检索结果-内蒙古大学图书馆

Support Vector Regression Based Traffic Prediction Machine Learning Model∗ 8

Support Vector Regression Based Traffic Prediction Machine L...

8th IEEE International Conference on Computational System and Information Technology for Sustainable Solutions, CSITSS 2024

作者： Srivastava, Ansh Singh, Mrigaannkaa Nandi, Somesh Rv College of Engineering Dept. of Computer Science and Engineering Bengaluru India Rv College of Engineering Dept. of Electronics and Communication Bengaluru India Rv College of Engineering Dept. of AI/ML Bengaluru India

ISBN: (纸本)9798331505462

To combat the rising issue of urban traffic congestion, optimization of traffic light timings at intersections is crucial. Traditional methods show stagnancy in managing traffic flow dynamically. This study introduces Support Vector Regression (SVR) as an unconventional solution for traffic signal optimization. The model predicts the traffic conditions and alters the green light to turn on and off accordingly. Utilization of a comprehensive dataset consisting of vehicle distributions and critical flow ratios have been implemented to training a machine learning model. The statistics and performance is checked by usage of Mean Squared Error, R Squared, Mean Absolute Error demonstrating that SVR can effectively enhance traffic signal control. This approach pledges significant improvements in reduction in congestion and streamlined traffic flow. Our findings majorly highlight the capability of the SVR Machine Learning model in improving urban traffic management systems and call for further enhancement and collaboration with experts to address dynamic traffic issues. © 2024 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Smart Home Automation with Smart Metering Using ZigBee Technology and Deep Belief Networks - Optimization Using MB-ABCOA Algorithm 2

Smart Home Automation with Smart Metering Using ZigBee Techn...

引用

2nd IEEE International Conference on Contemporary Computing and Communications, InC4 2024

作者： Navaz, K. Mano Raja Paul, M. Yamuna Bee, J. Kavitha, S. Bhuvanesh, A. Mariappan, R. Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Computer Science and Engineering Chennai India Nehru Institute of Engineering and Technology Department of Electrical and Electronics Engineering Coimbatore India PSN College of Engineering and Technology Department of Computer Science and Engineering Tirunelveli India Sri Eshwar College of Engineering Department of English Tamil Nadu Coimbatore India PSN College of Engineering and Technology Department of Electrical and Electronics Engineering Tirunelveli India

ISBN: (纸本)9798350383652

In the domain of smart homes and smart metering, ZigBee technology plays a pivotal role within the energy efficiency of homes, albeit facing challenges such as packet transmission delays and uneven energy consumption among nodes. To address these issues while emphasizing energy efficiency, we propose the Energy-efficient ZigBee Directionally Opportunistic Short-cut Trees Routings (EP-ZDOSTR), which optimizes network lifetimes and throughput by prioritizing energy-efficient packet transmission. Complemented by a hybrid Monarchy Butterfly and Artificial Bees Colonies Optimizations Algorithms (MB-ABCOA) approach, EP-ZDOSTR demonstrates significant improvements in network performances metric, including higher throughputs, increased packet delivery ratios, reduced transmission delays, and minimized energy consumption. Comparisons with existing methods like ZigBee shortcut tree routing (ZSTR), ZigBee opportunistic shortcut tree routing (ZOSTR), and Energy Efficient shortcut tree routing (EPSTR) validate its superiority in enhancing overall network efficiency and reliability. Furthermore, integrating ZigBee with Deep Belief Networks (DBNs) holds promise for further enhancing network intelligence, enabling predictive analysis of energy usage patterns and optimization of network operations, thereby advancing the capabilities of smart home in the context of smart homes and metering systems within the IoT landscape. © 2024 IEEE.

关键词： Zigbee

来源：评论

学校读者我要写书评

暂无评论

Economic Analysis of Joint Mobile Edge Caching and Peer Content Sharing 42

Economic Analysis of Joint Mobile Edge Caching and Peer Cont...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Jiang, Changkun Shenzhen University College of Computer Science and Software Engineering China

ISBN: (纸本)9798350334142

Mobile edge caching (MEC) allows edge devices to cache popular contents and deliver them to end-users directly, which can effectively alleviate increasing backbone loads and improve end-users' quality of service. Peer content sharing (PCS) enables edge devices to share the cached contents with others, and can further increase the caching efficiency. While many efforts have been made to content caching or sharing technologies, it remains open to study the complicated technical and economic interplay between both technologies. In this paper, we propose a joint MEC-PCS framework, and focus on capturing the strategic interactions between different types of edge devices. Specifically, we model their interactions as a non-cooperative game, where each device (player) can choose to be an agent (who caches and shares contents with others) or a requester (who doesn't cache but requests contents from others) of each content. We analyze the existence and uniqueness of the game equilibrium systematically under the generic usage-based pricing (for PCS). To address the incomplete information issue, we further design a behavior rule that allows players to achieve the equilibrium via a dynamic learning algorithm. Simulations show that the joint MEC-PCS framework can reduce the total system cost by 60%, compared with the benchmark pure caching system without PCS. © 2023 IEEE.

关键词： Economic analysis

来源：评论

学校读者我要写书评

暂无评论

Hyperparameter Adaptive Neural Network Model for E-Commerce Sales Prediction 9

Hyperparameter Adaptive Neural Network Model for E-Commerce ...

引用

9th International Conference on Fuzzy Systems and Data Mining, FSDM 2023

作者： Zhao, GuangLu Tian, Ran Wang, JingXia College of Computer Science & Engineering Northwest Normal University China

ISBN: (纸本)9781643684703

Sales forecasting plays a vital role in the daily operations of e-commerce companies, impacting market assessment, operational planning, and supply chain management. As the market is constantly changing, accurately predicting sales is a critical challenge that e-commerce companies need to urgently address. However, traditional statistical forecasting methods have disadvantages such as long run times, low accuracy, weak generalization, and strong data periodicity, which lead to unnecessary losses for companies. We propose the QLBiGRU model that utilizes the reinforcement learning Q-Learning algorithm combined with BiGRU to improve forecasting accuracy. Automatic parameter optimization technology is also used to reduce training time and demand for hardware resources, thereby enabling enterprices to accurately analyze the market and make informed decisions. © 2023 The authors and IOS Press.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Identification of Fake and Spam Users on Social Networking Platforms

Identification of Fake and Spam Users on Social Networking P...

引用

2023 Intelligent Computing and Control for engineering and Business Systems, ICCEBS 2023

作者： Rajesh, G. Kalaivani, K. Priya Hemalatha, D. Prabhu, V. Siva Rama Lingham, N. Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai India Jeppiaar Engineering College Department of Computer Science and Engineering Chennai India R.M.K Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350394580

Social networking sites attract several users from varied parts around the world. Some of the popular sites containing a huge volume of users are Twitter, Facebook, and so on. All these sites poses a significant impact among its users and sometimes undesirable for a standard of living. Considering the huge number of users, these online platforms are targeted by the spammers as a threat to the user's privacy as well as a harmful effect to the site itself. One among those sites is the Twitter, which in short time has attracted huge amount of users and in turn has lead forward to itself to the online spammers. These spammers act as authorized users and send fake users. Consequently, Twitter has become a typical analysis space in today's online social networks (OSN). In addition, a classified taxonomy of the Twitter spam detection movement is presented, categorizing the techniques supported in their detection: (i) fake content, (ii) spammed computer addresses, (iii) The bestowed options, structure options, and time options or information in the social media platform. Those information most of the time are found to be misleading or otherwise may affect the sentimental behavior of other valid users also. In this way, harmful content is widely spread, techniques are compared with many supported options, such as user settings content settings, the diagram triggers others to send unwanted tweets or misidentify other valid users among the network platform, and sometimes even makes users be. They needed to be more effectively provided with resources. To protect the users from this kind of spammers, recently, a methodology has used to detect and identify. © 2023 IEEE.

关键词： Client Side Error Detection Fake Users Online Social Networks Server Side Spam Detection Trending Topics Twitter

来源：评论

学校读者我要写书评

暂无评论

An Unbiased Fuzzy Weighted Relative Error Support Vector Machine for Reverse Prediction of Concrete Components

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第9期5卷 4574-4584页

作者： Fan, Zongwen Gou, Jin Weng, Shaoyuan College of Computer Science and Technology Huaqiao University Xiamen361021 China School of Software Engineering Xiamen Institute of Software Technology Xiamen361024 China

Concrete is a vital component in modern construction, prized for its strength, durability, and versatility. Accurately determining the quantities of concrete components is crucial in civil engineering applications to optimize resources (e.g., manpower and financial resources). In this article, we propose an unbiased fuzzy-weighted relative error support vector machine (UFW-RE-SVM) for reverse prediction of concrete components. First, we add an unbiased term to the target function of UFW-RE-SVM for obtaining an unbiased model. Second, we design a fuzzy-weighted operation to indicate sample importance by incorporating the fuzzy membership values into the UFW-RE-SVM. The nth root operation is introduced to address the exponential explosion issue in the fuzzy-weighted operation. Finally, considering the UFW-RE-SVM is sensitive to its hyperparameters for multioutput prediction, the whale optimization algorithm (WOA) is utilized for hyperparameter optimization for its effectiveness in optimization tasks. We design the fitness function based on the results from multiple components to balance the performance of multioutput predictions. Experimental results show that the performance of our proposed model outperforms existing works in predicting concrete components in terms of mean absolute relative error, standard deviation, and root mean square error. Further, the statistical test shows the WOA and two other metaheuristics can significantly improve the prediction performance. This indicates that the unbiased term, fuzzy-weighted operation, and WOA are effective for improving the proposed model for reverse prediction concrete components. With these promising results, the proposed model could provide decision-makers with a valuable tool for determining concrete component quantities based on desired concrete qualities. © 2020 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Secure Clustering Routing Mechanism Based on Trust Evaluation in WSN 15

A Secure Clustering Routing Mechanism Based on Trust Evaluat...

引用

15th International Conference on Communication Software and Networks, ICCSN 2023

作者： Wang, Ze Yi, Xiushuang Han, Zhenling Xu, Wenhao College of Computer Science and Engineering Northeastern University Shenyang China

ISBN: (纸本)9798350329360

Wireless Sensor Networks (WSN) are susceptible to malicious attacks, leading to network performance degradation. In this paper, we propose a novel secure clustering routing mechanism based on trust evaluation to address this challenge. To optimize energy consumption, we divide the network into neighborhood and non-neighborhood regions. In the non-neighborhood, nodes' trust levels are evaluated based on behavior characteristics and collected data, encompassing direct trust, recommendation trust, history trust, and data trust. The optimal cluster head is selected during the clustering stage by calculating competition time, considering factors like trust level and residual energy. To minimize energy consumption for remote nodes, a multi-hop routing mechanism is employed in the inter-cluster routing stage. The trust level is considered in selecting the next hop, thereby enhancing route security. A simulation experiment is conducted using the OMNET++ simulator to evaluate the performance of the proposed method. The proposed cluster routing mechanism is compared with two well-established clustering routing algorithms, LEACH and EEUC. Experimental results demonstrate that the proposed method effectively mitigates the impact of malicious nodes on the network and significantly improves network performance. © 2023 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Sugarcane Classification of Image Processing and Convolutional Neural Networks 2

Sugarcane Classification of Image Processing and Convolution...

引用

2nd International Conference on Smart Technologies and Systems for Next Generation Computing, ICSTSN 2023

作者： Kavitha, K. Umasankari, E. IFET College of Engineering Dept of Computer Science Villupuram India

ISBN: (纸本)9798350348002

Sugarcane is a significant crop with several uses in the food, bio-energy, and bio-based product sectors. Many elements, including climate, soil fertility, and plant diseases, can have an impact on the quality of sugarcane. In this study, it suggest a sugarcane classification system based on convolutional neural networks (CNNs) and image processing to automatically evaluate sugarcane crops' quality automatically. Using image processing techniques, the system uses digital photographs of sugarcane to extract attributes including color, texture, and form. These attributes are then sent into a CNN to be categorized into various grades or quality levels. By testing the proposed system using a sizable collection of photographs of sugarcane, comparing the outcomes to those attained using conventional visual inspection techniques. The findings indicate that the suggested system can classify sugarcane crops with a high degree of accuracy and dependability. The sugarcane industry may employ the suggested approach to increase the efficacy and precision of sugarcane quality evaluation. This research highlights the possibility of fusing deep learning models with image processing methods for agricultural applications. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Traffic Aware Routing with Round Robin Technique for Equating the Load in Software Defined WSN 2

Traffic Aware Routing with Round Robin Technique for Equatin...

引用

2nd International Conference on Electronics and Renewable Systems, ICEARS 2023

作者： Senkamalavalli, R. Nalini, M. Kalaimani, G. Iyyanar, P. East Point College of Engineering and Technology Department of Computer Science Engineering Karnataka Bangalore India S.A Engineering College Department of Computer Science and Engineering Tamil Nadu Chennai India Shadan Women's College of Engineering and Technology Department of Computer Science and Engineering Telangana Hyderabad India Sona College of Technology Department of Information Technology Tamil Nadu Salem India

ISBN: (纸本)9798350346640

Multiple uses of Wireless Sensor Networks (WSNs) in the real world would need the probable dispersion of a large number of sensor nodes. The adaptability and flexibility is very difficult in the traditional WSNs which uses balancing load technology. Software-defined networking (SDN) is a good choice because it lets you see what resources are used and also set up boundaries. In WSN, the highest traffic load causes an overflow of the data queue. As a result, important data should be lost. Also, the sensor node's energy is rapidly drained, and the whole network's lifespan is damaged. Traffic-aware routing with round robin technique (TARR) for equating the load in a software-defined WSN is proposed to solve this problem. The network contains two significant functions, namely, the formation of the network and the action of the network. This approach recognizes the traffic by obtaining or forwarding packets via control and data messages. In this approach, the round-robin technique is used during congestion situations. Thus, the data is forwarded constantly. As a result, the recipient node receives all data packets efficiently. The results of the simulation demonstrate that the TARR technique boosts network throughput while simultaneously reducing both packet loss and latency in a software-defined WSN. © 2023 IEEE.

关键词： Software defined networking

来源：评论

学校读者我要写书评

暂无评论

A whole-slide pathology segmentation framework for the diagnosis of non-small cell lung cancer 4

A whole-slide pathology segmentation framework for the diagn...

引用

4th International Conference on computer Vision, Image and Deep Learning, CVIDL 2023

作者： Fang, Kun Jia, Jingjing College of Computer Engineering and Science Shanghai University Shanghai China

ISBN: (纸本)9798350326444

Immunotherapy is one of the most important approaches to treat NSCLC. Patient treatment decisions are based on the analysis of NSCLC biopsy images by pathologists. Deep learning (DL) methods have the potential to enable automated segmentation and classification of tissues in biopsy images, allowing for quantitative analysis. However, performing segmentation requires high-precision algorithms and computational resources due to the large size of whole slide pathology images, which is a challenging task. In this paper, we propose a new approach that considers local and global information to effectively segment and classify tumor regions in pathology images. The core of our approach is a two-level hierarchical deep neural network that utilizes a classification network to quickly filter out background regions and form a global stage heatmap, to guide the segmentation task to improve segmentation speed and accuracy. Experimental results show that the proposed framework exhibits high segmentation performance compared to a single classification model, providing a new idea for developing an effective segmentation method. © 2023 IEEE.

关键词： Image classification

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：