Search

Parkinson's disease (PD) is a neurodegenerative disease that affects the neural, behavioral, and physiological systems of the brain. This disease is also known as tremor. The common symptoms of this disease are a slowness of movement known as 'bradykinesia', loss of automatic movements, speech/writing changes, and difficulty with walking at early stages. To solve these issues and to enhance the diagnostic process of PD, machine learning (ML) algorithms have been implemented for the categorization of subjective disease and healthy controls (HC) with comparable medical appearances. To provide a far-reaching outline of data modalities and artificial intelligence techniques that have been utilized in the analysis and diagnosis of PD, we conducted a literature analysis of research papers published up until 2022. A total of 112 research papers were included in this study, with an examination of their targets, data sources and different types of datasets, ML algorithms, and associated outcomes. The results showed that ML approaches and new biomarkers have a lot of promise for being used in clinical decision-making, resulting in a more systematic and informed diagnosis of PD. In this study, some major challenges were addressed along with a future recommendation. [ABSTRACT FROM AUTHOR]

In this paper, a microscopic oil displacement visualization experiment based on the glass etching model to simulate the tight oil reservoir of underground rocks is carried out. At present, water flooding technology is widely used in the development of oil and gas fields, and the remaining oil content is still very high after water flooding. It is the key to improving oil recovery to identify and study the remaining oil form distribution after water flooding. The experiment result shows there are five types of residual oil after water flooding: columnar residual oil, membranous residual oil, oil droplet residual oil, blind terminal residual oil and cluster residual oil. A convolution neural network is suitable for complex image characteristics with good robustness. In recent years, it has made a breakthrough in a set of small and efficient neural networks with SqueezeNet, Google Inception and the flattened network method put forward. In order to solve the problems of low automation, low efficiency and high error rate in the traditional remaining oil form recognition algorithm after water flooding in tight oil reservoirs, an image recognition algorithm based on the MobileNets convolutional neural network model was proposed in this paper to achieve accurate recognition of the remaining oil form. Based on traditional image processing methods which, respectively, extracted the whole picture of the different types of remaining oil in the image block, it uses the MobileNets network structure to classify different types of image block and realizes the layered depth convolution neural network system. The experiment result shows that the model can accurately identify the remaining oil forms, and the overall recognition accuracy is up to 83.8% after the convergence of the network model, which infinitely identifies the remaining oil forms in the morphological library, proving the strong generalization and robustness of the model. [ABSTRACT FROM AUTHOR]

With the rise of mobile social networks, an increasing number of consumers are shopping through Internet platforms. The information asymmetry between consumers and producers has caused producers to misjudge the positioning of agricultural products in the market and damaged the interests of consumers. This imbalance between supply and demand is detrimental to the development of the agricultural market. Sentiment tendency analysis of after-sale reviews of agricultural products on the Internet could effectively help consumers evaluate the quality of agricultural products and help enterprises optimize and upgrade their products. Targeting problems such as non-standard expressions and sparse features in agricultural product reviews, this paper proposes a sentiment analysis algorithm based on an improved Bidirectional Encoder Representations from Transformers (BERT) model with symmetrical structure to obtain sentence-level feature vectors of agricultural product evaluations containing complete semantic information. Specifically, we propose a recognition method based on speech rules to identify the emotional tendencies of consumers when evaluating agricultural products and extract consumer demand for agricultural product attributes from online reviews. Our results showed that the F1 value of the trained model reached 89.86% on the test set, which is an increase of 7.05 compared with that of the original BERT model. The agricultural evaluation classification algorithm proposed in this paper could efficiently determine the emotion expressed by the text, which helps to further analyze network evaluation data, extract effective information, and realize the visualization of emotion. [ABSTRACT FROM AUTHOR]

Simple Summary: Biodiversity monitoring is one of the primary means of ecological research. With the development of convolutional neural networks (CNNs) in the field of instance segmentation, CNNs are also used for species recognition. Almost all species recognition models apply pixel-based instance segmentation to recognize animal species. However, pixel-based instance segmentation models require a large number of annotations and labels, which makes them time-consuming and unsuitable for small datasets. Therefore, in this paper, we propose a contour-based wild animal instance segmentation model that can reach a balance between accuracy and real-time performance. Camera traps are widely used in wildlife research, conservation, and management, and abundant images are acquired every day. Efficient real-time instance segmentation networks can help ecologists label and study wild animals. However, existing deep convolutional neural networks require a large number of annotations and labels, which makes them unsuitable for small datasets. In this paper, we propose a two-stage method for the instance segmentation of wildlife, including object detection and contour approximation. In the object detection stage, we use FSOD (few-shot object detection) to recognize animal species and detect the initial bounding boxes of animals. In the case of a small wildlife dataset, this method may improve the generalization ability of the wild animal species recognition and even identify new species that only have a small number of training samples. In the second stage, deep snake is used as the contour approximation model for the instance segmentation of wild mammals. The initial bounding boxes generated in the first stage are input to deep snake to approximate the contours of the animal bodies. The model fuses the advantages of detecting new species and real-time instance segmentation. The experimental results show that the proposed method is more suitable for wild animal instance segmentation, in comparison with pixel-wise segmentation methods. In particular, the proposed method shows a better performance when facing challenging images. [ABSTRACT FROM AUTHOR]

Simple Summary: In this paper, we present an artificial Intelligence (AI) based automatic detection of mitoses in Uterine Leiomyosarcoma. Mitotic count is one of the important biomarkers in the field of histopathology. A dataset is also made available to research community which consists of images having moitotically active region. These regions are labeled by a trained AI expert in coordination with a senior histopathologist. Preliminary results show AI as promising solution for detection of mitotically active regions mitotic region in Uterine leiomyosarcoma cases and can be used as a second opinion system. Uterine leiomyosarcoma (ULMS) is the most common sarcoma of the uterus, It is aggressive and has poor prognosis. Its diagnosis is sometimes challenging owing to its resemblance by benign smooth muscle neoplasms of the uterus. Pathologists diagnose and grade leiomyosarcoma based on three standard criteria (i.e., mitosis count, necrosis, and nuclear atypia). Among these, mitosis count is the most important and challenging biomarker. In general, pathologists use the traditional manual counting method for the detection and counting of mitosis. This procedure is very time-consuming, tedious, and subjective. To overcome these challenges, artificial intelligence (AI) based methods have been developed that automatically detect mitosis. In this paper, we propose a new ULMS dataset and an AI-based approach for mitosis detection. We collected our dataset from a local medical facility in collaboration with highly trained pathologists. Preprocessing and annotations are performed using standard procedures, and a deep learning-based method is applied to provide baseline accuracies. The experimental results showed 0.7462 precision, 0.8981 recall, and 0.8151 F1-score. For research and development, the code and dataset have been made publicly available. [ABSTRACT FROM AUTHOR]

Despite advancements in smart grid (SG) technology, effective load forecasting utilizing big data or large-scale datasets remains a complex task for energy management, planning, and control. The Saudi SGs, in alignment with the Saudi Vision 2030, have been envisioned as future electrical grids with a bidirectional flow of power and data. To that end, data analysis and predictive models can enhance Saudi SG planning and control via artificial intelligence (AI). Recently, many AI methods including deep learning (DL) algorithms for SG applications have been published in the literature and have shown superior time series predictions compared with conventional prediction models. Current load-prediction research for the Saudi grid focuses on identifying anticipated loads and consumptions, on utilizing limited historical data and the behavior of the load's consumption, and on conducting shallow forecasting models. However, little scientific proof on complex DL models or real-life application has been conducted by researchers; few articles have studied sophisticated large-scale prediction models for Saudi grids. This paper proposes hybrid DL methods to enhance the outcomes in Saudi SG load forecasting, to improve problem-relevant features, and to accurately predict complicated power consumption, with the goal of developing reliable forecasting models and of obtaining knowledge of the relationships between the various features and attributes in the Saudi SGs. The model in this paper utilizes a real dataset from the Jeddah and Medinah grids in Saudi Arabia for a full year, 2021, with a one-hour time resolution. A benchmark strategy using different conventional DL methods including artificial neural network, recurrent neural network (RNN), conventional neural networks (CNN), long short-term memory (LSTM), gated recurrent unit (GRU), and different real datasets is used to verify the proposed models. The prediction results demonstrate the effectiveness of the proposed hybrid DL models, with CNN–GRU and CNN–RNN with NRMSE obtaining 1.4673% and 1.222% improvements, respectively, in load forecasting accuracy. [ABSTRACT FROM AUTHOR]

In recent years, deep convolutional neural network (CNN)-based image enhancement has shown outstanding performance. However, due to the problems of uneven illumination and low contrast existing in endoscopic images, the implementation of medical endoscopic image enhancement using CNN is still an exploratory and challenging task. An endoscopic image enhancement network (EIEN) based on the Retinex theory is proposed in this paper to solve these problems. The structure consists of three parts: decomposition network, illumination correction network, and reflection component enhancement algorithm. First, the decomposition network model of pre-trained Retinex-Net is retrained on the endoscopic image dataset, and then the images are decomposed into illumination and reflection components by this decomposition network. Second, the illumination components are corrected by the proposed self-attention guided multi-scale pyramid structure. The pyramid structure is used to capture the multi-scale information of the image. The self-attention mechanism is based on the imaging nature of the endoscopic image, and the inverse image of the illumination component is fused with the features of the green and blue channels of the image to be enhanced to generate a weight map that reassigns weights to the spatial dimension of the feature map, to avoid the loss of details in the process of multi-scale feature fusion and image reconstruction by the network. The reflection component enhancement is achieved by sub-channel stretching and weighted fusion, which is used to enhance the vascular information and image contrast. Finally, the enhanced illumination and reflection components are multiplied to obtain the reconstructed image. We compare the results of the proposed method with six other methods on a test set. The experimental results show that EIEN enhances the brightness and contrast of endoscopic images and highlights vascular and tissue information. At the same time, the method in this paper obtained the best results in terms of visual perception and objective evaluation. [ABSTRACT FROM AUTHOR]

The goal of reaching the peak of carbon in the construction industry is urgent. However, the research on the feasibility of realizing this goal and the implementation of relevant policies in China is relatively superficial. In view of the historical data of energy consumption and building CO2 emission from 1995 to 2019, this paper establishes a BP neural network model for predicting building CO2 emissions. Moreover, the influencing factors, such as population, GDP, and total construction output, are introduced as the parameters in the model. Through the scenario analysis method explores the practical path to accomplish the peak of building CO2 emissions. When using traditional prediction methods to predict building carbon emissions, the long prediction cycle will increase the possibility of significant errors. Therefore, this paper constructs the calculation model of building carbon emission and forecasts the future carbon emission value through the BP neural network to avoid the error caused by the nonlinear relationship between influencing factors and predicted value. It will effectively predict the feasibility of the carbon peak and the carbon-neutral target set by government, and provide a useful predictive tool for adjusting the new energy structure and formulating related emission reduction policies. [ABSTRACT FROM AUTHOR]

Unlimited access to information and data sharing wherever and at any time for anyone and anything is a fundamental component of fifth-generation (5G) wireless communication and beyond. Therefore, it has become inevitable to exploit the super-high frequency (SHF) and millimeter-wave (mmWave) frequency bands for future wireless networks due to their attractive ability to provide extremely high data rates because of the availability of vast amounts of bandwidth. However, due to the characteristics and sensitivity of wireless signals to the propagation effects in these frequency bands, more accurate path loss prediction models are vital for the planning, evaluating, and optimizing future wireless communication networks. This paper presents and evaluates the performance of several well-known machine learning methods, including multiple linear regression (MLR), polynomial regression (PR), support vector regression (SVR), as well as the methods using decision trees (DT), random forests (RF), K-nearest neighbors (KNN), artificial neural networks (ANN), and artificial recurrent neural networks (RNN). RNNs are mainly based on long short-term memory (LSTM). The models are compared based on measurement data to provide the best fitting machine-learning-based path loss prediction models. The main results obtained from this study show that the best root-mean-square error (RMSE) performance is given by the ANN and RNN-LSTM methods, while the worst is for the MLR method. All the RMSE values for the given learning techniques are in the range of 0.0216 to 2.9008 dB. Furthermore, this work shows that the models (except for the MLR model) perform excellently in fitting actual measurement data for wireless communications in enclosed indoor environments since they provide R-squared and correlation values higher than 0.91 and 0.96 , respectively. The paper shows that these learning methods could be used as accurate and stable models for predicting path loss in the mmWave frequency regime. [ABSTRACT FROM AUTHOR]

This paper presents datasets utilised for synthetic near-infrared (NIR) image generation and bounding-box level fruit detection systems. A high-quality dataset is one of the essential building blocks that can lead to success in model generalisation and the deployment of data-driven deep neural networks. In particular, synthetic data generation tasks often require more training samples than other supervised approaches. Therefore, in this paper, we share the NIR+RGB datasets that are re-processed from two public datasets (i.e., nirscene and SEN12MS), expanded our previous study, deepFruits, and our novel NIR+RGB sweet pepper (capsicum) dataset. We oversampled from the original nirscene dataset at 10, 100, 200, and 400 ratios that yielded a total of 127 k pairs of images. From the SEN12MS satellite multispectral dataset, we selected Summer (45 k) and All seasons (180k) subsets and applied a simple yet important conversion: digital number (DN) to pixel value conversion followed by image standardisation. Our sweet pepper dataset consists of 1615 pairs of NIR+RGB images that were collected from commercial farms. We quantitatively and qualitatively demonstrate that these NIR+RGB datasets are sufficient to be used for synthetic NIR image generation. We achieved Frechet inception distances (FIDs) of 11.36, 26.53, and 40.15 for nirscene1, SEN12MS, and sweet pepper datasets, respectively. In addition, we release manual annotations of 11 fruit bounding boxes that can be exported in various formats using cloud service. Four newly added fruits (blueberry, cherry, kiwi and wheat) compound 11 novel bounding box datasets on top of our previous work presented in the deepFruits project (apple, avocado, capsicum, mango, orange, rockmelon and strawberry). The total number of bounding box instances of the dataset is 162 k and it is ready to use from a cloud service. For the evaluation of the dataset, Yolov5 single stage detector is exploited and reported impressive mean-average-precision, mAP [ 0.5 : 0.95 ] results of min:0.49, max:0.812. We hope these datasets are useful and serve as a baseline for future studies. [ABSTRACT FROM AUTHOR]

Lately, adequate protection strategies need to be developed when Microgrids (MGs) are connected to smart grids to prevent undesirable tripping. Conventional relay settings need to be adapted to changes in Distributed Generator (DG) penetrations or grid reconfigurations, which is a complicated task that can be solved efficiently using Artificial Intelligence (AI)-based protection. This paper compares and validates the difference between conventional protection (overcurrent and differential) strategies and a new strategy based on Artificial Neural Networks (ANNs), which have been shown as adequate protection, especially with reconfigurable smart grids. In addition, the limitations of the conventional protections are discussed. The AI protection is employed through the communication between all Protective Devices (PDs) in the grid, and a backup strategy that employs the communication among the PDs in the same line. This paper goes a step further to validate the protection strategies based on simulations using the MATLABTM platform and experimental results using a scaled grid. The AI-based protection method gave the best solution as it can be adapted for different grids with high accuracy and faster response than conventional protection, and without the need to change the protection settings. The scaled grid was designed for the smart grid to advocate the behavior of the protection strategies experimentally for both conventional and AI-based protections. [ABSTRACT FROM AUTHOR]

Conservation through voltage reduction (CVR) aims to reduce the peak load and energy savings in electric power systems and is being deployed at various utilities. The effectiveness of the CVR program depends on the load characteristics, i.e., the sensitivity of the load to voltage variation, and voltage regulation device settings. In the current literature, there is a lack of discussion on the CVR factor calculation using different measurements, and there is a lack of method for active power loss estimation using substation measurements. This paper provides insights into CVR factor calculation based on the measurements captured at the substation and those at the load location. This paper also proposes a new method based on curve fitting and artificial neural network to estimate the active power loss using input active power, input reactive power and input voltage at the substation. The CVR comparison study conducted in this paper helps in understanding the factors affecting CVR factor and may provide guidance in CVR implementation and impact assessment. The proposed loss estimation method sheds light on the impacts of CVR in terms of load and loss reduction. The results based on simulation studies using the IEEE 13-bus and 34-bus systems are reported in this paper, noting that the proposed methods are applicable to larger systems, as long as the required measurements at the substation are available. Future research includes testing and refining the methods using large IEEE and utility distribution systems and considering the stochastic nature of the CVR factor with changing load and voltage regulator control schemes. [ABSTRACT FROM AUTHOR]

Siamese network trackers based on pre-trained depth features have achieved good performance in recent years. However, the pre-trained depth features are trained in advance on large-scale datasets, which contain feature information of a large number of objects. There may be a pair of interference and redundant information for a single tracking target. To learn a more accurate target feature information, this paper proposes a lightweight target-aware attention learning network to learn the most effective channel features of the target online. The lightweight network uses a designed attention learning loss function to learn a series of channel features with weights online with no complex parameters. Compared with the pre-trained features, the channel features with weights can represent the target more accurately. Finally, the lightweight target-aware attention learning network is unified into a Siamese tracking network framework to implement target tracking effectively. Experiments on several datasets demonstrate that the tracker proposed in this paper has good performance. [ABSTRACT FROM AUTHOR]

This document is a correction notice for a paper titled "An Investigation on Spiking Neural Networks Based on the Izhikevich Neuronal Model: Spiking Processing and Hardware Approach." The correction addresses an error in the affiliation of one of the authors, Ehsan Nazemi. The updated affiliation should include the Institute of Fundamental and Applied Sciences, Duy Tan University, Ho Chi Minh City, Vietnam. Additionally, there was an error in the Introduction section where a paragraph with unexplained references was mistakenly copied from one of the author's theses. This paragraph has been removed, and the order of references has been adjusted accordingly. The authors assure that these corrections do not affect the scientific conclusions of the paper. [Extracted from the article]

Inspired by classical graph neural networks, we discuss a novel quantum graph neural network (QGNN) model to predict the chemical and physical properties of molecules and materials. QGNNs were investigated to predict the energy gap between the highest occupied and lowest unoccupied molecular orbitals of small organic molecules. The models utilize the equivariantly diagonalizable unitary quantum graph circuit (EDU-QGC) framework to allow discrete link features and minimize quantum circuit embedding. The results show QGNNs can achieve lower test loss compared to classical models if a similar number of trainable variables are used, and converge faster in training. This paper also provides a review of classical graph neural network models for materials research and various QGNNs. [ABSTRACT FROM AUTHOR]

Hand gesture recognition (HGR) is a crucial area of research that enhances communication by overcoming language barriers and facilitating human-computer interaction. Although previous works in HGR have employed deep neural networks, they fail to encode the orientation and position of the hand in the image. To address this issue, this paper proposes HGR-ViT, a Vision Transformer (ViT) model with an attention mechanism for hand gesture recognition. Given a hand gesture image, it is first split into fixed size patches. Positional embedding is added to these embeddings to form learnable vectors that capture the positional information of the hand patches. The resulting sequence of vectors are then served as the input to a standard Transformer encoder to obtain the hand gesture representation. A multilayer perceptron head is added to the output of the encoder to classify the hand gesture to the correct class. The proposed HGR-ViT obtains an accuracy of 99.98%, 99.36% and 99.85% for the American Sign Language (ASL) dataset, ASL with Digits dataset, and National University of Singapore (NUS) hand gesture dataset, respectively. [ABSTRACT FROM AUTHOR]

Identifying statistical trends for a wide range of practical power system applications, including sustainable energy forecasting, demand response, energy decomposition, and state estimation, is regarded as a significant task given the rapid expansion of power system measurements in terms of scale and complexity. In the last decade, deep learning has arisen as a new kind of artificial intelligence technique that expresses power grid datasets via an extensive hypothesis space, resulting in an outstanding performance in comparison with the majority of recent algorithms. This paper investigates the theoretical benefits of deep data representation in the study of power networks. We examine deep learning techniques described and deployed in a variety of supervised, unsupervised, and reinforcement learning scenarios. We explore different scenarios in which discriminative deep frameworks, such as Stacked Autoencoder networks and Convolution Networks, and generative deep architectures, including Deep Belief Networks and Variational Autoencoders, solve problems. This study's empirical and theoretical evaluation of deep learning encourages long-term studies on improving this modern category of methods to accomplish substantial advancements in the future of electrical systems. [ABSTRACT FROM AUTHOR]

Physics-informed neural network (PINN) architectures are recent developments that can act as surrogate models for fluid dynamics in order to reduce computational costs. PINNs make use of deep neural networks, where the Navier-Stokes equation and freestream boundary conditions are used as losses of the neural network; hence, no simulation or experimental data in the training of the PINN is required. Here, the formulation of PINN for fluid dynamics is demonstrated and critical factors influencing the PINN design are discussed through a low Reynolds number flow over a cylinder. The PINN architecture showed the greatest improvement to the accuracy of results from the increase in the number of layers, followed by the increase in the number of points in the point cloud. Increasing the number of nodes per hidden layer brings about the smallest improvement in performance. In general, PINN is much more efficient than computational fluid dynamics (CFD) in terms of memory resource usage, with PINN requiring 5–10 times less memory. The tradeoff for this advantage is that it requires longer computational time, with PINN requiring approximately 3 times more than that of CFD. In essence, this paper demonstrates the direct formulation of PINN without the need for data, alongside hyperparameter design and comparison of computational requirements. [ABSTRACT FROM AUTHOR]

Network pruning has been widely used in model compression techniques, and offers a promising prospect for deploying models on devices with limited resources. Nevertheless, existing pruning methods merely consider the importance of feature maps and filters in the spatial domain. In this paper, we re-consider the model characteristics and propose a novel filter pruning method that corresponds to the human visual system, termed Low Frequency Preference (LFP), in the frequency domain. It is essentially an indicator that determines the importance of a filter based on the relative low-frequency components across channels, which can be intuitively understood as a measurement of the "low-frequency components". When the feature map of a filter has more low-frequency components than the other feature maps, it is considered more crucial and should be preserved during the pruning process. We conduct the proposed LFP on three different scales of datasets through several models and achieve superior performances. The experimental results obtained on the CIFAR datasets and ImageNet dataset demonstrate that our method significantly reduces the model size and FLOPs. The results on the UC Merced dataset show that our approach is also significant for remote sensing image classification. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) have been widely utilized in automatic visual navigation and recognition on modern unmanned aerial vehicles (UAVs), achieving state-of-the-art performances. However, DNN-based visual recognition systems on UAVs show serious vulnerability to adversarial camouflage patterns on targets and well-designed imperceptible perturbations in real-time images, which poses a threat to safety-related applications. Considering a scenario in which a UAV is suffering from adversarial attack, in this paper, we investigate and construct two ensemble approaches with CNN and transformer for both proactive (i.e., generate robust models) and reactive (i.e., adversarial detection) adversarial defense. They are expected to be secure under attack and adapt to the resource-limited environment on UAVs. Specifically, the probability distributions of output layers from base DNN models in the ensemble are combined in the proactive defense, which mainly exploits the weak adversarial transferability between the CNN and transformer. For the reactive defense, we integrate the scoring functions of several adversarial detectors with the hidden features and average the output confidence scores from ResNets and ViTs as a second integration. To verify their effectiveness in the recognition task of remote sensing images, we conduct experiments on both optical and synthetic aperture radar (SAR) datasets. We find that the ensemble model in proactive defense performs as well as three popular counterparts, and both of the ensemble approaches can achieve much more satisfactory results than a single base model/detector, which effectively alleviates adversarial vulnerability without extra re-training. In addition, we establish a one-stop platform for conveniently evaluating adversarial robustness and performing defense on recognition models called AREP-RSIs, which is beneficial for the future research of the remote sensing field. [ABSTRACT FROM AUTHOR]

Simple Summary: Breast cancer is one of the leading causes of cancer death among women. Developing machine learning-based diagnosis models receives great attention from researchers and scientists using histopathology images. Deep learning (DL) algorithms automatically extract features from raw data through convolutional operations. The generalization of the DL models' results relies on large datasets, although they eliminate the expert knowledge in the feature extraction stage. This work aimed to compare the performance of the features extracted via deep learning and a knowledge-based approach in breast cancer detection from histopathology images. Cancer develops when a single or a group of cells grows and spreads uncontrollably. Histopathology images are used in cancer diagnosis since they show tissue and cell structures under a microscope. Knowledge-based and deep learning-based computer-aided detection is an ongoing research field in cancer diagnosis using histopathology images. Feature extraction is vital in both approaches since the feature set is fed to a classifier and determines the performance. This paper evaluates three feature extraction methods and their performance in breast cancer diagnosis. Features are extracted by (1) a Convolutional Neural Network, (2) a transfer learning architecture VGG16, and (3) a knowledge-based system. The feature sets are tested by seven classifiers, including Neural Network (64 units), Random Forest, Multilayer Perceptron, Decision Tree, Support Vector Machines, K-Nearest Neighbors, and Narrow Neural Network (10 units) on the BreakHis 400× image dataset. The CNN achieved up to 85% for the Neural Network and Random Forest, the VGG16 method achieved up to 86% for the Neural Network, and the knowledge-based features achieved up to 98% for Neural Network, Random Forest, Multilayer Perceptron classifiers. [ABSTRACT FROM AUTHOR]

Traffic breakdown is the transition of traffic flow from an uncongested state to a congested state. During peak hours, when a large number of on-ramp vehicles merge with mainline traffic, it can cause a significant drop in speed and subsequently lead to traffic breakdown. Therefore, ramp meters have been used to regulate the traffic flow from the ramps to maintain stable traffic flow on the mainline. However, existing traffic breakdown prediction models do not consider on-ramp traffic flow. In this paper, an algorithm based on artificial neural networks (ANN) is developed to predict the probability of a traffic breakdown occurrence on freeway segments with merging traffic, considering temporal and spatial correlations of the traffic conditions from the location of interest, the ramp, and the upstream and downstream segments. The feature selection analysis reveals that the traffic condition of the ramps has a significant impact on the occurrence of traffic breakdown on the mainline. Therefore, the traffic flow characteristics of the on-ramp, along with other significant features, are used to build the ANN model. The proposed ANN algorithm can predict the occurrence of traffic breakdowns on freeway segments with merging traffic with an accuracy of 96%. Furthermore, the model has been deployed at a different location, which yields a predictive accuracy of 97%. In traffic operations, the high probability of the occurrence of a traffic breakdown can be used as a trigger for the ramp meters. [ABSTRACT FROM AUTHOR]

The performance of optimization algorithms, and consequently of AI/machine learning solutions, is strongly influenced by the setting of their hyperparameters. Over the last decades, a rich literature has developed proposing methods to automatically determine the parameter setting for a problem of interest, aiming at either robust or instance-specific settings. Robust setting optimization is already a mature area of research, while instance-level setting is still in its infancy, with contributions mainly dealing with algorithm selection. The work reported in this paper belongs to the latter category, exploiting the learning and generalization capabilities of artificial neural networks to adapt a general setting generated by state-of-the-art automatic configurators. Our approach differs significantly from analogous ones in the literature, both because we rely on neural systems to suggest the settings, and because we propose a novel learning scheme in which different outputs are proposed for each input, in order to support generalization from examples. The approach was validated on two different algorithms that optimized instances of two different problems. We used an algorithm that is very sensitive to parameter settings, applied to generalized assignment problem instances, and a robust tabu search that is purportedly little sensitive to its settings, applied to quadratic assignment problem instances. The computational results in both cases attest to the effectiveness of the approach, especially when applied to instances that are structurally very different from those previously encountered. [ABSTRACT FROM AUTHOR]

The generation of random numbers is crucial for practical implementations of cryptographic algorithms. In this sense, hardware security modules (HSMs) include true random number generators (TRNGs) implemented in hardware to achieve good random number generation. In the case of cryptographic algorithms implemented on FPGAs, the hardware implementation of RNGs is limited to the programmable cells in the device. Among the different proposals to obtain sources of entropy and process them to implement TRNGs, those based in ring oscillators (ROs), operating in parallel and combined with XOR gates, present good statistical properties at the cost of high area requirements. In this paper, these TRNGs are revisited, showing a method for area optimization independently of the FPGA technology used. Experimental results show that three ring oscillators requiring only three LUTs are enough to build a TRNG on Artix 7 devices from Xilinx with a throughput of 33.3 Kbps, which passes NIST tests. A throughput of 50 Kbps can be achieved with four ring oscillators, also requiring three LUTs in Artix 7 devices, while 100 Kbps can be achieved using an structure with four ring oscillators requiring seven LUTs. [ABSTRACT FROM AUTHOR]

All anonymous identity-based encryption (IBE) schemes that are group homomorphic (to the best of our knowledge) require knowledge of the identity to compute the homomorphic operation. This paper is motivated by this open problem, namely to construct an anonymous group-homomorphic IBE scheme that does not sacrifice anonymity to perform homomorphic operations. Note that even when strong assumptions, such as indistinguishability obfuscation (iO), are permitted, no schemes are known. We succeed in solving this open problem by assuming iO and the hardness of the DBDH problem over rings (specifically, Z N 2 for RSA modulus N). We then use the existence of such a scheme to construct an IBE scheme with re-randomizable anonymous encryption keys, which we prove to be IND-ID-RCCA secure. Finally, we use our results to construct identity-based anonymous aggregation protocols. [ABSTRACT FROM AUTHOR]

Neuronal networks are complex systems of interconnected neurons responsible for transmitting and processing information throughout the nervous system. The building blocks of neuronal networks consist of individual neurons, specialized cells that receive, process, and transmit electrical and chemical signals throughout the body. The formation of neuronal networks in the developing nervous system is a process of fundamental importance for understanding brain activity, including perception, memory, and cognition. To form networks, neuronal cells extend long processes called axons, which navigate toward other target neurons guided by both intrinsic and extrinsic factors, including genetic programming, chemical signaling, intercellular interactions, and mechanical and geometrical cues. Despite important recent advances, the basic mechanisms underlying collective neuron behavior and the formation of functional neuronal networks are not entirely understood. In this paper, we present a combined experimental and theoretical analysis of neuronal growth on surfaces with micropatterned periodic geometrical features. We demonstrate that the extension of axons on these surfaces is described by a biased random walk model, in which the surface geometry imparts a constant drift term to the axon, and the stochastic cues produce a random walk around the average growth direction. We show that the model predicts key parameters that describe axonal dynamics: diffusion (cell motility) coefficient, average growth velocity, and axonal mean squared length, and we compare these parameters with the results of experimental measurements. Our findings indicate that neuronal growth is governed by a contact-guidance mechanism, in which the axons respond to external geometrical cues by aligning their motion along the surface micropatterns. These results have a significant impact on developing novel neural network models, as well as biomimetic substrates, to stimulate nerve regeneration and repair after injury. [ABSTRACT FROM AUTHOR]

This paper presents a novel facial expression recognition network, called Distract your Attention Network (DAN). Our method is based on two key observations in biological visual perception. Firstly, multiple facial expression classes share inherently similar underlying facial appearance, and their differences could be subtle. Secondly, facial expressions simultaneously exhibit themselves through multiple facial regions, and for recognition, a holistic approach by encoding high-order interactions among local features is required. To address these issues, this work proposes DAN with three key components: Feature Clustering Network (FCN), Multi-head Attention Network (MAN), and Attention Fusion Network (AFN). Specifically, FCN extracts robust features by adopting a large-margin learning objective to maximize class separability. In addition, MAN instantiates a number of attention heads to simultaneously attend to multiple facial areas and build attention maps on these regions. Further, AFN distracts these attentions to multiple locations before fusing the feature maps to a comprehensive one. Extensive experiments on three public datasets (including AffectNet, RAF-DB, and SFEW 2.0) verified that the proposed method consistently achieves state-of-the-art facial expression recognition performance. The DAN code is publicly available. [ABSTRACT FROM AUTHOR]

Deep unrolling networks (DUNs) have emerged as a promising approach for solving compressed sensing (CS) problems due to their superior explainability, speed, and performance compared to classical deep network models. However, the CS performance in terms of efficiency and accuracy remains a principal challenge for approaching further improvements. In this paper, we propose a novel deep unrolling model, SALSA-Net, to solve the image CS problem. The network architecture of SALSA-Net is inspired by unrolling and truncating the split augmented Lagrangian shrinkage algorithm (SALSA) which is used to solve sparsity-induced CS reconstruction problems. SALSA-Net inherits the interpretability of the SALSA algorithm while incorporating the learning ability and fast reconstruction speed of deep neural networks. By converting the SALSA algorithm into a deep network structure, SALSA-Net consists of a gradient update module, a threshold denoising module, and an auxiliary update module. All parameters, including the shrinkage thresholds and gradient steps, are optimized through end-to-end learning and are subject to forward constraints to ensure faster convergence. Furthermore, we introduce learned sampling to replace traditional sampling methods so that the sampling matrix can better preserve the feature information of the original signal and improve sampling efficiency. Experimental results demonstrate that SALSA-Net achieves significant reconstruction performance compared to state-of-the-art methods while inheriting the advantages of explainable recovery and high speed from the DUNs paradigm. [ABSTRACT FROM AUTHOR]

Human activity recognition (HAR) is an important research problem in computer vision. This problem is widely applied to building applications in human–machine interactions, monitoring, etc. Especially, HAR based on the human skeleton creates intuitive applications. Therefore, determining the current results of these studies is very important in selecting solutions and developing commercial products. In this paper, we perform a full survey on using deep learning to recognize human activity based on three-dimensional (3D) human skeleton data as input. Our research is based on four types of deep learning networks for activity recognition based on extracted feature vectors: Recurrent Neural Network (RNN) using extracted activity sequence features; Convolutional Neural Network (CNN) uses feature vectors extracted based on the projection of the skeleton into the image space; Graph Convolution Network (GCN) uses features extracted from the skeleton graph and the temporal–spatial function of the skeleton; Hybrid Deep Neural Network (Hybrid–DNN) uses many other types of features in combination. Our survey research is fully implemented from models, databases, metrics, and results from 2019 to March 2023, and they are presented in ascending order of time. In particular, we also carried out a comparative study on HAR based on a 3D human skeleton on the KLHA3D 102 and KLYOGA3D datasets. At the same time, we performed analysis and discussed the obtained results when applying CNN-based, GCN-based, and Hybrid–DNN-based deep learning networks. [ABSTRACT FROM AUTHOR]

Recently, some effort went into explaining intransparent and black-box models, such as deep neural networks or random forests. So-called model-agnostic methods typically approximate the prediction of the intransparent black-box model with an interpretable model, without considering any specifics of the black-box model itself. It is a valid question whether direct learning of interpretable white-box models should not be preferred over post-hoc approximations of intransparent and black-box models. In this paper, we report the results of an empirical study, which compares post-hoc explanations and interpretable models on several datasets for rule-based and feature-based interpretable models. The results seem to underline that often directly learned interpretable models approximate the black-box models at least as well as their post-hoc surrogates, even though the former do not have direct access to the black-box model. [ABSTRACT FROM AUTHOR]

To boost productivity, commercial strategies, and social advancement, neural network techniques are gaining popularity among engineering and technical research groups. This work proposes a numerical scheme to solve linear and non-linear ordinary differential equations (ODEs). The scheme's primary benefit included its third-order accuracy in two stages, whereas most examples in the literature do not provide third-order accuracy in two stages. The scheme was explicit and correct to the third order. The stability region and consistency analysis of the scheme for linear ODE are provided in this paper. Moreover, a mathematical model of heat and mass transfer for the non-Newtonian Casson nanofluid flow is given under the effects of the induced magnetic field, which was explored quantitatively using the method of Levenberg–Marquardt back propagation artificial neural networks. The governing equations were reduced to ODEs using suitable similarity transformations and later solved by the proposed scheme with a third-order accuracy. Additionally, a neural network approach for input and output/predicted values is given. In addition, inputs for velocity, temperature, and concentration profiles were mapped to the outputs using a neural network. The results are displayed in different types of graphs. Absolute error, regression studies, mean square error, and error histogram analyses are presented to validate the suggested neural networks' performance. The neural network technique is currently used on three of these four targets. Two hundred points were utilized, with 140 samples used for training, 30 samples used for validation, and 30 samples used for testing. These findings demonstrate the efficacy of artificial neural networks in forecasting and optimizing complex systems. [ABSTRACT FROM AUTHOR]

Natural language generation (NLG) models combined with increasingly mature and powerful deep learning techniques have been widely used in recent years. Deployed NLG models in practical applications may be stolen or used illegally, and watermarking has become an important tool to protect the Intellectual Property (IP) of these deep models. Watermarking technique designs algorithms to embed watermark information and extracts watermark information for IP identification of NLG models can be seen as a symmetric signal processing problem. In terms of IP protection of NLG models, however, the existing watermarking approaches cannot provide reliable and timely model protection and prevent illegal users from utilizing the original performance of the stolen models. In addition, the quality of watermarked text sequences generated by some watermarking approaches is not high. In view of these, this paper proposes two embedding schemes to the hidden memory state of the RNN to protect the IP of NLG models for different tasks. Besides, we add a language model loss to the model decoder to improve the grammatical correctness of the output text sequences. During the experiments, it is proved that our approach does not compromise the performance of the original NLG models on the corresponding datasets and outputs high-quality text sequences, while forged secret keys will generate unusable NLG models, thus defeating the purpose of model infringement. Besides, we also conduct sufficient experiments to prove that the proposed model has strong robustness under different attacks. [ABSTRACT FROM AUTHOR]

Fractional differential equations (FDEs) arising in engineering and other sciences describe nature sufficiently in terms of symmetry properties. This paper proposes a numerical technique to approximate ordinary fractional initial value problems by applying fractional radial basis function neural network. The fractional derivative used in the method is considered Riemann-Liouville type. This method is simple to implement and approximates the solution of any arbitrary point inside or outside the domain after training the ANN model. Finally, three examples are presented to show the validity and applicability of the method. [ABSTRACT FROM AUTHOR]

Gait analysis plays an important role in the fields of healthcare and sports sciences. Conventional gait analysis relies on costly equipment such as optical motion capture cameras and wearable sensors, some of which require trained assessors for data collection and processing. With the recent developments in computer vision and deep neural networks, using monocular RGB cameras for 3D human pose estimation has shown tremendous promise as a cost-effective and efficient solution for clinical gait analysis. In this paper, a markerless human pose technique is developed using motion captured by a consumer monocular camera (800 × 600 pixels and 30 FPS) for clinical gait analysis. The experimental results have shown that the proposed post-processing algorithm significantly improved the original human pose detection model (BlazePose)'s prediction performance compared to the gold-standard gait signals by 10.7% using the MoVi dataset. In addition, the predicted T2 score has an excellent correlation with ground truth (r = 0.99 and y = 0.94x + 0.01 regression line), which supports that our approach can be a potential alternative to the conventional marker-based solution to assist the clinical gait assessment. [ABSTRACT FROM AUTHOR]

The increase in the concentration of geological gas emissions in the atmosphere and particularly the increase of methane is considered by the majority of the scientific community as the main cause of global climate change. The main reasons that place methane at the center of interest, lie in its high global warming potential (GWP) and its lifetime in the atmosphere. Anthropogenic processes, like engineering geology ones, highly affect the daily profile of gasses in the atmosphere. Should direct measures be taken to reduce emissions of methane, immediate global warming mitigation could be achieved. Due to its significance, methane has been monitored by many space missions over the years and as of 2017 by the Sentinel-5P mission. Considering the above, we conclude that monitoring and predicting future methane concentration based on past data is of vital importance for the course of climate change over the next decades. To that end, we introduce a method exploiting state-of-the-art recurrent neural networks (RNNs), which have been proven particularly effective in regression problems, such as time-series forecasting. Aligned with the green artificial intelligence (AI) initiative, the paper at hand investigates the ability of different RNN architectures to predict future methane concentration in the most active regions of Texas, Pennsylvania and West Virginia, by using Sentinel-5P methane data and focusing on computational and complexity efficiency. We conduct several empirical studies and utilize the obtained results to conclude the most effective architecture for the specific use case, establishing a competitive prediction performance that reaches up to a 0.7578 mean squared error on the evaluation set. Yet, taking into consideration the overall efficiency of the investigated models, we conclude that the exploitation of RNN architectures with less number of layers and a restricted number of units, i.e., one recurrent layer with 8 neurons, is able to better compensate for competitive prediction performance, meanwhile sustaining lower computational complexity and execution time. Finally, we compare RNN models against deep neural networks along with the well-established support vector regression, clearly highlighting the supremacy of the recurrent ones, as well as discuss future extensions of the introduced work. [ABSTRACT FROM AUTHOR]

Although the principal aim of the rockfall management is to prevent rock boulders from reaching the buildings instead of the buildings resisting the boulder impacts, there usually exists a residual risk that has to be assessed, even when structural protection measurements are taken. The evaluation of the expected damage of buildings due to rockfalls using empirical data from past events is not always possible, as transferring and applying damage observations from one area to another can be unrealistic. In order to simulate potential rockfall scenarios and their damage on buildings, numerical methods can be an alternative. However due to their increased requirements in expertise and computational costs, their integration into the risk analysis is limited, and simpler tools to assess the rockfall vulnerability of buildings are needed. This paper focuses on the application of artificial intelligence AI methods for providing the expected damage of masonry walls which are subjected to rockfall impacts. First, a damage database with 672 datasets was created numerically using the particle finite element method and the finite element method. The input variables are the rock volume (VR), the rock velocity (RV), the masonry wall (t) and the masonry tensile strength f m . The output variable is a damage index (DI) equal to the percentage of the damaged wall area. Different AI algorithms were investigated and the ANN LM 4-21-1 model was selected to optimally assess the expected wall damage. The optimum model is provided here (a) as an analytical equation and (b) in the form of contour graphs, mapping the DI value. Known the VR and the RV, the DI can be directly used as an input for the vulnerability of masonry walls into the quantitative rockfall risk assessment equation. [ABSTRACT FROM AUTHOR]

Geometallurgical models are commonly built by combining explanatory variables to obtain the response that requires prediction. This study presented a phosphate plant with three concentration steps: magnetic separation, desliming and flotation, where the yields and recoveries corresponding to each process unit were predicted. These output variables depended on the ore composition and the collector concentration utilized. This paper proposed a solution based on feature engineering to select the best set of explanatory variables and a subset of them able to keep the model as simple as possible but with enough precision and accuracy. After choosing the input variables, two neural network models were developed to simultaneously forecast the seven geometallurgical variables under study: the first, using the best set of variables; and the second, using the reduced set of inputs. The forecasts obtained in both scenarios were compared, and the results showed that the mean squared error and the root mean squared error increase in all output variables evaluated in the test set was smaller than 2.6% when the reduced set was used. The trade-off between simplicity and the quality of the model needs to be addressed when choosing the final neural network to be used in a 3D-block model. [ABSTRACT FROM AUTHOR]

Hydraulic turbines constitute an essential component within the hydroelectric power generation industry, contributing to renewable energy production with minimal environmental pollution. Maintaining stable turbine operation presents a considerable challenge, which necessitates effective fault diagnosis and warning systems. Timely and efficient fault w arnings are particularly vital, as they enable personnel to address emerging issues promptly. Although backpropagation (BP) networks are frequently employed in fault warning systems, they exhibit several limitations, such as susceptibility to local optima. To mitigate this issue, this paper introduces an improved social engineering optimizer (ISEO) method aimed at optimizing BP networks for developing a hydraulic turbine warning system. Experimental results reveal that the ISEO-BP-based approach offers a highly effective fault warning system, as evidenced by superior performance metrics when compared to alternative methods. [ABSTRACT FROM AUTHOR]

Aiming at the problems of long detection time and low detection accuracy in the existing coal gangue recognition, this paper proposes a method to collect the multispectral images of coal gangue using spectral technology and match with the improved YOLOv5s (You Only Look Once Version-5s) neural network model to apply it to coal gangue target recognition and detection, which can effectively reduce the detection time and improve the detection accuracy and recognition effect of coal gangue. In order to take the coverage area, center point distance and aspect ratio into account at the same time, the improved YOLOv5s neural network replaces the original GIou Loss loss function with CIou Loss loss function. At the same time, DIou NMS replaces the original NMS, which can effectively detect overlapping targets and small targets. In the experiment, 490 sets of multispectral data were obtained through the multispectral data acquisition system. Using the random forest algorithm and the correlation analysis of bands, the spectral images of the sixth, twelfth and eighteenth bands from twenty-five bands were selected to form a pseudo RGB image. A total of 974 original sample images of coal and gangue were obtained. Through two image noise reduction methods, namely, Gaussian filtering algorithm and non-local average noise reduction, 1948 images of coal gangue were obtained after preprocessing the dataset. This was divided into a training set and test set according to an 8:2 ratio and trained in the original YOLOv5s neural network, improved YOLOv5s neural network and SSD neural network. By identifying and detecting the three neural network models obtained after training, the results can be obtained, the loss value of the improved YOLOv5s neural network model is smaller than the original YOLOv5s neural network and SSD neural network, the recall rate is closer to 1 than the original YOLOv5s neural network and SSD neural network, the detection time is the shortest, the recall rate is 100% and the average detection accuracy of coal and gangue is the highest. The average precision of the training set is increased to 0.995, which shows that the improved YOLOv5s neural network has a better effect on the detection and recognition of coal gangue. The detection accuracy of the improved YOLOv5s neural network model test set is increased from 0.73 to 0.98, and all overlapping targets can also be accurately detected without false detection or missed detection. At the same time, the size of the improved YOLOv5s neural network model after training is reduced by 0.8 MB, which is conducive to hardware transplantation. [ABSTRACT FROM AUTHOR]

In integrated circuit manufacturing, defects in epoxy drops for die attachments are required to be identified during production. Modern identification techniques based on vision-based deep neural networks require the availability of a very large number of defect and non-defect epoxy drop images. In practice, however, very few defective epoxy drop images are available. This paper presents a generative adversarial network solution to generate synthesized defective epoxy drop images as a data augmentation approach so that vision-based deep neural networks can be trained or tested using such images. More specifically, the so-called CycleGAN variation of the generative adversarial network is used by enhancing its cycle consistency loss function with two other loss functions consisting of learned perceptual image patch similarity (LPIPS) and a structural similarity index metric (SSIM). The results obtained indicate that when using the enhanced loss function, the quality of synthesized defective epoxy drop images are improved by 59%, 12%, and 131% for the metrics of the peak signal-to-noise ratio (PSNR), universal image quality index (UQI), and visual information fidelity (VIF), respectively, compared to the CycleGAN standard loss function. A typical image classifier is used to show the improvement in the identification outcome when using the synthesized images generated by the developed data augmentation approach. [ABSTRACT FROM AUTHOR]

In advanced transportation-management systems, variable speed limits are a crucial application. Deep reinforcement learning methods have been shown to have superior performance in many applications, as they are an effective approach to learning environment dynamics for decision-making and control. However, they face two significant difficulties in traffic-control applications: reward engineering with delayed reward and brittle convergence properties with gradient descent. To address these challenges, evolutionary strategies are well suited as a class of black-box optimization techniques inspired by natural evolution. Additionally, the traditional deep reinforcement learning framework struggles to handle the delayed reward setting. This paper proposes a novel approach using covariance matrix adaptation evolution strategy (CMA-ES), a gradient-free global optimization method, to handle the task of multi-lane differential variable speed limit control. The proposed method uses a deep-learning-based method to dynamically learn optimal and distinct speed limits among lanes. The parameters of the neural network are sampled using a multivariate normal distribution, and the dependencies between the variables are represented by a covariance matrix that is optimized dynamically by CMA-ES based on the freeway's throughput. The proposed approach is tested on a freeway with simulated recurrent bottlenecks, and the experimental results show that it outperforms deep reinforcement learning-based approaches, traditional evolutionary search methods, and the no-control scenario. Our proposed method demonstrates a 23% improvement in average travel time and an average of a 4% improvement in CO, HC, and NOx emission.Furthermore, the proposed method produces explainable speed limits and has desirable generalization power. [ABSTRACT FROM AUTHOR]

Recently, biomass has become an increasingly widely used energy resource. The problem with the use of biomass is its variable composition. The most important property that determines the energy content and thus the performance of fuels such as biomass is the heating value (HHV). This paper focuses on selecting the optimal number of input variables using linear regression (LR) and the multivariate adaptive regression splines approach (MARS) to create an artificial neural network model for predicting the heating value of selected biomass. The MARS model selected the input data better than the LR model. The best modeling results were obtained for a network with three input neurons and nine neurons in the hidden layer. This was confirmed by a high correlation coefficient of 0.98. The obtained results show that artificial neural network (ANN) models are effective in predicting the calorific value of woody and field biomass, and can be considered a worthy simulation model for use in selecting biomass feedstocks and their blends for renewable fuel applications. [ABSTRACT FROM AUTHOR]

Simple Summary: This paper discusses the importance of early detection of brain tumors and the limitations of traditional diagnosis methods. The use of deep learning models for brain tumor detection is introduced as a potential solution, but the high computing costs and potential biases in training data pose challenges. The study proposes a new, end-to-end, lightweight deep learning model for brain tumor detection that outperforms other models and is suitable for real-time applications. The study also provides a framework for secure data transfer of medical lab results and security recommendations to ensure security on the Internet of Medical Things (IoMT). In the field of medical imaging, deep learning has made considerable strides, particularly in the diagnosis of brain tumors. The Internet of Medical Things (IoMT) has made it possible to combine these deep learning models into advanced medical devices for more accurate and efficient diagnosis. Convolutional neural networks (CNNs) are a popular deep learning technique for brain tumor detection because they can be trained on vast medical imaging datasets to recognize cancers in new images. Despite its benefits, which include greater accuracy and efficiency, deep learning has disadvantages, such as high computing costs and the possibility of skewed findings due to inadequate training data. Further study is needed to fully understand the potential and limitations of deep learning in brain tumor detection in the IoMT and to overcome the obstacles associated with real-world implementation. In this study, we propose a new CNN-based deep learning model for brain tumor detection. The suggested model is an end-to-end model, which reduces the system's complexity in comparison to earlier deep learning models. In addition, our model is lightweight, as it is built from a small number of layers compared to other previous models, which makes the model suitable for real-time applications. The optimistic findings of a rapid increase in accuracy (99.48% for binary class and 96.86% for multi-class) demonstrate that the new framework model has excelled in the competition. This study demonstrates that the suggested deep model outperforms other CNNs for detecting brain tumors. Additionally, the study provides a framework for secure data transfer of medical lab results with security recommendations to ensure security in the IoMT. [ABSTRACT FROM AUTHOR]

No study has been reported to use machine learning methods to predict the full-range test curves of circular CFST columns. In this paper, the long short-term memory (LSTM) network was introduced to calculate the axially compressive load–strain curves of the circular CFST columns according to an experiment database of limited scale. To improve the feasibility of input data for the recurrent neural network algorithm, data preprocessing methods and data configurations were discussed. The prediction results indicate that the LSTM network provides more accurate estimations compared with the artificial neural networks, random forest and support vector regression. Meanwhile, this method can be used to calculate the mechanical properties including the elastic modulus, ultimate bearing capacity, and the ductility of the columns with acceptable accuracy for engineering practice (the prediction error within 20%). For future research, it is expected that the machine learning method will be applied to predict the structural response of different members under various loading conditions. [ABSTRACT FROM AUTHOR]

The paper was devoted to the application of saliency analysis methods in the performance analysis of deep neural networks used for the binary classification of brain tumours. We have presented the basic issues related to deep learning techniques. A significant challenge in using deep learning methods is the ability to explain the decision-making process of the network. To ensure accurate results, the deep network being used must undergo extensive training to produce high-quality predictions. There are various network architectures that differ in their properties and number of parameters. Consequently, an intriguing question is how these different networks arrive at similar or distinct decisions based on the same set of prerequisites. Therefore, three widely used deep convolutional networks have been discussed, such as VGG16, ResNet50 and EfficientNetB7, which were used as backbone models. We have customized the output layer of these pre-trained models with a softmax layer. In addition, an additional network has been described that was used to assess the saliency areas obtained. For each of the above networks, many tests have been performed using key metrics, including statistical evaluation of the impact of class activation mapping (CAM) and gradient-weighted class activation mapping (Grad-CAM) on network performance on a publicly available dataset of brain tumour X-ray images. [ABSTRACT FROM AUTHOR]

In recent years, convolutional neural networks have been in the leading position for ground-based cloud image classification tasks. However, this approach introduces too much inductive bias, fails to perform global modeling, and gradually tends to saturate the performance effect of convolutional neural network models as the amount of data increases. In this paper, we propose a novel method for ground-based cloud image recognition based on the multi-modal Swin Transformer (MMST), which discards the idea of using convolution to extract visual features and mainly consists of an attention mechanism module and linear layers. The Swin Transformer, the visual backbone network of MMST, enables the model to achieve better performance in downstream tasks through pre-trained weights obtained from the large-scale dataset ImageNet and can significantly shorten the transfer learning time. At the same time, the multi-modal information fusion network uses multiple linear layers and a residual structure to thoroughly learn multi-modal features, further improving the model's performance. MMST is evaluated on the multi-modal ground-based cloud public data set MGCD. Compared with the state-of-art methods, the classification accuracy rate reaches 91.30%, which verifies its validity in ground-based cloud image classification and proves that in ground-based cloud image recognition, models based on the Transformer architecture can also achieve better results. [ABSTRACT FROM AUTHOR]

Medical image analysis using deep neural networks (DNN) has demonstrated state-of-the-art performance in image classification and segmentation tasks, aiding disease diagnosis. The accuracy of the DNN is largely governed by the quality and quantity of the data used to train the model. However, for the medical images, the critical security and privacy concerns regarding sharing of local medical data across medical establishments precludes exploiting the full DNN potential for clinical diagnosis. The federated learning (FL) approach enables the use of local model's parameters to train a global model, while ensuring data privacy and security. In this paper, we review the federated learning applications in medical image analysis with DNNs, highlight the security concerns, cover some efforts to improve FL model performance, and describe the challenges and future research directions. [ABSTRACT FROM AUTHOR]

Detecting changes in urban areas presents many challenges, including complex features, fast-changing rates, and human-induced interference. At present, most of the research on change detection has focused on traditional binary change detection (BCD), which becomes increasingly unsuitable for the diverse urban change detection tasks as cities grow. Previous change detection networks often rely on convolutional operations, which struggle to capture global contextual information and underutilize category semantic information. In this paper, we propose SIGNet, a Siamese graph convolutional network, to solve the above problems and improve the accuracy of urban multi-class change detection (MCD) tasks. After maximizing the fusion of change differences at different scales using joint pyramidal upsampling (JPU), SIGNet uses a graph convolution-based graph reasoning (GR) method to construct static connections of urban features in space and a graph cross-attention method to couple the dynamic connections of different types of features during the change process. Experimental results show that SIGNet achieves state-of-the-art accuracy on different MCD datasets when capturing contextual relationships between different regions and semantic correlations between different categories. There are currently few pixel-level datasets in the MCD domain. We introduce a new well-labeled dataset, CNAM-CD, which is a large MCD dataset containing 2508 pairs of high-resolution images. [ABSTRACT FROM AUTHOR]

Currently, we can solve a wide range of tasks using computer vision algorithms, which reduce manual labor and enable rapid analysis of the environment. The remote sensing domain provides vast amounts of satellite data, but it also poses challenges associated with processing this data. Baseline solutions with intermediate results are available for various tasks, such as forest species classification, infrastructure recognition, and emergency situation analysis using satellite data. Despite these advances, two major issues with high-performing artificial intelligence algorithms remain in the current decade. The first issue relates to the availability of data. To train a robust algorithm, a reasonable amount of well-annotated training data is required. The second issue is the availability of satellite data, which is another concern. Even though there are a number of data providers, high-resolution and up-to-date imagery is extremely expensive. This paper aims to address these challenges by proposing an effective pipeline for building segmentation that utilizes freely available Sentinel-2 data with 10 m spatial resolution. The approach we use combines a super-resolution (SR) component with a semantic segmentation component. As a result, we simultaneously consider and analyze SR and building segmentation tasks to improve the quality of the infrastructure analysis through medium-resolution satellite data. Additionally, we collected and made available a unique dataset for the Russian Federation covering area of 1091.2 square kilometers. The dataset provides Sentinel-2 imagery adjusted to the spatial resolution of 2.5 m and is accompanied by semantic segmentation masks. The building footprints were created using OpenStreetMap data that was manually checked and verified. Several experiments were conducted for the SR task, using advanced image SR methods such as the diffusion-based SR3 model, RCAN, SRGAN, and MCGR. The MCGR network produced the best result, with a PSNR of 27.54 and SSIM of 0.79. The obtained SR images were then used to tackle the building segmentation task with different neural network models, including DeepLabV3 with different encoders, SWIN, and Twins transformers. The SWIN transformer achieved the best results, with an F1-score of 79.60. [ABSTRACT FROM AUTHOR]

The classification that distinguishes whether machines are driving on roads or working in fields based on their global navigation satellite system (GNSS) trajectories is essential for effective management of cross-regional agricultural machinery services in China. In this paper, a novel field–road classification method utilizing multiple deep neural networks (MultiDNN) is proposed to enhance the accuracy of field and road point classification. The MultiDNN model incorporates a bi-directional long short-term memory network (BiLSTM), a topology adaptive graph convolution network (TAG), and a self-attention network (ATT) to effectively extract spatio-temporal features for field–road classification. The BiLSTM is used to capture temporal relationships along the time axis of a trajectory, providing global contextual information for each point. Then, the TAG network is used to obtain the spatio-temporal relationships between adjacent points in a trajectory, offering local contextual information for each point. Finally, the ATT network assigns varying weights to features to emphasize important characteristics. The performance of the MultiDNN model was evaluated using a wheat harvesting trajectory dataset, and the results showed that it achieved a high degree of accuracy, up to 89.75%, outperforming the best baseline method (GCN) by 2.79%. [ABSTRACT FROM AUTHOR]