Through-wall Human Pose Reconstruction and Action Recognition Using Four-dimensional Imaging Radar by Rui ZHANG, Hanqin GONG, Ruiyuan SONG, Yadong LI, Zhi LU, Dongheng ZHANG, Yang HU, Yan CHEN

“…Through-wall human pose reconstruction and behavior recognition have enormous potential in fields like intelligent security and virtual reality. However, existing methods for through-wall human sensing often fail to adequately model four-Dimensional (4D) spatiotemporal features and overlook the influence of walls on signal quality. …”
Get full text

Enhancing Autism Spectrum Disorder Classification with Lightweight Quantized CNNs and Federated Learning on ABIDE-1 Dataset by Simran Gupta, Md. Rahad Islam Bhuiyan, Sadia Sultana Chowa, Sidratul Montaha, Rashik Rahman, Sk. Tanzir Mehedi, Ziaur Rahman

Get full text

Constructing segmentation method for wheat powdery mildew using deep learning by Hecang Zang, Hecang Zang, Congsheng Wang, Qing Zhao, Qing Zhao, Jie Zhang, Jie Zhang, Junmei Wang, Guoqing Zheng, Guoqing Zheng, Guoqiang Li, Guoqiang Li

“…Finally, in the deep bottleneck of Swin-Unet network, ResNet network layers are used to increase the expressive power of feature. …”
Get full text

A review on artificial intelligence thermal fluids and the integration of energy conservation with blockchain technology by Abdullah Ayub Khan, Asif Ali Laghari, Syed Azeem Inam, Sajid Ullah, Laila Nadeem

Get full text

Ensemble of Chaotic and Naive Approaches for Performance Enhancement in Video Encryption by Jeyamala Chandrasekaran, S. J. Thiruvengadam

“…Although naive approaches are the most secure for video encryption, the computational cost associated with them is very high. …”
Get full text

Trustworthiness of Deep Learning Under Adversarial Attacks in Power Systems by Dowens Nicolas, Kevin Orozco, Steve Mathew, Yi Wang, Wafa Elmannai, George C. Giakos

Get full text

Peculiarities of evidence in the course of investigation of criminal offences under parts 1, 2 of Article 111-1 of the Criminal Code of Ukraine by S. Ye. Ablamskyi, O. V. Kovtun, V. V. Ablamska

“…It is substantiated that in modern conditions, evidence in the course of investigation of criminal offences under Parts 1, 2 of Art. 111-1 of the Criminal Code of Ukraine is inseparable from taking into account the features of modern equipment which can be used for information transmission, analysis of computer information and information from correspondence, channels and groups in social networks containing valuable information, samples of signatures, seals and other details of documents which reflect information about the collaboration activities of individuals and groups. …”
Get full text

A hybrid data-driven method for voltage state prediction and fault warning of Li-ion batteries by Yufeng Huang, Xuejian Gong, Zhiyu Lin, Lei Xu

“…Firstly, an 1DCNN module is introduced to extract voltage-related multi-dimension features. Secondly, a Bi-LSTM module is used to learn long-term dependence relationships among fused features while integrating a self-attention mechanism. …”
Get full text

Real-Time Corn Variety Recognition Using an Efficient DenXt Architecture with Lightweight Optimizations by Jin Zhao, Chengzhong Liu, Junying Han, Yuqian Zhou, Yongsheng Li, Linzhe Zhang

“…Representative Batch Normalization (RBN) is introduced into the DenseNet-121 model to improve the generalization ability of the model, and the SE module and deep separable convolution are integrated to enhance the feature representation and reduce the computational complexity, and the Dropout regularization is introduced to further improve the generalization ability of the model and reduce the overfitting. …”
Get full text

Cloud-based optimized deep learning framework for automated glaucoma detection using stationary wavelet transform and improved grey-wolf-optimization with ELM approach by Debendra Muduli, Syed Irfan Yaqoob, Santosh Kumar Sharma, Anuradha S. Kanade, Mohammad Shameem, Harendra S. Jangwan, P.M. Ashok Kumar, Abu Taha Zamani

Get full text

OPTISTACK: A Hybrid Ensemble Learning and XAI-Based Approach for Malware Detection in Compressed Files by Khaled Mahmud Sujon, Rohayanti Binti Hassan, M. Abdullah-Al-Wadud, Jia Uddin

Get full text

Unveiling smart contract vulnerabilities: Toward profiling smart contract vulnerabilities using enhanced genetic algorithm and generating benchmark dataset by Sepideh HajiHosseinKhani, Arash Habibi Lashkari, Ali Mizani Oskui

Get full text

Survey of deep fake audio generation and detection techniques by ZENG Zhiping, ZHANG Xulong, QU Xiaoyang, XIAO Chunguang, WANG Jianzong

“…Subsequently, an in-depth analysis was conducted on both acoustic feature-based and end-to-end model-based fake audio detection strategies, delving into details such as deep acoustic feature detection, pre-trained neural network feature detection, end-to-end model optimization, generalization enhancement techniques, and the enhancement of real-time detection. …”
Get full text

Improving internet of vehicles research: A systematic preprocessing framework for the VeReMi datasetZenodo by Aparup Roy, Debotosh Bhattacharjee, Ondrej Krejcar

“…The optimized dataset is well-suited for ITS and IoV applications, such as anomaly detection and network security, underscoring the crucial role of preprocessing in overcoming real-world constraints and enhancing model performance.…”
Get full text

Machine Learning and Deep Learning for Crop Disease Diagnosis: Performance Analysis and Review by Habiba Njeri Ngugi, Andronicus A. Akinyelu, Absalom E. Ezugwu

Get full text

InterAcT: A generic keypoints-based lightweight transformer model for recognition of human solo actions and interactions in aerial videos. by Mubashir Shah, Tahir Nawaz, Rab Nawaz, Nasir Rashid, Muhammad Osama Ali

“…To this end, this paper presents a generic lightweight and computationally efficient Transformer network-based model, referred to as InterAcT, that relies on extracted bodily keypoints using YOLO v8 to recognize human solo actions as well as interactions in aerial videos. …”
Get full text

Issues, Challenges, and Solution Options for On-Grid Multi-Microgrid Game Theory: A Systematic Review by Dimas Jalaluddin Ahmad, Nanang Hariyanto, Umar Khayam

“…This connection provides more flexibility in operation and various features, including multi-level interactions beyond peer-to-peer, asymmetric agents, the presence of distribution network operator, support and backup power from the grid, and an energy market pool. …”
Get full text

An Improved Machine Learning-Based Model for Detecting and Classifying PQDs with High Noise Immunity in Renewable-Integrated Microgrids by Irfan Ali Channa, Dazi Li, Mohsin Ali Koondhar, Fida Hussain Dahri, Ibrahim Mahariq

“…Recently, renewable energy sources integrated with microgrid (MG) networks have provided safe, secure, and reliable power supply to both utility and industrial purposes. …”
Get full text

CRYPTO-RESISTANT METHODS AND RANDOM NUMBER GENERATORS IN INTERNET OF THINGS (IOT) DEVICES by Petro Klimushyn, Tetiana Solianyk, Oleksandr Mozhaiev, Yurii Gnusov, Oleksandr Manzhai, Vitaliy Svitlychny

“…The analysis of technologies and circuit solutions allowed to draw the following conclusions: protection of IoT solutions includes: security of IoT network nodes and their connection to the cloud using secure protocols, ensuring confidentiality, authenticity and integrity of IoT data by cryptographic methods, attack analysis and network cryptographic stability; the initial basis for the protection of IoT solutions is the true randomness of the formed RNG sequences and used in algorithms for cryptographic transformation of information to protect it; feature of IoT devices is their heterogeneity and geographical distribution, limited computing resources and power supply, small size; The most effective (reduce power consumption and increase the generation rate) for use in IoT devices are RNG exclusively on a digital basis, which implements a three-stage process: the initial digital circuit, normalizer and random number flow generator; Autonomous Boolean networks (ABN) allow to create RNG with unique characteristics: the received numbers are really random, high speed – the number can be received in one measure, the minimum power consumption, miniature, high (up to 3 GHz) throughput of Boolean chaos; a promising area of ABN development is the use of optical logic valves for the construction of optical ABN with a bandwidth of up to 14 GHz; the classification of known classes of RNG attacks includes: direct cryptanalytic attacks, attacks based on input data, attacks based on the disclosure of the internal state of RNG, correlation attacks and special attacks; statistical test packages to evaluate RNG sequences have some limitations or shortcomings and do not replace cryptanalysis; Comparison of cryptoaccelerators with cryptographic transformation software shows their significant advantages: for AES block encryption algorithm, speeds increase by 10-20 times in 8/16-bit cryptoaccelerators and 150 times in 32-bit, growth hashing of SHA-256 in 32-bit cryptoaccelerators more than 100 times, and for the NMAS algorithm - up to 500 times. …”
Get full text

PHRF-RTDETR: a lightweight weed detection method for upland rice based on RT-DETR by Xianjin Jin, Jinheng Zhang, Fei Wang, Mengyan Zhao, Yunshuang Wang, Jianping Yang, Jinfeng Wu, Bing Zhou

“…To address this issue, we enhanced the baseline model RT-DETR and proposed a lightweight weed detection model for upland rice, named PHRF-RTDETR.MethodsFirst, we propose a novel lightweight backbone network, termed PGRNet, to replace the original computationally intensive feature extraction network in RT-DETR. …”
Get full text