Steel surface defect detection method based on improved YOLOv9 by Cong Chen, Hoileong Lee, Ming Chen

“…To address this issue, this paper proposes an improved steel surface defect detection algorithm based on YOLOv9. First, introducing Depthwise Separable Convolution (DSConv) can effectively reduce the computational complexity of the model, thereby enhancing its operational efficiency. …”
Get full text

Multi-Scale Hierarchical Feature Fusion for Infrared Small-Target Detection by Yue Wang, Xinhong Wang, Shi Qiu, Xianghui Chen, Zhaoyan Liu, Chuncheng Zhou, Weiyuan Yao, Hongjia Cheng, Yu Zhang, Feihong Wang, Zhan Shu

“…Detecting small targets in infrared images presents significant challenges due to their tiny size and complex backgrounds, making this task a hotspot for research. …”
Get full text

A Systematic Review and Comparative Analysis Approach to Boom Gate Access Using Plate Number Recognition by Asaju Christine Bukola, Pius Adewale Owolawi, Chuling Du, Etienne Van Wyk

“…The result of the analysis reveals that each YOLO version has distinct advantages depending on the application’s specific requirements. In complex detection conditions with changing lighting and shadows, it was revealed that YOLOv8 performed better in terms of reduced loss rates and increased precision and recall metrics.…”
Get full text

Intelligent Detection of Tomato Ripening in Natural Environments Using YOLO-DGS by Mengyuan Zhao, Beibei Cui, Yuehao Yu, Xiaoyi Zhang, Jiaxin Xu, Fengzheng Shi, Liang Zhao

“…To achieve accurate detection of tomato fruit maturity and enable automated harvesting in natural environments, this paper presents a more lightweight and efficient maturity detection algorithm, YOLO-DGS, addressing the challenges of subtle maturity differences between regular and cherry tomatoes, as well as fruit occlusion. …”
Get full text

Target Detection Technology of Mechanical, Electrical, and Plumbing Components Based on CV by Guohua Wei, Ding Zhou, Xiaojun Yuan

“…The developed system uses deep learning algorithms for real-time data collection to enhance monitoring efficiency and accuracy, as well as advanced object detection algorithms to compare real-time construction images with BIMs. …”
Get full text

AI-Based Anomaly Detection and Optimization Framework for Blockchain Smart Contracts by Hassen Louati, Ali Louati, Elham Kariri, Abdulla Almekhlafi

“…However, the increasing complexity of these contracts introduces significant challenges, including high computational costs, scalability limitations, and difficulties in detecting anomalous behavior. …”
Get full text

A Strawberry Ripeness Detection Method Based on Improved YOLOv8 by Yawei Yue, Shengbo Xu, Huanhuan Wu

“…An enhanced YOLOv8-based network was developed to accurately and efficiently detect the ripeness of strawberries in complex environments. …”
Get full text

Pedestrian dynamics modeling and social force analysis based on object detection by Fangyan Yang, Rong Liu, Daoyu Zhu

“…IGVIF formulates pedestrian detection as a probabilistic inference problem, leveraging principles from information geometry to efficiently explore high-dimensional parameter spaces. …”
Get full text

Massive MIMO signal detection based on approximate message passing algorithm by Chuang QIN, Ziwei ZHENG, Daping LOU, Xianzu FU

“…Massive multiple-input multiple-output(MIMO)brings huge improvements in energy efficiency and reduces emission power by using a large number of antennas,which is known as a key technology in the fifth generation (5G)mobile communication.With the increasing number of antennas,the complexity of signal detection is increasing at the same time.According to the research status of massive MIMO signal detection,approximate message passing algorithm was proposed.The complexity of AMP was compared to some iteration algorithm like Richarson algorithm and Neumann series approximation algorithm.The results indicate that the proposed algorithm can use less iteration to achieve almost the same performance of MMSE algorithm.…”
Get full text

A Suggested Point Search Algorithm for Circle Detection in Binary Images by Sundus Ebraheem

“…The proposed algorithm was more efficient, where the average ratio of the running time for the proposed algorithm to HT method was 1:646, and the accuracy of the proposed algorithm was 100% for circles detection. …”
Get full text

Log Anomaly Detection Method Based on Transformer and Temporal Convolutional Networks by Niandong Liao, Zihan Liu

“…However, the rapid development of distributed technologies has led to the increasing scale and complexity of log data, resulting in existing methods facing difficulties in fully mining log features and information loss during parsing. …”
Get full text

Security anomaly detection for enterprise management network based on attention mechanism by Zhaohan You, Yucai Zheng

“…It is an enterprise management network security anomaly detection method based on deep learning, aiming to achieve efficient and intelligent monitoring and management of security anomaly data in enterprise management network. …”
Get full text

LiteTom-RTDETR: A Lightweight Real-Time Tomato Detection System for Plant Factories by Wenshuai Liu, Qingzheng Liu, Wenyong Quan, Junli Wang, Xiaomin Yao, Qiang Liu, Yuxiang Tian

“…The proposed LiteTom-RTDETR model was shown to balance high tomato identification accuracy (88.2%) with an excellent real-time inference speed (52.2 frames per second) and computational efficiency (36.3 GFLOPs). Notably, the average detection accuracy of LiteTom-RTDETR was 0.6% higher, its detection speed was 15.5% faster, and its computational load and model size were 36.2% and 31.6% smaller, respectively, than those of the original RTDETR model. …”
Get full text

Insulator Defect Detection Algorithm Based on Improved YOLOv11n by Junmei Zhao, Shangxiao Miao, Rui Kang, Longkun Cao, Liping Zhang, Yifeng Ren

“…Ensuring the reliability and safety of electrical power systems requires the efficient detection of defects in high-voltage transmission line insulators, which play a critical role in electrical isolation and mechanical support. …”
Get full text

Enhancing Cybersecurity: Hybrid Deep Learning Approaches to Smishing Attack Detection by Tanjim Mahmud, Md. Alif Hossen Prince, Md. Hasan Ali, Mohammad Shahadat Hossain, Karl Andersson

“…Experimental results demonstrate that the proposed CNN-Bi-GRU model outperforms existing approaches, achieving an overall highest accuracy of 99.82% in detecting SMS phishing messages. This study provides an empirical analysis of the effectiveness of hybrid deep learning techniques for SMS phishing detection, offering a more precise and efficient solution to enhance cybersecurity in mobile communications.…”
Get full text

Contrastive Learning Algorithm for Low-Resource Cryptographic Attack Event Detection by Peng Luo, Rangjia Cai, Yuanbo Guo

“…Additionally, assigning appropriate weights to keywords of different event types and employing clustering methods for effective classification reduce reliance on manually labeled data, thereby facilitating the training of an efficient cryptographic attack event detection model. …”
Get full text

Anomaly detection in encrypted network traffic using self-supervised learning by Sadaf Sattar, Shumaila Khan, Muhammad Ismail Khan, Ainur Akhmediyarova, Orken Mamyrbayev, Dinara Kassymova, Dina Oralbekova, Janna Alimkulova

“…Compared with existing methods, ET-SSL does not rely on labeled data, scales better, and detects zero day attack in dynamic network environment more effectively, serving as a paradigm for private and energy efficient anomaly detection in encrypted traffic.…”
Get full text

Optimal resource allocation for two-stage connectionless access with collision detection by Xin JIAN, Fang WANG, Jian SONG, Shu FU, Xiaoheng TAN, Xiaoping ZENG

“…Connectionless access allows massive machine type communication (mMTC) devices to transmit small packets without establishment of radio bearers,significantly reducing device power consumption and control signaling overhead.Two-stage connectionless access (TSCLA) improves throughput and resource efficiency by optimally allocating resources between scheduling request (SR) phase and data transmission phase,which can be used for bigger packets and high traffic load.Based on this,a comprehensive theoretical analysis of one kind of TSCLA with collision detection was conducted to investigate its performance limit and devise its optimal resource allocation scheme.In addition,to avoid the complexity of user number estimation,a dynamic resource allocation algorithm with feedback control was proposed.Numerical results are provided to validate the effectiveness of aforementioned theoretical results and show that comparing with the genie aided algorithm known exactly the number of users,the performance loss of the proposed algorithm is within 4%.These works together provide good references for appropriate resource dimensioning for mMTC related protocols.…”
Get full text

A Novel Approach to Speed Up Hampel Filter for Outlier Detection by Mario Roos-Hoefgeest Toribio, Alejandro Garnung Menéndez, Sara Roos-Hoefgeest Toribio, Ignacio Álvarez García

“…This paper proposes a novel Hampel filter variant that replaces the MAD with an original estimator (mMAD) that retains statistical robustness but is computationally more efficient. This reduces the filter’s computational complexity from <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>O</mi><mo>(</mo><mi>N</mi><mo>·</mo><mi>w</mi><mo form="prefix">log</mo><mi>w</mi><mo>)</mo></mrow></semantics></math></inline-formula> to <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>O</mi><mo>(</mo><mi>N</mi><mo>·</mo><mi>w</mi><mo>)</mo></mrow></semantics></math></inline-formula>, where <i>N</i> is the data length and <i>w</i> the window size. …”
Get full text

A Small Target Pedestrian Detection Model Based on Autonomous Driving by Yang Zhang, Shuaifeng Zhang, Dongrong Xin, Dewang Chen

“…Finally, a cascaded autofocus query module is proposed to increase the inference speed of the feature pyramid network through focusing and querying, thus improving the performance and efficiency of small-target pedestrian detection. The experimental results show that the proposed model achieves better detection results than previous models.…”
Get full text