A hybrid attack detection strategy for cybersecurity using moth elephant herding optimisation‐based stacked autoencoder by Abdullah Shawan Alotaibi

“…The class‐aware features, like traffic‐based features, content‐based features and basic features are selected efficiently. …”
Get full text

An open flame and smoke detection dataset for deep learning in remote sensing based fire detection by Ming Wang, Peng Yue, Liangcun Jiang, Dayu Yu, Tianyu Tuo, Jian Li

“…Taking the advantage of rapid advancements in remote sensing technology and artificial intelligence, we introduce the Flame And Smoke Detection Dataset (FASDD), a pioneering collection comprising over 120,000 heterogeneous images covering various fire scenarios, aiming to promote the evolution of fire detection models. FASDD serves as a challenging benchmark for object detection tasks and features three sub-datasets: FASDD_CV, FASDD_UAV, and FASDD_RS. …”
Get full text

Artificial Intelligence Applied in Early Prediction of Lower Limb Fracture Complications by Aurelian-Dumitrache Anghele, Virginia Marina, Liliana Dragomir, Cosmina Alina Moscu, Iuliu Fulga, Mihaela Anghele, Cristina-Mihaela Popescu

“…Key features included patient demographics, laboratory investigations, and clinical outcomes. …”
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

A Comprehensive All-sky Catalog of 3345 Molecular Clouds from Three-dimensional Dust Extinction by Tao Wang, Haibo Yuan, Bingqiu Chen, Guangxing Li, Bowen Huang, Helong Guo, Ruoyi Zhang

“…Understanding the distribution and properties of molecular clouds is crucial for tracing the structure and evolution of the interstellar medium (ISM) and the large-scale morphology of the Milky Way. …”
Get full text

Machine Learning for Identifying Damage and Predicting Properties in 3D-Printed PLA/Lygeum Spartum Biocomposites by Khalil Benabderazag, Moussa Guebailia, Zouheyr Belouadah, Lotfi Toubal, Salah Eddine Tachi

“…This comprehensive methodology not only enhances our understanding of damage evolution in composite materials but also establishes a data-driven framework for non-destructive evaluation and structural health monitoring.…”
Get full text

Analysis and prediction of land use changes: the case study of coastal areas of Gilan province by Sahar Abdollahi, Hashem Dadashpoor

“…This region is important in terms of its unique features and human use of this environment for a variety of residential, industrial, and recreational activities. …”
Get full text

Improved YOLOv8 Model for Multi-type Lung Nodule Detection by BAO Qiangqiang, TANG Siyuan, LI Qingqian, WANG Naiyu, YANG Min, GU Yu, ZHAO Jinliang, GAO Jingbo, WANG Jiaxin, QU Yuhan

“…Then, the KAN network is integrated into the model further to improve the detection accuracy of tiny lung nodules and enhance the generalization ability of the model based on the strong learning ability of nonlinear features of the KAN network. …”
Get full text

DBA-ViNet: an effective deep learning framework for fruit disease detection and classification using explainable AI by Saravanan Srinivasan, Lalitha Somasundharam, Sukumar Rajendran, Virendra Pal Singh, Sandeep Kumar Mathivanan, Usha Moorthy

“…A new model, the Dual-Branch Attention-Guided Vision Network (DBA-ViNet), was introduced. A hybrid with two branches of DBA-ViNet can efficiently integrate global and local features for improved disease identification accuracy. …”
Get full text

Systems thinking and modelling to support transformative change: key lessons from inter-disciplinary analysis of socio-ecological systems in applied land systems research by Miriam Glendell, Matt Hare, Kerry A. Waylen, Kerr Adams, Jean Léon Boucher, Zisis Gagkas, Alessandro Gimona, Simone Martino, Keith B. Matthews, J. Gareth Polhill

“…We also reiterate the call for sustained funding for long-term, standards-based evaluation of systems thinking approaches with respect to whether their use can demonstrate instrumental impacts leading to the kind of transformation the IPCC has called for, i.e. fundamental system change that goes beyond capacity development impacts such as network-building.…”
Get full text

TF-CEP: carbon emission prediction with data augmentation and temporal-frequency fusion contrasting by Zhiqiang Ma, Qi Yang, Fei Liang, Yuliang Shi, Jieying Kang, Peng Liu

“…In order to improve the generalization ability of the model, GAN is used for data augmentation of the power data, and 1-Dimensional Convolutional Neural Network and frequency enhanced channel attention Mechanism methods are used to learn the temporal domain feature information and the frequency domain feature information of the power data, respectively. …”
Get full text

A synergistic approach for enhanced eye blink detection using wavelet analysis, autoencoding and Crow-Search optimized k-NN algorithm by M. Chandralekha, N. Priyadharshini Jayadurga, Thomas M. Chen, Mithileysh Sathiyanarayanan, Kasif Saleem, Mehmet A. Orgun

“…It becomes evident after a detailed evaluation that conventional machine learning algorithms if implemented with correct feature extraction and fine-tuning surpass the deep learning approaches including the frameworks composed of Convolutional Neural Network and Principal Component Analysis and empirical mode decomposition by approximately 96% across all datasets. …”
Get full text

Monitoring Vegetation Dynamics in Desertification Restoration Areas of Wuzhumuqin Grassland Ecosystem by Fuguang Yang, Zhiguo Wang, Yongguang Zhai, Xiangli Yang, Tengfei Bao, Yonghui Wang

“…At the same time, a transform three-branch network structure based on deep learning is proposed to extract visual features. …”
Get full text

Visual nutrition analysis: leveraging segmentation and regression for food nutrient estimation by Yaping Zhao, Yaping Zhao, Ping Zhu, Ping Zhu, Yizhang Jiang, Kaijian Xia, Kaijian Xia

“…Specifically, we first applied the UNet model to segment the food, then used a backbone network to extract features, and enhanced the feature expression capability through the Squeeze-and-Excitation structure. …”
Get full text

ILN-YOLOv8: A Lightweight Image Recognition Model for Crimped Wire Connectors by Xiaojian Zhou, Jicheng Kan, Nur Fatin Liyana Mohd Rosely, Xu Duan, Jiajing Cai, Zihan Zhou

“…Taking the original YOLOv8 model as a baseline, the new model enhances the ability to extract shallow features from small targets by increasing the P2 detection layer and improving the Feature Pyramid Network(FPN) and Path Aggregation Network(PAN) structures. …”
Get full text

Artificial Intelligence for Automatic Pain Assessment: Research Methods and Perspectives by Marco Cascella, Daniela Schiavo, Arturo Cuomo, Alessandro Ottaiano, Francesco Perri, Renato Patrone, Sara Migliarelli, Elena Giovanna Bignami, Alessandro Vittori, Francesco Cutugno

“…Although proper pain evaluation is mandatory for establishing the appropriate therapy, self-reported pain level assessment has several limitations. …”
Get full text

A deep learning-based prognostic approach for predicting turbofan engine degradation and remaining useful life by Samiha M. Elsherif, Bassel Hafiz, M. A. Makhlouf, Osama Farouk

“…A fully connected layer of the convolutional neural network is used to further process the important features. …”
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

“…It features a lightweight architecture with 0.0709M parameters and 0.0389G flops, distinguishing it from the AcT models. …”
Get full text

A novel framework integrating GeoAI and human perceptions to estimate walkability in Wuhan, China by Xue Yang, Tianyu Li, Yanjia Cao, Xiaoyun Zheng, Luliang Tang

“…Additionally, existing image segmentation techniques return low accuracy when extracting complex street environment features. Therefore, we developed a hierarchical evaluation framework for urban walkability with high precision image segmentation techniques, and subjective measurements on four first-level indicators (greenness, openness, crowding, safety) and their corresponding second-level indicators. …”
Get full text

A texture enhanced attention model for defect detection in thermal protection materials by Jialin Song, Zhaoba Wang, Kailiang Xue, Youxing Chen, Guodong Guo, Maozhen Li, Asoke K. Nandi

“…Moreover, we improve the model’s ability to detect multi-scale defects through a path aggregation network. The evaluation on the TPMDR-dataset and public dataset shows that the TADD model achieves a higher mean Average Precision (mAP) compared to other methods while maintaining 25 frames per second, exceeding the baseline model by 11.05%.…”
Get full text