence.

Sublobar resection is a standard surgical procedure for small-sized non-small cell lung cancer (NSCLC). However, clinical role of adjuvant chemotherapy for small-sized NSCLC with pathological lymph node (LN) metastasis after sublobar resection is unknown. National Cancer Database was queried for NSCLC patients between 2004 and 2018. Eligibility included sublobar resection with pathological LN metastasis, R0 resection, Charlson comorbidity score = 0, clinical stage T1a-b, and tumor size ≤ 20 mm. Kaplan-Meier method with log-rank test and multivariable Cox proportional hazards analyses were used for assessing survival. Samples were evaluated before and after propensity score matching (PSM) with respect to age, sex, histologic type, and pathological LN status. Of 810 patients who met the eligibility criteria, 567 (70.0%) underwent adjuvant chemotherapy. After PSM, patients with adjuvant chemotherapy had a significantly longer survival than those without (median survival: 64.3 vs. 34.0 months, hazard ratio for death: 0.61, p < 0.0001). Multivariate analyses after PSM showed that younger age (p = 0.0206), female (p = 0.0005), and adjuvant chemotherapy (p < 0.0001) were independent prognostic factors for longer survival. Adjuvant chemotherapy has a prognostic impact in patients with small-sized NSCLC and pathological lymph node metastasis who undergo sublobar resection.

According to Young Minds [1] ‘everyone gets angry sometimes’. Their website offers a number of de-escalating strategies, including staying calm, managing responses and setting limits to help young people who most deem resistive. Yet, Young Minds are not alone because such logical advice is ubiquitous in the literature about challenging behaviour despite the fact that in our experience when faced with high states of arousal, most young people tend to act first and deal with the consequences later. It’s not that they are stupid or non-caring, but they are human capable of great feats as well as stupidity. The same is true for any claims that solution focused (SF) conversations can put right the several decades of psychological theory suggesting resistance requires logic and better cognition. By giving the correct thinking skills, young people will walk away from risk, avoid physical confrontation, handle challenging situations like logical thinkers, and generally discount that the process of growing up is part of the challenge. It is with this in mind that over recent years in our current SF practice (with staff group supervision) we have examined the concept of ‘resistance’ and how it can be put to use as a process of collaboration. To do this, we have revisited SF theory that preoccupied many of its pioneers during the 1980’s and 1990’s and attempted to make it useful for the early 2020’s for professionals having conversations with young people, who, in traditional models, are labelled challenging. We want to introduce key differences of solution focused practice and how Anita started to formulate a 6D-SF model (details, dynamics, dimensions, dispositions, dislocations, descriptions) for contemplating how groups of professionals relate to each other and are triggered by challenging behaviour. We do not claim to have proof, logic or exactness on our side, but we’re happy to suggest how our resistance mirrors what many of the staff teams feel and describe when working through their work.

Background: Critical states present scale-free dynamics, optimizing neuronal complexity. We explored electroencephalogram (EEG) criticality in amnesic Mild Cognitive Impairment (aMCI) patients with clinical improvement in working memory, verbal memory, verbal fluency and overall executive functions after the completion of a 6-month prospective memory training. (2) Methods: We compared “before” and “after” stationary resting-state EEG records of right-handed MCI patients (n = 17; 11 females), using the method of critical fluctuations and Haar wavelet analysis. (3) Results: Significant criticality enhancement was present in frontotemporal electrodes [mean dif: 0.10; Z = 7, p = .019] and isolated electrodes T6 [mean dif: 0.204; t (10) = - 2.3, p = .044] and F4 [mean dif: 0.0194; t (10) = - 2.82; p = .018]. (4) Conclusions: EEG criticality agreed with clinical improvement, consisting a possible monitoring biomarker in MCI and Alzheimer’s disease. Further evaluation is needed in patients under cognitive training or even drug-modifying therapies.

This study investigates the potential of natural compounds against HIV-1 protease, a critical enzyme in the replication cycle of human immunodeficiency virus type 1 (HIV-1). HIV-1 protease is essential for cleaving large precursor proteins into smaller functional proteins necessary for viral maturation and infectivity. Protease inhibitors, specifically targeting HIV-1 protease, effectively suppress viral replication, aiding in the management of HIV infection. Using the SWISS DOCK Server, several natural compounds were investigated for their potential as inhibitors of HIV-1 protease. Docking results revealed that Amentoflavone showed excellent binding affinity with high Estimated ΔG values, suggesting its potential as an inhibitor of HIV-1 protease. Additionally, Amentoflavone exhibited similar promising results when tested against Roussarcoma virus protease. These findings indicate the potential of Amentoflavone as a natural compound against HIV and warrant further investigation into its therapeutic applications.

Urbanization influences food culture, particularly in low- and middle-income countries, where there is an increasing consumption of processed and pre-packaged foods. This shift is contributing to a rise in non-communicable diseases. Food labeling standards are crucial for regulating manufacturing practices and aiding consumers in making healthy food choices. We aimed to assess the compliance of local and imported pre-packaged snacks with Tanzanian and international labeling standards in Dar es Salaam, Tanzania. A cross-sectional study was conducted on 180 snack products. A checklist based on Tanzanian and Codex labeling standards was used to evaluate adherence. We also examined factors influencing adherence, such as product origin, price, category, purchase location, and package size. The majority of the snacks demonstrated partial adherence to labeling standards. Imported products showed significantly better full adherence to both Tanzanian and International standards. Notably, over half of the products used English for labeling, and infrequently used the recommended World Health Organization Front-of-Pack nutrition Labeling. Product category, origin, and package size were significantly associated with higher levels of International standard adherence (p<0.05). The inadequate adherence to mandatory labeling standards, scarce use of Swahili and FoPL highlight the need to strengthen labeling practices and potential challenges faced by consumers in understanding nutritional information. Thus, strengthening and emphasizing good labeling practices is of urgency as we seek to address diet-related Non-communicable diseases.

Intelligent ship technology is currently an international research hotspot, and model predictive control is widely used in the path-tracking control of intelligent vehicles. To construct an intelligent ship anti-disturbance path-tracking control method, firstly, an environmental disturbance model was constructed with the actual meteorological data of the target sea area. Secondly, the Fossen ship equation of motion is linearized and discretized as the ship motion model. Thirdly, the expression of the prediction equation is derived from the ship motion model. Fourthly, the cost function is constructed by using the polar diameter and polar angle values of the ship. Fifth, the power function in the cost function is replaced with an exponential function to obtain an improved cost function. Sixthly, according to the Lyapunov theory and the MPC terminal constraint theory, the stability of the improved cost function is verified. Seventh, different test paths are set up, the environmental disturbance model is taken as the external disturbance, the ship motion model, the prediction equation, and the improved cost function are used to design the anti-disturbance path-tracking control algorithm according to the model prediction control idea for simulation experiments. Finally, different MATLAB simulation results show that the improved cost function can resist disturbance of the external wave, current, and wind, and effectively track the target path. Therefore, this study provides a reference for improving the navigation safety of ship path-tracking.

The IEEE 802.11ah standard is introduced to address the growing scale of Internet of Things (IoT) applications. To reduce contention and enhance energy efficiency within the system, the restricted access window (RAW) mechanism is introduced at the medium access control (MAC) layer to manage the significant number of stations accessing the network. However, the RAW parameters need to be appropriately determined to achieve optimal network performance. In this paper, we optimize the configuration of RAW parameters in the IEEE 802.11ah-based IoT network. We analyze and propose an RAW parameters optimization problem with the objective of improving network throughput and formulate it as a Markov decision process. To cope with the complex and dynamic network conditions, we propose a proximal policy optimization (PPO)-based deep reinforcement learning (DRL) algorithm to find the optimal RAW parameters. We construct network environments with periodic and random traffic in the NS-3 simulator to validate the performance of the proposed PPO-based RAW parameters optimization algorithm. Simulation results reveal that using the PPO-based DRL algorithm, optimal RAW parameters can be obtained under different network conditions, thereby significantly improving network throughput.

As one of the critical state parameters of the battery management system, lithium battery state of charge (SOC) can provide an essential reference for battery safety management, charge/discharge control, and energy management of electric vehicles. To analyze the application of deep learning in electric vehicle power battery SOC estimation, this study reviewed the technical process, common public datasets, and the neural networks used, structural characteristics, advantages and disadvantages of lithium battery SOC estimation in deep learning method. First, the specific technical processes of the deep learning method for SOC estimation were analyzed, including data collection, data preprocessing, feature engineering, model training, and model evaluation. Secondly, the current commonly and publicly used lithium battery dataset was summarized. Then, the input variables, data sets, errors, and advantages and disadvantages of four types of deep learning methods, were concluded using the structure of neural network used for training as the classification criterion. Finally, the challenges and future development directions of lithium battery SOC estimation in deep learning method were explained.

In this review we summarize existing trends of flow control used to improve the aerodynamic efficiency of wings. We first discuss active methods to control turbulence, starting with flat-plate geometries and building towards the more complicated flow around wings. Then, we discuss active approaches to control separation, a crucial aspect towards achieving high aerodynamic efficiency. Furthermore, we highlight methods relying on turbulence simulation, and discuss various levels of modelling. Finally, we thoroughly revise data-driven methods, their application to flow control, and focus on deep reinforcement learning (DRL). We conclude that this methodology has the potential to discover novel control strategies in complex turbulent flows of aerodynamic relevance.

The escalation of climate change and the increasing frequency of extreme weather events have amplified the importance of precise and timely lightning prediction. This predictive capability is pivotal for the preservation of life, protection of property, and maintenance of crucial infrastructure safety. Recently, the rapid advancement and successful application of data-driven deep learning across diverse sectors, particularly in computer vision and spatio-temporal data analysis, have opened up innovative avenues for enhancing both the accuracy and efficiency of lightning prediction. This article presents a comprehensive review of the broad spectrum of existing lightning prediction methodologies. Starting from traditional numerical forecasting techniques, we traverse the path to the most recent breakthroughs in deep learning research. We encapsulate these diverse methods, shedding light on their progression and summarizing their capabilities, while also predicting their future development trajectories. This exploration is designed to enhance our understanding of these methodologies, allowing us to better utilize their strengths, navigate their limitations, and potentially integrate these techniques to create novel and powerful lightning prediction tools. Through such endeavors, our aim is to bolster our preparedness against the growing unpredictability of our climate and ensure a proactive stance towards lightning prediction.

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

Recent advances in artificial intelligence combined with behavioral sciences have led to the development of cutting-edge tools for recognizing human emotions based on text, video, audio, and physiological data. However, these data sources are expensive, intrusive, and regulated, unlike plants which have been shown to be sensitive to human steps and sounds. A methodology is proposed to use plants as human emotion detectors. Electrical signals from plants are tracked and labeled based on video data. Labeled data are then used for classification. MLP, biLSTM, MFCC-CNN, MFCC-ResNet, and additionally, Random Forests, 1-Dimensional CNN, and biLSTM without windowing models are set using a grid search algorithm with cross-validation. Finally, best-parameterized models are trained and used with the test set for classification. The performance of this methodology is measured with a case study with 54 participants, who were watching an emotionally charged video, as ground truth their facial emotions were simultaneously measured using face emotion analysis. The Random Forest model shows the best performance, particularly in recognizing high-arousal emotions, achieving an overall weighted accuracy of 55.2% and demonstrating high weighted recall in emotions such as fear 61.0% and happiness 60.4%. The MFCC-ResNet model offers decently balanced results, with Accuracy(MFCC-ResNet)=0.318 and Recall (MFCC-ResNet)=0.324. With the MFCC-ResNet model fear and anger are recognized with 75% and 50% recall respectively. Thus, using plants as an emotion recognition tool seems worth investigating, addressing both cost and privacy concerns.

Autism Spectrum Disorder (ASD) is a neuro developmental condition that impacts social interac-tion, communication, and behavior. It is called a spectrum because its symptoms and degrees of severity can vary greatly from one person to the next. Differentiations in brain structure and function have been observed between autistic and typically developing brains. Various aspects of brain function, including information processing, sensory perception, and the capacity to interpret and respond to social cues, may be affected by these differences. The signs and symptoms of ASD are readily apparent to parents in the first few years of their child’s life. The symptoms of ASD, it is said, first appear in early childhood and continue into maturity. Brain MRI analysis utilizing deep learning methods show encouraging findings in the study of ASD. In this study, we look at how well a customized VGG16 architecture compares models that have already been trained. Inception v3, ResNet50, DenseNet121, and MobileNet are used to identify and analyze ASD problems in a brain MRI dataset from people with ASD. The proposed methods have been vali-dated on the unlabeled ABIDE 1 dataset that is freely available to the public. After the unlabeled data has been clustered, five different Deep Learning (DL) methods are used and compared. The results are compared to those of other studies that have already been conducted.

Deep learning has achieved lots of successes in many fields, but when trainable sample are extremely limited, deep learning often under or overfitting to few samples. Meta-learning was proposed to solve difficulties in few-shot learning and fast adaptive areas. Meta-learner learns to remember some common knowledge by training on large scale tasks sampled from a certain data distribution to equip generalization when facing unseen new tasks. Due to the limitation of samples, most approaches only use shallow neural network to avoid overfitting and reduce the difficulty of training process, that causes the waste of many extra information when adapting to unseen tasks. Euclidean space-based gradient descent also make meta-learner's update inaccurate. These issues cause many meta-learning model hard to extract feature from samples and update network parameters. In this paper, we propose a novel method by using multi-stage joint training approach to post the bottleneck during adapting process. To accelerate adapt procedure, we also constraint network to Stiefel manifold, thus meta-learner could perform more stable gradient descent in limited steps. Experiment on mini-ImageNet shows that our method reaches better accuracy under 5-way 1-shot and 5-way 5-shot conditions.

There is only a very short reaction time for people to find the best way out of a building in a fire outbreak. Software applications can be used to assist the rapid evacuation of victims; however, this is an arduous task, which requires an understanding of advanced technologies. Since well-known pathway algorithms (such as, Dijkstra, Bellman-Ford and A*) can lead to serious problems over performance, we decided to make use of deep reinforcement learning techniques. A wide range of strategies including a random initialization of replay buffer and transfer learning were assessed in three projects involving schools of different sizes. The results showed the proposal was viable and that in most cases the performance of transfer learning was superior. In addition, the study raised challenges that had to be faced in the future.

The robust control of high precision electromechanical systems, such as micropositioners, is challenging in terms of the inherent high nonlinearity, the sensitivity to external interference, and the complexity of accurate identification of the model parameters. To cope with these problems, this work investigates a disturbance observer-based deep reinforcement learning control strategy to realize high robustness and precise tracking performance. Reinforcement learning has shown great potential as optimal control scheme, however, its application in micropositioning systems is still rare. Therefore, embedded with the integral differential compensator (ID), deep deterministic policy gradient (DDPG) is utilized in this work with the ability to not only decrease the state error but also improves the transient response speed. In addition, an adaptive sliding mode disturbance observer (ASMDO) is proposed to further eliminate the collective effect caused by the lumped disturbances. The sterling performance is revealed with intensive tracking simulation experiments and demonstrates the improvement in the accuracy and response time of the controller.

Existing methods for building extraction from remotely sensed images strongly rely on aerial or satellite-based images with very high resolution, which are usually limited by spatiotemporally accessibility and cost. In contrast, relatively low-resolution images have better spatial and temporal availability but cannot directly contribute to fine- and/or high-resolution building extraction. In this paper, based on image super-resolution and segmentation techniques, we propose a two-stage framework (SRBuildingSeg) for achieving super-resolution (SR) building extraction using relatively low-resolution remotely sensed images. SRBuildingSeg can fully utilize inherent information from the given low-resolution images to achieve high-resolution building extraction. In contrast to the existing building extraction methods, we first utilize an internal pairs generation module (IPG) to obtain SR training datasets from the given low-resolution images and an edge-aware super-resolution module (EASR) to improve the perceptional features, following the dual-encoder building segmentation module (DES). Both qualitative and quantitative experimental results demonstrate that our proposed approach is capable of achieving high-resolution (e.g. 0.5 m) building extraction results at 2×, 4× and 8× SR. Our approach outperforms 8 other methods with respect to the extraction result of mean Intersection over Union (mIoU) values by a ratio of 9.38%, 8.20% and 7.89% with SR ratio factors of 2, 4, and 8, respectively. The results indicate that the edges and borders reconstructed in super-resolved images serve a pivotal role in subsequent building extraction and reveal the potential of the proposed approach to achieve super-resolution building extraction. Our code is available at https://github.com/xian1234/SRBuildSeg.

Chronic venous disease (CVD) occurs in a substantial proportion of the world's population. If the onset of CVD looks like a cosmetic defect, then over time, it can develop into serious problems that require surgical intervention. The aim of the work is to use deep learning (DL) methods for automatic classification of the stage of CVD for self-diagnosis of a patient by using the image of the patient’s legs. The required for DL algorithms images of legs with CVD were obtained by using Internet Data Mining. For images preprocessing, the binary classification problem “legs - no legs” was solved based on Resnet50 with accuracy 0.998. The application of this filter made it possible to collect a data set of 11,118 good quality leg images with various stages of CVD. For classification of various stages of CVD according to CEAP classification, the multi classification problem was set and resolved by using two neural networks with completely different architecture - Resnet50 and DeiT. The model based on DeiT without any tuning shows better results than the model based on Resnet50 (precision = 0.770 (DeiT) and 0.615 (Resnet50)). To demonstrate the results of the work, a telegram bot was developed, in which fully functioning DL algorithms are implemented. This bot allows evaluating the condition of the patient's legs with a fairly good accuracy for the CVD classification.

This study proposes a mobile positioning method which adopts recurrent neural network algorithms to analyze the received signal strength indications from heterogeneous networks (e.g., cellular networks and Wi-Fi networks) for estimating the locations of mobile statioThis study proposes a mobile positioning method which adopts recurrent neural network algorithms to analyze the received signal strength indications from heterogeneous networks (e.g., cellular networks and Wi-Fi networks) for estimating the locations of mobile stations. The recurrent neural networks with multiple consecutive timestamps can be applied to extract the features of time series data for the improvement of location estimation. In practical experimental environments, there are 4,525 records, 59 different base stations, and 582 different Wi-Fi access points detected in Fuzhou University in China. The lower location errors can be obtained by the recurrent neural networks with multiple consecutive timestamps (e.g., 2 timestamps and 3 timestamps); the experimental results can be observed that the average error of location estimation was 9.19 meters by the proposed mobile positioning method with 2 timestamps.

This paper presents an approach to enhancing the clarity and intelligibility of speech in digital communications compromised by various background noises. Utilizing deep learning techniques, specifically a Variational Autoencoder (VAE) with 2D convolutional filters, we aim to suppress background noise in audio signals. Our method focuses on four simulated environmental noise scenarios: storms, wind, traffic, and aircraft. Training dataset has been obtained from public sources (TED-LIUM 3 dataset, which includes audio recordings from the popular TED-TALK series) combining with these background noises. The audio signals were transformed into 2D power spectrograms, upon which our VAE model was trained to filter out the noise and reconstruct clean audio. Our results demonstrate that the model outperforms existing state-of-the-art solutions in noise sup-pression. Although differences in noise types were observed, it was challenging to definitively conclude which background noise most adversely affects speech quality. Results have been assessed with objective methods (mathematical metrics) and subjective (listening to a set of audios by humans). Notably, wind noise showed the smallest deviation between the noisy and cleaned audio, perceived subjectively as the most improved scenario. Future work involves refining the phase calculation of the cleaned audio and creating a more balanced dataset to minimize differences in audio quality across scenarios. Additionally, practical ap-plications of the model in real-time streaming audio are envisaged. This research contributes significantly to the field of audio signal processing by offering a deep learning solution tailored to various noise conditions, enhancing digital communication quality.

We confirm that energy dissipation weighting provides the most accurate approach to determining the effective hydraulic conductivity (Keff) of a binary K grid. A deep learning algorithm (UNET) can infer Keff with extremely high accuracy (R2 > 0.99). The UNET architecture could be trained to infer the energy dissipation weighting pattern from an image of the K distribution with high fidelity, although it was less accurate for cases with highly localized structures that controlled flow. Furthermore, the UNET architecture learned to infer the energy dissipation weighting even if it was not trained on this information directly. However, the weights were represented within the UNET in a way that was not immediately interpretable by a human user. This reiterates the idea that even if ML/DL algorithms are trained to make some hydrologic predictions accurately, they must be designed and trained to provide each user-required output if their results are to be used to improve our understanding of hydrologic systems most effectively.

White matter hyperintensity (WMH) has been considered the primary biomarker from small-vessel cerebrovascular disease to Alzheimer’s disease (AD) and has been reported for its correlation of brain structural changes. To perform WMH related analysis with brain structure, both T1-weighted (T1w) and (Fluid Attenuated Inversion Recovery(FLAIR) are required. However, in a clinical situation, it is limited to obtain 3D T1w and FLAIR images simultaneously. Also, the most of brain segmentation technique supports 3D T1w only. Therefore, we introduced the semi-supervised learning method that can perform brain segmentation using FLAIR image only. Our method achieved a dice overlap score of 0.86 for brain tissue segmentation on FLAIR, with the relative volume difference between T1w and FLAIR segmentation under 4.8%, which is just as reliable as the segmentation done by its paired T1w image. We believe our semi-supervised learning method has a great potential to be used to other MRI sequences and provide encouragement to people who seek brain tissue segmentation from a non-T1w image.

To improve the tangerine crop yield, the work of recognizing and then disposing of specific pests is becoming increasingly important. The task of recognition is based on the features extracted from the images that have been collected from websites and outdoors. Traditional recognition and deep learning methods, such as KNN (k-nearest neighbors) and AlexNet, are not preferred by knowledgeable researchers, who have proven them inaccurate. In this paper, we exploit four kinds of structures of advanced deep learning to classify 10 citrus pests. The experimental results show that Inception-ResNet-V3 obtains the minimum classification error.

In computer vision, human action recognition is a hot topic, popularized by the development of deep learning. Current models have achieved high accuracy results on public datasets. Despite this success, they require significant computational resources for training. Given that transfer learning based techniques allow reusing what other models have already learned and training models with less computational resources, in this work we propose using a transfer learning based approach for action recognition in videos. We describe a methodology for human action recognition using transfer learning techniques in a custom dataset. The proposed method consists of four stages: 1) human detection and tracking, 2) video preprocessing, 3) feature extraction (using pretrained models with ImageNet), and 4) action recognition using a two-stream model consisting of TCNs, LSTMs, and CNNs layers. The custom dataset is imbalanced with 189, 390, 490, 854, and 890 videos per class, respectively. For feature extraction, we analyzed the performance of seven pretrained models: Inception-v3, MobileNet-v2, MobileNet-v3-L, VGG-16, VGG-19, Xception, and ConvNeXt-L. We show that the best results were obtained with the last one. Finally, using pretrained models for feature extraction allowed training in a PC with a single GPU with an accuracy of 94.9%.

The steep rise in reinforcement learning (RL) in various applications in energy as well as the penetration of home automation in recent years are the motivation for this article. It surveys the use of RL in various home energy management system (HEMS) applications. There is a focus on deep neural network (DNN) models in RL. The article provides an overview of reinforcement learning. This is followed with discussions on state-of-the-art methods for value, policy, and actor–critic methods in deep reinforcement learning (DRL). In order to make the published literature in reinforcement learning more accessible to the HEMS community, verbal descriptions are accompanied with explanatory figures as well as mathematical expressions using standard machine learning terminology. Next, a detailed survey of how reinforcement learning is used in different HEMS domains is described. The survey also considers what kind of reinforcement learning algorithms are used in each HEMS application. It suggests that research in this direction is still in its infancy. Lastly, the article proposes four performance metrics to evaluate RL methods.

One of the most rapidly advancing areas of deep learning research aims at creating models that learn to disentangle the latent factors of variation from a data distribution. However, modeling joint probability mass functions is usually prohibitive, which motivates the use of conditional models assuming that some information is given as input. In the domain of numerical cognition, deep learning architectures have successfully demonstrated that approximate numerosity representations can emerge in multi-layer networks that build latent representations of a set of images with a varying number of items. However, existing models have focused on tasks requiring to conditionally estimate numerosity information from a given image. Here we focus on a set of much more challenging tasks, which require to conditionally generate synthetic images containing a given number of items. We show that attention-based architectures operating at the pixel level can learn to produce well-formed images approximately containing a specific number of items, even when the target numerosity was not present in the training distribution.

Conventional tutoring approaches are confronted with limitations such as restricted availability, inconsistent pedagogical quality, and scalability con-straints. Furthermore, the exclusive use of Large Language Models (LLMs) like ChatGPT in education has its shortcomings, including the potential for incorrect responses and the lack of customized guidance aligned with specific course con-tent. This research proposes an innovative intelligent chatbot tutoring system, in-tegrating the Retrieval Augmented Generation (RAG) approach with a custom LLM. The developed system aims to overcome the limitations of traditional tu-toring and general-purpose LLMs by providing accurate, contextually relevant, and personalized assistance, thereby enhancing student understanding and en-gagement. The system, powered by an intelligent agent, retrieves relevant information from curated academic sources, incorporates interactive features for user feedback, and utilizes machine learning algorithms for ongoing performance enhancement, ensuring a robust and effective tutoring experience. The anticipated outcome is an enriched educational experience for university students, advance-ment in personalized learning, and improved student engagement, retention, and academic performance. Through continuous research and refinement, it is expected that the intelligent chatbot tutor will assume an important role in enhancing and supporting the educational journey of students.

Orificed Hollow Cathodes are electric devices necessary for the functioning of common plasma thrusters for space applications. From their reliability mainly depends the success of a spacecraft’s mission equipped by electric propulsion. The development of plasma models is crucial in the evaluation of plasma properties within the cathodes that are difficult to measure due to the small dimensions. Many models, based on non-linear system of plasma equations, have been proposed in the open literature. These are solved commonly by means of iterative procedures. This paper investigates the possibility to solve them by means of Particle Swarm Optimization method. The results of the validation tests confirm the expected trends for all the unknowns; the confidence bound of the discharge current as function of mass flow rate is very narrow (2÷5V), moreover the results match very well the experimental data except at the lowest mass flow rate (0.08mg/s) and discharge current (1A), where the computations underpredict the discharge current to the utmost by 40%; the highest data dispersion regards the plasma density in the emitter region (± 20 % of the average value) and the wall temperatures (± 50K respect to the average values) of orifice and insert; those of the others variables are very tiny.

The construction sector is a paradigm shift into the sustainable era to solve environmental issues, combat global warming. And the reflection of this is on Green Buildings where energy savings, cost savings, occupant comfort takes priority. The idea of green building efficiency merges sophisticated technologies, creative architectural design templates, and reusable materials into the whole life cycle of a building process in order to render minimum environmental impact. The pilot project of The National Institute of Geophysics and Volcanology (INGV) - Irpinia headquarters, illustrates in this context, innovative technologies of energy transition with a photovoltaic parking with geothermal piles. The project is consistent with the concepts of Nearly Zero Energy Buildings (NZEBs), directed to a high energy performance and very low environmental impact. Incorporating geothermal piles is a major area of advancement in sustainable building ideas that use the Earth's natural heat to create an energy efficient solution in heating and cooling. Project Goals – The project aims to install emission free renewable cleaning energy cost-effective clean production and increase energy efficiency, reduce CO2 emissions and energy security. For this purpose this paper, using as a support the PVGis software, evaluates the potential produced with the photovoltaic system installed in the canopies. With the help of this analysis, it is feasible to determine the amount of electricity produced as well as the system's amortization based on the excess energy sent to the public grid. The project is regarded as creative from the standpoints of energy given the use of geothermal and photovoltaic systems, as well as from an architectural and design perspective due to the use of novel materials. This all-encompassing strategy establishes INGV as a pioneer in the promotion of environmentally friendly technologies and shows a dedication to sustainability and energy efficiency.

We experimentally demonstrate waveguide and microring resonator (MRR) polarizers by integrating 2D graphene oxide (GO) films onto silicon (Si) photonic devices. The 2D GO films with highly anisotropic light absorption are on-chip integrated with precise control over their thicknesses and sizes. Detailed measurements are performed for the fabricated devices with different GO film thicknesses, coating lengths, and Si waveguide widths. The results show that a maximum polarization-dependent loss (PDL) of ~17 dB is achieved for the hybrid waveguides, and the hybrid MRRs achieved a maximum polarization extinction ratio (PER) of ~10 dB. We also characterize the wavelength- and power-dependent response for these polarizers. The former demonstrates a broad operation bandwidth of over ~100 nm, and the latter verifies performance improvement enabled by photo-thermal changes in GO films. By fitting the experimental results with theoretical simulations, we find that the anisotropy in the loss of GO films dominates the polarization selectivity of these devices. These results highlight the strong potential of 2D GO films for realizing high-performance polarization selective devices in Si photonic platform.

Background: Research articles are essential for describing new ideas, techniques, and procedures and consolidating concepts. It creates an opportunity to expose studies and publicly assimilate published knowledge. Therefore, one of them is the most used and accepted index to verify the author’s scientific impact is the H-index or Hirsch index. It provides a robust single metric that combines quality and quantity. Therefore, it presents disadvantages, (1) researchers with shorter scientific carriers may have fewer articles and citations than those with longer scientific life; (2) it allows scientists to receive citations even if no new papers are published; (3) it is only useful for comparing the better scientists in a field; (4) this indicator can never decrease; (5) it is only weakly sensitive to the number of citations received; (6) the major and minor (or no) contributor in the research gained equal h-index. Then, the H-index ignores the total of citations and the time of a researcher's experience (“scientific age” [sa]). Objective: Thus, the goal of this study was to present a new index system (GFsa index ©) based on the two variables completely forgotten (total of citations and “scientific age”), introducing a new terminology “scientific age”, to evaluate the best-ranked researchers in Dentistry. Methods: The AD Scientific Index was used, and all researchers included in this study were cited in the AD Scientific Index (2024) in the Dentistry field and had the Google Scholar page accessible for a consultation to manually obtain the total of citations and calculate the “scientific age”. The information was retrieved by two authors (G.V.O.F. and J.C.H.F.), who assessed the data twice to avoid errors or mistakes. For inclusion: a minimum H-index value of 30; for exclusion: (i) the author did not have a Google Scholar page; (ii) duplicated author; or (iii) presented any suspicious activities about manipulation of articles. Then, a dataset of all researchers who were reported in Dentistry was prepared (name, H-index, i10 index, and publications). The formula developed and applied was GFsa=(total number of citations)/(“scientific age)². The Pearson correlation statistically evaluated the data obtained; the confidence interval was 95%. Results: A total of 9,093 researchers in Dentistry were recorded, of whom 1,020 were included. Then, we collected all 1,020 researchers' Google Scholar data (publications, citations, and indexes), and each researcher's total citations and “scientific age” were registered and calculated. The mean “scientific age” registered was 34.18 ± 13.34 (standard error of mean = 0.4181). With this information and data collected, GFsa index © was calculated, presenting a minimum value of 0.2186 and a maximum of 154.8 (mean = 10.33 ± 11.82; standard error of mean = 0.3706). Then, the data was organized and sorted following the ranking obtained in the GFsa index ©. The Pearson correlation showed that the H-index had a weakly positive association with the researcher’s “scientific age”; this fact means that the H-index will increase according to the “scientific age” increase. Otherwise, a moderately negative correlation between GFsa and “scientific age” was demonstrated, whereby a higher GFsa © had a lower “Scientific age”. This assessment shows that the variables introduced were fairly used. Moreover, a positive correlation was observed between both indexes (H-index and GFsa). Conclusion: It is possible to conclude that the new variable reported (“Scientific age”) and using the total citations brought a fairer and more feasible evaluation among the researchers. Thus, we are launching the new GFsa index © and the new information named “Scientific age” for the first time in the literature. The future perspective of the GFsa © application will be (1) the evaluation of the 9,093 researchers in Dentistry (total initially registered), including more authors/researchers in the Dentistry field, (2) expanding the exposition of this new index for other areas of the knowledge, and (3) provide free access of all data through the website (http://gfindex.us.to).

This study investigated the relationship between aluminum adjuvant vaccines and the prevalence of 4 childhood diseases (Autism, Allergies, Asthma, ADD/ADHD) using data from the 2020-2021 National Survey of Children's Health (NSCH) [1] and the Centers for Disease Control National Immunization Survey (CDC NIS) [2]. The study found an association with aluminum adjuvant dosage and the prevalence of each disease studied (Autism, Allergies, Asthma, ADD/ADHD) through a weighted regression analysis of disease prevalence against the summed likelihood of aluminum adjuvant vaccine uptake.

This paper presents the perspective that universe is relative. The universe, which changes according to the traveler’s proper time, is dynamic. While the universe generally expands, it could also contract if traveler accelerates sufficiently. The Hubble parameter merely represents that change. If the Hubble parameter is dependent on the proper time, the measurement can only be uncertain. Identifying the factors that influence the proper time could potentially lead to a more accurate measurement of the universe’s age, and it could also offer insights into the state of the early universe and the causes of the accelerated expansion observed in the current epoch.

This paper presents a novel approach for accurate counting and localization of tropical plants in aerial images that is able to work in new visual domains in which the available data is not labeled. Our approach uses deep learning and domain adaptation, designed to handle domain shift between the training and test data, which is a common challenge in this agricultural applications. This method uses a source dataset with annotated plants and a target dataset without annotations, and adapts a model trained on the source dataset to the target dataset using unsupervised domain alignment and pseudolabeling. The experimental results show the effectiveness of this approach for plant counting in aerial images of pineapples under significative domain shift, achieving a reduction up to 97% in the counting error when compared to the supervised baseline.

Immune-cell reprogramming driven by mitochondria-derived reactive electrophilic immunometabolites (mt-REMs—e.g., fumarate, itaconate) is an emerging phenomenon of major biomedical importance. Despite their localized production, mt-REMs elicit significantly-large local and global footprints within and across cells, through mechanisms involving electrophile signaling. Burgeoning efforts are being put into profiling mt-REMs’ potential protein-targets and phenotypic mapping of their multifaceted inflammatory behaviors. Yet, precision indexing of mt-REMs’ first-responders with spatiotemporal intelligence and locale-specific function assignments remains elusive. Highlighting the latest advances and overarching challenges, this perspective aims to stimulate thoughts and spur interdisciplinary innovations to address these unmet chemical-biotechnological needs at therapeutic immuno-signaling frontiers.

Background: Chronic Myeloid Leukemia (CML) is initiated in the bone marrow due to the chromosomal translocation t(9;22), resulting in the fusion oncogene BCR-ABL. Tyrosine kinase inhibitors (TKIs) targeting BCR-ABL have transformed fatal CML into an almost curable disease. However, TKIs lose efficacy during disease progression, and the mechanism of CML progression remains to be fully understood. Additionally, common molecular biomarkers for CML progression are lacking. Our studies previously detected ANKRD36 (c.1183_1184 delGC and c.1187_1188 dupTT) associated exclusively with advanced phase CML. However, clinical validation of this finding was pending. Therefore, this study aimed to clinically validate mutated ANKRD36 as a novel biomarker of CML progression. Materials and Methods: The study enrolled 124 patients in all phases of CML, recruited from Mayo Hospital and Hameed Latif Hospital in Lahore, Punjab, between January 2020 and September 2023. All response criteria were adopted from the European LeukemiaNet guideline 2020. Informed consent was obtained from all study subjects. The study was approved byscientific and ethical review committees of all participating centers. Sanger sequencing was employed to detect ANKRD36mutations in CML patients in accelerated phase (AP) (n=11) and blast crisis (BC) (n=10), with chronic-phase CML (CP-CML) patients as controls (n=103). Samples were processed using Big Dye Terminator Cycle Sequencing Ready Reaction kits and sequenced using ABI Prism 3730 Genetic Analyzer, and sequencing using forward and reverse primers for ANKRD36.Results: During our study, 17% of CML patients progressed to advanced phases AP-CML n= 11 (8.9%) and BC-CML n=10(8.1%). The chronic- and advanced-phase patients showed significant difference with respect to male-to-female ratio, hemoglobin level, WBC count, and platelet count. Sanger sequencing detected ANKRD36 mutations c.1183_1184 delGC and c.1187_1185 dupTT exclusively in all AP- and BC-CML patients but in none of the CP-CML patients. Nevertheless, mutations status was not associated with male-to-female ratio, hemoglobin level, WBC count, and platelet count, which makes ANKRD32 as an independent predictor of early and terminal disease progression in CML. Conclusions: The study confirms ANKRD36 as a novelgenomic biomarker for early and late CML progression. Further prospective studies should be carried out in this regard. ANKRD36, although fully uncharacterized in humans, shows the highest expression in bone marrow, particularly myeloid cells. Functional integrated genomic studies are recommended to further explore the role of ANKRD36 in the biology and pathogenesis of CML.

The automotive industry is continuously developing to meet the needs of users in terms of efficiency and convenience. The Thailand government has set a policy for Thailand to be a hub for the production of electric vehicles and key components in the region, with a target to produce electric and zero-emission vehicles by 2030. This article is an example of communication in an electric vehicle system. The CAN Bus system is a communication system in electric vehicles that can receive and send communication data via CAN-Hight/Low lines designed for vehicles. CAN Bus is a standard communication system supported by global organizations and used in modern automotive systems. The design of the communication system in electric vehicles uses MRS Developers Studio software to help write programs to receive and send data and prioritize the importance of the received data. The system consists of communication examples studied, such as pressing the start button, turning on/off the headlights, turning on/off the turn signal, turning on/off the brake light, turning on/off the emergency light, sending the horn signal, sending the signal to shift forward/backward, and tuning the motor gear system. From the communication examples mentioned, the communication will be a prototype transport set for small electric vehicles under the scope of the lithium battery energy storage system, NMC type, size 72 V 25 Ah, to test the use, efficiency, and stability in CAN Bus communication up to 1000 times.

Audio classification using deep learning models, essential for applications like voice assistants and music analysis, faces challenges when deployed on edge devices due to their limited computational resources and memory. Achieving a balance between performance, efficiency, and accuracy is a significant obstacle in optimizing these models for such constrained environments. In this investigation, we evaluate diverse deep learning architectures, including Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM), for audio classification tasks on the ESC 50, UrbanSound8k, and Audio Set datasets. Our empirical findings indicate that Mel Spectrograms outperform raw audio data, attributing this enhancement to their synergistic alignment with advanced image classification algorithms and their congruence with human auditory perception. To address the constraints of model size, we apply model compression techniques, notably magnitude pruning, Taylor Pruning, and 8-bit quantization. The research demonstrates that a hybrid pruned model achieves a commendable accuracy rate of 89 percent, which, although marginally lower than the 92 percent accuracy of the uncompressed CNN, strikingly illustrates an equilibrium between efficiency and performance. Subsequently, we deploy the optimized model on Raspberry Pi 4 and NVIDIA Jetson Nano platforms for audio classification tasks. These findings highlight the significant potential of model compression strategies in enabling effective deep learning applications on resource-limited devices, with minimal compromise on accuracy.

Capsizing accidents are regarded as marine accidents with a high rate of casualties per accident. Approximately 89% of all such accidents occur in small ships (vessels with gross tonnage less than 10 tons). Stability calculations are critical for assessing the risk of capsizing incidents and evaluating a ship's seaworthiness. Despite the high frequency of capsizing accidents involving small ships, they are generally exempt from adhering to stability regulations, thus remaining systemically exposed to the risk of capsizing. Moreover, the absence of essential design documents complicates direct ship stability calculations. This study utilizes hull form feature data—obtained from the general arrangement of small ships—as input for a deep learning model. The model is structured as a multilayer neural network and aims to infer hydrostatic curves, which is required data for stability calculations.

One of the most prevalent brain diseases, epilepsy is characterized by recurring seizures that happen quite frequently. During seizures, a patient suffers uncontrollable muscle contractions that cause loss of motion and balance, which could lead to harm or even death. Establishing an automatic method for warning patients about impending seizures requires extensive research. It is possible to anticipate seizures by analyzing the Electroencephalogram (EEG) signal from the scalp region of the human brain. Time domain-based features such as Hurst exponent (Hur), Tsallis Entropy (TsEn), improved permutation entropy (impe), and amplitude-aware permutation entropy (AAPE) were extracted from EEG signals. In order to diagnose epileptic seizure children from normal children automatically, this study conducted two sessions, in the first session, the extracted features from the EEG dataset were classified using three machine learning (ML)-based models including support vector machine (SVM), K nearest neighbor (KNN), or decision tree (DT), while in the second session, the dataset was classified using three deep learning (DL)-based recurrent neural network (RNN) classifiers including a gated recurrent unit (GRU), long short-term memory (LSTM), and bidirectional (BiLSTM). The EEG dataset obtained from the Neurology Clinic at the Ibn-Rushd Training Hospital. In this regard, detailed explanations and research from the time domain and entropy characteristics show that using GRU, LSTM, and BiLSTM RNN deep learning classifiers on the All−time−entropy fusion feature improves the final classification results.

Taste determination in small molecules is critical in food chemistry, but traditional experimental methods can be time-consuming. Consequently, computational techniques have emerged as val-uable tools for this task. In this study, we explore taste prediction using various molecular feature representations and assess the performance of different machine learning algorithms on a dataset comprising 2,601 molecules. The results reveal that GNN-based models outperform other ap-proaches in taste prediction. Moreover, consensus models that combine diverse molecular repre-sentations demonstrate improved performance. Among these, molecular fingerprints + GNN con-sensus model emerges as the top performer, highlighting the complementary strengths of GNNs and molecular fingerprints. These findings have significant implications for food chemistry research and related fields. By leveraging these computational approaches, taste prediction can be expedited, leading to advancements in understanding the relationship between molecular structure and taste perception in various food components and related compounds.

In this study, we aimed to develop a deep learning model for identifying bacterial keratitis (BK) and fungal keratitis (FK) by using slit-lamp images. We retrospectively collected slit-lamp images of patients with culture-proven microbial keratitis between January 1, 2010, and December 31, 2019, from two medical centers in Taiwan. We constructed a deep learning algorithm, consisting of a segmentation model for cropping cornea images and a classification model that applies convolutional neural networks to differentiate between FK and BK. The model performance was evaluated and presented as the area under the curve (AUC) of the receiver operating characteristic curves. A gradient-weighted class activation mapping technique was used to plot the heatmap of the model. By using 1330 images from 580 patients, the deep learning algorithm achieved an average diagnostic accuracy of 80.00%. The diagnostic accuracy for BK ranged from 79.59% to 95.91% and that for FK ranged from 26.31% to 63.15%. DenseNet169 showed the best model performance, with an AUC of 0.78 for both BK and FK. The heat maps revealed that the model was able to identify the corneal infiltrations. The model showed better diagnostic accuracy than the previously reported diagnostic performance of both general ophthalmologists and corneal specialists.

River flow prediction is a pivotal task in the field of water resource management during the era of rapid climate change. The highly dynamic and evolving nature of the climatic variables e.g., precipitation has a significant impact on the temporal distribution of the river discharge in recent days making the discharge forecasting even more complicated for diversified water-related issues e.g., flood prediction and irrigation planning. To predict the discharge, various physics-based numerical models are used using numerous hydrologic parameters. Extensive lab-based investigation and calibration are required to reduce the uncertainty involved in those parameters. However, in the age of data-driven predictions, several deep learning algorithms showed satisfactory performance in dealing with sequential data. In this research, Long Short-term Memory (LSTM) neural network regression model is trained using over 80 years of daily data to forecast the discharge time series up to 3 days ahead of time. The performance of the model is found satisfactory through the comparison of the predicted data with the observed data, visualization of the distribution of the errors and Root Mean Squared Error (RMSE) value of 0.09. Higher performance is achieved through the increase in the number of epochs and hyper parameter tuning. This model can be transferred to other locations with proper feature engineering and optimization to perform univariate predictive analysis and potentially be used to perform real-time river discharge prediction.

Geometrical assessments of human skull have been done based on the anatomical landmarks. Automatic detection of the landmarks, if developed, will be a great help not only medically, but also anthropologically. An automated system with multi-phased deep learning networks to predict three-dimensional coordinate values of cranio-facial landmarks, was developed. From a publicly available database, computed tomography images of craniofacial area were obtained. They were digitally reconstructed into three-dimensional models. Sixteen anatomical landmarks were plotted on each of the models and coordinate values of them were recorded. Three-phased regression deep learning networks were trained respectively with 90 training datasets. For evaluation, 30 testing datasets were employed. Three-dimensional error for the first phase, testing 30 data, was 11.60 pixels in average. (1 pixel = 500 / 512 mm) For the second phase, it was significantly improved to 4.66 pixels. For the third phase, it was significantly progressed to 2.88. This was comparable to the gaps between the landmarks, plotted by two experienced practitioners. Our proposing method of multi-phased prediction, coarse detection first and narrowing down the detection area, may be a possible solution, within the physical limitation of memory and computation.

Barrett's esopaghagus (BE) is a known precursor of esophageal adenocarcinoma (EAC). Patients with BE undergo regular surveillance to early detect stages of EAC. Volumetric laser endomicroscopy (VLE) is a novel technology capable of imaging the inner tissue layers of the esophagus over a 6-cm length scan. However, interpretation of full VLE scans is still a challenge for human observers. In this work, we train an ensemble of deep convolutional neural networks to detect neoplasia in BE patients, using a dataset of images acquired with VLE in a multicenter study. We achieve values of AUC=$0.96$ on the unseen test dataset and we compare our results with previous work done with VLE analysis. Our method for detecting neoplasia in BE patients facilitates future advances on patient treatment and provides clinicians with new assisting solutions to process and better understand VLE data.

The application of deep learning in autonomous vehicles has surged over the years with the advances in technologies. This research explores the integration of deep learning algorithms into autonomous vehicles (AVs), focusing on their role in perception, decision-making, localization, mapping, and navigation. It shows that deep learning, which as a part of machine learning, mimics the human brain's neural networks, enabling advancements in perception, decision-making, localization, mapping, and overall navigation. Techniques like convolutional neural networks are used for image detection and steering control, while deep learning is crucial for path planning, automated parking, and traffic maneuvering. Localization and mapping are essential for AVs' navigation, with deep learning-based object detection mechanisms like Faster R-CNN and YOLO proving effective in real-time obstacle detection. Apart from the roles, the study also revealed that integration of deep learning in AVs faces challenges such as dataset uncertainty, sensor challenges, and model training intricacies. However, these issues can be addressed through increased standardization of sensors, real-life testing for model training, and advancements in model compression technologies can optimize the performance of deep learning in AVs. The study concludes that deep learning plays a crucial role in enhancing the safety and reliability of AV navigation. This study contributes to the ongoing discourse on the optimal integration of deep learning in AVs, aiming to foster their safety, reliability, and societal acceptance.

Microscopic and ultra-microscopic vascular sutures are indispensable in the surgical procedures such as arm transplantation and finger reattachment. The state of the blood vessels after suturing, such as vascular patency, narrow, and blocked, determines the success rate of the operation. If we can grasp the golden window period after blood vessel suture and before muscle tissue suture to achieve accurate and objective assessment of blood vessel status, it can not only reduce medical costs but also improve social benefits. Doppler optical coherence tomography enables high-speed, high-resolution imaging of biological tissues, especially microscopic and ultra-microscopic blood vessels. Using Doppler optical coherence tomography to image the sutured blood vessels, not only the three-dimensional structure of the blood vessels, but also the blood flow information can be obtained. By extracting the contour of blood vessel wall and the contour of blood flow area, the three-dimensional shape of blood vessel can be reconstructed in three dimensions, which provides parameter support for the assessment of blood vessel status. In this work, we propose a neural network-based multi-classification deep learning model that can simultaneously and automatically extract blood vessel boundaries from Doppler OCT vessel intensity images and the contours of blood flow regions from corresponding Doppler OCT vessel phase images. Compared with the traditional random walk segmentation algorithm and cascade neural network method, the proposed model has better performance. This method is easier to realize system integration and has great potential for clinical evaluation. It is expected to be applied to the evaluation of microscopic and ultra-microscopic vascular status in microvascular anastomosis.

X-ray Fluorescence Computed Tomography (XFCT) is an emerging non-invasive imaging technique providing molecular-level data, gaining attention for high-resolution imaging. However, increased sensitivity with benchtop X-ray sources raises radiation exposure. Artificial Intelligence (AI), particularly deep learning (DL), has revolutionized medical imaging by delivering high-quality images in the presence of noise. In XFCT, traditional methods rely on complex algorithms for noise reduction, but AI holds promise in addressing high-dose concerns. We present an optimized SCUNet model for noise reduction in low-concentration XRF images. Compared to higher-dose images, our method’s effectiveness is evaluated. While various denoising techniques exist for X-ray and CT, few address to XFCT. The DL model is trained and assessed using the augmented data, focusing on background noise reduction. Image quality is measured using PSNR and SSIM, comparing outcomes with 100% X-ray dose images. Results show the proposed algorithm achieves high-quality images from low-dose and low-contrast agents, with a maximum PSNR of 39.05 and SSIM of 0.86. The model outperforms BM3D, NLM, DnCNN, and SCUNet in both visual inspection and quantitative analysis, particularly in high-noise scenarios. This indicates the potential of AI, specifically the SCUNet model, in significantly improving XFCT imaging by mitigating the trade-off between sensitivity and radiation exposure.

Solar energy adoption worldwide has expanded exponentially due to a surge in international interest in producing clean energy and the declining cost of solar power plants and their technology. It is anticipated that by 2050, solar will have surpassed fossil fuels to become the primary source of energy. However, one of the main challenges associated with solar energy production is the instability of photovoltaic (PV) power generation because of weather changes. Short-term forecasting of the power output of photovoltaic systems is essential for efficient management of the power grid and energy markets. This paper aims to evaluate the ability of deep learning (DL) models to provide accurate forecasting of hourly global horizontal irradiance (GHI) using different sets of features, including weather and aerosol variables along with solar radiation components. The results show that the best forecast skills are achieved by the long short-term memory autoencoder (LSTM-AE) model.

A high-resolution catalog for the 2014 Ms6.5 Ludian aftershocks was constructed based on the deep learning phase-picking model (CERP) and the seismic-phase association technology (PALM). A specific training strategy, which combines the advantages of the conventional short-long window average energy ratio algorithm (STA/LTA) and AI algorithm, is employed to retrain the CERP model. The P & S phases were accurately detected and picked on continuous seismic waveforms by the retained AI model. Hypoinverse and HypoDD were utilized for precise location of 3286 events. Compared to the previous results, our new catalog exhibits superior performances in terms of location accuracy and the number of aftershock events, thereby enabling a more de-tailed depiction of the deep-seated tectonic features. According to the distribution of aftershocks, it can be inferred that, (1) the seismogenic fault of Ludian earthquake is the NW-trending Baogunao-Xiaohe Fault. (2) the Ludian aftershocks interconnected the discontinuous NW-trending Baogunao-Xiaohe Fault, and intersected with the Zhaotong-Ludian Fault. (3) It suggests that the NE-trending Zhaotong-Ludian Fault may have been intersected by the NW-trending Baogunao -Xiaohe Fault, indicating that the Baogunao-Xiaohe Fault is likely a rela-tively young Neogene fault.

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

In a super-aged society, maintaining healthy aging, preventing death, and enabling a continua-tion of economic activities are crucial. This study sought to develop a model for predicting the survival time in community-dwelling older individuals by using a deep learning method, and to identify the level of influence of various risk factors on the survival period, so that older in-dividuals can manage their own health. This study used the Korean National Health Insurance Service claims data. We observed community-dwelling older people, aged 66 years, for 11 years and developed a survival time prediction model. Of the 189,697 individuals enrolled at baseline, 180,235 (95.0%) survived from 2009 to 2019, while 9,462 (5.0%) died. Using deep learning based models (C statistics = 0.7011), we identified Charlson’s comorbidity index; the frailty index; long-term care benefit grade; disability grade; income level; a combination of diabetes mellitus, hypertension, and dyslipidemia; sex; smoking status; and alcohol consumption habit as factors impacting survival. In particular, Charlson’s comorbidity index (SHAP value: 0.0445) and frailty index (SHAP value: 0.0443) were strong predictors of survival time. Older individuals should rec-ognize modifiable risk factors that affect survival period in order to manage their own health.

The unreliable prediction of the low frequency components from inverted acoustic impedance causes uncertainty in quantitative seismic interpretation. To address this issue, we first calculate various seismic and geological attributes that contain low frequency information, such as relative geological age, interval velocity, and integrated instantaneous amplitude. Then, we develop a method to predict the low frequency content of seismic data using these attributes, their high frequency components, and recurrent neural networks. Next, we test how to predict the low frequency components using stacking velocity obtained from velocity analysis. Using all the attributes and seismic data, we propose a supervised deep learning method to predict the low frequency components of the inverted acoustic impedance. The results obtained in both synthetic and real data cases show that the proposed method can improve the prediction accuracy of the low frequency components of the inverted acoustic impedance, with the best improvement in a real data example of 57.7% compared with the impedance predicted using well log interpolation.

This paper presents ConF, a novel deep learning model designed for accurate and efficient prediction of non-coding RNA families. NcRNAs are essential functional RNA molecules involved in various cellular processes, including replication, transcription, and gene expression. Identifying ncRNA families is crucial for comprehensive RNA research, as ncRNAs within the same family often exhibit similar functionalities. Traditional experimental methods for identifying ncRNA fam-ilies are time-consuming and labor-intensive. Computational approaches relying on annotated secondary structure data face limitations in handling complex structures like pseudoknots and have restricted applicability, resulting in suboptimal prediction performance. To overcome these chal-lenges, ConF integrates mainstream techniques such as residual networks with dilated convolutions and cross multi-head attention mechanisms. By employing a combination of dual-layer convolu-tional networks and BiLSTM, ConF effectively captures intricate features embedded within RNA sequences. This feature extraction process leads to significantly improved prediction accuracy compared to existing methods. Experimental evaluations conducted on a ten-fold publicly available dataset demonstrate the superiority of ConF in terms of accuracy, sensitivity, and other perfor-mance metrics. Overall, ConF represents a promising solution for accurate and efficient ncRNA family prediction, addressing the limitations of traditional experimental and computational methods.

The modern supply chain (SC) is growing in terms of data, devices, users, and stakeholders, which introduced new security challenges and threats, especially with the reliance on centralized servers or cloud platforms. In addition, increased trust among system participants exposes the SC to a higher risk of vulnerabilities which require strong security measures. This article proposes a hybrid security framework for SC systems, BC-DRLzSC, that integrates Blockchain (BC) and Deep Reinforcement Learning (DRL) designed to operate in a zero trust (ZT) environment. In particular, we propose a decentralized BC-based approach integrated with smart contracts to manage system participant registration and authentication and to control access to system resources. BC-DRLzSC adopts a ZT architecture to reinforce SC security, which can be achieved with an advocate to verify each entity’s trustworthiness before granting or retaining access to system resources. Incorporating the ZT architecture, with BC and DRL, can potentially and significantly bolster SC system security. DRL is employed to develop a proactive attack detection model that continuously monitors the incoming traffic from authenticated nodes within the network and predicts any malicious actions. Finally, we evaluate the performance of our proposed DRL solution using the NSL-KDD dataset.

Reinforcement Learning (RL) has demonstrated considerable potential in solving challenges across various domains, notably in autonomous driving. Nevertheless, implementing RL in autonomous driving comes with its own set of difficulties, such as the overestimation phenomenon, extensive learning time, and sparse reward problems. Although solutions like Hindsight Experience Replay (HER) have been proposed to alleviate these issues, the direct utilization of RL in autonomous vehicles remains constrained due to the intricate fusion of information and the possibility of system failures during the learning process. In this paper, we present a novel RL-based autonomous driving system technology that combines Obstacle Dependent Gaussian (ODG) RL, Soft Actor-Critic (SAC), and meta-learning algorithms. Our approach addresses key issues in RL, including the overestimation phenomenon and sparse reward problems, by incorporating prior knowledge derived from the ODG algorithm. We evaluated our proposed algorithm on official F1 circuits, using high-fidelity racing simulations with complex dynamics. The results demonstrate exceptional performance, with our method achieving up to 89% faster learning speed compared to existing algorithms in these environments.

An electrocardiograph (ECG) reflects the health of the human heart and is used to help diagnose arrhythmia and myocardial infarction(MI) in clinical practice. Early diagnosis of arrhythmia helps implement preventive measures and plays a crucial role in saving a patient's life. With the increasing demand of clinicians for ECG analysis technology, intelligent detection and diagnosis of ECG signals has become a more efficient means to assist physicians in diagnosing cardiovascular diseases. This paper introduces an ECG diagnosis approach based on an ensemble deep learning combination of CNN(convolutional neural network) and SLAP(stacked-long short term memory architecture for prediction) architecture. ECG data is denoised and further divided into single heartbeats to achieve data standardization and sample diversity. Adam optimizer and BCEwithlogitsloss multi-classification loss function were used to enhance the model effect, and the system achieved the classification effect of 99.3% average accuracy, 99.0% F1-value, and 99.2% sensitivity in MIT-BIH standard database classification. It also shows good generalization ability on the Tianchi data set.

Automated spectrum analysis serves as a troubleshooting tool that helps to diagnose faults in wireless networks like difficult signal propagation conditions and coexisting wireless networks. It provides a higher monitoring coverage while requiring less expertise compared to manual spectrum analysis. In this paper, we introduce a data set that can be used to train and evaluate deep learning models, capable of detecting frames from different wireless standards as well as interference between single frames. Since manually labelling a high variety of frames in different environments is too challenging, an artificial data generation pipeline has been developed. The data set consists of 20 000 augmented signal segments, each containing a random number of different Wi-Fi and Bluetooth frames, their spectral image representations and labels that describe the position and type of frame within the spectrogram. The data set contains results of intermediate processing steps that enables the research or teaching community to create new data sets for specific requirements or to provide new interesting examination examples.

Modern hyperspectral imaging technologies generate enormous datasets that could potentially transmit a wealth of information, but such a resource presents numerous difficulties for data analysis and interpretation. Deep learning techniques undoubtedly provide a wide range of potential for solving both traditional imaging tasks and exciting new problems in the spatial-spectral domain. This is true in the primary application area of remote sensing, where hyperspectral technology originated and has made the majority of its progress, but it may be even more true in the vast array of now existing and developing application areas that make use of these imaging technologies. The current review advances on two fronts: on the one hand, it is directed at domain experts who desire an updated overview of how deep learning architectures might work in conjunction with hyperspectral acquisition techniques to address specific tasks in various application sectors. On the other hand, by providing them with a picture of how deep learning technologies are applied to hyperspectral data from (near)real-time perspective. The contributions of this review include the existence of these two points of view and the inclusion of opportunities and important problems associated with the development of future CHIME mission to be launched by European Space Agency (ESA).

This review systematically examines the progression of the You Only Look Once (YOLO) object detection algorithms from YOLOv1 to the recently unveiled YOLOv10. Employing a reverse chronological analysis, this study examines the advancements introduced by YOLO algorithms, beginning with YOLOv10 and progressing through YOLOv9, YOLOv8, and subsequent versions to explore each version's contributions to enhancing speed, accuracy, and computational efficiency in real-time object detection. The study highlights the transformative impact of YOLO across five critical application areas: automotive safety, healthcare, industrial manufacturing, surveillance, and agriculture. By detailing the incremental technological advancements that each iteration brought, this review not only chronicles the evolution of YOLO but also discusses the challenges and limitations observed in each earlier versions. The evolution signifies a path towards integrating YOLO with multimodal, context-aware, and General Artificial Intelligence (AGI) systems for the next YOLO decade, promising significant implications for future developments in AI-driven applications.

A novel concept of ion separation Anisotropic Diffusion Mobility Analyser (ADMA) with Individual Ion Counter (IIC) was shown by numerical modelling to be able to separate ions with high resolution and ultra-high sensitivity. An ADMA-IIC device has been developed and tested at sheath flow rates below 40 l/min with a number of chemicals relevant to airport security and military applications. The resolving power of the ADMA was observed to be in the range of 40 to 80. These data were close to the resolution obtained in numerical modelling predictions. It is greater than or comparable with the RP of currently available on-the-market devices for airport security and other applications. It was also confirmed that the ADMA technology enables very fast detection of analytes, at least 100 times faster than ion mobility spectrometers. It was shown that Brownian diffusion can be controlled and even overpowered by generating highly anisotropic diffusion in the ADMA device. The ultimate sensitivity of single-ion detection below the ppq range has been demonstrated.

The fractal dimension of is identified in this paper. More importantly, the undertaken research has shown how affects the Koch snowflake . The study has demonstrated the existence of negative values of (Koch snowflake), which connects to a considerable number of extremely intriguing mathematical and physical research areas. The information-theoretic impact on the Sierpiniski Gasket dimension , which corresponds to , was treated in a more fundamental way. Notably, the credibility of this current study adds to the existing kThe fractal dimension of is identified in this paper. More importantly, the undertaken research has shown how affects the Koch snowflake . The study has demonstrated the existence of negative values of (Koch snowflake), which connects to a considerable number of extremely intriguing mathematical and physical research areas. The information-theoretic impact on the Sierpiniski Gasket dimension , which corresponds to , was treated in a more fundamental way. Notably, the credibility of this current study adds to the existing knowledge for the information- theoretic fractal dimensions. On another applicative note, this paper offers some potential applications of fractal dimension to smart cities. The investigation of the threshold theorems for and in terms of the triad is part of the next study phase. Additionally, investigating the newly obtained 's corresponding arbitrary Sierpinski Gasket for the first time.applicative note, this paper offers some potential applications of fractal dimension to smart cities. The investigation of the threshold theorems for and in terms of the triad is part of the next study phase. Additionally, investigating the newly obtained 's corresponding arbitrary Sierpinski Gasket for the first time.

Amidst the challenges posed by the COVID-19 crisis, marked variations in individuals' resilience and vulnerability have emerged. This eight-month longitudinal study engaged 535 community adults (58% female, M_age = 43.97) to explore the nuanced aspects of coping and personal growth during the challenging period. Grounded in Self-Determination Theory, the research examines the influence of autonomy support from close others—manifested through active listening and providing choices—on psychological need satisfaction (i.e., autonomy, competence, and relatedness), integrative regulation of emotions; posttraumatic growth; and subjective well-being (positive affect and life satisfaction). Structural equation modeling revealed that, over time, the experience of psychological need satisfaction was intricately related to integrative regulation, posttraumatic growth, positive affect, and life satisfaction. Notably, the impact was partially mediated by autonomy support. These findings shed light on the pivotal role that autonomy supported relationships play in fostering personal growth and meaning making during life's difficult junctures. The study underscores the practical significance of purposeful support from close others and paves the way for future research endeavors.

Analysis of complex DNA mixtures is limited by the selected genetic markers characterized and assay technology. Small panels of short tandem repeats (STRs) are the current standards in most countries. Extension of STRs with hundreds of single nucleotide polymorphisms (SNPs) is now commercially available. The current set of extension SNPs focus on phenotypic and biogeographic ancestry informative SNPs. Larger panels with thousands of SNPs have been developed that can identify up to 10 contributors to forensic DNA samples. Herein, multiple sets of SNPs were selected with the focus of increasing the upper limit of detectable contributors. Larger SNP panel sets with lower minor allele frequency (MAF) alleles can detect large numbers of contributors to in silico mixtures of randomly selected profiles from the 1,000 Genomes project. These results provide a path to enable characterization of complex DNA mixtures that are currently impossible to analyse.

AbstractThe escalating impact of artificial intelligence (AI) has birthed the fascinating technology of deepfakes, capable of meticulously crafting hyper-realistic audio-visual manipulations. Within the realm of healthcare, this technology presents a double-edged sword, brimming with potential for revolutionizing various facets of care delivery while simultaneously harboring significant ethical and practical challenges. This research delves into the complex narrative surrounding AI deepfakes in healthcare, meticulously analyzing both the exciting opportunities they offer, and the inherent risks associated with their implementation.Background:Traditional healthcare practices face limitations in patient engagement, accessibility, and training efficacy. Deepfakes, with their ability to simulate real-world scenarios and interactions, emerge as a potential solution, offering personalized patient education, immersive mental health interventions, remote consultations with virtual avatars, and realistic training simulations for medical professionals.Objective:This research aims to comprehensively understand the multifaceted impact of AI deepfakes in healthcare systems. It seeks to: Identify and analyze the potential benefits of deepfakes in specific healthcare applications. Assess the ethical and practical challenges associated with deepfake implementation in healthcare settings. Propose recommendations for safe, responsible, and ethical integration of deepfakes within the healthcare system.Results/Conclusion:The research findings illuminate a landscape replete with opportunities and challenges. Deepfakes offer the potential to enhance patient education, personalize mental health interventions, facilitate remote consultations, and revolutionize medical training. However, concerns regarding misinformation, ethical breaches, data privacy, and technical limitations pose significant challenges.The conclusion emphasizes the need for a balanced approach that capitalizes on the innovative potential of deepfakes while mitigating potential harm. Collaborative efforts involving healthcare professionals, technologists, and policymakers are crucial for establishing ethical frameworks, ensuring responsible development, and harnessing the positive power of deepfakes to build a future where healthcare benefits from cutting-edge technology while prioritizing patient well-being and ethical principles.

Existing studies often lack a systematic solution for Unmanned Aerial Vehicles (UAV) inspection system, which hinders their widespread application in crack detection. To enhance its practicality, this study proposes a formal and systematic framework for UAV inspection systems, specifically designed for automatic crack detection and pavement distress evaluation. The framework integrates UAV data acquisition, deep learning based crack identification, and road damage assessment in a comprehensive and orderly manner. Firstly, the flight control strategy is presented, and road crack data is collected using the DJI Mini 2 UAV imagery, establishing a high-quality UAV crack image datasets with ground truth information. Secondly, a validation and comparison study is conducted to enhance the automatic crack detection capability and provide an appropriate deployment scheme for UAV inspection systems. This study develops automatic crack detection models based on mainstream deep learning algorithms(namely, Faster-RCNN, YOLOv5s, YOLOv7-tiny, and YOLOv8s) in urban road scenarios. The results demonstrate that the Faster-RCNN algorithm achieves the highest accuracy and is suitable for online data collection of UAV and offline inspection at work stations. Meanwhile, the YOLO models, while slightly lower in accuracy, are the fastest algorithm and are suitable for lightweight deployment of UAV with online collection and real-time inspection. Quantitative measurement methods for road cracks are presented to assess road damage, which will enhance the application of UAV inspection systems and provide factual evidence for maintenance decisions made by road authorities.

In an ever-evolving landscape of higher education, this study delves into the transformative potential of merging deep learning principles and meaningful pedagogy in language acquisition, aided by artificial intelligence (AI) technologies. Drawing from a qualitative research design, it navigates the post-pandemic educational landscape, examining shifts in language education, student perspectives, and adaptations. Through comprehensive data collection methods, including literature review, interviews, and classroom observations, the study presents insights from 30 participants from SMC. The qualitative findings reveal emerging themes related to deep learning, meaningful learning, AI integration, and language acquisition, underscoring their profound impact on teaching methods and student engagement. This research contributes to the field by shedding light on innovative approaches that elevate language acquisition in an AI-evolving educational environment. The study concludes with implications for school administrators, teachers, and students, offering recommendations for future research directions, ultimately striving to enhance language education in the modern era.

Modern power system integrates more and more new energy and use a large number of power electronic equipment. This makes it face more challenges in online optimization and real-time control. Deep reinforcement learning(DRL) has the ability of processing big data and high-dimensional features, as well as the ability of independently learning and optimizing decision-making in complex environments. In this paper, we explore DRL based online combination optimization method of grid section for large complex power system. In our method, to improve the convergence speed of the model, we propose to discretize the output action of the unit and simplify the action space. We also design a reinforcement learning loss function with strong constraints to further improve the convergence speed of the model and facilitate the algorithm to obtain the stable solution. Moreover, to avoid the local optimal solution problem caused by the discretization of the output action, we propose to use the annealing optimization algorithm to make the granularity of the unit output finer. We verify our method on IEEE 118-bus system. The experimental results show that our model has fast convergence speed and better performance, and can obtain stable solutions.

Newly build offshore wind farms (OWFs) render a collision risk between ships and installations. The paper proposed a real-time traffic monitoring method based on machine vision and deep learning technology to improve the efficiency and accuracy of the traffic monitoring system in the vicinity of offshore wind farms. Specifically, the method employs real automatic identification system (AIS) data to train a machine vision model, which is then used to identify passing ships in OWF waters. Furthermore, the system utilizes stereo vision techniques to track and locate the positions of passing ships. The method is tested in offshore water in China to validate its reliability. The results prove that the system sensitively detects the dynamic information of the passing ships, such as the distance between ships and OWFs, ship speed and course. Overall, this study provides a novel approach to enhancing the safety of OWFs, which is increasingly important as the number of such installations continues to grow. By employing advanced machine vision and deep learning techniques, the proposed monitoring system offers an effective means of improving the accuracy and efficiency of ship monitoring in challenging offshore environments.

The recent rise of deep learning (DL) and its promising capabilities in capturing non-explicit detail from large datasets have attracted substantial research attention in the field of medical image processing. DL provides ground for technology development for computer-aided diagnosis and segmentation in radiology and radiation oncology. Amongst the anatomical locations where recent auto-segmentation algorithms have been employed, the pelvis remains one of the most challenging due to large intra- and inter-patient soft-tissue variabilities. This review provides a comprehensive and clinically-oriented overview of DL-based segmentation studies for bladder, prostate, cervical and rectal cancers, highlighting the key findings, challenges and limitations.

This paper offers a novel geometric and visual approach to the renowned Four Color Map Theorem and K5 non-planarity problem while unveiling their profound connection to the "kissing number" problem in 2D. We represent planar graphs through circles and tangents, simplifying complex structures and shedding light on these classic problems. Our proofs by contradiction, rooted in the kissing number concept, reveal that both the Four Color Map Theorem and K5 non-planarity are fundamentally linked, as they pivot around the concept of coloring. This study bridges the realms of geometry and graph theory, providing fresh insights and emphasizing the significance of the kissing number problem in various fields.

Deep reinforcement learning (DRL) has achieved significant results in many Machine Learning (ML) benchmarks. In this short survey we provide an overview of DRL applied to trading on financial markets, including a short meta-analysis using Google Scholar, with an emphasis on using hierarchy for dividing the problem space as well as using model-based RL to learn a world model of the trading environment which can be used for prediction. In addition, multiple risk measures are defined and discussed, which not only provide a way of quantifying the performance of various algorithms, but they can also act as (dense) reward-shaping mechanisms for the agent. We discuss in detail the various state representations used for financial markets, which we consider critical for the success and efficiency of such DRL agents. The market in focus for this survey is the cryptocurrency market.

Oral Squamous Cell Carcinoma is one among the most common cancer and early detection is the main key to avoid deaths. Automated diagnostic tools that process the histopathological images of a patient to detect abnormal oral lesions will be very much useful for the clinicians. A deep learning framework have been designed with an intermediate layer between feature extraction layers and classification layers for classifying the histopathological images into two categories, namely normal and oral squamous cell carcinoma. The intermediate layer is constructed using the proposed Swarm Intelligence technique called Modified Gorilla Troops Optimizer. Various optimization algorithms are implemented in literature for optimal parameter identification, weights updating and feature selection in deep learning models, but this work focuses on usage of optimization algorithm as intermediate layer that transforms the extracted features into the features that are more suitable for classification. Three datasets totally comprising 2784 normal and 3632 oral squamous cell carcinoma subjects are considered in this work. Three popular CNN architectures namely InceptionV2, MobileNetV3, and EfficientNetB3 are investigated as feature extraction layers. Two fully connected Neural Network layers along with batch normalization and dropout are used as classification layers. Among the investigated feature extraction models, MobileNetV3 performs well in all the three datasets with the highest accuracy of 0.89. Usage of the proposed Modified Gorilla Troops Optimizer as an intermediate layer boosts this accuracy to 0.95.

Background: External beam radiation therapy requires a sophisticated and laborious planning procedure. To improve the efficiency and quality of the planning procedure, machine learning predictions of the dose distributions have been introduced to speed up the planning procedure and to serve as quality assurance. The most recent dose prediction models are based on deep learning U-Nets that give good approximations of the dose in 3D almost instantly. It is our purpose to train a 3D dose prediction for glioblastoma VMAT treatment and test its robustness and sensitivity for the purpose of quality assurance of automatic contouring. Methods: From a cohort of 125 glioblastoma (GBM) patients, VMAT plans were created according to a clinical protocol. The initial model was trained on a concatenated 3D U-Net. A total of 60 cases were used for training, 15 for validation and 20 for testing. The prediction model was tested for sensitivity to dose changes according to realistic contour variations. Additionally, the model was tested for robustness by exposing it to a worst-case test set containing out-of-distribution cases.Results: The initially trained prediction model had a dose score of 0.94 Gy and a mean DVH score for all structures of 1.95 Gy. In terms of sensitivity, the model was able to predict the dose changes that occurred due to the contour variations with a mean error of 1.38 Gy.Conclusions: We obtained a 3D VMAT dose prediction model for GBM with limited data, providing good sensitivity to realistic contour variations. We tested and improved the model's robustness, by targeted updating the training set, making it a useful technique for dose awareness in the contouring evaluation and quality assurance.

Near-surface humidity (Qa) is a key parameter that modulates oceanic evaporation and influences the global water cycle. Remote sensing observations act as feasible sources for long-term and large-scale Qa monitoring. However, existing satellite Qa retrieval models are subject to apparent uncertainties due to model errors and insufficient training data. Based on in situ observations collected over the China Seas over the last two decades, a deep learning approach named Ensemble Mean of Target deep neural networks (EMTnet) was proposed to improve the satellite Qa retrieval over the China Seas for the first time. The EMTnet model outperforms five representative existing models by nearly eliminating the mean bias and significantly reducing the root-mean-square error in satellite Qa retrieval. According to its target deep neural networks selection process, the EMTnet model can obtain more objective learning results when the observational data are divergent. The EMTnet model was subsequently applied to produce a 30-year monthly gridded Qa data over the China Seas. It indicates that the climbing rate of Qa over the China Seas under the background of global warming are probably underestimated by current products.

This review is a first attempt at bringing together various concepts from research on wall- and magnetically-bounded turbulent flows. Brief reviews of both fields are provided: The main similarities identified are coherent (turbulent) structures, flow generation and transport barriers. Examples are provided and discussed.

Objectives: The purpose of the study was to evaluate the effectiveness of dental caries segmentation on the panoramic radiographs taken from children in primary dentition, mixed dentition, and permanent dentition with an Artificial Intelligence (AI) models developed using the deep learning method. Methods: This study used 6075 panoramic radiographs taken from children aged between 4 and 14 to develop the AI model. The radiographs included in the study were divided into three groups as primary dentition (n: 1857), mixed dentition (n: 1406), and permanent dentition (n: 2812). U-Net model implemented with PyTorch library was used for segmentation of caries lesions. Confusion matrix was used to evaluation of model performance. Results: In the primary dentition group, the sensitivity, precision and F1 scores calculated using the confusion matrix were found to be 0.8525, 0.9128, and 0.8816, respectively. In the mixed dentition group, the sensitivity, precision, and F1 scores calculated using the confusion matrix were found as 0.7377, 0.9192, and 0.8185, respectively. In the permanent dentition group, the sensitivity, precision, and F1 scores calculated using the confusion matrix were found as 0.8271, 0.9125, and 0.8677, respectively. In the total group including primary, mixed, and permanent dentition, the sensitivity, precision and F1 score calculated using the confusion matrix were 0.8269, 0.9123 and 0.8675, respectively. Conclusion: Deep learning-based AI models are promising tools for the detection and diagnosis of caries in panoramic radiographs taken from children in different dentitions.

Accurate prostate volume estimation is crucial for effective prostate disease management. Ultrasound (US) imaging, particularly transrectal ultrasound, offers a cost-effective and rapid assessment. However, US images often suffer from artifacts and poor contrast, making prostate volume estimation challenging. This review explores recent advancements in deep learning (DL) techniques for automatic prostate segmentation in US images as a primary step for prostate volume estimation. We examine various DL architectures, including traditional U-Net modifications and innovative designs incorporating residual connections, multi-directional image data, and attention mechanisms. Additionally, we discuss pre-processing methods to enhance image quality, the integration of shape information, and strategies to improve the consistency and robustness of DL models. The effectiveness of these techniques is evaluated through metrics such as Dice Similarity Coefficient, Jaccard Index, and Hausdorff Distance. The review highlights the potential of DL in improving prostate volume estimation accuracy and reducing clinical workload, while also identifying areas for future research to enhance model performance and generalizability.

Availability and continuous operation under critical conditions are very important in electric machine drive systems. However, such systems, are suffering from several type of failures that affect the electric machine or the associated voltage source inverter. Therefore, fault diagnosis and fault tolerance are highly required. This paper presents a new robust deep learning-based approach to diagnosis multiple open-circuit fault in three phase two level voltage source inverter for induction motor drive applications. The proposed approach uses fault diagnosis variables obtained from sigmoid transformation of the motor stator currents. The open-circuit fault diagnosis variables are then introduced to a Bidirectional Long Short-Term Memory algorithm to detect the faulty switch(es). Several simulation and experimental results are presented to show the proposed fault diagnosis algorithm effectiveness and robustness.

This literature review investigates the importance of simulation and measurement techniques in the development of transmission lines and antennas, which are crucial to the reliability and efficiency of communication system. It emphasizes the necessity of exact measurement and computational approaches for simulating complicated electromagnetic process, which help to optimize designs before physical prototypes are built. The review examines a variety of research articles that offer innovative solutions to improving accuracy in antenna design, scalability and cost challenges in antenna measurements, and crosstalk measurement methods. It also explores how these methodologies affect antenna design parameters such as gain, bandwidth, and radiation patterns, emphasizing the importance of correct modeling to ensure the performance of transmission lines and antennas in modern communication system. The review serves as a valuable reference for guiding future research and technological advancements in these fields.

Cancer is one of the leading causes of death, making timely diagnosis and prognosis very important. Utilization of AI (artificial intelligence) enables providers to organize and process patient data in a way that can lead to better overall outcomes. This review paper aims to look at the varying uses of AI for diagnosis and prognosis and clinical utility. PubMed and EBSCO databases were utilized for finding publications from January 1, 2013, to December 22, 2023. Articles were collected using key search terms such as “artificial intelligence” and “machine learning.” Included in the collection were studies of the application of AI in determining cancer diagnosis and prognosis using multi-omics data, radiomics, pathomics, clinical and laboratory data. The resulting 89 studies were categorized into eight sections based on the type of data utilized and then further subdivided into two subsections focusing on cancer diagnosis and prognosis, respectively. 8 studies integrated more than one form of omics, namely genomics, transcriptomics, epigenomics, and proteomics. Incorporating AI into cancer diagnosis and prognosis alongside omics and clinical data represents a significant advancement. Given the considerable potential of AI in this domain, ongoing prospective studies are essential to enhance algorithm interpretability and to ensure safe clinical integration.

Biases in Artificial Intelligence (AI) or Machine Learning (ML) systems due to skewed datasets problematise the application of prediction models in practice. Representation bias is a prevalent form of bias found in the majority of datasets. This bias arises when training data inadequately represents certain segments of the data space, resulting in poor generalisation of prediction models. Despite AI practitioners employing various methods to mitigate representation bias, their effectiveness is often limited due to a lack of thorough domain knowledge. To address this limitation, this paper introduces human-in-the-loop interaction approaches for representation debiasing of generated data involving domain experts. Our work advocates for a controlled data generation process involving domain experts to effectively mitigate the effects of representation bias. We argue that domain experts can leverage their expertise to assess how representation bias affects prediction models. Moreover, our interaction approaches can facilitate domain experts in steering data augmentation algorithms to produce debiased augmented data and validate or refine the generated samples to reduce representation bias. We also discuss how these approaches can be leveraged for designing and developing user-centred AI systems to mitigate the impact of representation bias through effective collaboration between domain experts and AI.

The existence of palindrome numbers of arbitrary length greater than 2 that are divisible by the prime number 37 is proven in this paper. The method to construct such a palindrome is also described. It turns out that a palindrome number divisible by 37 is also divisible by 3 and, consequently, divisible by 111.

Models of quantum measurements are presented, including observers subject to the laws of quantum mechanics. Observers perform multiple measurements in an attempt to disprove the collapse hypothesis. It is shown that under reasonable assumptions the effort cannot succeed. Under a unitary evolution the end state is a correlation between the result of the first measurement and the result(s) of the others, consistent with the observer's collapse hypothesis. The observer may conclude that the laws of nature include a non-unitary collapse mechanism, even if one does not actually exist. Discard of information is the crucial factor which distinguishes entanglement from measurement.

Aiming to improve medical diagnosis and treatment, artificial intelligence (AI) has emerged as a transformational force in the healthcare industry. In this article, we examine how AI is increasingly being used to improve healthcare, with an emphasis on how it is changing medical diagnosis and treatment. We explore the opportunities, threats, and ethical concerns of incorporating AI into healthcare practice. In addition, we feature important AI applications in radiology, pathology, cardiology, and cancer. AI has great potential to improve patient outcomes, diagnostic accuracy, and the ability to provide individualized treatment plans in the future if it is used and refined with care.

Background: India leads in road traffic accident (RTA) deaths, according to the 2018 World Road Statistics. Most unidentified patients exhibit poor Glasgow Coma Scale (GCS) scores ,often less than eight , heightened trauma severity, and suboptimal outcomes despite standard treatment. Our study concentrates on individuals involved in hit-and-run RTAs or found unconscious and brought to the emergency department and their final outcome.Case Presentation: We are presenting a case series featuring five patients admitted to our hospital for treatment. At the time of admission, all these patients' identities were unknown.We did not face any legal challenges in managing the unidentified patients as we followed preestablished protocols. We report a case series of five male patients who had been admitted after road traffic accidents. All of them regained consciousness after conservative management. These complex cases frequently led to extended hospital stays, underscoring the intricacies of providing care to individuals with uncertain medical histories. All of the patients were treated and successfully discharged. Conclusion: Addressing challenges with unidentified adult patients requires proactive measures like staff training and improved resources. In a developing nation, prioritizing public awareness on road safety, prehospital trauma care, and enhancing healthcare delivery, especially in hospitals, is essential for optimal outcomes.

Climate change related issues, such as yield decline, quality losses, accelerated phenology, extreme abiotic stress, pose growers new challenges in olive growing areas. Main cultural solutions that could alleviate stress and improve long-term sustainability of modern olive orchards are here briefly reviewed. Selecting varieties that are more resistant to drought or high temperatures would be the optimal solution to mitigate the effects of climate change, but the available scientific information is relatively scarce. Sustainability of irrigation implies that the less water is used, the better. Best results in terms of saving water and uniform application are obtained using micro-irrigation methods. Water can also be saved by not fully satisfying the tree water needs and different deficit irrigation strategies have been developed and tested for olive orchards. The use of green covers and the application of organic mulches and shredded pruning materials should be encouraged as these practices tend to stock carbon, increase organic matter content and water holding capacity of the soil. Olive orchards are efficient CO2 sinks as they can store considerable amounts of carbon in their organs and permanent structures. Using environmental friendly practices improves the ecosystem carbon budget and contributes to mitigate climate change.

For a number of reasons, a curative treatment for most chronic diseases is still unrealized [2–4] and the incidence of many chronic diseases is rapidly increasing [5–9]. A new model is offered as a solution; that being the individualized diagnosis of homeostasis, leading to the correction of epimutations. Individuals with chronic diseases are increasingly being defined by their epigenetic signatures [10,11]. Modern innovations in toxicogenomic studies are also becoming more accurate in their ability to identify the unique epigenetic signature of each toxin [12–14]. Hormesis studies (over 5,000) [15] suggest a universal principle, that a small dose is always a stimulant [16–18].These three facts present an opportunity; a method to diagnose and reverse chronic disease tendencies. This new model requires a paradigm shift in our understanding of disease origins: that dysfunctions in homeostasis [19,20] are the primary and deepest level of chronic disease causation. This is the level where the diagnosis needs to be made and where the corrections need to take place [21].

The lung epithelium regulates gas exchange and is the first line of defense against airborne toxicants and microbial infections. Disruption of the integrity of lung epithelium results in altered permeability and severely impacts normal lung functions. To develop biomarkers of potential harm (BoPH) for assessing adverse health effects of cigarette smoking, we have evaluated lung barrier function. In a single-center, ambulatory, clinical study we measured lung permeability, as the half-life (T1/2) of inhaled 99mTC-DTPA, in 17 subjects consisting of 6 Smokers (SMK), 5 Moist Snuff Consumers (MSC), and 6 Non-Tobacco Consumers (NTC) at three weekly test visits. Smokers, relative to MSC and NTC, exhibited significantly faster clearance of the inhaled probe (shorter T1/2), indicating increased lung permeability. NTC and MSC had comparable clearance times of the inhaled probe (longer T1/2). Least squares regression modeling showed that the variability of the test was minimal and was not significant. Prediction profiling showed that the repeatability of the lung permeability test was robust and was able to differentiate the tobacco product use groups in this study. Thus, altered lung barrier function may serve as a BoPH for assessing the effects of tobacco use.

Active magnetic bearings have higher efficiency than other bearings because there is no physical contact. However, this benefit is mitigated by the addition of electrical power consumption. It is therefore important for magnetic bearings to have efficient power electronics. Gallium nitride-based transistors are a relatively new form of transistor which have shown to be more efficient than MOSFETs. There is an insufficient body of literature in the area of application of these transistors for magnetic levitation. This work presents a simple 1 degree-of-freedom voltage controlled levitation experiment in which levitation is achieved with both a gallium nitride transistor and a MOSFET.
Voltage losses and current consumption are measured when using each transistor during levitation. In particular, transients during open-to-closed and closed-to-open states are measured for PWM pulsing. It is found that the
gallium nitride transistor is superior in both switching time and efficiency in situ for magnetic levitation.

Long Covid has become a blight, its economic consequences overwhelming. But Long Covid (LC) may represent persistent Covid-19 in those with preexisting Candida overgrowth (CO). The features shared by both are striking. LC may be a growing subset of CO. The altered tryptophan metabolism encountered in LC is driven by IFN-γ in reaction to CO. Females are robust producers of IFN-γ, yet estrogen promotes CO.The consequent decline in serotonin and melatonin triggers the mood swings and sleeplessness respectively in LC. The low serotonin, the primary messenger in the gut brain axis, creates autonomic dysfunction. The CO induced gut dysbiosis and leaky gut initiate an autoimmune path. TNFα seen in both LC and this opportunistic yeast is at the center of the cytokine triad that leads to neurodegeneration. The Western diet, high in carbohydrates, alcohol, and glutamate, is exploited by this commensal turned parasite. Residual SARS CoV2 and Candida generate abundant ROS, inducing mitochondrial dysfunction. Alcohol tastes different for many with LC, because acetaldehyde requires functioning hepatic mitochondria. This article delves into the complex physiology and biochemistry that drive the symptoms of this conspicuous connection. Recent research has revealed innovative approaches that might address this global scourge, including D-mannose for the immune dysfunction and butyrate for the gut dysbiosis created by and seen in both LC and intestinal Candidiasis.