Search

The integration of deep learning, computer vision, and advanced algorithms has ushered in a transformative era in the prediction of human driving behavior, consequently revolutionizing road safety. This paper focuses on an innovative convergence of technology that addresses critical issues like driver fatigue and distracted driving by automatically identifying and categorizing diverse driving behaviors. Neural network architectures, such as VGG16, AlexNet, and ResNet are described in this paper that have propelled accuracy in behavior classification to remarkable levels. However, the quest for safer roads remains ongoing, with promising avenues lying ahead. First and foremost, the creation of extensive, diverse, and meticulously annotated datasets is paramount. These datasets serve as the bedrock upon which future models can be trained, enhancing their robustness and generalizability across a spectrum of driving scenarios. Real-time models represent another pivotal frontier. These models hold the potential to provide timely interventions and support systems for drivers, thus preventing accidents proactively. The exploration of hybrid techniques that amalgamate the strengths of various neural network architectures presents an exciting avenue, promising to further push the boundaries of prediction accuracy. Furthermore, this paper also discusses the fusion of multi-modal data, encompassing sensor data from IoT and smartphone devices, that holds immense promise. This holistic approach promises a more comprehensive understanding of driver behavior by integrating diverse data sources, ultimately contributing to the creation of safer road environments.In this research paper, we also explore these cutting-edge developments in deep learning and computer vision, emphasizing technical novelty and innovation. Through an interdisciplinary approach, we envision a future where the synergy of technology, data, and human behavior leads to a substantial reduction in road accidents and improved road safety. [ABSTRACT FROM AUTHOR]

Major Depressive Disorder (MDD) is characterized by low mood, loss of interest and even suicidal ideation. Electroencephalogram based diagnosis of a variety of neurological conditions has been conducted in recent years using modern neurocomputing and deep learning approaches. Privacy is a high concern for medical data over distributed training scenarios. Hence, this paper aims to develop an EEG-based privacy-preserved system to identify MDD through the Federated Learning (FL) approach. In this study, training for 3-channel EEG-based MDD screening is introduced over FL using deep learning (DL) algorithms such as Long Short-Term Memory (LSTM), Bidirectional LSTM (Bi-LSTM), Gated Recurrent Unit (GRU), and One Dimensional Convolutional Neural Network (1D-CNN). A privacy-preserving solution for MDD patients utilizing FL is advantageous because clinical data is sensitive and most people do not want to share their personal information. Hence, the analysis of the comparative results for multiple applicable strategies including Independent and Identically Disturbed (IID) data, non-IID data, and algorithms provide proof that FL can be used to train DL models. The MODMA dataset of 3-channel EEG with 26 MDD and 29 non-MDD individuals is used in this paper. Future study on MDD has several potential areas of use and these FL approaches can also be coupled with new technologies. [ABSTRACT FROM AUTHOR]

Switchgear is a vital component of modern power systems, responsible for regulating the flow of electrical power. Contact issues, irregular loads, and other similar problems can cause switchgear to overheat, leading to unexpected disturbances and potential damage to the power equipment. Thermal imaging shows significant potential and is increasingly employed to detect faults in power equipment. However, the unique characteristics of thermal images often pose challenges to accurate fault detection. This research aims to study the effectiveness of transfer learning architectures for switchgear fault detection. This paper applies eleven transfer learning architectures, including SqueezeNet, GoogLeNet, InceptionV3, DenseNet201, ResNet50, Xception, InceptionResNetV2, ShuffleNet, EfficientNetB0, AlexNet, and VGG19. The results of the testing phase demonstrated that the application of transfer learning by fine-tuning pre-trained convolutional neural network architectures was highly effective in the classification of thermal images captured from switchgear units. The models achieved accuracy rates between 83.87% and 98.38%, and values of F 1 -Scores between 83.11% and 98.34% in the pre-trained architectures. [Display omitted] • Transfer learning is applied to address the unique characteristics of thermal images for switchgear fault detection. • A thermal image dataset is setup and augmented to improve the classification performance. • Establish standard comparisons among eleven transfer learning architectures. • Achieve rapid and precise classification with the proposed transfer learning architectures. [ABSTRACT FROM AUTHOR]

The large number of near-Earth asteroids (NEAs) has greatly impacted human space activities and Earth security. However, detecting NEAs in astronomical images with complex, varying backgrounds is still extremely challenging. In this paper, we propose a deep segmentation assisted asteroid tracking algorithm, termed DSAT, to construct a possible pipeline for faint NEA tracking in astronomical images. First, the single-frame object detection problem is converted to a segmentation problem, enabling robust extraction of faint potential moving objects. Then, a multiframe motion prior-based moving object tracking algorithm is proposed to find real NEAs. We further propose a distance tolerance criterion to help DSAT achieve effective tracking in practical situations when detection has partially failed. Finally, the pipeline is tested with both simulated and real astronomical images at different SNRs and in crowded fields. The results showed that our pipeline has the potential to detect and track faint NEAs in complex backgrounds. Our code is publicly available at https://github.com/zhenhongdu/DeepSegAsteroidTracker. [ABSTRACT FROM AUTHOR]

Human age and gender prediction from facial images has garnered significant attention due to its importance in various applications. Traditional models struggle with large-scale variations in unfiltered images. Convolutional Neural Networks (CNNs) have emerged as effective tools for facial analysis due to their robust performance. This paper presents a novel CNN approach for robust age and gender classification using unconstrained real-world images. The CNN architecture includes convolution, pooling, and fully connected layers for feature extraction, dimension reduction, and mapping to output classes. Adience and UTKFace datasets were utilized, with the best training and testing accuracies achieved using an 80% training and 20% testing data split. Robust image pre-processing and data augmentation techniques were applied to handle dataset variations. The proposed approach outperformed existing methods, achieving age prediction accuracies of 86.42% and 81.96%, and gender prediction accuracies of 97.65% and 96.32% on the Adience and UTKFace datasets, respectively. [ABSTRACT FROM AUTHOR]

Video Super-Resolution (VSR) is gaining massive attention in the digital age across various application domains such as video surveillance and ultra-high-definition displays. Deep learning (DL) has recently made significant progress in research and industry domains. Existing researchers used numerous VSR methods based on deep learning to improve the resolution. VSR is based on inter-frame information utilization. Video frames provide the leverage information of data that modalities record sequentially, i.e.; the object's temporal changes cause inconsistent measurements. Consequently, suitable models and algorithms must be developed to provide artifact-free images. This paper goes through two reconstruction methods incorporating various motion data sources. Initially, it describes an iterative approach that implicitly treats dynamic behavior as uncertainty in the forward model. Further direct reconstruction techniques can be derived for an explicit motion map. This paper compares both explicit and implicit motion compensation-based methods. Convolutional neural networks (CNN) and recurrent, residual network (RRN) based methods from a deep learning environment are analyzed to reconstruct the High-Resolution (HR) frames. This paper shows numerical findings for both methods using simulated data. Observations show that RRN can boost the super-resolution (SR) performance and achieve considerable visual quality after reconstruction; however, performance is limited to small datasets due to shallow network parameters. Extensive experiments show that RRN significantly impacts SR results due to its substantial computational efficiency. [ABSTRACT FROM AUTHOR]

Traffic congestion has become a critical issue in metropolitan areas, inflicting significant hardships on individuals on a daily basis. This adverse situation poses multifaceted challenges, including increased air pollution, heightened fuel consumption, and compromised road safety. Deep learning algorithms, encompassing both Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN) have showcased remarkable performance in areas such as computer vision, natural language processing, healthcare, finance, and autonomous systems. This research paper proposes a novel methodology to develop a vehicle detection model - VehiNet, which can subsequently be refined to create an automated traffic signal system. The study explores the effectiveness of various CNN, RNN, and deep learning algorithms and techniques in accomplishing this objective. The dataset picked for the study in addition to being compiled from internet resources, was also painstakingly assembled manually using a variety of methods to collect over 2000 photographs from various angles, lighting conditions, and locations within Bengaluru city. The main motive is to apply CNN, RNN, and other Deep Learning classification techniques for object detection and classification of Indian vehicles and see how well these deep learning algorithms and techniques affect prediction efficiency. This research stands out from others and makes its novelty clear thanks to the carefully collected dataset and the detailed analysis of the methodologies. [ABSTRACT FROM AUTHOR]

The proliferation of fake images in today's digital landscape poses a significant threat to various domains, including media integrity, social media, and online security. Recognizing the urgent need to distinguish real images from their deceptive counterparts, this paper underscores the importance of developing a robust detection system. While substantial efforts have been made in the realms of computer vision and deep learning, the advent of Generative Adversarial Networks (GANs) has added a new layer of complexity to this challenge. In response to these evolving threats, we present a novel two-step methodology for detecting fake images, with a specific focus on those generated by GANs. Our approach harnesses the combined strengths of GANs and traditional Convolutional Neural Networks (CNNs), offering a comprehensive solution that significantly enhances accuracy in identifying both fake images and machine-generated fake images. The results of our experiments demonstrate the efficacy of our methodology. Using CNNs alone, we achieved a training accuracy of 87%. However, when employing the collaborative power of GANs and CNNs, our model exhibited a remarkable accuracy rate of 94.4%. This substantial improvement underscores the superiority of the GANs+CNN approach, suggesting its potential as a groundbreaking solution in the realm of fake image detection. This research opens up new horizons in fields such as media forensics, social media monitoring, and online security, where the ability to discern genuine content from manipulated or synthetic media is of paramount importance. The promising outcomes of this study not only provide an immediate and effective solution but also pave the way for further exploration and innovation in this critical area of digital security. [ABSTRACT FROM AUTHOR]

In recent years, the advancement of deep learning technologies has significantly impacted various domains and the field of transportation is no exception. As the demand for robust and accurate traffic sign classification systems continues to rise, this study presents an in-depth exploration and comparison of various techniques employed in the field. Focusing on state-of-the-art methodologies, we assess the effectiveness and performance of multiple classification approaches for traffic sign recognition. The review presents an extensive survey of the literature, encompassing traditional computer vision methods, machine learning algorithms, and the latest advancements in deep learning. The comparative analysis aims to identify the strengths and limitations of each technique, considering factors such as computational efficiency and accuracy. Additionally, the paper implements four models—CNN, ResNet50, VGG19, and EfficientNetB7—for traffic sign classification on the GTSRB dataset, the accuracy results are reported as 99.25%, 99.28%, 98.95%, and 98.24% respectively. [ABSTRACT FROM AUTHOR]

This paper identifies the model for classifying the bird sounds using the Convolutional Neural Network (CNN) algorithm. CNN are considered as one of the powerful toolkits developed in the machine learning and that have shown to be more efficient particularly in the field of image processing and sound recognition. The two-step verification process which will participating in the creation of datasets and neural network input. This system uses the collection of labelled and categorized recordings. Spectrograms are generated from the downloaded data which is used as the input for the neural network. The experiments are conducted and it will match with the different configurations, which including the number of bird species and Spectrograms. As a result, we can identify the bird species from its audio recordings. By identifying the bird species on a large scale, it provides a vital information about our ecosystems and biodiversity. The changes in the ecological environment can be reflected by the quantity and composition of bird species. It is one of the major challenges which leads to recognition of many bird species based on their audio. In modern years, the deep learning techniques namely convolutional neural networks (CNN) have played a major role in many areas of science and also successfully provided efficient methodologies, such as pattern recognition, object detection in images, and classification of patterns in audios and speech recognition. [ABSTRACT FROM AUTHOR]

Pulmonary Embolism (PE) is a blood clot in the pulmonary arteries of the lungs. Currently, Computerized Tomography Pulmonary Angiography (CTPA) scans are used to diagnose this condition. However, to manually locate the presence of a PE in the scan is laborious. In this paper, the detection of PE and prediction of its features like location, Right Ventricle to Left Ventricle (RV/LV) ratio, and chronicity are automated. First, for the detection of the embolisms, image features from the RSNA Pulmonary Embolism CT (RSPECT) dataset - containing over 12,000 CTPA studies, are extracted by several pre-trained Convolutional Neural Networks (CNN) - AlexNet, Inception V3, ResNet-18, and ResNet-50. Then, various Machine Learning (ML) classifiers are trained on these features and their performances are compared. Second, for the prediction of labels, multi-label classification is performed by training these networks with Binary Cross Entropy Logits (BCE Logits) loss. The results showed that for the detection task, k-NN classifier trained on ResNet-50 features achieved the highest sensitivity of 0.98 with 1.7 false positives per scan and an AUROC score of 97.4%. This system also improved on the state-of-the-art sensitivity score by 0.0975 and AUROC score by 3.4%. For multi-label classification, ResNet-18 performed comparatively better with the best validation loss of 0.07 and weighted macro-average ROC AUC score of 0.61. [ABSTRACT FROM AUTHOR]

• The deep learning model can better extract the deeper features of the multi-point deformation sequence. • MVMD algorithm reduces the complexity of multi-point displacement sequence. • The model considers the spatiotemporal characteristics of dam deformation, the prediction accuracy is obviously improved. It is difficult for single measuring point model to synchronously characterize the spatial correlation of deformation sequence of concrete dam and the similarity of displacements of different measuring points. Considering the limitation of conventional model in dealing with spatial-temporal data structure, In this study, a deep learning technique for multi-point and multi-output deformation prediction of concrete dams is proposed, which is based on Multivariate Variational Mode Decomposition (MVMD) and three-dimensional convolutional neural network (3D-CNN) combined model. Firstly, the multi-point sequence is decomposed into several relatively stable sub-sequences with different frequency scales by MVMD, which reduces the complexity of the multi-point displacement sequence. Then, In order to enhance the model 's ability to fit the time and spatial features of the sequence, the 3D-CNN model is used to predict the decomposed components and reconstruct the displacement data of the measuring points. This study focuses on the principle, process and calculation steps of the proposed model, and verifies the proposed model through the deformation data of three typical measuring points. The test results show that the prediction model proposed in this paper is an effective method for dam deformation prediction. [ABSTRACT FROM AUTHOR]

Recently, deep learning (DL) has become increasingly important in the field of image processing, and its application in dental radiology has become particularly relevant. DL-based image recognition has become a key component of image interpretation in dental radiology, making it possible to automate diagnosis and treatment planning. These techniques can be applied to areas such as caries, tooth detection, periodontal disease, oral lesions, age determination, gender estimation, and osteoporosis. In addition, recent studies have shown that DL algorithms in these areas have high accuracy, with some studies achieving accuracy rates of over 90%. Such high accuracy can significantly improve the efficiency and accuracy of dental diagnostics and treatment planning. Thus, using DL in dental imaging may become an everyday tool in dentistry with the current advances in applications. In this paper, recent applications and potential challenges of using deep convolutional neural network architectures in dental image analysis will be reviewed. [ABSTRACT FROM AUTHOR]

The running band on the rail surface serves as a crucial indicator of the wheel-rail contact relationship, making quantitative detection of the running band vital for railroad inspection and maintenance. However, current rail running band detection methods remain manual, and leveraging state-of-the-art deep learning technology can significantly enhance detection efficiency and minimize the reliance on human labor. This paper presents an improved version of ShuttleNet, called ShuttleNetM2T, for rail surface running band detection, emphasizing high stability. Efficient self-attention in ShuttleNetM2T captures global information, maintaining efficiency and rectifying issues like misrecognition and incomplete edges. Experimental results show ShuttleNetM2T achieves 0.9823 average F-measure and 0.9653 average Intersection-Over-Union on test images. For automatic running band width detection, we propose a pixel-to-physical distance conversion-based calculation, yielding just 0.625% relative error. Overall, the findings in this paper facilitate accurate detection and automatic calculation of the running band width, with promising applications in intelligent rail surface detection. • A stable ShuttleNetM2T model for detecting running bands on track surfaces has been proposed. • The ShuttleNetM2T can fully recognize the running bands' edges on the surface of rails. • A precise automatic detection algorithm for running band width has been developed. [ABSTRACT FROM AUTHOR]

In recent years, decomposition-based combination models have been widely used in wind power prediction. This type of method decomposes the highly volatile wind power into some relatively smooth subsequences, which reduces the difficulty of modeling. However, this might use information from future data in advance, creating the illusion of high prediction accuracy. Therefore, this paper proposes a wind power ultra-short-term prediction model based on fixed scale dual mode decomposition (FSDMD) and deep learning networks. First, the wind power series after fixed scale blocking is decomposed using ensemble empirical mode decomposition (EEMD), and use the improved variational mode decomposition (VMD) based on Spearman rank order correlation coefficient (SROCC) to decompose the obtained high-frequency components twice. Then, the appropriate mode components were selected by calculating the SROCC and experimental analysis, and combined with the convolutional neural network (CNN) and the bidirectional long short-term memory (BiLSTM) network to train the model. Finally, the historical data of wind turbines in a wind farm in Northwest China is used for example verification, and the comparison with other models in the two scenarios of sufficient and insufficient features. The results show that the proposed FSDMD–CNN–BiLSTM model has high prediction accuracy in both scenarios. Especially in the scenario of insufficient features, compared with CNN-BiLSTM model, RMSE, MAE and MAPE are reduced by 8.20,14.24 and 0.15, respectively. In addition, this paper verifies that mode decomposition can improve the performance of prediction model without using future features, which provides ideas for solving similar problems. [ABSTRACT FROM AUTHOR]

Accurate detection of pavement markings at the pixel level is crucial for enhancing traffic safety. The majority of current advanced deep-learning networks predominantly focus on localized features, neglecting the global context of pavement image. Such networks often result in discontinuous segmentation outcomes and suboptimal recovery of local details. In this paper, a robust model named C-Transformer is proposed to provide an effective solution to this challenge. The contributions of this paper primarily involve two aspects. Firstly, the proposed C-Transformer is designed to succinctly integrate convolution operations and self-attention, facilitating a comprehensive understanding of essential features. Secondly, an efficient Feed-Forward Network called Inverse Residual Feed-Forward Network is also proposed in this paper and deployed in C-Transformer to improve latent representations. Experimental results demonstrate that, compared to other state-of-the-art networks, the proposed C-Transformer achieves a performance enhancement of 0.93% in F-measure and a 1.64% improvement in Intersection-Over-Union. In particular, the robustness and effectiveness of the C-Transformer in accurate pavement marking detection are proved through field test results. This paper illustrates the feasibility of employing a hybrid Convolutional neural network-Transformer-based network for automatic robust pavement marking detection under noisy conditions. [ABSTRACT FROM AUTHOR]

The development of stereo matching algorithm is still one of the challenging problems, especially in ill-posed regions. Hence, this article presents a survey on the algorithm frameworks related to the stereo matching algorithm. Based on the early survey that had been conducted, two major frameworks available in current stereo matching algorithm development, they are traditional and artificial intelligence (AI) frameworks. Most of the traditional methods are very low accuracy compared to the AI-based approach. This can be observed in the standard benchmarking dataset, such as from the KITTI and the Middlebury, where AI methods rank at the top of the accuracy list. Additionally, the trend for solving computer vision problems uses AI or machine learning tools that become more apparent in recent years. Thus, this paper is focusing on the survey between the deep learning frameworks, which is one of the machine learning tools related to the convolutional neural network (CNN). Several mixed approaches between CNN based method and traditional handcraft method, as well as the end to end CNN method also discussed in this paper. [ABSTRACT FROM AUTHOR]

Groundwater level (GWL) prediction is important for ecological protection and resource utilization; it helps in formulating policies for artificial groundwater recharge, modifying the number of extraction wells, etc., and can support sustainable human development as well as inform water resource management decisions. However, climate change, anthropogenic impacts, and the complex coupling between surface water and groundwater increase the difficulty of predicting groundwater levels. The model proposed in this paper combines external data as well as multiple models. The method leverages long and short-term memory (LSTM) and convolutional neural network (CNN) models, combined with secondary modal decomposition and slime mould algorithm (SMA), together with an adaptive weight module (AWM). The study applies this method to predict GWL for three different hydrological conditions in China, specifically for the Jinan Baotu Spring, Heihu Spring, and Zhongtianshe watershed of Taihu Lake. A comparison of metrics such as mean absolute error and Nash efficiency coefficient for single and hybrid models shows that the model in this paper is more advantageous than the single model and other hybrid models. The interpretability of the model is enhanced by SHAP values that demonstrate the degree of contribution of the input variables. This paper uses SHAP analyses to identify the key drivers affecting groundwater levels. These factors must be detected in order to develop groundwater resource protection measures. [Display omitted] • Multivariate fusion data including hydrology and meteorology are used as model input. • A secondary modal decomposition module for historical groundwater level data was utilized. • The neural network hyperparameters are optimized using the slime mould algorithm. • Aggregate subsets of prediction with adaptive modules rather than linear summation. • The interpretable SHAP model measures the degree of influence of external variables. [ABSTRACT FROM AUTHOR]

Depression is one of the leading forms of mental health issues encountered by individuals of diverse age groups today worldwide. Like any other mental health concerns, depression too poses diagnostic challenges for medical practitioners and clinical experts, given obvious social reservations and lack of awareness and acceptance in the society. Since long researchers have been looking for methods to identify symptoms of depression among individuals from their speech and responses, by utilizing automation systems and computers. In this paper, we propose an audio based depression detection method, which relies on neural networks for audio spectrogram based feature extraction as well as classification between speech/response patterns of depressed vs. non-depressed persons. We adopt a multi-modal approach in our work, by combining Mel-Frequency Cepstral Coefficients (MFCC) features, as well as Spectrogram features extracted from an audio file, by a novel CNN network. Our CNN model demonstrates optimized residual blocks and the "glorot uniform" kernel initializer. The proposed method's performance is assessed in both multi-modal and multi-feature trials. We show our results on standard benchmark datasets DAIC-WOZ and MODMA, which provide repositories of questionnaire and patient responses, relevant in identification of depressive symptoms. We have also tested our model on standard emotion recognition audio dataset, RAVDESS. The proposed model achieves detection accuracy of over 90% in DAIC-WOZ and MODMA, and over 85% in RAVDESS, which is proven to surpass the present state-of-the-art. • We introduce a novel deep neural network for depression detection through audio signals. • We used a multi-modal concept considering mfcc and spectrogram to detect the depression. • This paper shows optimized residual block to extract the detailed information to enhance the performance of the model. • Our model gets better results on the three benchmark datasets. [ABSTRACT FROM AUTHOR]

With the continuous development of social economy, the road traffic system as one of the basis of national economy is also increasingly developed, which is followed by the traffic safety problems are increasingly prominent. Among them, driving violations such as not obeying traffic signs are the main cause of traffic accidents. In this research, Traffic Sign Recognition (TSR) has become a hot research topic. The research status and application field of traffic sign detection and recognition technology are introduced and analyzed in detail, and the improvement of traffic sign database is introduced. After that, the application of CNN in image processing and traffic sign recognition is introduced, and the existing problems in traffic sign recognition are analyzed. The CNN deep learning network used in this paper can conduct training while identifying targets, effectively improve the recognition accuracy of traffic signs under complex natural conditions and reduce the time consumption. [ABSTRACT FROM AUTHOR]

The fault management process is facilitated by equipping power distribution systems with automated devices, especially remote-controlled switches (RCSs). Although RCS plays a key role in improving the system's reliability, it imposes significant investment, installation, and maintenance costs. Hence, RCSs should be optimally located in distribution feeders for the highest profit. In previous works, reliability-oriented mathematical optimization models have been formulated to reach this goal. However, the number of test solutions exponentially grows with the problem size to find the globally optimal solution. This paper uses machine learning to propose a scalable and easy-to-implement model for optimal switch placement in real power distribution systems. At first, the features of candidate points for installing RCSs are introduced. Then, a learning model is applied to deeply explore the relationship between these features and optimal locations for installing RCSs. After training, the learning-based surrogate model directly determines the optimal RCS placement strategy in real power distribution systems by leveraging knowledge gained from past experiences. Simulation results demonstrate that the proposed surrogate model is approximately 29 times faster than the integer programming-based mathematical model, without a significant loss of accuracy, when implemented on a modified 11 kV network connected to Bus 4 of the Roy Billiton test system. This paper also employs explainable artificial intelligence (XAI) tools to select the most important features, where the Hamming loss is decreased by approximately 5%. [ABSTRACT FROM AUTHOR]

Automated detection of pineapple-picking robots in complex agricultural environments is challenging due to uneven lighting and occluded fruit. In this paper, a lightweight pineapple detection model based on the YOLOv7-tiny model is presented for real-time accurate detection by agricultural robots. Firstly, The SIoU loss function is designed to substitute for the CIoU loss function in the initial model. The mismatched direction can be used to minimize the overall degree of freedom and expedite model convergence. Then, incorporating the CBAM module into the backbone network enhances the model's capacity to emphasize key features of the pineapple fruit, resulting in improved generalization ability and overall robustness. Ultimately, the improved YOLOv7-tiny model achieves a mAP@0.5 of 96.9%, surpassing the original model by 1.6%. [ABSTRACT FROM AUTHOR]

This paper investigates visual navigation and control of a cooperative unmanned surface vehicle (USV)-unmanned aerial vehicle (UAV) system for marine search and rescue. First, a deep learning-based visual detection architecture is developed to extract positional information from the images taken by the UAV. With specially designed convolutional layers and spatial softmax layers, the visual positioning accuracy and computational efficiency are improved. Next, a reinforcement learning-based USV control strategy is proposed, which could learn a motion control policy with an enhanced ability to reject wave disturbances. The simulation experiment results show that the proposed visual navigation architecture can provide stable and accurate position and heading angle estimation in different weather and lighting conditions. The trained control policy also demonstrates satisfactory USV control ability under wave disturbances. • Cooperative USV–UAV systems for marine search and rescue. • Convolutional neural network with spatial softmax layers for visual navigation. • Reinforcement learning based USV control with disturbance rejection ability. [ABSTRACT FROM AUTHOR]

This article deals with the construction of a deep learning model based on convolutional networks for classifying images of melanocytic skin lesions. The results of preliminary tests on the original publicly available HAM10000 database are presented. In addition, experiments were performed on a set of images with different image resolutions and a data augmentation method was applied to balance the dataset within seven categories of melanocytic lesions. The results show high performance of the classifier, especially after data augmentation, where the Classification qualities, about 88-89% for the validation set and about 95-97% for the training set, were achieved. Various network architectures were used in the calculations, and the best one is presented in the paper. [ABSTRACT FROM AUTHOR]

The COVID-19 pandemic has radically changed our daily habits. One of these habits introduced is the use of a face mask, to avoid the spread of the infection, to be used especially in closed and crowded environments. To protect people and to counter the spread of COVID-19, in this paper we propose a method to automatically verify from images whether people are wearing a face mask. We designed a deep learning network to classify whether an image under analysis is with a mask or without a face mask. With the aim to provide explainability to the classifier decision, the proposed method is able to localise the areas of the image under analysis symptomatic of a certain prediction: in this way it is possible to understand the reason why the model predicts a certain label. The experimental analysis considers 7553 (with mask and without mask) images showing that the proposed approach is able to obtain interesting performances in face mask detection. [ABSTRACT FROM AUTHOR]

The economic and social effects from electric disruptions have been increasing. They can cause current and voltage interferences and result in disasters. Therefore, online assessment of transit stability is essential for the control of power systems, which can prevent transmission of power disturbances and enable operators to decide on emergency control measures. This paper proposes a power-disturbance-detection system to analyze online voltage signals and prevent transmission of disturbance signals. The system consists of four stages. The first stage is data augmentation, which adds noisy signals and more generated signals with multiple events with different magnitudes of disturbance time and locations. The second stage is data division, which partitions the generated dataset into trained and evaluated datasets. The third stage constructs convolutional neural network (CNN) architecture and trains it. The fourth stage develops the constructed CNN model into an electronic circuit to analyze the online voltage signal and prevent transmission of the disturbance signal. To investigate the suggested stages of the detection system, several experiments are conducted. The experimental results demonstrate that the proposed data augmentation stage provides a beneficial influence, and the proposed CNN model is architecturally efficient. It is not affected by the noise, period of modifications, or displacements of the disturbance signals in the real-time detection process. In addition, it obtained a clear improvement rate in the weighted accuracy metrics over the state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

In recent years, deep learning (DL) methods have proven their efficiency for various computer vision (CV) tasks such as image classification, natural language processing, and object detection. However, training a DL model is expensive in terms of both complexities of the network structure and the amount of labeled data needed. In addition, the imbalance among available labeled data for different classes of interest may also adversely affect the model accuracy. This paper addresses these issues using a new convolutional neural network (CNN) based architecture. The proposed network incorporates both spatial and spectral information that combines two sub-networks: spatial-CNN and spectral-CNN. The spectral-CNN extracts spectral information, while spatial-CNN captures spatial information. Moreover, to make the features more robust, a multiscale spatial CNN architecture is introduced using different kernels. The final feature vector is formed by concatenating the outputs obtained from both spatial-CNN and spectral-CNN. To address the data imbalance problem, a generative adversarial network (GAN) was used to generate data for the underrepresented class. Finally, relatively a shallower network architecture was used to reduce the number of parameters in the network and improve the processing speed. The proposed model was trained and tested on Senitel-2 images for the classification of the debris-covered glacier. The results showed that the proposed method is well-suited for mapping and monitoring debris-covered glaciers at a large scale with high classification accuracy. In addition, we compared the proposed method with conventional machine learning approaches, support vector machine (SVM), random forest (RF) and multilayer perceptron (MLP). [ABSTRACT FROM AUTHOR]

Recently, Convolutional neural network (CNN), a class of deep neural network, has been widely used for processing images and video data. The reason that CNN performs better than the classic neural network on images and video is basically because convolutional layers take advantage of the inherent properties of images. Therefore, in this paper, we propose and investigate two-step a cascaded classification model using CNN for the detection of gravitational wave (GW) signals emitting from the two different heavenly astronomical objects in the noisy time-series data. To build a robust model for the detection of GW waves, we considered prominent binary black holes (BBH) and binary neutron stars (BNS). In the proposed model, first, we used CNN to know whether in the noisy data stream, the considered GW signal is present or not. While in the second step, we further applied CNN to know that the present GW signal in the stream is BBH or BNS. The analysis shows that the proposed two-step cascaded classification model can detect not only the presence of the signal but also able to distinguish between the type of signal i.e., whether the gravitational wave signal is from BBH or BNS. [ABSTRACT FROM AUTHOR]

The management of an online footwear retail store - also known as marketplace - usually involves activities that directly or indirectly end up to interface with customers, wherein communication efficiency and effectiveness is crucially relevant. Critical factors concerning entities developing remote business in these areas or similar include: (i) production of appealing catalogues and (ii) digital tools to shorten the distance between customers and marketplaces. The former requires using specific third parties - often technically complex - to arrange and prepare photographic entries acquired in studio-like environments. This can delay the diffusion of products supply that may result in financial losses. The latter prevents the retailer of reaching critical mass at a higher potential. Considering such issues, this paper proposes a couple of modules for footwear marketplaces, powered by deep learning: one to segment shoes as a fully automatic background removal tool for easing and quickening catalogue creation activities in a back-office perspective; and another to provide visual search services that allow a customer to submit photographs of footwear of interest to obtain recommendations of similar products directly retrieved from online retail databases, establishing another digital bridge with potential buyers. Preliminary implementation and pilot tests point out Mask-RCNN as a promising approach for shoes segmentation. The same applies to ResNet101 and Xception, but for shoes recommendation, based on multi-label classification. [ABSTRACT FROM AUTHOR]

One of the critical issues in detecting depression is using facial expressions with image data classification. In This research paper, we proposed Fusion Fuzzy Logic((FFL) with deep learning for identifying depressed people based on their facial expressions. Our proposed model the based on an advanced fuzzy algorithm with deep learning for unordered fuzzy rule(FR) initiation to offer appropriate and suitable opinions based on depressed people's facial expressions(FE), to allow Depression Recognition(DR) from image files and recorded video files. The primary goal of this research work was to use the fusion method to turn these facial expressions (FE) into the detection of depressed states. To elevate the performance of the Fusion Fuzzy Logic((FFL) (fuzzy logic and CNN)), delivering them entreated them several times to imitate specific facial expressions. Our proposed FFL with the CNN model produces exact and dependable results with a 94.3% overall accuracy comparable to human recognition. [ABSTRACT FROM AUTHOR]

The standard approach for automated clinical image diagnosis is being held with the use of Convolutional Neural Networks (CNN) for a decade. Vision Transformers (ViT) are new in this domain and yield similar levels of performance to that of CNN making them a competitive alternative to CNNs. This paper proposes an alternative off-the-shelf ViT-based approach to detecting lung diseases. This approach has been compared with a CNN-based hybrid deep learning approach that outperforms existing different deep learning techniques. The hybrid deep learning model used for comparison is called Visual Geometric Group Data Spatial Transformer with CNN (VDSNet) and the experimental results are computed by using the open-source NIH chest X-rays dataset from Kaggle. In this study, we observe vision transformers that are pre-trained outperform CNN-based VDSNet in several metrics on full as well as different subsets of the dataset. Vision Transformers also show an increase in accuracy with the addition of internal layers and reduction in patch size at the expense of slightly higher training time making them a potential alternative to Convolutional Neural Networks. [ABSTRACT FROM AUTHOR]

The general method for classification of brain tumors is through biopsy, but biopsy is performed only after a surgery where a small tissue is removed from the brain and examined under a microscope to determine if it is a tumor. Due to the advancement in technology especially in machine learning and artificial intelligence, it is possible for us to determine and classify a tumor without performing any surgery and feeding the present data of various MRI images to the machine for classification. Through our work, we put forward a technique for the detection of tumors by using EfficientNet, a pre-trained model using the approach of transfer learning. This paper focuses on three models from the family of models of EfficientNet namely EfficientNet-B2, EfficientNet-B3, and EfficientNet-B4. The proposed framework not only uses the pre-trained model to improve the performance of training a better model but also uses thresholding to improve the dataset for better accuracy and data augmentation for increasing the number of images in the dataset. Preliminary outcome shows that the family of models of EfficientNet performs better than previous CNN architectures because to scale all dimensions of depth, width, and resolution of an image with a constant ratio it uses the compound coefficient. The results also demonstrated that by scaling the baseline architecture the model is able to capture complicated features and thus the overall performance of the model is improved. [ABSTRACT FROM AUTHOR]

With the advent of deep learning in recent years, the integration of computer vision with natural language processing has garnered a lot of attention. Generating descriptions from images is one of the most intriguing and focused areas of Machine Learning that faces a number of obstacles, particularly when describing images in languages other than English. In image captioning, a computer is trained to understand the visual information of an image and then generate a description based on the image features and reference sentences. Having an application that automatically describes events in their environment and then translates them into a caption or message can make a significant contribution to society. This paper presents a multi-layered CNN-LSTM neural network model that is utilized to recognize and generate Hindi captions for the objects in images. In addition, a variety of models were trained by adjusting hyperparameters and the number of hidden layers to find the optimum model and maximize the likelihood of the resultant Hindi description. Moreover, after testing the effectiveness of our models, it was observed that our model has shown an increase of 34.64% and 29.13% in terms of BLEU score (Unigram) and BLEU score (Bigram) respectively when compared to the existing work done in this field. Image captioning in Hindi can have a multitude of applications in today's society, and it can also provide a user-friendly interface for Hindi speakers. [ABSTRACT FROM AUTHOR]

Skin cancer has been one of the major worldwide public health issue with more than 1 million cases every year. Skin cancer is classified into three categories: Basal Cell Carcinoma, Melanoma and Squamous Cell Carcinoma [ 1 ]. Melanoma is the most critical category of skin cancer with very thin chances of recovery and survival of the patient. Early diagnosis of skin cancer can drastically improve survival rate to as high as 95 percent. This served as a motivation to contribute to this noble cause using technology based solutions. In the process of diagnosis for the disease, the process is divided into four basic components: image processing including hair removal, noise removal, sharpening, and increasing the resolution of the image given to the skin dimension. Recent developments in identification of skin cancer technology uses machine learning and in-depth based reading segmentation algorithms. Most used algorithms are: InceptionV3, ResNet, VGGNet. This paper suggests an artificial skin cancer screening process using techniques like image processing and machine learning. Image super-resolution (ISR) techniques recreate an image with high resolution or sequence from visual LR images. An approach using deep learning on the Image super resolution was used to boost the accuracy of the convolutional neural network model. This model was developed using the Keras backend and tested the model by modifying the layers of neural network which are used for training. The model is built on publicly sourced dataset from the ISIC data archives. [ABSTRACT FROM AUTHOR]

Smart manufacturing uses emerging deep learning models, and particularly Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs), for different industrial diagnostics tasks, e.g., classification, detection, recognition, prediction, synthetic data generation, security, etc., on the basis of image data. In spite of being efficient for these objectives, the majority of current deep learning models lack interpretability and explainability. They can discover features hidden within input data together with their mutual co-occurrence. However, they are weak at discovering and making explicit hidden causalities between the features, which could be the reason behind the particular diagnoses. In this paper, we suggest Causality-Aware CNNs (CA-CNNs) and Causality-Aware GANs (CA-GANs) to address the issue of learning hidden causalities within images. The core architecture includes an additional layer of neurons (after the last convolution-pooling and just before the dense layers), which learns pairwise conditional probabilities (aka causality estimates) for the features. Computations for these neurons are driven by the adaptive Lehmer mean function. Learned causalities are merged with the features during flattening and (via fully connected layers) influence the classification outcomes. Such causality estimates can be done for the mixed inputs where images are combined with other data. We argue that CA-CNNs not only improve the classification performance of normal CNNs but also open additional opportunities for the explainability of the models' outcomes. We consider as an additional advantage for CA-CNNs (if used as a discriminator within CA-GANs) the possibility to generate realistically looking images with respect to the causalities. [ABSTRACT FROM AUTHOR]

In recent years, artificial intelligence (AI) has been developed vigorously, and a great number of AI autonomous applications have been proposed. However, how to decrease computations and shorten training time with high accuracy under the limited hardware resource is a vital issue. In this paper, on the basis of MobileNet architecture, the dense squeeze with depthwise separable convolutions model is proposed, viz. MiniNet. MiniNet utilizes depthwise and pointwise convolutions, and is composed of the dense connection technique and the Squeeze-and-Excitation operations. The proposed MiniNet model is implemented and experimented with Keras. In experimental results, MiniNet is compared with three existing models, i.e., DenseNet, MobileNet, and SE-Inception-Resnet-v1. To validate that the proposed MiniNet model is provided with less computation and shorter training time, two types as well as large and small datasets are used. The experimental results showed that the proposed MiniNet model significantly reduces the number of parameters and shortens training time efficiently. MiniNet is superior to other models in terms of the lowest parameters, shortest training time, and highest accuracy when the dataset is small, especially. [ABSTRACT FROM AUTHOR]

Nowadays, standard intake of healthy food is necessary for keeping a balanced diet to avoid obesity in the human body. In this paper, we present a novel system based on machine learning that automatically performs accurate classification of food images and estimates food attributes. This paper proposes a deep learning model consisting of a convolutional neural network that classifies food into specific categories in the training part of the prototype system. The main purpose of the proposed method is to improve the accuracy of the pre-training model. The paper designs a prototype system based on the client server model. The client sends an image detection request and processes it on the server side. The prototype system is designed with three main software components, including a pre-trained CNN model training module for classification purposes, a text data training module for attribute estimation models, and a server-side module. We experimented with a variety of food categories, each containing thousands of images, and through machine learning training to achieve higher classification accuracy. [ABSTRACT FROM AUTHOR]

A bacterial infection named Tuberculosis is a persistent disease that has caused a large number of deaths worldwide according to WHO's data. This disease is caused by a particular bacteria called Mycobacterium which usually affects the lungs. If early treatments are not provided to the patients it may result in fatality. So, early diagnosis and treatment are crucial. In this paper, we present a new and better way of automated detection of tuberculosis using a Deep Learning method known as the Antialiased Convolution Neural Networks proposed by Richard Zhang in his Research Paper titled "Making Convolution Neural Networks Shift-Invariant Again". The objective of this task is the detection of tuberculosis lesions in the lungs using Image Segmentation and then using the trained models and the metadata the patient cases were classified to tuberculosis of low or high severity. The data in consideration here is the ImageCLEF med Tuberculosis 2019 data set. The data set comprises of 3D CT images. So, here the 3D images were split into 2D slices and segmentation was applied to each slicing using UNet, FPN, and LinkNet architecture. For better accuracy and predictions Antialiased Convolution Neural Networks based on shift-invariant pooling is applied instead of the conventional Convolution Neural Networks. Here the Antialiased Convolution Neural Networks provided better results. This is a generalized attempt on our end which can be applied for other similar and related datasets as well. [ABSTRACT FROM AUTHOR]

Recently, deep learning has proven to be a successful technique especially in medical image analysis. This paper aims to highlight the importance of deep learning architectures in lung disease diagnosis using CXR images. Related articles were identified through searches of electronic resources, including IEEE, Springer, Elsevier, PubMed, Nature and, Hindawi digital library. The inclusion of articles was based on high-performance artificial intelligence models, developed for the classification of possible findings in CXR images published from 2018 to 2023. After the quality assessment of papers, 129 articles were included according to PRISMA guidelines. Papers were studied by types of lung disease, data source, algorithm type, and outcome metrics. Three main categories of computer-aided lung disease detection were covered: traditional machine learning, deep learning-based methods, and combination of aforementioned methods for all lung diseases. The results showed that various pre-trained networks including ResNet, VGG, and DenseNet, are the most frequently used CNN architectures and would result in a notable increase in sensitivity and accuracy. Recent research suggests that utilizing a combination of deep networks with a robust machine learning classifier can outperform deep learning approaches that rely solely on fully connected neural networks as their classifier. Finally, the limitations of the existing literature and potential future research opportunities in possible findings in CXR images using deep learning architectures are discussed in this systematic review. • A systematic review based on PRISMA framework on machine learning applications to analyze chest X-ray images. • Trends of architectures used in last 5 years. • Preprocessing and processing techniques used by the researchers. • Future trends and open problems. [ABSTRACT FROM AUTHOR]

This paper proposes a robust algorithm using two convolutional neural networks (CNN) to find a lost gamma source in a room despite various unpredictable obstacles. This algorithm is an improved and complementary method to our previous research, which does not limit the use of the algorithm to a specific geometry, and the presence of obstacles does not reduce the performance and inability of the method. In our previous research, an algorithm including a CNN was used to estimate the location of the lost gamma source in known geometry. In this paper, by adding another CNN to the previous algorithm, the algorithm can be used in environments with unknown geometry. The environmental simulations and data generation are performed using the Geant4 simulation program. The method has been tested in a designed scenario to check its effectiveness. The results show that by using these two CNNs, an agent can intelligently find the gamma source place in a room with multiple obstacles without human intervention with 95 percent accuracy. [ABSTRACT FROM AUTHOR]

In this paper, a new crude oil price forecasting model using data embedding and Convolutional Neural Network has been proposed to predict more accurate crude oil price movement. It uses the time delayed embedding technique to transform the data into two-dimensional phase space. The Convolutional Neural Network model is used to extract the main data characteristics more effectively, taking advantage of the hierarchical feature extraction and modeling capability of CNN model. Empirical evaluation of the performance of the proposed TDE-CNN model has been conducted using daily price observations in West Taxes Intermediate market. Experiment results confirm that the TDE-CNN forecasting model produces forecasts with the improved forecasting accuracy. [ABSTRACT FROM AUTHOR]

Time series(TS) forecasting has been widely applied in many fields and industrial soft sensor is one of them. Most time series modeling methods require that all inputs are sampled at equal intervals. However, in industry, the process variables are often sampled on different time scales with varying intervals. To address this problem, in this paper, we designed a framework using deep learning with time representation techniques to model the long temporal industrial data with multiple sampling frequency. Data are aggregated into different time scale by time representation and the network extracts the information on both temporal and spatial dimensions simultaneously using the bottleneck layer and one-dimensional filter. The proposed model has a significant improvement compared with other methods and has been deployed in the factory and updated every month. [ABSTRACT FROM AUTHOR]

The present paper suggests a hybrid solution to address two key authentication challenges: data privacy and the limitations of mobile devices resources. The former is addressed using Partially Homomorphic Encryption based on Paillier Algorithm for the encryption. While the latter is handled using a combination of Deep Convolutional Neural Network and Local Ternary Pattern for face recognition. We compare the accuracy and performance of our proposed solution to others proposed by the literature on ORL dataset and Extended Yale data set. Our findings suggest our proposed methods return higher recognition rates including 98.75% on encrypted ORL data set and 98.78% on encrypted Extended Yale data. In contrast, the existing methods achieved lower recognition rates, which have achieved only 92.50% and 95.44% of recognition rates on encrypted ORL and Extended Yale data set, respectively. [ABSTRACT FROM AUTHOR]

The statistical variability of electroencephalographic (EEG) signals across individuals poses a common challenge for brain–computer interfaces (BCI). Specifically, the reuse of pre-recorded data from previous subjects presents a significant obstacle in decoding new subjects. To address these challenges, this paper introduces EEGTransferNet, an end-to-end modular transfer learning framework that enhances the similarity of statistical distributions across subjects. It utilizes convolutional neural networks as backbones for feature extraction and incorporates statistical distribution alignment and domain adaptation in different network layers to learn general features and domain-specific features respectively. The robust generalization design of EEGTransferNet enables it to handle multiple BCI paradigms using a single network making it efficient and effective. Its modular structure facilitates customization of backbone and transfer modules for diverse tasks. The optimal structure of EEGTransferNet was determined through analysis and extensive experimentation. We validated it on motor imagery (MI), error-related negativity (ERN), and rapid serial visual presentation (RSVP) datasets, which exhibits competitive performance compared to state-of-the-art methods. The experimental results confirm the effectiveness and superiority of EEGTransferNet. [ABSTRACT FROM AUTHOR]

Architectural floor plans are essential documents for conveying building information among designers, engineers, and clients. Automated analysis of floor plans enhances user productivity and accuracy, though research on automatic object detection within architectural floor plans has been limited. In this paper, a convolutional neural network (CNN) based architecture, ArchNetv2, is proposed to detect various visual objects, such as stairs, windows, and doors. The proposed ArchNetv2 includes a convolutional block attention module to improve feature learning. It works at multiple detection scales and can efficiently recognize large objects (e.g., stairs) and small objects (e.g., windows) simultaneously. Experimental results show that ArchNetv2 can recognize thirteen types of objects commonly found in architectural floor plans with a mAP of 93.5%, which is superior compared to the state-of-the-art techniques. The proposed architecture can serve as an important module in an automated floor plan analysis system. • Novel technique for detecting 13 object types in a complex floor plan image. • The proposed technique is based on an efficient deep learning network. • The mean average precision for object detection is over 93%. • The technique is very fast and requires less than 100 ms for one image on a typical desktop computer. [ABSTRACT FROM AUTHOR]

• To develop a hybrid deep learning model for student behavior analysis. • To develop an Opposition-based Food Foraging-Pelican Optimizer (O-FFPO) algorithm. • To carry out optimal feature selection by utilizing developed O-FFPO algorithm. • To develop an O-FFPO to enhance the classification performance of developed model. • To adopt a Radian Basis-Recurrent Neural Networks (RB-RNN) deep learning model. With the development of the internet, e-learning is rapidly growing in worldwide, which pave more attention to the students. Further, the learning materials like video lectures, shared assignments as well as lecture slides are performed during the online courses. Moreover, these activities among the students exhibit different behaviors. Hence, the analysis of student behavior becomes complicated in the existing models. This research focuses on developing a deep learning model for analyzing student behaviour in an accurate manner. This paper aims to develop a new student behavior prediction model for E-learning by evaluating brain signals and chatbot interaction. This suggested model collects data from both chatbots and the Brain waves of students. The collected textual data from the chatbot are forwarded to the feature extraction phase by word2vector and bag-of-n grams. Then, the optimal features are selected using an Opposition-based Food Foraging-Pelican Optimizer (O-FFPO). Similarly, the second set of Brain waves of students are forwarded to the phase feature extraction stage by Short-time Fourier transforms (STFT), and then, deep features are extracted using Convolutional Neural Network (CNN). These gathered data can also be forwarded to the optimal feature selection process using the same O-FFPO. Finally, these fused features are fed to Radian Basis-Recurrent Neural Networks (RB-RNN) to get student behaviors, where the constraints are optimized by the same O-FFPO. Various performance metrics are compared and validated with the existing approaches. Moreover, the developed model shows 95% and 93% concerning accuracy and F1-score. Finally, experimental evaluation was carried out with the estimation of both brain waves and chatbot queries of students. [ABSTRACT FROM AUTHOR]

Surveillance video can capture a variety of realistic scenarios for providing security in both private and public spaces. The prediction of anomalies promptly is essential. However, existing methods are time-consuming due to marking conflicting clips in training videos. Therefore, this paper proposes a CBVR (Content-Based Video Retrieval) framework for detecting anomalies in surveillance videos. The proposed method leverages deep learning techniques and the HNSW (Hierarchical Navigable Small World) index to achieve efficient and accurate video retrieval. To preprocess the video data, frames are resized and normalized, and the dataset is augmented with data transformations such as rotations, translations, and flips to improve model generalization. The best results are offered while evaluating with the UCSD Ped2 dataset which produces the MAP score of 94.25%, and recall, precision, and F1-scores of 96.15%, 98.03%, and 92.63% respectively. The results proved that maximizing the number of layers in the HNSW index enhances the MAP score, suggesting that deeper layers are more effective at retrieving relevant results. Overall, the proposed CBVR framework provides an efficient and accurate method for anomaly detection in surveillance videos. It has potential applications in various domains, including video summarization, recommendation, and surveillance, among others. [ABSTRACT FROM AUTHOR]

Accurate positioning of curtain wall frames is crucial for the automated installation of curtain wall modules. However, the current robot-based installation methods overly depend on visual guidance from operators, resulting in high costs and limiting construction efficiency. The development of deep learning has introduced an image segmentation approach that offers a new solution for the visual positioning of curtain wall frames. This paper proposes a context collaboration pyramid network to automatically segment curtain wall frames by incorporating context interaction and channel guided pyramid structure. The model adopts an "encoder-decoder" architecture with a feature interaction block strategically inserted between the encoder and decoder. Specifically, the encoder utilizes the pyramid pooling Transformer as a backbone to extract multi-level features from original RGB images. The decoder employs a channel guided pyramid convolution module to integrate multi-scale features and achieve finer prediction. Meanwhile, a context interaction fusion module between the features of adjacent levels was designed carefully to enhance the collaboration of the architecture. In addition, a benchmark dataset for the curtain wall frame segmentation task, consisting of 1547 images, was established. The dataset incorporates challenging scenarios, including strong lights, low contrast, and cluttered backgrounds. This method is evaluated on the collected dataset, and achieves an impressive accuracy of 97.30% and an F1-Score of 88.95%, outperforming other segmentation networks. Overall, the proposed method can extract target information accurately and efficiently and provide critical visual guidance for the robot, so as to promote the automatic installation level of the curtain wall module. [ABSTRACT FROM AUTHOR]

Macrodispersivity is critical for predicting solute behaviors with dispersive transport models. Conventional methods of estimating macrodispersivity usually need to solve flow equations and are time-consuming. Convolutional neural networks (CNN) have recently been proven capable of efficiently mapping the hydraulic conductivity field and macrodispersivity. However, the mapping accuracy still needs further improvement. In this paper, we present a new network shortcut connection style called weighted multi-scale connections (WMC) for convolutional neural networks to improve mapping accuracy. We provide empirical evidence showing that the WMC can improve the performance of CNN in macrodispersivity estimation by implementing the WMC in CNNs (CNN without short-cut connections, ResNet, and DenseNet), and evaluating them on datasets of macrodispersivity estimation. For the CNN without short-cut connections, the WMC can improve the estimating R2 by at least 3% on three datasets of conductivity fields. For ResNet18, the WMC improved the estimated R2 by an average of 2.5% on all three datasets. For ResNet34, the WMC improved the estimated R2 by an average of 5.6%. For ResNet50, the WMC improved the estimated R2 by an average of 16%. For ResNet101, the WMC improved the estimating R2 by an average of 30%. For DenseNets, the improved estimated R2 ranges from 0.5% to 5%. The WMC can strengthen feature propagation of different sizes and alleviate the vanishing-gradient issue. Moreover, it can be implemented to any CNN with down-sampling layers or blocks. • We proposed a short-cut connection (WMC) to improve the performance of CNN in macrodispersivity estimation. • We validated the effectiveness of WMC in ResNet and DenseNet. • The WMC can be implemented in any CNN with down-scaling layers. [ABSTRACT FROM AUTHOR]

Regular patrol inspection of concrete dams can detect cracks at an early stage. However, conventional crack segmentation models based on deep learning (DL) are difficult to be deployed in resource-constrained mobile devices due to the large number of parameters. This paper describes a lightweight semantic segmentation model, termed as CrackTrNet, for images of concrete dam cracks. CrackTrNet is a hybrid U-shaped model based on convolutional neural network (CNN) and Vision Transformer. The CNN is adopted to extract low-level visual features and the Transformer focuses on learning the global contextual information. The results demonstrate that its segmentation accuracy can reach 97.60%, while the model size is only 34.86 MB, which is 66.12%–87.85% lower than that of current mainstream DL-based models. To make the model more practical, a crack inspection mobile application (APP) is developed using Android Studio. The integration of lightweight CrackTrNet and APP can effectively assist the intelligent inspection of dam cracks to ensure structural safety. • A lightweight hybrid network, CrackTrNet, is presented for semantic segmentation of dam cracks. • The integration of CNN and Transformer maximizes the preservation of global and local features. • Transfer learning and depthwise separable convolution are introduced to optimize the model size. • The mobile application is developed to assist patrol inspection of cracks in concrete dams. [ABSTRACT FROM AUTHOR]