检索结果-内蒙古大学图书馆

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Ghogare, Snehal Dhupe, Shivkanya Kulkarni, Abhijit Shingane, Tanish Gound, Renuka Department of Computer Science and Business Systems JSPM’s Rajarshi Shahu College of Engineering Tathawade Maharashtra Pune India

ISBN: (纸本)9798331522667

The advancement of Artificial Intelligence (AI) and machine learning (ML) has introduced trans- formative solutions in plant care. This review investigates the integration of deep learning and image recognition technologies for identifying and managing plant diseases. The proposed project focuses on developing a user-centric web application designed to detect plant diseases automatically, provide treatment recommendations, suggest nearby nurseries for obtaining necessary supplies, and offer chatbot assistance for user inquiries. Leveraging advanced image recognition techniques, this system aims to make plant care more efficient and accessible. The integration of Google Maps enhances navigation to local nurseries, further simplifying access to resources and promoting better plant care practices. This study outlines current methodologies, explores challenges and opportunities, and proposes a structured framework for creating an intelligent plant care platform to meet the evolving demands of farmers and horticulture professionals. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Psychological Impact of Internet Blackouts: A Case Study With Machine Learning-Based Stress Analysis

引用

IEEE Access 2025年 13卷 83505-83527页

作者： Islam, Mohammad Ariful Islam, Tahidul Hossain, Gahangir Mofazzal Hossain, M. The University of Melbourne Department of Computing and Information Systems MelbourneVIC3010 Australia Bangladesh University of Engineering and Technology Department of Computer Science and Engineering Dhaka1000 Bangladesh University of North Texas Department of Data Science DentonTX76205 United States Southeast University Department of Electrical and Electronic Engineering Dhaka1208 Bangladesh

Access to the internet has become a vital part of modern life, especially for communication and essential services. However, during politically sensitive times, internet blackouts can disrupt daily routines, leading to significant psychological impacts. This study explores the mental health effects of the internet shutdown imposed during the Bangladesh Quota Movement in July 2024, when the government cut off access to control information flow. The blackout hindered communication, financial transactions, and critical services, amplifying stress, feelings of isolation, and emotional distress. A survey of 2,085 participants was conducted to assess the behavioral, emotional, and psychological consequences, particularly in academic, work, and social settings. Stress levels among respondents varied from minimal to extreme, reflecting widespread mental distress. To classify these stress levels, machine learning models;Decision Tree (DT), Random Forest (RF), Bernoulli Naive Bayes (BNB), Logistic Regression (LR), eXtreme Gradient Boosting (XGBoost), and Support Vector Machine (SVM) were applied. The SVM model outperformed others, achieving high precision (99.33%), recall (99.00%), F1-score (99.33%), and accuracy (99.49%). This study underscores the urgent need for mental health support during such crises, particularly in low- and middle-income countries like Bangladesh, where mental health care is often neglected. These findings are aligned with Sustainable Development Goal (SDG 3), "Good Health and Well-Being," stressing the importance of mental health interventions in fostering resilience, well-being, and social stability during crises. © 2013 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

YOLOv8n-CGW: A novel approach to multi-oriented vehicle detection in intelligent transportation systems

引用

Multimedia Tools and Applications 2025年第7期84卷 3809-3840页

作者： Berwo, Michael Abebe Fang, Yong Sarwar, Nadeem Mahmood, Jabar Aljohani, Mansourah Elhosseini, Mostafa School of Information and Engineering Chang’an University Shaanxi Xi’an710064 China Department of Computer Science Bahria University Lahore Campus Punjab Lahore54600 Pakistan Department of Information Technology Faculty of Computing and Information Technology University of Sialkot Punjab Sialkot51040 Pakistan College of Computer Science and Engineering Taibah University Yanbu46421 Saudi Arabia Computers and Control Systems Engineering Department Faculty of Engineering Mansoura University Mansoura35516 Egypt

In the context of Intelligent Transportation systems (ITS), the role of vehicle detection and classification is indispensable for streamlining transportation management, refining traffic control, and conducting in-depth accident analyses. However, the intricate task of accurately detecting multi-oriented vehicles in diverse scenarios remains a challenge, even with the advancements in ITS. Factors such as vehicle morphology, design, road conditions, structural details, and climatic variables provide a significant part in the detection. To address this, our study introduces an advanced YOLOv8n model, specifically the YOLOv8n-CGW, which is built upon pre-trained deep learning frameworks. This model is meticulously tailored to enhance the detection capabilities for multi-oriented vehicles. Comprehensive evaluations on esteemed datasets like MtV, MERGED, Custom dataset, DAWN, WEDGE, and UA-DETRAC underscore the superiority of our approach over existing models. Notably, our YOLOv8n-CGW model achieves a remarkable mAP of 83.3% and boasts a swift inference time of 0.0019s, setting a new benchmark in the domain. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

LightHand99K: A Synthetic Dataset for Hand Pose Estimation With Wrist-Worn Cameras

引用

IEEE Access 2025年 13卷 81423-81433页

作者： Lee, Jeongho Kim, Changho Kim, Jaeyun Kim, Seon Ho Choi, Younggeun Choi, Sang-Il Dankook University Department of Computer Science and Engineering Yongin-si16890 Korea Republic of University of Southern California Integrated Media Systems Center Los AngelesCA90089 United States

Although hand-pose estimation using external camera systems has made significant progress driven by large annotated datasets, wrist-worn camera-based hand-pose estimation offers unique advantages owing to its ability to capture nearby images. However, datasets primarily collected from multi-angle external systems are unsuitable for wrist-camera-based estimation. To address this gap, we developed LightHand99K, a synthetic dataset comprising 99,792 synthetic RGB hand images designed explicitly for hand-pose estimation using wrist-worn cameras. The dataset was generated using a Unity 3D-based hand image generator optimized to efficiently enhance the performance of hand-pose estimation models for wrist-worn camera images by incorporating human finger joint movement information while minimizing computational cost. This tool allows users to customize their poses, camera angles, backgrounds, lighting, and hand-orientation settings. Incorporating three data augmentation techniques, LightHand99K demonstrated a 36% increase in area under the curve (AUC) and a 6.2-mm reduction in average endpoint error (EPE) compared to existing datasets. These results underscore the value of LightHand99K in advancing hand-pose estimation, particularly in wrist-worn camera applications. © 2013 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Binary Stochastic Flip Optimization for Training Binary Neural Networks

Binary Stochastic Flip Optimization for Training Binary Neur...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Shibuya, Tatsukichi Inoue, Nakamasa Kawakami, Rei Sato, Ikuro Department of Computer Science Institute of Science Tokyo Tokyo Japan Department of Systems and Control Engineering Institute of Science Tokyo Tokyo Japan Denso IT Laboratory Tokyo Japan

ISBN: (纸本)9798350368741

For deploying deep neural networks on edge devices with limited resources, binary neural networks (BNNs) have attracted significant attention, due to their computational and memory efficiency. However, once a neural network is binarized, finetuning it on edge devices becomes challenging because most conventional training algorithms for BNNs are designed for use on centralized servers and require storing real-valued parameters during training. To address this limitation, this paper introduces binary stochastic flip optimization (BinSFO), a novel training algorithm for BNNs. BinSFO employs a parameter update rule based on Boolean operations, eliminating the need to store real-valued parameters and thereby reducing memory requirements and computational overhead. In experiments, we demonstrated the effectiveness and memory efficiency of BinSFO in finetuning scenarios on six image classification datasets. BinSFO performed comparably to conventional training algorithms with a 70.7% smaller memory requirement. Code is released at https://***/TatsukichiShibuya/ICASSP2025_BinSFO. © 2025 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Data Aggregation in Cluster-Based Wireless Sensor Networks with LCSS: Longest Common Subsequence Empowerment 8th

Enhancing Data Aggregation in Cluster-Based Wireless Sensor ...

引用

8th World Conference on Smart Trends in systems Security and Sustainability, WorldS4 2024

作者： Jamil, Muhammad Farooq, Umer Tariq, Noshina Alwakid, Ghadah Humayun, Mamoona Khan, Nadia Department of Computer Science Abdul Wali Khan University Mardan Pakistan Department of Computer Science National University of Computer and Emerging Sciences Islamabad Pakistan Department of Avionics Engineering Air University Islamabad Pakistan Department of Computer Science College of Computer and Information Sciences Jouf University Sakaka Al-Jouf Saudi Arabia Department of Information Systems College of Computer and Information Sciences Jouf University Sakaka Al-Jouf Saudi Arabia Institute of Computer Sciences and Information Technology Faculty of Management and Computer Sciences The University of Agriculture Peshawar Pakistan

ISBN: (纸本)9789819793266

A wireless sensor network (WSN) is a system of interconnected sensors that can gather environmental information. On the other hand, data redundancy is a common source of problems with WSNs. The literature presents a plethora of approaches. Despite these mechanisms’ best efforts, most current systems still need help with difficulties like noise, redundancy, or application specificity. Thus, we proposed an algorithm to overcome all the problems with redundant and highly correlated data. The longest common subsequence (LCSS)-enabled sliding window algorithm can resolve issues in constrained networks related to energy conservation and congestion control. The proposed method exhibits remarkable performance on multiple benchmark datasets. According to the result analysis, the suggested technique can outperform its equivalents for a range of data sets by about 32%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Congestion control (communication)

来源：评论

学校读者我要写书评

暂无评论

Hybrid Approach for Electricity Price Forecasting using AlexNet and LSTM 3

Hybrid Approach for Electricity Price Forecasting using Alex...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Sambana, Bosubabu Devi, Kotamsetty Geethika Reddy, Bandi Rajeswara Hussain, Galeti Mohammad Siddartha, Gownivalla School of Computing Mohan Babu University Tirupati India Department of Computer Science and Systems Engineering Sree Vidyanikethan Engineering College Tirupati India

ISBN: (纸本)9798331527549

The recent development of advanced machine learning methods for hybrid models has greatly addressed the need for the correct prediction of electrical prices. This method combines AlexNet and LSTM algorithms, which are used to introduce a new model with higher accuracy in price forecasting. Despite RNN and ANN being effective, they often fail to deal with forex time sequence data. The traditional methods do not accurately forecast the prices. These traditional methods only focus on demand and price which leads to insufficient analysis of data. To address this issue, using the hybrid approach, which focuses on external variables that also effect the predicted prices. Nevertheless, due to AlexNet's excellent feature extraction and LSTM's learning sequential patterns, the prediction accuracy is vastly increased. The model is built on the past data, which has been supplied with the most significant elements like demand, temperature, sunlight, and rain. For example, the model applies methods, such as minimum-maximum scaling and a time window, to predict the electricity prices of the future. The results show that this hybrid model is good than the standalone ones in terms of accuracy. Although we got our accuracy rating of 97.08, it shows higher accompaniments than remaining models RNN and ANN with accuracies of 96.64 and 96.63 respectively. © 2025 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Ladon: High-Performance Multi-BFT Consensus via Dynamic Global Ordering 25

Ladon: High-Performance Multi-BFT Consensus via Dynamic Glob...

引用

20th European Conference on computer systems, EuroSys 2025, co-located 30th ACM International Conference on Architectural Support for programming Languages and Operating systems, ASPLOS 2025

作者： Lyu, Hanzheng Xie, Shaokang Niu, Jianyu Feng, Chen Zhang, Yinqian Beschastnikh, Ivan Canada Southern University of Science and Technology China Canada Research Institute of Trustworthy Autonomous Systems Department of Computer Science and Engineering SUSTech China

ISBN: (纸本)9798400711961

Multi-BFT consensus runs multiple leader-based consensus instances in parallel, circumventing the leader bottleneck of a single instance. However, it contains an Achilles’ heel: the need to globally order output blocks across instances. Deriving this global ordering is challenging because it must cope with different rates at which blocks are produced by instances. Prior Multi-BFT designs assign each block a global index before creation, leading to poor performance. We propose Ladon, a high-performance Multi-BFT protocol that allows varying instance block rates. Our key idea is to order blocks across instances dynamically, which eliminates blocking on slow instances. We achieve dynamic global ordering by assigning monotonic ranks to blocks. We pipeline rank coordination with the consensus process to reduce protocol overhead and combine aggregate signatures with rank information to reduce message complexity. Ladon’s dynamic ordering enables blocks to be globally ordered according to their generation, which respects inter-block causality. We implemented and evaluated Ladon by integrating it with both PBFT and HotStuff protocols. Our evaluation shows that Ladon-PBFT (resp., Ladon-HotStuff) improves the peak throughput of the prior art by ≈ 8× (resp., 2×) and reduces latency by ≈ 62% (resp., 23%), when deployed with one straggling replica (out of 128 replicas) in a WAN setting. © 2025 Copyright held by the owner/author(s).

关键词： Network protocols

来源：评论

学校读者我要写书评

暂无评论

Adaptive Quantum and Graph-Attentive Security Framework for DoS Attack Mitigation in VANETs 2

Adaptive Quantum and Graph-Attentive Security Framework for ...

引用

2nd International Conference on Machine Learning and Autonomous systems, ICMLAS 2025

作者： Anjum, Asma Rao, P. S. V. Srinivasa Sindhu, M. Bhatt, Pooja Priya, M.R. Maranan, Ramya HKBK College of Engineering Department of Computer Science and Engineering Karnataka Bengaluru560045 India Joginpally B R Engineering College Department of Computer Science and Engineering Telangana Hyderabad500075 India R.M.K Engineering College Department of Computer Science and Business Systems Tamil Nadu Thiruvallur601206 India Parul institute of Engineering and Technology Parul University Computer Science and Engineering Faculty of Engineering and Technology Post Limda Gujarat 391760 India NIE First Grade College Department of Computer Science Karnataka Mysuru570008 India Saveetha School of Engineering SIMATS Department of Research and Innovation Tamil Nadu Chennai602105 India

ISBN: (纸本)9798331505745

Vehicular Ad Hoc Networks (VANETs) are considered crucial for real-time vehicle-to-vehicle communication, which in turn enhances the efficiency of traffic and road safety. VANETs are very vulnerable to Denial-of-Service (DoS) attacks, which seriously disrupt communication and degrade network performance. This paper introduces a high-performance neural network-based detection and prevention mechanism that can effectively counter DoS attacks. The proposed method is initiated with the real-time monitoring of the network. Data collection and preprocessing through the Adaptive Self-Guided Loop Filter (ASGLF) are used to filter out noise from the data. The Fast Hybrid Vision Transformer (FHVT) conducts feature extraction for network traffic to effectively preserve the spatial and temporal relationships. Using the Reflecting Equivariant Quantum Neural Network (REQNN) integrated with Heterogeneous Edge-Enhanced Graph Attention Network (HEEGAT) ensures timely anomaly detection accuracy of attacks. Subtraction-Average-Based Optimizer (SAO) optimizes the detection parameters to effectively utilize resources. The experimental results have shown accuracy in the detection of DoS attacks as 99.9% with a PDR of 99.9% and also improved throughput efficiency by 99.8%. These results validate the effectiveness of the proposed model in securing VANETs from DoS attacks, offering uninterrupted network availability and improved vehicular communication security for intelligent transportation systems. © 2025 IEEE.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

Segmentation of CAD models using hybrid representation

引用

虚拟现实与智能硬件(中英文) 2025年第2期7卷 188-202页

作者： Claude UWIMANA Shengdi ZHOU Limei YANG Zhuqing LI Norbelt MUTAGISHA Edouard NIYONGABO Bin ZHOU State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Peace-Bay Academy of Virtual Reality Shenyang 110004China China Aerospace Systems Engineering Corporation Beijing 100070China Department of Signal and Information Processing Beihang UniversityBeijing 100191China Department of Computer Science University of SherbrookeSherbrooke J1C0A1Canada

In this paper,we introduce an innovative method for computer-aided design(CAD)segmentation by concatenating meshes and CAD *** previous CAD segmentation methods have achieved impressive performance using single representations,such as meshes,CAD,and point ***,existing methods cannot effectively combine different three-dimensional model types for the direct conversion,alignment,and integrity maintenance of geometric and topological ***,we propose an integration approach that combines the geometric accuracy of CAD data with the flexibility of mesh representations,as well as introduce a unique hybrid representation that combines CAD and mesh models to enhance segmentation *** combine these two model types,our hybrid system utilizes advanced-neural-network techniques to convert CAD models into mesh *** complex CAD models,model segmentation is crucial for model retrieval and *** partial retrieval,it aims to segment a complex CAD model into several simple *** first component of our hybrid system involves advanced mesh-labeling algorithms that harness the digitization of CAD properties to mesh *** second component integrates labelled face features for CAD segmentation by leveraging the abundant multisemantic information embedded in CAD *** combination of mesh and CAD not only refines the accuracy of boundary delineation but also provides a comprehensive understanding of the underlying object *** study uses the Fusion 360 Gallery *** results indicate that our hybrid method can segment these models with higher accuracy than other methods that use single representations.

关键词： B-RepNet hybrid segmentation CAD models classification MeshCNN MeshCAD-Net

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：