WindDefNet: A Multi-Scale Attention-Enhanced ViT-Inception-ResNet Model for Real-Time Wind Turbine Blade Defect Detection by Majad Mansoor, Xiyue Tan, Adeel Feroz Mirza, Tao Gong, Zhendong Song, Muhammad Irfan

“…Real-time non-intrusive monitoring of wind turbines, blades, and defect surfaces poses a set of complex challenges related to accuracy, safety, cost, and computational efficiency. …”
Get full text

Evaluation of Effectiveness of a New Kit of Reagents for Detection of Mutations Associated with Drug Resistance of Tuberculous Mycobacteria to Rifampicin and Isoniazid, by PCR acco... by Yu. L. Mikulovich, Yu. A. Savochkina, A. I. Zaytseva, A. E. Panova, A. S. Vinokurov, G. A. Shipulin

“…Efficiency of detecting mutations associated with MTB resistance to RIF and INH using the new kit of reagent of AmpliTest® MBT-Resist-I was evaluated in comparison with HP Amplitube-MDR-RV (OOO Sintol, Russia). …”
Get full text

Remote Sensing Image Enhancement Via Edge-Preserving Multiscale Retinex by Lu Teng, Feng Xue, Qiudi Bai

“…Comparing with the previous algorithms, the proposed one can obtain more edge details and better color fidelity but with lower computational complexity and higher efficiency.…”
Get full text

A Comprehensive Study on Lightweight Convolution Techniques for Malicious Traffic Synthesis in Diffusion Models by Fuhao Li, Ifiok Udoidiok, Jielun Zhang

“…The experimental results demonstrate that the investigated lightweight approaches can efficiently generate high-quality and diverse malicious traffic data for enhancing the performance of intrusion detection systems while the computational complexity is reduced to around 19.69% of the baseline.…”
Get full text

Predicting communities with high tuberculosis case-finding efficiency to optimise resource allocation in Pakistan: comparing the performance of a negative binomial spatial lag mode... by Hasan Tahir, Frank Cobelens, Christina Mergenthaler, Mirjam I Bakker, Tanveer Ahmed, Jake D Mathewson, Daniella Brals, Abdullah Latif, Stephanie Lako, Andreas Werle van der Merwe, Matthys Potgieter, Vincent Meurrens, Zia Samad, Ente Rood

Get full text

Outlier Ensemble Based on Isolation Forest: The CBOEA Approach by Chaabouni Ali, Boujelben Mohamed Ayman

“…This approach handles large data sets quite well, thanks to its low time complexity. However, IF struggles to detect local outliers. …”
Get full text

LocaLock: Enhancing Multi-Object Tracking in Satellite Videos via Local Feature Matching by Lingyu Kong, Zhiyuan Yan, Hanru Shi, Ting Zhang, Lei Wang

“…Specifically, LocaLock utilizes an anchor-free detection backbone for efficiency and employs a local cost volume (LCV) module to perform precise feature matching in the local area. …”
Get full text

A New Approach Based on Metaheuristic Optimization Using Chaotic Functional Connectivity Matrices and Fractal Dimension Analysis for AI-Driven Detection of Orthodontic Growth and D... by Orhan Cicek, Yusuf Bahri Özçelik, Aytaç Altan

“…To effectively model the nonlinear dynamics, chaotic maps were generated, representing a significant advance over traditional methods. Feature selection was performed using a wrapper-based approach combining k-nearest neighbors (kNN) and the Puma optimization algorithm, which efficiently handles the chaotic and computationally complex nature of cervical vertebrae images. …”
Get full text

A comparative study of machine learning algorithms for fall detection in technology-based healthcare system: Analyzing SVM, KNN, decision tree, random forest, LSTM, and CNN by Afuan Lasmedi, Isnanto R. Rizal

“…The implications of these findings that the selection of fall detection algorithms must consider system priorities, whether focused on high accuracy or processing efficiency. …”
Get full text

Deep eutectic solvent-based magnetic molecular nanomaterials coupled with fluorescent carbon dots as a new strategy to highly enrich and sensitively detect doxycycline in food matr... by Yanqiong Luo, Han Zhang, Jun Liu, Aleeza Jamil, Yujiao Hou, Qian Li, Min Zhao, Chunjie Zhao, Wenjing Li, Bo Hong

“…This strategy of integrating CDs and DES–MMIP for DOX detection conforms to the green concept of environmental protection and provides a new material and research approach for efficient analysis of DOX in complex matrices.…”
Get full text

Research and application of Gaussian coupled control bistable stochastic resonance system with independent parameter regulation by Tiantian Hou, Shangbin Jiao, Yi Wang, Nianlong Song, Jianghua Li, Wenchuan Cui

Get full text

A hybrid constrained multi-objective algorithm for dynamic economic emission dispatch by Shuqu Qian, Huihui He, Huihong Wu, Philippe Fournier-Viger, Hui Li, Shoude Huang

“…Dynamic Economic Emission Dispatch (DEED) problems present a critical multi-objective optimization challenge in power systems, requiring simultaneous minimization of conflicting objectives of costs and emissions while addressing complex operational constraints. This problem becomes particularly intricate when considering the Valve-Point Effect Cost (VPEC) in generation units, which exhibits non-smooth, non-convex characteristics that significantly complicate solution landscapes. …”
Get full text

Cross-attention swin-transformer for detailed segmentation of ancient architectural color patterns by Lv Yongyin, Yu Caixia

“…Traditional approaches, including convolutional neural networks (CNNs) and standard transformer-based models, have achieved significant success; however, they often face challenges in capturing fine-grained details and maintaining efficiency across diverse datasets. These methods struggle with balancing precision and computational efficiency, especially when dealing with complex patterns and high-resolution images.MethodsTo address these limitations, we propose a novel segmentation model that integrates a hierarchical vision transformer backbone with multi-scale self-attention, cascaded attention decoding, and diffusion-based robustness enhancement. …”
Get full text

Design and Implementation of an Intelligent Pest Status Monitoring System for Farmland by Xinyu Yuan, Zeshen He, Caojun Huang

“…For overlapping pest detection, EfficientNetv2-S replaces the YOLOv5s backbone and is combined with an Adaptive Feature Pyramid Network (AFPN), achieving 95.72% detection accuracy, 94.04% mAP, and 127 FPS. …”
Get full text

AFQSeg: An Adaptive Feature Quantization Network for Instance-Level Surface Crack Segmentation by Shaoliang Fang, Lu Lu, Zhu Lin, Zhanyu Yang, Shaosheng Wang

“…However, under real-world conditions such as poor image quality, environmental interference, and complex crack patterns, existing models still face challenges in detecting fine cracks and often rely on large training parameters, limiting their practicality in complex environments. …”
Get full text

Multi-Stage Neural Network-Based Ensemble Learning Approach for Wheat Leaf Disease Classification by Samia Nawaz Yousafzai, Inzamam Mashood Nasir, Sara Tehsin, Dania Saleem Malik, Ismail Keshta, Norma Latif Fitriyani, Yeonghyeon Gu, Muhammad Syafrudin

“…The various stages in the EL approach employ a multi-level framework to enhance feature extraction and capture complex data patterns. This improves the model’s emphasis on diseases while reducing the influence of complex backgrounds on disease identification. …”
Get full text

Secure Biometric Identification Using Orca Predators Algorithm With Deep Learning: Retinal Iris Image Analysis by Louai A. Maghrabi, Mohammed Altwijri, Sami Saeed Binyamin, Fouad Shoie Alallah, Diaa Hamed, Mahmoud Ragab

“…Besides, the SBRIC-OPADL technique exploits the EfficientNet model for the extraction of feature vectors. …”
Get full text

Accuracy and robustness evaluation of deep learning algorithms in facial recognition systems by Jing Zhang, Ningyu Hu

“…First, the YOLO model is improved by introducing the EfficientNet to enhance the performance of the facial detection model. …”
Get full text

Automatic serving method of volleyball training robot based on improved YOLOv5 and improved Hough transform by Tao Sun, Xiaolong He, Jiajun Zhang

“…However, due to the characteristics of volleyball, such as small size, fast speed, and susceptibility to occlusion and noise interference in complex backgrounds, traditional object detection methods are hard to meet their real-time and accuracy requirements. …”
Get full text

Hierarchical proxy consensus optimization for IoV based on blockchain and trust value by Baoqin ZHAI, Jian WANG, Lei HAN, Jiqiang LIU, Jiahao HE, Tianhao LIU

“…With the rapid development of Internet of vehicles, 5G and artificial intelligence technologies, intelligent transportation has become the development trend of transportation technology.As a vehicle-vehicle and vehicle-road information interaction platform, the Internet of vehicles is the basic support platform for intelligent traffic information sharing and processing.At the same time, the security of Internet of vehicles has attracted much attention, especially data security which may cause user privacy leakage.The blockchain technology has become a solution, but it still faces new challenges in efficiency, security and other aspects.With the increase of vehicle nodes and information, how to efficiently achieve information consensus in high-speed vehicle moving environment has become a key problem.Then a bottom-up RSU (road side unit) chain consensus protocol was proposed based on blockchain and trust value.Several typical consensus structures were compared, and bottom-up two-layer consensus structure was adopted according to the actual scenarios of the Internet of vehicles.Moreover, a group leader node election algorithm was proposed which is based on node participation, work completion and message value.The system security was ensured by assigning trust value to each vehicle.Following the consensus structure and algorithm work mentioned above, the specific process of the protocol was comprehensively described, which was divided into six steps: region division, group leader node selection, local consensus, leader primary node selection, global consensus, and intra-domain broadcast.Then the experiments were analyzed from four aspects: security, communication complexity, consensus algorithm delay and fault tolerance rate.Experiments showed that, compared with other schemes, the proposed protocol can effectively reduce communication complexity and shorten consensus delay under the condition of resisting conspiracy attack, witch attack and other attacks.On the premise of security, the protocol improves fault tolerance rate and enables more nodes to participate in information sharing to satisfy the requirements of Internet of vehicles scenarios.…”
Get full text