检索结果-内蒙古大学图书馆

Bipartite Consensus in the Presence of Denial of Service Adversary

IFAC-PapersOnLine 2022年第1期55卷 771-776页

作者： R Gopika Ankita Sharma Rakesh R Warier PhD Scholar Department of Electrical Electronics and Instrumentation Engineering BITS Pilani KK Birla Goa Campus Zuari Nagar Goa India Assistant Professor School of Basic Science (Mathematics) Indian Institute of Information Technology Una Himachal Pradesh India Assistant Professor Department of Electrical Electronics and Instrumentation Engineering BITS Pilani KK Birla Goa Campus Zuari Nagar Goa India

In this paper, we consider a Denial of Service (DoS) attack on a set of agents interacting over an undirected signed graph attempting to achieve linear bipartite consensus. In bipartite consensus, two clusters are formed, agents in each cluster converging to a final state which is negative of the other cluster’s final state. The adversary seeks to slow down the bipartite consensus by a DoS type attack where the attacker has the capability to break a fixed maximum number of links at each time instant. The problem is formulated as an optimal control problem and the optimal strategy for the adversary is determined. The optimal strategy is provided as an algorithm and results are demonstrated with numerical simulations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Incorporating self-assembled MXene to improve electrical conductivity of novel ZIF67 derivatives induced by NH4BF4 and NH4HF2 for energy storage

引用

Journal of Energy Storage 2024年 82卷

作者： Lee, Pin-Yan Chiou, Yu-Ren Cheng, Cheng-Siang Chen, Yu-Chun Kongvarhodom, Chutima Chen, Hung-Ming Yougbaré, Sibidou Husain, Sadang Ho, Kuo-Chuan Kuo, Tsung-Rong Lin, Lu-Yin Department of Chemical Engineering National Taiwan University Taipei Taiwan Graduate Institute of Nanomedicine and Medical Engineering College of Biomedical Engineering Taipei Medical University Taipei11031 Taiwan Department of Chemical Engineering and Biotechnology National Taipei University of Technology Taipei Taiwan Department of Chemical Engineering King Mongkut's University of Technology Thonburi 126 Pracha-u-thit Toong-kru Bangkok10140 Thailand Gingen technology Co. LTD. Rm. 7 10F. No.189 Sec. 2 Keelung Rd. Xinyi Dist. Taipei11054 Taiwan /Nanoro 03 B.P 7192 Ouagadougou03 Burkina Faso Department of Physics Faculty of Mathematics and Natural Science Lambung Mangkurat University Banjarmasin70124 Indonesia International PhD Program in Biomedical Engineering College of Biomedical Engineering Taipei Medical University Taipei11031 Taiwan

Zeolitic imidazolate framework (ZIF-67) with high surface area and tunable pore size are considered as a promising active material for energy storage, but the low electrical conductivity restricts its performance. Developing ZIF67 derivatives with improved electrical conductivity is necessary to broaden its application in electrochemical fields. In this work, two strategies are applied to improve electrical conductivity and electrochemical performance of ZIF67. Novel structure directing agents of NH4BF4 and NH4HF2 are used to synthesize ZIF67 derivatives with higher theoretical capacitances and favorable layered structures. Self-assembled MXene with different amounts is further incorporated in ZIF67 derivatives to establish composites. The optimal composite electrode shows a high specific capacitance (CF) of 1410.4 F/g (775.6C/g) at 20 mV/s, while the ZIF67 derivative electrode without MXene only shows a CF value of 942.3 F/g (518.3C/g), due to the high surface area and better pore structure as well as the close combination of MXene and the layered ZIF67 derivative for the former case. An energy storage device with the optimal composite and carbon electrodes shows the maximum energy density of 32.40 Wh/kg at 375 W/kg. The Coulombic efficiency of 100% and the CF retention of 77.4% are also achieved after 10,000 cycles. © 2024 Elsevier Ltd

关键词： Energy storage

来源：评论

学校读者我要写书评

暂无评论

An Interactive Dashboard to Study the Impact of Hurricane Florence on Food Bank Operations

An Interactive Dashboard to Study the Impact of Hurricane Fl...

引用

2020 International Conference on Computational science and Computational Intelligence, CSCI 2020

作者： Enyew, Bantwale Odubela, Kehinde Jiang, Steven Davis, Lauren North Carolina at State University Applied Science Technology Phd Program Greensboro United States North Carolina at State University Department of Industrial and Systems Engineering Greensboro United States

ISBN: (纸本)9781728176246

North Carolina is the third most hurricane-prone states in the US. In 2018, Hurricane Florence caused a lot of damages to households in North Carolina. The Food Bank of Central and Eastern North Carolina (FBCENC) serves 34 counties in North Carolina, and 22 of them were affected by Hurricane Florence. This research aims to investigate the impact of Hurricane Florence on the operations of FBCENC. We developed interactive dashboards to visualize food bank operational data and other relevant data and studied the trends and patterns of food distribution in three key stages: preparedness, response, and recovery. These dashboards enable food bank operations managers to explore and interact with the data with ease to explore the operational data at different stages, at different branch level, and on a different time scale (monthly, weekly, or daily). The impact on the operations of affected service areas vs. not affected areas could be investigated as well. The findings of this research will provide insight into how humanitarian relief agencies can better prepare for, respond to, and recover from the disruptions caused by hurricanes. © 2020 IEEE.

关键词： Hurricanes

来源：评论

学校读者我要写书评

暂无评论

Establishment and risk factor assessment of the abnormal body temperature probability prediction model (ABTP) for dairy cattle

引用

Scientific Reports 2024年第1期14卷 1-12页

作者： Lee, Tsair-Fwu Chiu, Chien-Liang Liu, Yen-Hsien Chang, Chu-Ho Shao, Jen-Chung Guo, Shih-Sian Liao, Yi-Lun Chen, Chia-Hui Tseng, Chin-Dar Chao, Pei-Ju Lee, Shen-Hao Department of Electronic Engineering National Kaohsiung University of Science and Technology Kaohsiung 80778 Taiwan Medical Physics and Informatics Laboratory of Electronic Engineering National Kaohsiung University of Science and Technology Kaohsiung 80778 Taiwan Department of Medical Imaging and Radiological Sciences Kaohsiung Medical University Kaohsiung 80708 Taiwan PhD Program in Biomedical Engineering Kaohsiung Medical University Kaohsiung 80708 Taiwan School of Dentistry College of Dental Medicine Kaohsiung Medical University Kaohsiung 80708 Taiwan Department of Radiation Oncology Linkou Chang Gung Memorial Hospital and Chang Gung University College of Medicine Linkou Taiwan

The study aims to develop an abnormal body temperature probability (ABTP) model for dairy cattle, utilizing environmental and physiological data. This model is designed to enhance the management of heat stress impacts, providing an early warning system for farm managers to improve dairy cattle welfare and farm productivity in response to climate change. The study employs the Least Absolute Shrinkage and Selection Operator (LASSO) algorithm to analyze environmental and physiological data from 320 dairy cattle, identifying key factors influencing body temperature anomalies. This method supports the development of various models, including the Lyman Kutcher-Burman (LKB), Logistic, Schultheiss, and Poisson models, which are evaluated for their ability to predict abnormal body temperatures in dairy cattle effectively. The study successfully validated multiple models to predict abnormal body temperatures in dairy cattle, with a focus on the temperature-humidity index (THI) as a critical determinant. These models, including LKB, Logistic, Schultheiss, and Poisson, demonstrated high accuracy, as measured by the AUC and other performance metrics such as the Brier score and Hosmer–Lemeshow (HL) test. The results highlight the robustness of the models in capturing the nuances of heat stress impacts on dairy cattle. The research develops innovative models for managing heat stress in dairy cattle, effectively enhancing detection and intervention strategies. By integrating advanced technologies and novel predictive models, the study offers effective measures for early detection and management of abnormal body temperatures, improving cattle welfare and farm productivity in changing climatic conditions. This approach highlights the importance of using multiple models to accurately predict and address heat stress in livestock, making significant contributions to enhancing farm management practices. © The Author(s) 2024.

关键词： Abnormal body temperature probability (ABTP) Dairy cattle Least absolute shrinkage and selection operator (LASSO) Temperature-humidity index (THI)

来源：评论

学校读者我要写书评

暂无评论

Enhancing Fraud Detection in Online E-Commerce Transactions through Deep Learning Auto encoder Model

Enhancing Fraud Detection in Online E-Commerce Transactions ...

引用

Intelligent Systems and Advanced Applications (ICISAA), International Conference on

作者： K. Raghuveer Taviti Naidu Gongada Divya Nimma Mohd Aarif Keerthi Samudrala B Kiran Bala School of Management V.R. Siddhartha Engineering College (Deemed to be University) Kanuru A.P India Dept of Operations GITAM School of Business GITAM (Deemed to be) University Visakhapatnam India PhD in Computational Science University of Southern Mississippi Data Analyst in UMMC USA Department of Commerce Aligarh Muslim University Aligarh Uttar Pradesh India Department of CSE Marri laxman Reddy Institute Of Technology and Management India Department of AI & DS K.Ramakrishnan College of Engineering Trichy India

ISBN: (数字)9798331539948

ISBN: (纸本)9798331539955

Fraud detection in internet transactions is crucial for maintaining security in digital transactions. Traditional methods often rely on rule-based systems or supervised learning algorithms, which struggle to capture complex patterns in fraudulent behaviour and require extensive manual feature engineering. In this study, a novel approach using deep learning auto encoder models is proposed to enhance fraud detection accuracy. Unlike conventional methods, this approach does not necessitate fraudulent data for training, as the auto encoder learns to reconstruct legitimate transactions and identify anomalies based on reconstruction error. The trained model is integrated into the market for real-time detection. Results demonstrate significant improvements in fraud detection accuracy compared to traditional methods, with reduced reliance on manual feature engineering and labelled fraudulent data. This approach offers a scalable and effective solution for detecting fraudulent activities in online e-commerce transactions, thereby safeguarding users and businesses from financial losses and maintaining trust in digital transactions. The autoencoder model expands detection accuracy by 2% over RF and 1% over SVM, with an AUCROC increase of 1%.

关键词： Deep learning Training Support vector machines Adaptation models Accuracy Manuals Real-time systems Fraud Electronic commerce Business

来源：评论

学校读者我要写书评

暂无评论

In-situ growth of novel iron oxide/iron organic framework composites as efficient electroactive materials of battery supercapacitor hybrids

引用

Journal of Energy Storage 2024年 97卷

作者： Kuo, Tsung-Rong Saukani, Muhammad Kuo, Tsung-Rong Kubendhiran, Subbiramaniyan Wang, Yu-Min Tai, Po-Chun Wu, Chang-Feng Lin, Lu-Yin Kongvarhodom, Chutima Kongvarhodom, Chutima Husain, Sadang Yougbaré, Sibidou Chen, Hung-Ming International PhD Program in Biomedical Engineering College of Biomedical Engineering Taipei Medical University Taipei11031 Taiwan Graduate Institute of Nanomedicine and Medical Engineering College of Biomedical Engineering Taipei Medical University Taipei11031 Taiwan Department of Chemical Engineering and Biotechnology National Taipei University of Technology Taipei Taiwan Department of Chemical Engineering King Mongkut's University of Technology Thonburi 126 Pracha-u-thit Toong-kru Bangkok10140 Thailand Department of Chemical Engineering University of New Brunswick FrederictonNBE3B5A3 Canada Department of Physics Faculty of Mathematics and Natural Science Lambung Mangkurat University Banjarmasin70124 Indonesia /Nanoro 03 B.P 7192 Ouagadougou03 Burkina Faso Gingen technology Co. LTD. Rm. 7 10F. No.189 Sec. 2 Keelung Rd. Xinyi Dist. Taipei11054 Taiwan

Iron oxide (Fe2O3) with a high theoretical capacitance, wide potential ranges and easy availability has attracted much attentions as the electrode material of battery supercapacitor hybrids (BSH). Metal–organic framework (MOF) is one of the promising potential energy storage materials due to its large surface area and controllable pore structures. In this work, novel iron oxide/iron organic framework composites (Fe2O3/FeMOF) are in-situ grown on the Ni foam as efficient energy storage electrodes of BSH. By tuning the solvothermal durations, the morphology changes from random sizes of sheets, regular grown vertical sheets, to flower-like structures. The d-spacing also increases for the Fe2O3/FeMOF synthesized using longer solvothermal durations. The optimal Fe2O3/FeMOF electrode synthesized using 9 h shows a high areal capacitance of 10.97 F/cm2 along with an areal capacity of 5.49 F/cm2 at the current density of 35 mA/cm2, owing to the most regular growth of sheets, the large d-spacing, and the smallest charge-transfer resistances. A BSH composed of the Fe2O3/FeMOF positive electrode and a graphene negative electrode shows a maximum energy density of 0.76 mWh/cm2 at 22.5 mW/cm2. The excellent long-term cycling stability with the capacitance retention of 85% and Coulombic efficiency of 98% are also achieved after 10,000 charge/discharge cycles. © 2024 Elsevier Ltd

关键词： Supercapacitor

来源：评论

学校读者我要写书评

暂无评论

Slotting Learning Rate in Deep Neural Networks to Build Stronger Models 2

Slotting Learning Rate in Deep Neural Networks to Build Stro...

引用

2nd International Conference on Smart Electronics and Communication, ICOSEC 2021

作者： Sharma, Dilip Kumar Singh, Bhopendra Anam, Mamoona Villalba-Condori, Klinge Orlando Gupta, Ankur Kumar Ali, Ghassan Khazal Jaypee University of Engineering and Technology Department of Mathematics India Amity University Dubai United Arab Emirates International Islamic University PhD Computer Science Islamabad Pakistan Universidad Católica De Santa Mariá Peru IIMT University R&D Department SOCSA Meerut India Tomsk State University Russia

ISBN: (纸本)9781665433686

In recent years, deep neural networks have made substantial progress in object recognition. However, one issue with deep learning is that it is currently unclear which proposed framework is exaggerated for a specific hitch. As a result, distinct dispositions are attempt before one that produces satisfactory results is discovered. This paper described a distributed supervised learning method for finding the best network architecture by modifying specifications for a perceived task dynamically. In the case of the MNIST information gathering, it is shown that asynchronous supervised learning can agree on a solution space. Setting several hyperparameters can be time-consuming when constructing neural networks. In this post, we'll provide you with some tips and instructions for better organizing your hyperparameter tuning process, which should help you find a good setting for the hyperparameters much faster. © 2021 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Impact of Robotic Process Automation on Enterprise Resource Planning Systems

Impact of Robotic Process Automation on Enterprise Resource ...

引用

Confluence of Advancements in Robotics, Vision and Interdisciplinary Technology Management (IC-RVITM), International Conference on th

作者： Dileep Kumar Yendluri Jainath Ponnala Ramya Thatikonda M. Kempanna Reshmi Tatikonda A. Bhuvanesh Masters in Computer Science University of the Cumberlands USA Bachelors in ECE Jawaharlal Technological University Hyderbad India PhD in Information Technology University of the Cumberlands Williamsburg USA Department of Artificial Intelligence and Machine Learning Bangalore Institute of Technology Bengaluru Karnataka India Masters in Computer Information Systems University of the Central Missouri Warrensburg USA Department of Electrical and Electronics Engineering PSN College of Engineering and Technology Tirunelveli Tamil Nadu India

ERP systems are merging their powers to generate a dynamic collaboration. By examining the integration between RPA (Robotic Process Automation) and ERP (Enterprise Resource Planning) systems, we can identify their shared potential for enhancing process flow. Combining automation and ERP integration makes RPA a powerful tool for process management across multiple industries. The paper examines the basics of RPA and its ERP integration, highlighting the advantages of enhanced productivity and fewer errors. Addressing security, compliance, and change management issues simultaneously. In addition to top-down and bottom-up methods, process analysis and selecting suitable processes are covered. Practical examples offer insightful observations on this integration’s success. The union of RPA and ERP creates a powerful combination that can elevate operational effectiveness, facilitate strategic insights, and reshape the workplace.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High-Accuracy Animal Species Classification Using Transfer Learning with ResNet50 on Wildlife Camera Trap Images for Enhanced Conservation Efforts

High-Accuracy Animal Species Classification Using Transfer L...

引用

Innovations in High Speed Communication and Signal Processing (IHCSP), International Conference on

作者： Divya Nimma Varalakshmi Dandu Ankur Singh Bisht Vuda Sreenivasa Rao P. Santosh Kumar S Muthuperumal PhD in Computational Science University of Southern Mississippi Data Analyst in UMMC USA Department of School of Management Presidency University Bangalore Karnataka India Department of CSE Graphic Era Hill University Bhimtal Graphic Era Deemed to be University Dehradun Uttarakhand India Department of CSE Koneru Lakshmaiah Education Foundation Vaddeswaram A.P. India Dept of ECE Vignan's Institute of Engineering for Women Visakhapatnam Andhra Pradesh India Department of Mathematics K. Ramakrishnan College of Engineering Trichy India

ISBN: (数字)9798350368949

ISBN: (纸本)9798350368956

Accurately identifying animal species from wildlife camera trap images is essential for conservation and biodiversity monitoring. However, manual processing is severely constrained by the massive volume of data collected by camera traps. Using transfer learning and the ResNet50 model, a high-accura cy animal species classification framework was offered as an approach to this challenge. Utilization of the iWildCam2020_256 dataset—a varied collection of wildlife photos taken in a range of ecosystems optimize ResNet50, a pre-trained neural network to improve its performance on this particular job. With the use of transfer learning approaches, this approach aims to maximize the model's feature extraction capabilities and make it capable of accurately differentiating between a large number of animal species. Compared with traditional techniques, the suggested framework significantly improved classification accuracy when trained and verified on the iWildCam2020_256 dataset. the application of data augmentation techniques and network hyperparameter tuning to reduce overfitting and enhance generalization in various contexts. The outcomes show how well the model can classify species in difficult situations, like changing lighting and partial occlusions. By offering a reliable instrument for automated species identification, our study advances the area of animal conservation by enabling more effective and scalable biodiversity assessments. With a 97% accuracy score, the suggested framework performs remarkably well and shows consistent species recognition across a wide range of animal images. It is essential to include the suggested framework into conservation initiatives, which would help with the precise and timely monitoring of wildlife populations—a crucial component in maintaining biodiversity.

关键词： Technological innovation Accuracy Biological system modeling Wildlife Transfer learning Cameras Biodiversity Monitoring Tuning Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

Boosting Anomaly Detection in Financial Transactions: Leveraging Deep Learning with Isolation Forest for Enhanced Accuracy

Boosting Anomaly Detection in Financial Transactions: Levera...

引用

Artificial Intelligence and Quantum Computation-Based Sensor Application (ICAIQSA), International Conference on

作者： Prateek Kumar Bansal Divya Nimma Nripendra Narayan Das BVN Prasad Paruchuri Harishchander Anandaram M. Karthik Institute of Business Management GLA University Mathura India PhD in Computational Science Data Analyst in UMMC University of Southern Mississippi USA Department of Information Technology Manipal University Jaipur India Department of CSE KL University(Deemed to be) Vijayawada India Amrita School of Artificial Intelligence Amrita Vishwa Vidyapeetham Coimbatore India Department of AI & DS K.Ramakrishnan College of Engineering Trichy India

ISBN: (数字)9798331517953

ISBN: (纸本)9798331517960

Anomaly detection in financial transactions is paramount for safeguarding against fraudulent activities that pose significant risks to financial institutions and customers alike. Traditional methods often struggle to accurately identify complex and evolving patterns of fraud, necessitating innovative approaches that leverage advanced techniques such as deep learning and isolation forest. In this study, we propose a novel framework for boosting anomaly detection in financial transactions by integrating deep learning with isolation forest to achieve enhanced accuracy. Firstly, it employ an autoencoder, a type of neural network, to learn complex representations of normal transaction patterns and reconstruct input data. The autoencoder's ability to capture subtle variations in transaction attributes enables it to effectively distinguish between normal and anomalous instances based on the reconstruction error. Furthermore, we augment the anomaly detection process by incorporating isolation forest, a tree-based algorithm that isolates anomalies in the feature space by recursively partitioning data subsets. By combining the representation learning capabilities of deep learning with the outlier detection prowess of isolation forest, our framework offers a comprehensive solution for detecting fraudulent activities in financial transactions. Through experimentation on real-world financial datasets, we demonstrate the superior performance of our proposed framework compared to existing methods. The proposed method is implemented in Python software and has an accuracy of about 99.12% which is 1.49% higher than other existing methods like Conv-LSTM, Convolutional Neural Network (CNN)-LSTM, and CNN-GRU (Gated Recurrent Unit). Moreover, the integration of deep learning with isolation forest enables our framework to adapt to evolving patterns of fraud, ensuring robust and reliable anomaly detection in dynamic financial environments. Overall, our study contributes to the advancement

关键词： Deep learning Accuracy Autoencoders Forestry Boosting Software Fraud Software reliability Convolutional neural networks Anomaly detection

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：