Search

Flat bands in 2D twisted materials are key to the realization of correlation-related exotic phenomena. However, a flat band often was achieved in the large system with a very small twist angle, which enormously increases the computational and experimental complexity. In this work, we proposed group-V twisted bilayer materials, including P, As, and Sb in the β phase with large twist angles. The band structure of twisted bilayer materials up to 2524 atoms has been investigated by a deep learning method DeepH, which significantly reduces the computational time. Our results show that the bandgap and the flat bandwidth of twisted bilayer β-P, β-As, and β-Sb reduce gradually with the decreasing of twist angle, and the ultra-flat band with bandwidth approaching 0 eV is achieved. Interestingly, we found that a twist angle of 9.43° is sufficient to achieve the band flatness for β-As comparable to that of twist bilayer graphene at the magic angle of 1.08°. Moreover, we also find that the bandgap reduces with decreasing interlayer distance while the flat band is still preserved, which suggests interlayer distance as an effective routine to tune the bandgap of flat band systems. Our research provides a feasible platform for exploring physical phenomena related to flat bands in twisted layered 2D materials. [ABSTRACT FROM AUTHOR]

Deep learning (DL)-based approaches are notable for their ability to establish feature associations without relying on physical constraints, unlike traditional strategies that are complex and dependent on expert experience. However, three main challenges hinder the versatility of semantic segmentation models. First, the targets in these images are dense and exist at varying spatial scales, which imposes higher demands on the model for accurate segmentation across scales. Second, the segmentation of small targets in the images is often overlooked, leading to a compromise between fine segmentation and model efficiency. Lastly, the data-intensive nature of remote sensing images and the resource-intensive operations of large-scale networks impose significant communication and computation burdens on edge devices, which may not have sufficient resources to handle them effectively. To address these challenges, this paper proposes a lightweight semantic segmentation method for remote sensing images to achieve high-precision segmentation for multi-scale targets while maintaining low computational complexity. The main components include: (1) embedding the inverted residual block structure to minimize the number of model parameters and computational costs; (2) introducing the parallel irregular space pyramid pooling module to efficiently aggregate multi-scale contextual information for fine-grained recognition of small targets; and (3) embedding transfer learning into the encoder-decoder structure to speed up the convergence rate and improve multi-scale feature fusion capability, thereby reducing semantic information loss. The proposed lightweight method has been extensively tested on real-world high-resolution remote sensing datasets. It achieved PA, MPA, MIoU, and FWIoU scores of 87.90%, 75.76%, 66.29%, and 78.81% on the Vaihingen dataset; 87.03%, 85.31%, 74.85%, and 77.54% on the Potsdam dataset; and 95.37%, 83.33%, 75.70%, and 91.31% on the Aeroscapes dataset. Compared to other popular semantic segmentation models, the proposed method achieved the highest values in all four evaluation indicators, demonstrating its effectiveness and superiority. [ABSTRACT FROM AUTHOR]

The purpose of long-term forecasting is to meet the needs of practical applications, such as the prediction of the development trend of infectious diseases and the planning of electricity consumption. In this paper, we study the long-term forecasting of time series. Studies have shown that previous Transformer-based models have the potential to improve prediction capabilities, but there are also some problems, such as the lack of location information and the slow training speed. To solve these problems, we designed an efficient Transformer-based model called AD-Autoformer, which is specifically designed for long-term series prediction. By introducing position embedding, the model can better understand the patterns and relationships in the sequence, to improve the performance and generalization ability of the model when processing sequence data, and the self-attention distilling mechanism realizes the compression and acceleration of the model by halving the cascading layer input to highlight the dominant attention. This method significantly reduces the computational complexity of the model and improves the training speed of the model while maintaining the performance of the model. Experimental results on five large datasets show that the proposed AD-Autoformer model has different degrees of improvement in MSE and MAE indicators compared with other benchmark methods. [ABSTRACT FROM AUTHOR]

Printed circuit boards (PCBs) play a critical role in electronic products. Ensuring these products' long-term reliability and consistent performance requires effective PCB defect detection. Although existing deep learning models for PCB defect detection are not highly accurate, they often neglect capability considerations. This paper introduces a precise, fast, and lightweight defect detection model, CCG-YOLO, based on an enhanced YOLOv5 model to address this issue. The enhancements in CCG-YOLO can be summarized as follows: (1) Improved Backbone network: The feature extraction ability of the Backbone network is enhanced by introducing a C3HB module, which fosters spatial interaction capabilities. (2) Lightweight feature fusion network: A lightweight convolution structure called Ghost-Shuffle Convolution is incorporated in the feature fusion network, remarkably reducing model parameters while maintaining performance. (3) Efficient residual networking: To enhance model performance further, a CNeB module is introduced based on the ConvNeXt network, which replaces the C3 module in the Neck. CNeB improves model detection accuracy and reduces the number of model parameters. The combination of these enhancements results in impressive performance. CCG-YOLO achieves mean average precision (mAP@0.5) of 99.5% and 88.75% in mAP@0.5:0.95 on the TDD-Net public dataset. Compared with the original YOLOv5s algorithm, CCG-YOLO offers a 4.24% improvement in mAP@0.5:0.95, a 1 MB reduction in model size, a 0.472 M decrease in the number of parameters, a 0.6G floating point operation reduction in computational complexity, and a 120 frames per second real-time inference speed. These experimental results underscore that the proposed model excels in accuracy and speed and has a compact size for PCB defect detection. Moreover, CCG-YOLO is easily deployable on low-end devices, making it well-suited for meeting the real-time requirements of industrial defect detection. [ABSTRACT FROM AUTHOR]

Gait recognition is a long-distance biometric technique with significant potential for applications in crime prevention, forensic identification, and criminal investigations. Existing gait recognition methods typically introduce specific feature refinement modules on designated models, leading to increased parameter volume and computational complexity while lacking flexibility. In response to this challenge, we propose a novel framework called GaitAE. GaitAE efficiently learns gait representations from large datasets and reconstructs gait sequences through an autoencoder mechanism, thereby enhancing recognition accuracy and robustness. In addition, we introduce a horizontal occlusion restriction (HOR) strategy, which introduces horizontal blocks to the original input sequences at random positions during training to minimize the impact of confounding factors on recognition performance. The experimental results demonstrate that our method achieves high accuracy and is effective when applied to existing gait recognition techniques. [ABSTRACT FROM AUTHOR]

The utilization of Synthetic Aperture Radar (SAR) for real-time ship detection proves highly advantageous in the supervision and monitoring of maritime activities. Ship detection in the range-compressed domain of SAR rather than in fully focused SAR imagery can significantly reduce the time and computational resources required for complete SAR imaging, enabling lightweight real-time ship detection methods to be implemented on an airborne or spaceborne SAR platform. However, there is a lack of lightweight ship detection methods specifically designed for the SAR range-compressed domain. In this paper, we propose Fast Range-Compressed Detection (FastRCDet), a novel lightweight network for ship detection in the SAR range-compressed domain. Firstly, to address the distinctive geometric characteristics of the SAR range-compressed domain, we propose a Lightweight Adaptive Network (LANet) as the backbone of the network. We introduce Arbitrary Kernel Convolution (AKConv) as a fundamental component, which enables the flexible adjustment of the receptive field shape and better adaptation to the large scale and aspect ratio characteristics of ships in the range-compressed domain. Secondly, to enhance the efficiency and simplicity of the network model further, we propose an innovative Multi-Scale Fusion Head (MSFH) module directly integrated after the backbone, eliminating the need for a neck module. This module effectively integrates features at various scales to more accurately capture detailed information about the target. Thirdly, to further enhance the network's adaptability to ships in the range-compressed domain, we propose a novel Direction IoU (DIoU) loss function that leverages angle cost to control the convergence direction of predicted bounding boxes, thereby improving detection accuracy. Experimental results on a publicly available dataset demonstrate that FastRCDet achieves significant reductions in parameters and computational complexity compared to mainstream networks without compromising detection performance in SAR range-compressed images. FastRCDet achieves a low parameter of 2.49 M and a high detection speed of 38.02 frames per second (FPS), surpassing existing lightweight detection methods in terms of both model size and processing rate. Simultaneously, it attains an average accuracy (AP) of 77.12% in terms of its detection performance. This method provides a baseline in lightweight network design for SAR ship detection in the range-compressed domain and offers practical implications for resource-constrained embedded platforms. [ABSTRACT FROM AUTHOR]

Steganalysis techniques play a crucial role in forensic investigation, aiding professionals in identifying digital images with unsafe content. This work proposes a novel and improved lightweight deep-learning convolution neural network architecture called CIRNet, which provides universal steganalysis capabilities. CIRNet leverages inverted residual blocks integrated with a self-attention mechanism that effectively minimises the detection error rate and the computational complexity for steganalysis. The inverted residual blocks include lightweight depth-wise and point-wise convolutions supplemented by a self-attention module. This integration strengthens the saliency of feature maps corresponding to the embedding regions while reducing the network's parameters and the total floating-point operations. Consequently, CIRNet achieves superior accuracy, making it an excellent choice for deployment on lightweight smart mobile systems. Experimental results validate the superiority of the proposed CIRNet over several state-of-the-art deep-learning networks commonly employed in steganalysis. The results further demonstrate the enhanced generalisation ability, particularly when applied to diverse datasets generated from BOSSbase 1.01 and BOWS2 using HUGO, WOW, and S-UNIWARD steganography methods with two distinct payloads. These findings establish CIRNet as an efficient and elite performer in the domain of lightweight steganalysis. [ABSTRACT FROM AUTHOR]

Hand pose estimation is a fundamental task in computer vision with applications in virtual reality, gesture recognition, autonomous driving, and virtual surgery. Keypoint detection often relies on deep learning methods and high-resolution feature map representations to achieve accurate detection. The HRNet framework serves as the basis, but it presents challenges in terms of extensive parameter count and demanding computational complexity due to high-resolution representations. To mitigate these challenges, we propose a lightweight keypoint detection network called LGCANet (Lightweight Ghost-Coordinate Attention Network). This network primarily consists of a lightweight feature extraction head for initial feature extraction and multiple lightweight foundational network modules called GCAblocks. GCAblocks introduce linear transformations to generate redundant feature maps while concurrently considering inter-channel relationships and long-range positional information using a coordinate attention mechanism. Validation on the RHD dataset and the COCO-WholeBody-Hand dataset shows that LGCANet reduces the number of parameters by 65.9% and GFLOPs by 72.6% while preserving the accuracy and improves the detection speed. [ABSTRACT FROM AUTHOR]

Speech enhancement performance has improved significantly with the introduction of deep learning models, especially methods based on the Long–Short-Term Memory architecture. However, these methods face challenges such as high computational complexity and redundancy of input features. To address these issues, we propose a U-Net-based approach that utilizes an encoder/decoder to extract more concise features, thereby enhancing single-channel speech performance and reducing computation complexity. The proposed method includes a Cross-Swin-Transformer block and a masked bottleneck module, which down-samples features while preserving the detailed representation through skip connections and carefully designed blocks. The bottleneck module extracts coarse representations of hidden features as masks. We evaluated our method against other U-Net-based approaches on VCTK and DNS corpora using CBAK, eSTOI, PESQ, STOI, and SI-SDR metrics. The results demonstrate that the proposed method achieves promising performance while significantly reducing computational complexity. [ABSTRACT FROM AUTHOR]

Reconfigurable intelligent surface (RIS) is one of the promising technologies for sixth generation communications due to its advantages including energy saving, high spectral efficiency, etc. However, the non-convex joint beamforming design is a challenge, especially in the multi-hop RIS-assisted communication system. This paper proposes a deep learning-based joint beamforming (DLBF) design, aiming to maximize the system data rate for multi-hop RIS-aided communication systems. The proposed DLBF design consists of the reflection matrices design of all RISs and the transmit beamforming design at the base station, which has a reduced computational complexity. Numerical results show that the proposed DLBF can achieve 1.8 bit/s/Hz sum rate gain compared to the conventional beamforming method for the two-user scenario, which can be enhanced by large-scale users. The sum rate performance can be improved by increasing the number of RISs due to the reflection gain, and corresponding results provide a guidance of the multi-hop number selection for further investigation. [ABSTRACT FROM AUTHOR]

Several studies have attempted to solve traveling salesman problems (TSPs) using various deep learning techniques. Among them, Transformer-based models show state-of-the-art performance even for large-scale Traveling Salesman Problems (TSPs). However, they are based on fully-connected attention models and suffer from large computational complexity and GPU memory usage. Our work is the first CNN-Transformer model based on a CNN embedding layer and partial self-attention for TSP. Our CNN-Transformer model is able to better learn spatial features from input data using a CNN embedding layer compared with the standard Transformer-based models. It also removes considerable redundancy in fully-connected attention models using the proposed partial self-attention. Experimental results show that the proposed CNN embedding layer and partial self-attention are very effective in improving performance and computational complexity. The proposed model exhibits the best performance in real-world datasets and outperforms other existing state-of-the-art (SOTA) Transformer-based models in various aspects. Our code is publicly available at https://github.com/cm8908/CNN_Transformer3. [ABSTRACT FROM AUTHOR]

Wireless Sensor Networks (WSNs) play a vital role in various applications, necessitating robust network security to protect sensitive data. Intrusion Detection Systems (IDSs) are crucial for preserving the integrity, availability, and confidentiality of WSNs by detecting and countering potential attacks. Despite significant research efforts, the existing IDS solutions still suffer from challenges related to detection accuracy and false alarms. To address these challenges, in this paper, we propose a Bayesian optimization-based Deep Learning (DL) model. However, the proposed optimized DL model, while showing promising results in enhancing security, encounters challenges such as data dependency, computational complexity, and the potential for overfitting. In the literature, researchers have employed Reinforcement Learning (RL) to address these issues. However, it also introduces its own concerns, including exploration, reward design, and prolonged training times. Consequently, to address these challenges, this paper proposes an Innovative Integrated RL-based Advanced DL Algorithm (IRADA) for attack detection in WSNs. IRADA leverages the convergence of DL and RL models to achieve superior intrusion detection performance. The performance analysis of IRADA reveals impressive results, including accuracy (99.50%), specificity (99.94%), sensitivity (99.48%), F1-Score (98.26%), Kappa statistics (99.42%), and area under the curve (99.38%). Additionally, we analyze IRADA's robustness against adversarial attacks, ensuring its applicability in real-world security scenarios. [ABSTRACT FROM AUTHOR]

Human activity recognition (HAR) is a crucial task in various applications, including healthcare, fitness, and the military. Deep learning models have revolutionized HAR, however, their computational complexity, particularly those involving BiLSTMs, poses significant challenges for deployment on resource-constrained devices like smartphones. While BiLSTMs effectively capture long-term dependencies by processing inputs bidirectionally, their high parameter count and computational demands hinder practical applications in real-time HAR. This study investigates the approximation of the computationally intensive BiLSTM component in a HAR model by using a combination of alternative model components and data flipping augmentation. The proposed modifications to an existing hybrid model architecture replace the BiLSTM with standard and residual LSTM, along with convolutional networks, supplemented by data flipping augmentation to replicate the context awareness typically provided by BiLSTM networks. The results demonstrate that the residual LSTM (ResLSTM) model achieves superior performance while maintaining a lower computational complexity compared to the traditional BiLSTM model. Specifically, on the UCI-HAR dataset, the ResLSTM model attains an accuracy of 96.34% with 576,702 parameters, outperforming the BiLSTM model's accuracy of 95.22% with 849,534 parameters. On the WISDM dataset, the ResLSTM achieves an accuracy of 97.20% with 192,238 parameters, compared to the BiLSTM's 97.23% accuracy with 283,182 parameters, demonstrating a more efficient architecture with minimal performance trade-off. For the KU-HAR dataset, the ResLSTM model achieves an accuracy of 97.05% with 386,038 parameters, showing comparable performance to the BiLSTM model's 98.63% accuracy with 569,462 parameters, but with significantly fewer parameters. [ABSTRACT FROM AUTHOR]

Data and reports indicate an increasing frequency and intensity of natural disasters worldwide. Buildings play a crucial role in disaster responses and damage assessments, aiding in planning rescue efforts and evaluating losses. Despite advances in applying deep learning to building extraction, challenges remain in handling complex natural disaster scenes and reducing reliance on labeled datasets. Recent advances in satellite video are opening a new avenue for efficient and accurate building extraction research. By thoroughly mining the characteristics of disaster video data, this work provides a new semantic segmentation model for accurate and efficient building extraction based on a limited number of training data, which consists of two parts: the prediction module and the automatic correction module. The prediction module, based on a base encoder–decoder structure, initially extracts buildings using a limited amount of training data that are obtained instantly. Then, the automatic correction module takes the output of the prediction module as input, constructs a criterion for identifying pixels with erroneous semantic information, and uses optical flow values to extract the accurate corresponding semantic information on the corrected frame. The experimental results demonstrate that the proposed method outperforms other methods in accuracy and computational complexity in complicated natural disaster scenes. [ABSTRACT FROM AUTHOR]

Streaming data are present all around us. From traditional radio systems streaming audio to today's connected end-user devices constantly sending information or accessing services, data are flowing constantly between nodes across various networks. The demand for appropriate outlier detection (OD) methods in the fields of fault detection, special events detection, and malicious activities detection and prevention is not only persistent over time but increasing, especially with the recent developments in Telecommunication systems such as Fifth Generation (5G) networks facilitating the expansion of the Internet of Things (IoT). The process of selecting a computationally efficient OD method, adapted for a specific field and accounting for the existence of empirical data, or lack thereof, is non-trivial. This paper presents a thorough survey of OD methods, categorized by the applications they are implemented in, the basic assumptions that they use according to the characteristics of the streaming data, and a summary of the emerging challenges, such as the evolving structure and nature of the data and their dimensionality and temporality. A categorization of commonly used datasets in the context of streaming data is produced to aid data source identification for researchers in this field. Based on this, guidelines for OD method selection are defined, which consider flexibility and sample size requirements and facilitate the design of such algorithms in Telecommunications and other industries. [ABSTRACT FROM AUTHOR]

Distracted driving is one of the major factors leading drivers to ignore potential road hazards. In response to the challenges of high computational complexity, limited generalization capacity, and suboptimal detection accuracy in existing deep learning-based detection algorithms, this paper introduces a novel approach called StarDL-YOLO (StarNet-detectlscd-yolo), which leverages an enhanced version of YOLOv8n. Initially, the StarNet integrated into the backbone of YOLOv8n significantly improves the feature extraction capability of the model with remarkable reduction in computational complexity. Subsequently, the Star Block is incorporated into the neck network, forming a C2f-Star module that offers lower computational cost. Additionally, shared convolution is introduced in the detection head to further reduce computational burden and parameter size. Finally, the Wise-Focaler-MPDIoU loss function is proposed to strengthen detection accuracy. The experimental results demonstrate that StarDL-YOLO significantly improves the efficiency of the distracted driving behavior detection, achieving an accuracy of 99.6% on the StateFarm dataset. Moreover, the parameter count of the model is minimized by 56.4%, and its computational load is decreased by 45.1%. Additionally, generalization experiments are performed on the 100-Driver dataset, revealing that the proposed scheme enhances generalization effectiveness compared to YOLOv8n. Therefore, this algorithm significantly reduces computational load while maintaining high reliability and generalization capability. [ABSTRACT FROM AUTHOR]

As artificial intelligence technology progresses, deep learning models are increasingly utilized for machine fault classification. However, a significant drawback of current state-of-the-art models is their high computational complexity, rendering them unsuitable for deployment in portable devices. This paper presents a compact fault diagnosis model that integrates a self-attention SqueezeNet architecture with a hybrid texture representation technique utilizing empirical mode decomposition (EMD) and a gammatone spectrogram (GS) filter. In the model, the dominant signal is first isolated from the audio fault signals by discarding lower intrinsic mode functions (IMFs) from EMD, and subsequently, the dominant signals are transformed into 2D texture maps using the GS filter. These generated texture maps feed as input into the modified self-attention SqueezeNet classifier, featuring reduced model width and depth, for training and validation. Different attention modules were tested in the paper, including the self-attention, channel attention, spatial attention, and convolutional block attention module (CBAM). The models were tested on the MIMII and ToyADMOS datasets. The experimental results demonstrated that the self-attention mechanism with SqueezeNet achieved an accuracy of 97% on the previously unseen MIMII and ToyADMOS datasets. Furthermore, the proposed model outperformed the SqueezeNet attention model with other attention mechanisms and state-of-the-art deep architectures, exhibiting a higher precision, recall, and F1-score. Lastly, t-SNE is applied to visualize the features of the self-attention SqueezeNet for different fault classes of both MIMII and ToyADMOS. [ABSTRACT FROM AUTHOR]

In order to shorten detection times and improve average precision in embedded devices, a lightweight and high-accuracy model is proposed to detect passion fruit in complex environments (e.g., with backlighting, occlusion, overlap, sun, cloud, or rain). First, replacing the backbone network of YOLOv5 with a lightweight GhostNet model reduces the number of parameters and computational complexity while improving the detection speed. Second, a new feature branch is added to the backbone network and the feature fusion layer in the neck network is reconstructed to effectively combine the lower- and higher-level features, which improves the accuracy of the model while maintaining its lightweight nature. Finally, a knowledge distillation method is used to transfer knowledge from the more capable teacher model to the less capable student model, significantly improving the detection accuracy. The improved model is denoted as G-YOLO-NK. The average accuracy of the G-YOLO-NK network is 96.00%, which is 1.00% higher than that of the original YOLOv5s model. Furthermore, the model size is 7.14 MB, half that of the original model, and its real-time detection frame rate is 11.25 FPS when implemented on the Jetson Nano. The proposed model is found to outperform state-of-the-art models in terms of average precision and detection performance. The present work provides an effective model for real-time detection of passion fruit in complex orchard scenes, offering valuable technical support for the development of orchard picking robots and greatly improving the intelligence level of orchards. [ABSTRACT FROM AUTHOR]

We study the computational complexity of (deterministic or randomized) algorithms based on point samples for approximating or integrating functions that can be well approximated by neural networks. Such algorithms (most prominently stochastic gradient descent and its variants) are used extensively in the field of deep learning. One of the most important problems in this field concerns the question of whether it is possible to realize theoretically provable neural network approximation rates by such algorithms. We answer this question in the negative by proving hardness results for the problems of approximation and integration on a novel class of neural network approximation spaces. In particular, our results confirm a conjectured and empirically observed theory-to-practice gap in deep learning. We complement our hardness results by showing that error bounds of a comparable order of convergence are (at least theoretically) achievable. [ABSTRACT FROM AUTHOR]

Machine learning approaches have become a crucial tool in graph analysis. Despite the accurate results of the existing approaches, most of them are not scalable enough to be used in real-world problems. Networks provide two different kinds of information, nodes contents and nodes relations (network structure). Training deep graph neural networks (GNN) over large-scale graphs is challenging due to the limitation of the message passing framework. Graph Convolutional Networks (GCN) work on all node neighbours at once. Furthermore, it is usual to transform node features with a deep neural network before the GC operation. Therefore, the deep transform operation may apply up to hundreds of times for each target node which is heavy computation and hard to batch. This paper presents an abstract framework with two embedding components, the first component embeds node relations, and the second one embeds node contents. The model makes predictions by aggregating these embeddings through a combination component. The presented approach limits the deep transform only to the target node and uses random walk-based embedding instead of the GC operator to reduce the cost. The main goal of the proposed approach is to provide a light framework for the task. To this aim, node relations are embedded based on node neighbourhood structure by a biased variant of the DeepWalk model, called GuidedWalk, and an autoencoder embeds node contents. The experimental results on three well-known datasets show the superiority of the proposed model compared to the state-of-the-art GraphSAGE and TADW models with less computational complexity. On the Citeseer, Cora, and PubMed datasets, the model has achieved 3.23%, 0.88%, and 7.63% improvement in Macro-F1 and 3.25%, 0.7%, and 6.34% improvement in Micro-F1, respectively. Although GNNs are state-of-the-art models, considering node content is their main advantage. This paper shows that even a simple integration of node content to available random walk-based methods improves their performance up to GCNs without increasing the complexity. [ABSTRACT FROM AUTHOR]

NeRF is a deep learning model aimed at modeling three-dimensional implicit spaces, and it holds significant value in the representation and rendering of 3D scenes. However, due to the complex training process, substantial computational resources, and time requirements, the usability and practicality of the NeRF algorithm are somewhat limited. Addressing the pain points of NeRF optimization has become a hot topic in the field of computer vision. This paper aimed to provide a comprehensive review of the optimization and application of NeRF. Firstly, it delved into the basic principles of NeRF and outlined the current optimization status from the perspectives of rendering quality, computational complexity, and pose. Secondly, it enumerated the application scenarios of NeRF to provide references for future, more efficient and practical algorithmic optimizations. Finally, it summarized the strengths and limitations of NeRF and proposed potential future directions tailored to harness the tremendous potential of NeRF in 3D rendering, scene synthesis, and beyond. [ABSTRACT FROM AUTHOR]

Despite the ongoing advancements in deep learning, challenges persist in the domain of change detection in remote sensing imagery. Objects with intricate structures and features may exhibit different shapes or appearances at different times or spatial locations. While most models aim to improve the performance of change detection tasks, these enhancements may lead to significantly increased computational efficiency. In this paper, we propose a global context enhancement network. Firstly, we use ResNet18 to extract dual-temporal features, which are then represented as concise semantic labels by an image semantic extractor. Subsequently, we process these semantic labels through a contextual transformer encoder to generate more refined remote sensing semantic labels enriched with abundant contextual information. The refined semantic labels are integrated with the original features and processed through a Transformer decoder to generate enhanced dual-temporal feature maps. Finally, through the processing of the classification head, we obtain pixel-level predictive images. Extensive experiments conducted on two public change detection datasets yielded impressive results, achieving an F1 score of 89.95% on the WHU-CD dataset and 95.16% on the SVCD dataset. When compared to state-of-the-art change detection models, our approach not only achieves significant performance gains but also maintains relatively high computational efficiency. Our method excels in capturing relevant features and relationships within input data, thereby enhancing the model's ability to represent relationships between different features. This results in a significant performance improvement without adding to the computational complexity. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) represents the backbone of current and future technologies. The main objective of IoT is to make human life easier by automating most daily jobs. The endless web of connections entices opponents to utilize the IoT's weaknesses. For that reason, this technological innovation faces a few serious safety and confidentiality problems. These problems are the actual motivation of this research. This paper reviews the latest research and possible types of attacks that can affect IoT systems including the exploration of IoT infrastructure. Various cybersecurity threats, including network, application, and physical attacks, that aim to compromise the IoT are discussed. Moreover, regarding attack types, we performed a statistical analysis using Excel for the percentage of most attacks and found that DDoS is the most common with 21%. In addition, by comparing Deep Learning (DL) accuracy measures with traditional methods, DL methods achieved an accuracy of more than 98%, so they are better and more effective in detecting and classifying the attack types due to their high accuracy. However, rarely do researchers focus on computational complexity. Finally, the paper highlights some statistics using Python language on the negative impact of attacks on network traffic. [ABSTRACT FROM AUTHOR]

This study proposes novel sales forecasting approaches that merge deep learning methods in a hybrid model. Long short‐term memory (LSTM) is adopted for modeling the temporal characteristics of the data, whereas the convolutional neural network (CNN) focuses on identifying and extracting relevant exogenous information. We propose stacked (S‐CNN‐LSTM) and parallel (P‐CNN‐LSTM) hybrid architectures to understand complex time series data with varying seasonal patterns and multiple products correlations. The performance drivers of both architectures were empirically tested with a real‐world multivariate retail dataset and outperformed when compared with simple neural network architectures and standard autoregressive methods for short and long‐term forecasting horizons. When compared with traditional predictive approaches, the proposed hybrid models reduce the computational complexity while providing flexibility and robustness. [ABSTRACT FROM AUTHOR]

Pneumatic artificial muscles (PAMs) possess compliant properties desirable for certain applications such as prosthetics and robotic structures. However, this compliance along with their inherent nonlinear dynamics make them difficult to accurately model and as such accurately control under certain control architectures. Common approaches to this problem include measuring the actuator's physical properties and approximating a model based on these parameters or using deep learning methods to train a model with the actuator's behaviours. This paper introduces an optimisation-based modelling approach based on a particle swarm optimisation (PSO) algorithm using a mass–spring–damper approximation for the PAM, as well as a piecewise modelling method that accounts for nonlinear dynamics. The use of optimisation to estimate model parameters removes the need to measure physical properties, and the three-element approximation allows for fast model generation with low computational complexity and training data requirements. Through multiple tests comparing model behaviour with real PAM motion, the accuracy of these models is confirmed to be promising for future work. Dynamic nonlinearities are properly accounted for using the piecewise modelling method, including both hysteresis and disproportionate input/output relationship across the stroke length of the actuator. Compared with other PAM modelling techniques, this method has improved generation time, lower computational load requirements, and complexity and can be applied to actuators for which the phenomenological mass–spring–damper model is a good approximation. [ABSTRACT FROM AUTHOR]

Deep learning (DL) models are used in a variety of real-world applications but are often vulnerable to privacy attacks. Nevertheless, this DL model is attacked by membership inference attacks, model inversion attacks, reconstruction attacks, model extraction attacks, gradient leakage attacks, correlation attacks, and white box attacks (inference attacks). In order to mitigate this issue, various existing research has attempted to design an effective privacy mechanism. However, the existing schemes failed to obtain higher security in DL because of several limitations like computational complexity, lower efficiency, difficult-to-select parameters, cumulative privacy loss, etc. Recently, the auto-encoder-based deep learning model has become more popular due to its great ability, and its variants have achieved notable success in various fields such as medicine, healthcare and NLP (Natural Language Programming). However, the privacy of the auto-encoder model is affected because of the vulnerable attacks. Thus, to avoid this issue, the proposed study prefers the differential privacy (DP) method for securing the deep auto-encoder model. DP is a privacy-preserving technique that can be used to protect deep learning models from the aforementioned attacks. In this paper, a Differential Privacy-Improved Stochastic Gradient Descent (DP-ISGD) algorithm is proposed to improve the privacy and utility of the Deep Autoencoder method by adding Gaussian noise to the gradients before the clipping process. Thus, the convergence speed and accuracy of the proposed algorithm are enhanced. The experimentation is conducted in the Python platform, and metrics like convergence, accuracy and TPVD (Total Parameters Value Difference) are evaluated to measure the performance of the proposed study. The comparative analysis is performed for the no privacy, privacy with SGD, privacy with batch gradient descent (BGD) and mini-batch gradient descent (MBGD) models. The proposed approach is evaluated against six datasets, Pima Indians Diabetes (PID), Adult, MNIST, CIFAR-10, MovieLens 20 M and CD-FSL, with improved accuracy results of 98.6%, 98.6%, 98.3%, 98.14%, 97.92% and 98.17% for each dataset at the epsilon (ε ) value of 0.2. The comparison analysis showed that the proposed algorithm achieves better accuracy than other privacy protection methods. Thus, the significant findings in the proposed work state that the proposed privacy model is suitable for several applications, including medical fields, algorithm development, education and awareness, by affording strong privacy guarantees. [ABSTRACT FROM AUTHOR]

The presence of fog in the background can prevent small and distant objects from being detected, let alone tracked. Under safety-critical conditions, multi-object tracking models require faster tracking speed while maintaining high object-tracking accuracy. The original DeepSORT algorithm used YOLOv4 for the detection phase and a simple neural network for the deep appearance descriptor. Consequently, the feature map generated loses relevant details about the track being matched with a given detection in fog. Targets with a high degree of appearance similarity on the detection frame are more likely to be mismatched, resulting in identity switches or track failures in heavy fog. We propose an improved multi-object tracking model based on the DeepSORT algorithm to improve tracking accuracy and speed under foggy weather conditions. First, we employed our camera-radar fusion network (CR-YOLOnet) in the detection phase for faster and more accurate object detection. We proposed an appearance feature network to replace the basic convolutional neural network. We incorporated GhostNet to take the place of the traditional convolutional layers to generate more features and reduce computational complexities and costs. We adopted a segmentation module and fed the semantic labels of the corresponding input frame to add rich semantic information to the low-level appearance feature maps. Our proposed method outperformed YOLOv5 + DeepSORT with a 35.15% increase in multi-object tracking accuracy, a 32.65% increase in multi-object tracking precision, a speed increase by 37.56%, and identity switches decreased by 46.81%. [ABSTRACT FROM AUTHOR]

This study addresses the challenges inherent in the maintenance and inspection of wind turbines through the application of deep learning methodologies for fault detection on Wind Turbine Blades (WTBs). Specifically, this research focuses on defect detection on the blades of small-scale WTBs due to the unavailability of commercial wind turbines. This research compared popular object localization architectures, YOLO and Mask R-CNN, to identify the most effective model to detect common WTB defects, including cracks, holes, and erosion. YOLOv9 C emerged as the most effective model, with the highest scores of mAP50 and mAP50-95 of 0.849 and 0.539, respectively. Modifications to Mask R-CNN, specifically integrating a ResNet18-FPN network, reduced computational complexity by 32 layers and achieved a mAP50 of 0.8415. The findings highlight the potential of deep learning and computer vision in improving WTB fault analysis and inspection. [ABSTRACT FROM AUTHOR]

The offshore environment is complex during automatic target annotation at sea, and the difference between the focal lengths of visible and infrared sensors is large, thereby causing difficulties in matching multitarget electro-optical images at sea. This study proposes a target-matching method for visible and infrared images at sea based on decision-level topological relations. First, YOLOv9 is used to detect targets. To obtain markedly accurate target positions to establish accurate topological relations, the YOLOv9 model is improved for its poor accuracy for small targets, high computational complexity, and difficulty in deployment. To improve the detection accuracy of small targets, an additional small target detection head is added to detect shallow feature maps. From the perspective of reducing network size and achieving lightweight deployment, the Conv module in the model is replaced with DWConv, and the RepNCSPELAN4 module in the backbone network is replaced with the C3Ghost module. The replacements significantly reduce the number of parameters and computation volume of the model while retaining the feature extraction capability of the backbone network. Experimental results of the photovoltaic dataset show that the proposed method improves detection accuracy by 8%, while the computation and number of parameters of the model are reduced by 5.7% and 44.1%, respectively. Lastly, topological relationships are established for the target results, and targets in visible and infrared images are matched based on topological similarity. [ABSTRACT FROM AUTHOR]

Recently, transformer has gradually attracted interest for its excellence in modeling the long-range dependencies of spatial-spectral features in HSI. However, transformer has the problem of the quadratic computational complexity due to the self-attention mechanism, which is heavier than other models and thus has limited adoption in HSI processing. Fortunately, the recently emerging state space model-based Mamba shows great computational efficiency while achieving the modeling power of transformers. Therefore, in this paper, we first proposed spectral-spatial Mamba (SS-Mamba) for HSI classification. Specifically, SS-Mamba mainly includes a spectral-spatial token generation module and several stacked spectral-spatial Mamba blocks. Firstly, the token generation module converts any given HSI cube to spatial and spectral tokens as sequences. And then these tokens are sent to stacked spectral-spatial mamba blocks (SS-MB). Each SS-MB includes two basic mamba blocks and a spectral-spatial feature enhancement module. The spatial and spectral tokens are processed separately by the two basic mamba blocks, correspondingly. Moreover, the feature enhancement module modulates spatial and spectral tokens using HSI sample's center region information. Therefore, the spectral and spatial tokens cooperate with each other and achieve information fusion within each block. The experimental results conducted on widely used HSI datasets reveal that the proposed SS-Mamba requires less processing time compared with transformer. The Mamba-based method thus opens a new window for HSI classification. [ABSTRACT FROM AUTHOR]

Quantum error correction techniques are important for implementing fault-tolerant quantum computation, and topological quantum error correcting codes provide feasibility for implementing large-scale fault-tolerant quantum computation. Here, we propose a deep reinforcement learning framework for implementing quantum error correction algorithms for errors on heavy hexagonal codes. Specifically, we construct the double deep Q learning model with policy reuse method, so that the decoding agent does not have to explore the learning from scratch when dealing with new error syndrome, but instead reuses past policies, which can reduce the computational complexity. And the double deep Q network can avoid the problem of threshold being overestimated and get the true decoding threshold. Our experimental results show that the error correction accuracy of our decoder can reach 91.86%. Different thresholds are obtained according to the code distance, which is 0.0058 when the code distance is 3, 5, 7, and 0.0065 when the code distance is 5, 7, 9, both higher than that of the classical minimum weight perfect matching decoder. Compared to the threshold of the MWPM decoder under the depolarizing noise model, the threshold of our decoder is improved by 32.63%, which enables better fault-tolerant quantum computation. [ABSTRACT FROM AUTHOR]

Boron-doped diamond thin films exhibit extensive applications in chemical sensing, in which the performance could be further enhanced by nano-structuring of the surfaces. In order to discover the relationship between diamond nanostructures and properties, this paper is dedicated to deep learning target detection methods. However, great challenges, such as noise, unclear target boundaries, and mutual occlusion between targets, are inevitable during the target detection of nanostructures. To tackle these challenges, DWS-YOLOv8 (DCN + WIoU + SA + YOLOv8n) is introduced to optimize the YOLOv8n model for the detection of diamond nanostructures. A deformable convolutional C2f (DCN_C2f) module is integrated into the backbone network, as is a shuffling attention (SA) mechanism, for adaptively tuning the perceptual field of the network and reducing the effect of noise. Finally, Wise-IoU (WIoU)v3 is utilized as a bounding box regression loss to enhance the model's ability to localize diamond nanostructures. Compared to YOLOv8n, a 9.4% higher detection accuracy is achieved for the present model with reduced computational complexity. Additionally, the enhancement of precision (P), recall (R), mAP@0.5, and mAP@0.5:0.95 is demonstrated, which validates the effectiveness of the present DWS-YOLOv8 method. These methods provide effective support for the subsequent understanding and customization of the properties of surface nanostructures. [ABSTRACT FROM AUTHOR]

Deep learning based video depression analysis has been recently an interesting and challenging topic. Most of existing works focus on learning single-scale facial dynamics of participants for depression detection. Besides, they usually adopt expensive deep learning models with high computational complexity, resulting in difficulty in real-time clinical applications. To address these two issues, this work proposes a lightweight Multi-scale Temporal Difference Attention Networks (MTDAN) integrating the temporal difference and attention mechanism to model both short-term and long-term temporal facial behaviors for automated video depression detection. Initially, two simple yet effective sub-branches, i.e., a Short-term Temporal Difference Attention Network (ST-TDAN), and a Long-term Temporal Difference Attention Network (LT-TDAN), are designed to perform individually short-term and long-term depressive behavior modeling. Then, a simple Interactive Multi-head Attention Fusion (IMHAF) strategy is employed for integrating short-term and long-term spatiotemporal features, followed by a linear fully-collected layer for depression score prediction. Experiments on two public AVEC2013 and AVEC2014 datasets show that our proposed method not only achieves highly competitive performance to state-of-the-art methods, but also has much smaller computational complexity than them on video depression detection tasks. [ABSTRACT FROM AUTHOR]

As two important contents in WiFi-based action perception, detection and recognition require localizing motion regions from the entire temporal sequences and classifying the corresponding categories. Existing approaches, though yielding reasonably acceptable performances, are suffering from two major drawbacks: heavy empirical dependency and large computational complexity. In order to solve these issues, we develop LiteWiSys in this article, a lightweight system in an end-to-end deep learning manner to simultaneously detect and recognize WiFi-based human actions. Specifically, we assign different attentions on sub-carriers, which are then compressed to reduce noise and information redundancy. Then, LiteWiSys integrates deep separable convolution and a channel shuffle mechanism into a multi-scale convolutional backbone structure. By feature channel split, two network branches are obtained and further trained with a joint loss function for dual tasks. We collect different datasets at multi-scenes and conduct experiments to evaluate the performance of LiteWiSys. In comparison to existing WiFi sensing systems, LiteWiSys achieves promising precision with lower complexity. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Chongqing University of Technology (Natural Science) is the property of Chongqing University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Mulberry leaves, when infected by pathogens, can suffer significant yield loss or even death if early disease detection and timely spraying are not performed. To enhance the detection performance of mulberry leaf diseases in natural environments and to precisely locate early small lesions, we propose a high-precision, high-efficiency disease detection algorithm named YOLOv8-RFMD. Based on improvements to You Only Look Once version 8 (YOLOv8), we first proposed the Multi-Dimension Feature Attention (MDFA) module, which integrates important features at the pixel-level, spatial, and channel dimensions. Building on this, we designed the RFMD Module, which consists of the Conv-BatchNomalization-SiLU (CBS) module, Receptive-Field Coordinated Attention (RFCA) Conv, and MDFA, replacing the Bottleneck in the model's Residual block. We then employed the ADown down-sampling structure to reduce the model size and computational complexity. Finally, to improve the detection precision of small lesion features, we replaced the Complete Intersection over Union (CIOU) loss function with the Normalized Wasserstein Distance (NWD) loss function. Results show that the YOLOv8-RFMD model achieved a mAP50 of 94.3% and a mAP50:95 of 67.8% on experimental data, representing increases of 2.9% and 4.3%, respectively, compared to the original model. The model size was reduced by 0.53 MB to just 5.45 MB, and the GFLOPs were reduced by 0.3 to only 7.8. YOLOv8-RFMD has displayed great potential for application in real-world mulberry leaf disease detection systems and automatic spraying operations. [ABSTRACT FROM AUTHOR]

Detecting intrusions in real-time within cloud networks presents a multifaceted challenge involving intricate processes such as feature representation, intrusion type classification and post-processing procedures. Distributed Intrusion Detection Systems (DIDSs) constitute a complex landscape characterized by diverse contextual nuances, distinct functional advantages and limitations specific to deployment scenarios. Despite these challenges, DIDS offers immense potential for addressing evolving intrusion detection challenges through tailored contextual adaptations and unique functional advantages. Moreover, exploring the limitations associated with different deployment contexts facilitates targeted improvements and refinements, unlocking new avenues for innovation in intrusion detection technologies. Notably, deep learning (DL) integrated with blockchain technology emerges as a superior approach in terms of security, while bioinspired models excel in Quality of Service (QoS). These models demonstrate higher accuracy across various network scenarios, underscoring their efficacy in intrusion detection. Additionally, edge-based models exhibit high accuracy and scalability with reduced delay, complexity and cost in real-time network environments. The fusion of these models holds promise for enhancing classification performance across diverse attack types, offering avenues for future research exploration. This text conducts a comprehensive comparison of performance metrics, including accuracy, response delay, computational complexity, scalability and deployment costs. The proposed Novel DIDS Rank (NDR) streamlines model selection by considering these metrics, enabling users to make well-informed decisions based on multiple performance aspects simultaneously. This unified ranking approach facilitates the identification of DIDS that achieves high accuracy and scalability while minimizing response delay, cost and complexity across varied deployment scenarios. [ABSTRACT FROM AUTHOR]

Recent advancements in deep learning have enabled gaze estimation from images of the face and eye areas without the need for precise geometric locations of the eyes and face. This approach eliminates the need for complex user-dependent calibration and the issues associated with extracting and tracking geometric positions, making further exploration of gaze position performance enhancements challenging. Motivated by this, our study focuses on an ensemble loss function that can enhance the performance of existing 2D-based deep learning models for gaze coordinate (x, y) prediction. We propose a new function and demonstrate its effectiveness by applying it to models from prior studies. The results show significant performance improvements across all cases. When applied to ResNet and iTracker models, the average absolute error reduced significantly from 7.5 cm to 1.2 cm and from 7.67 cm to 1.3 cm, respectively. Notably, when implemented on the AFF-Net, which boasts state-of-the-art performance, the average absolute error was reduced from 4.21 cm to 0.81 cm, based on our MPIIFaceGaze dataset. Additionally, predictions for ranges never encountered during the training phase also displayed a very low error of 0.77 cm in terms of MAE without any personalization process. These findings suggest significant potential for accuracy improvements while maintaining computational complexity similar to the existing models without the need for creating additional or more complex models. [ABSTRACT FROM AUTHOR]

Neonatal epilepsy is an early postnatal brain disorder, and automatic seizure detection is crucial for timely diagnosis and treatment to reduce potential brain damage. This work proposes a novel Lightweight Multi-Attention Network, LMA-EEGNet, for diagnosing neonatal epileptic seizures from multi-channel EEG signals employing dilated depthwise separable convolution (DDS Conv) for feature extraction and using pointwise convolution followed by global average pooling for classification. The proposed approach substantially reduces the model size, number of parameters, and computational complexity, which are crucial for real-time detection and clinical diagnosis of neonatal epileptic seizures. LMA-EEGNet integrates temporal and spectral features through distinct temporal and spectral branches. The temporal branch uses DDS Conv to extract temporal features, enhanced by a channel attention mechanism. The spectral branch utilizes similar convolutions alongside a spatial attention mechanism to highlight key frequency components. Outputs from both branches are merged and processed through a pointwise convolution layer and a global average pooling layer for efficient neonatal seizure detection. Experimental results show that our model, with only 2471 parameters and a size of 23 KB, achieves an accuracy of 95.71% and an AUC of 0.9862, demonstrating its potential for practical deployment. This study provides an effective deep learning solution for the early detection of neonatal epileptic seizures, improving diagnostic accuracy and timeliness. [ABSTRACT FROM AUTHOR]

Cell-penetrating peptides comprise a group of molecules that can naturally cross the lipid bilayer membrane that protects cells, sharing physicochemical and structural properties, and having several pharmaceutical applications, particularly in drug delivery. Investigations of molecular descriptors have provided not only an improvement in the performance of classifiers but also less computational complexity and an enhanced understanding of membrane permeability. Furthermore, the employment of new technologies, such as the construction of deep learning models using overfitting treatment, promotes advantages in tackling this problem. In this study, the descriptors nitrogen, oxygen, and hydrophobicity on the Eisenberg scale were investigated, using the proposed ConvBoost-CPP composed of an improved convolutional neural network with overfitting treatment and an XGBoost model with adjusted hyperparameters. The results revealed favorable to the use of ConvBoost-CPP, having as input nitrogen, oxygen, and hydrophobicity together with ten other descriptors previously investigated in this research line, showing an increase in accuracy from 88% to 91.2% in cross-validation and 82.6% to 91.3% in independent test. [ABSTRACT FROM AUTHOR]

Visual simultaneous localization and mapping (VSLAM) enhances the navigation of autonomous agents in unfamiliar environments by progressively constructing maps and estimating poses. However, conventional VSLAM pipelines often exhibited degraded performance in dynamic environments featuring mobile objects. Recent research in deep learning led to notable progress in semantic segmentation, which involves assigning semantic labels to image pixels. The integration of semantic segmentation into VSLAM can effectively differentiate between static and dynamic elements in intricate scenes. This paper provided a comprehensive comparative review on leveraging semantic segmentation to improve major components of VSLAM, including visual odometry, loop closure detection, and environmental mapping. Key principles and methods for both traditional VSLAM and deep semantic segmentation were introduced. This paper presented an overview and comparative analysis of the technical implementations of semantic integration across various modules of the VSLAM pipeline. Furthermore, it examined the features and potential use cases associated with the fusion of VSLAM and semantics. It was found that the existing VSLAM model continued to face challenges related to computational complexity. Promising future research directions were identified, including efficient model design, multimodal fusion, online adaptation, dynamic scene reconstruction, and end-to-end joint optimization. This review shed light on the emerging paradigm of semantic VSLAM and how deep learning-enabled semantic reasoning could unlock new capabilities for autonomous intelligent systems to operate reliably in the real world. [ABSTRACT FROM AUTHOR]

The evolution of super-resolution (SR) technology has seen significant advancements through the adoption of deep learning methods. However, the deployment of such models by resource-constrained devices necessitates models that not only perform efficiently, but also conserve computational resources. Binary neural networks (BNNs) offer a promising solution by minimizing the data precision to binary levels, thus reducing the computational complexity and memory requirements. However, for BNNs, an effective architecture is essential due to their inherent limitations in representing information. Designing such architectures traditionally requires extensive computational resources and time. With the advancement in neural architecture search (NAS), differentiable NAS has emerged as an attractive solution for efficiently crafting network structures. In this paper, we introduce a novel and efficient binary network search method tailored for image super-resolution tasks. We adapt the search space specifically for super resolution to ensure it is optimally suited for the requirements of such tasks. Furthermore, we incorporate Libra Parameter Binarization (Libra-PB) to maximize information retention during forward propagation. Our experimental results demonstrate that the network structures generated by our method require only a third of the parameters, compared to conventional methods, and yet deliver comparable performance. [ABSTRACT FROM AUTHOR]

The acquisition of digital images is susceptible to haze, and images captured under such adverse conditions may impact high-level applications designed for clean input data. Image dehazing emerges as a practical solution to this problem, as it can be employed to pre-process images immediately after acquisition. This paper presents a concise review of impactful algorithms, including those based on deep learning models, to identify the existing gap in real-time processing capabilities. Subsequently, a real-time dehazing system on a multiprocessor system-on-a-chip (MPSoC) platform is introduced to bridge this gap. The proposed system balances the trade-off between dehazing performance and computational complexity; hence, the name "Symmetric" is coined. Additionally, the entire system is implemented in programmable logic and wrapped by an interface circuit supporting double-buffering, rendering it highly suitable for seamless integration into existing camera systems. Implementation results on a Zynq UltraScale+ MPSoC ZCU106 Evaluation Kit demonstrate a maximum operating frequency of 356.51 MHz, equivalent to a maximum processing speed of 40.27 frames per second for DCI 4K resolution. [ABSTRACT FROM AUTHOR]

The design and optimization of floating offshore wind turbines (FOWTs) pose significant challenges, stemming from the complex interplay among aerodynamics, hydrodynamics, structural dynamics, and control systems. In this context, this study introduces an innovative method for forecasting the dynamic behavior of FOWTs under various conditions by merging Convolutional Neural Network (CNN) with a Gated Recurrent Unit (GRU) network. This model outperforms traditional numerical models by delivering precise and efficient predictions of dynamic FOWT responses. It adeptly handles computational complexities and reduces processing duration, while maintaining flexibility and effectively managing nonlinear dynamics. The model's prowess is showcased through an analysis of a spar-type FOWT in a multivariate parallel time series dataset using the CNN–GRU structure. The outcomes are notably promising, underscoring the model's proficiency in accurately forecasting the performance of FOWTs. [ABSTRACT FROM AUTHOR]

The intrinsic similarity between camouflaged objects and background environment impedes the automatic detection/segmentation of camouflaged objects, and novel network architectures for deep learning are promising to overcome this challenge and improve detection accuracy. However, these existing network architectures for distinguishing between camouflaged objects and their backgrounds do not account for the constraint of detection speed, which results in high computational complexity and the inability to meet the requirements of rapid detection. Therefore, based on the human visual system, this study proposes a single-stage lightweight camouflage object detection network using multilevel feature fusion, integrating features of various feature layers and receptive field sizes. Using three benchmark datasets for normal camouflaged objects, the lightweight network (LINet) model demonstrated an accuracy superior to those of six existing mainstream camouflaged object detection methods. Its detection speed, 126.3 frames per second, is significantly higher than those of the existing mainstream methods, enabling rapid detection with a maximum increase of 187.62%. The accuracy of LINet is the minimum and maximum for Resnet101 and Resnet152, respectively. These findings pave the way for diverse applications of camouflaged target detection algorithms. [ABSTRACT FROM AUTHOR]

In this paper, we introduce deep learning (DL)‐based backlight extraction methods for local dimming display. The main objective is to better handle the trade‐off between the displayed image quality and power consumption. To this end, we propose an enhanced power regularization. Moreover, we design a smaller model with reduced computational complexity and propose an efficient post‐processing for better generalization. Experimental results show that the proposed methods reduce power consumption while better maintaining the image quality than the selected benchmarks. [ABSTRACT FROM AUTHOR]

The short-offset transient electromagnetic (SOTEM) method carries out surveys in the near source region; the strong signal makes it suitable for deep detection with high precision. When the underground structure is complex, three-dimensional (3D) inversion of SOTEM data is necessary to meet the need of high-precision detection. Currently, difficulties faced by the conventional 3D inversion methods include high computational complexity, and the influence of the initial model. Deep learning (DL), as a completely nonlinear algorithm, can predict the underground structure from the measured data. DL is completely data-driven and does not use traditional misfit optimization methods. In this study, an efficient method is proposed to conduct 3D inversion for SOTEM data, which trains a 3D U-Net based on massive data to establish a mapping from SOTEM data to geoelectric models. After the training is completed, we input the new SOTEM data into the trained network, and the corresponding geoelectric model can be obtained. Although the training is a time-consuming process, prediction for new data can be completed in seconds. The inversion results for simulated data indicate that the 3D U-Net has good generalization performance and anti-noise ability. The inversion performance of 3D U-Net on the double-anomaly model improves by 51.1% compared to a 3D fully convolutional network (FCN). The inversion results of the 3D U-Net on the field data successfully delineated the aquiferous collapse column. The inversion results for simulated and field data demonstrate that the proposed method can achieve accurate 3D inversion for large volume of data while greatly saving computational time. [ABSTRACT FROM AUTHOR]

In inland waterways, there is a high density of various objects, with a predominance of small objects, which can easily affect navigation safety. To improve the navigation safety of inland ships, this paper proposes a new lightweight water-surface object-detection model named LWS-YOLOv7, which is based on the baseline model YOLOv7. Firstly, the localization loss function is improved and the w-CIoU function is introduced to reduce the model's sensitivity to position deviations of small objects and to improve the allocation accuracy of positive and negative sample labels. Secondly, a new receptive field amplification module named GSPPCSPC is proposed to reduce the model's parameters and enhance its receptive field. Thirdly, a small-object feature-fusion layer, P2, is added to improve the recall rate of small objects. Finally, based on the LAMP model pruning method, the weights with lower importance are pruned to simplify the parameters and computational complexity of the model, facilitating the deployment of the model on shipborne devices. The experimental results demonstrate that, compared to the original YOLOv7 model, the map of LWS-YOLOv7 increased by 3.1%, the parameters decreased by 38.8%, and the GFLOPS decreased by 28.8%. Moreover, the model not only has better performance and higher speed for input images of different sizes, but it can also be applied to different meteorological conditions. [ABSTRACT FROM AUTHOR]

Code classification and code clone detection are crucial for understanding and maintaining large software systems. Although deep learning surpasses traditional techniques in capturing the features of source code, existing models suffer from low processing power and high complexity. We propose a novel source code representation method based on the multi-head attention mechanism (SCRMHA). SCRMHA captures the vector representation of entire code segments, enabling it to focus on different positions of the input sequence, capture richer semantic information, and simultaneously process different aspects and relationships of the sequence. Moreover, it can calculate multiple attention heads in parallel, speeding up the computational process. We evaluate SCRMHA on both the standard dataset and an actual industrial dataset, and analyze the differences between these two datasets. Experiment results in code classification and clone detection tasks show that SCRMHA consumes less time and reduces complexity by about one-third compared with traditional source code feature representation methods. The results demonstrate that SCRMHA reduces the computational complexity and time consumption of the model while maintaining accuracy. [ABSTRACT FROM AUTHOR]