检索结果-内蒙古大学图书馆

6th International Conference on Intelligent Computing and Signal Processing (ICSP)

作者： Longxiang Qu School of Computer Science Wuhan Vocational College of Software and Engineering (Wuhan Open University) Wuhan China

ISBN: (数字)9798350376548

ISBN: (纸本)9798350376555

With the rapid growth and increasing complexity of data, there are significant challenges to security and efficiency when using the traditional centralized machine learning model to deal with large-scale data. However, as a distributed learning mechanism, federated learning also has potential threats to handle data applications. For example, attackers can attempt to infer sensitive information of data providers by analyzing model or gradient information. Therefore, we propose a privacy-preserving scheme against collusion attacks based on federated learning to mitigate the above-mentioned threats. Specifically, combined with the federated learning mechanism, the local gradients are blinded by random numbers, and the local data security are ensured by aggregating the blinded gradients. Through experimental analysis on real data sets, we validate the performance of our scheme, which incurring minimal computational overhead, effectively achieves resistance against collusion attacks.

关键词： Training Resistance computer aided instruction Federated learning Distance learning Computational modeling Signal processing Data models Performance analysis Cryptography

来源：评论

学校读者我要写书评

暂无评论

TransFiLM: An Efficient and Lightweight Audio Enhancement Network for Low-Cost Wearable Sensors

TransFiLM: An Efficient and Lightweight Audio Enhancement Ne...

引用

IEEE Internatonal Conference on Mobile Adhoc and Sensor Systems (MASS)

作者： Shilin Chen Jianhao Weng Shicong Hong Yanbo He Yongpan Zou Kaishun Wu College of Computer Science and Software Engineering Shenzhen University Information Hub Hong Kong University of Science and Technology (Guangzhou)

ISBN: (数字)9798350363999

ISBN: (纸本)9798350364002

Wearable devices such as headphones are increasingly popular in people's lives, and there is an increasing focus on how to achieve continuous and reliable information input using these devices. However, due to constraints in computing power, low power consumption, and low operating frequencies, such devices often record and transmit signals at lower sampling rates, the resultant lower-quality signals often have catastrophic implications for system performance. Efficient real-time conversion of low-resolution speech signals to full-resolution high-quality signals using low-cost wearable sensors on edge devices is a challenging research endeavor. To address this, this paper designs TransFiLM, a mobile deep learning network. It allows users to obtain full-resolution high-quality audio signals using low-cost wearable sensors on edge devices. TransFiLM integrates residual learning and super-resolution networks and employs effective signal processing strategies to achieve audio upscaling and noise reduction, significantly improving audio quality. We implement a prototype on commercial devices and conduct a series of experiments to evaluate its performance. Using signal-to-noise ratio (SNR) and log-spectral distance (LSD) as evaluation metrics, TransFiLM exhibits superior performance compared to other time-domain methods in cross-user, cross-corpus, and cross-noise environment testing. Additionally, our TransFiLM network handles 8192 samples with a response time of 181 ms, which meets the requirement to run in real-time on edge devices.

关键词： Performance evaluation Deep learning Noise reduction Real-time systems Time factors Wearable devices Time-domain analysis Wearable sensors Intelligent sensors Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Navigating the Fermi Multiverse: Assessing LLMs for Complex Multi-hop Queries 7

Navigating the Fermi Multiverse: Assessing LLMs for Complex ...

引用

7th Workshop on Natural Language for Artificial Intelligence, NL4AI 2023

作者： Rahgouy, Mostafa Giglou, Hamed Babaei Feng, Dongji Rahgooy, Taher Dozier, Gerry Seals, Cheryl D. Department of Computer Science and Software Engineering Auburn University AuburnAL United States TIB Leibniz Information Centre for Science and Technology Hannover Germany Department of Mathematics Computer Science and Statistics Gustavus Adolphus College MN United States Meta Menlo ParkCA United States

Recently, large language models (LLMs) have gained significant attention in the field of Natural Language Processing (NLP) and have shown promise across various tasks, even when given only a few examples to learn from. However, their ability to understand and reason with natural language remains uncertain. While there have been attempts to evaluate these models using reasoning tests, these evaluations have mostly focused on models' final answers, often overlooking the step-by-step reasoning processes behind their performance. Additionally, these analyses have typically concentrated on just one or a few aspects of reasoning, especially for tasks that do not require much complex thinking to find the answer. This limits our understanding of LLMs' potential and limitations when it comes to more complex and realistic questions. To address this issue, we conduct a comprehensive analysis of LLMs using the existing Fermi reasoning challenge, a task that combines different aspects of reasoning into a single question-answering format, requiring deeper levels of reasoning. In this paper, we examine various advanced LLMs in this reasoning challenge and explore how their performance is affected by their size (i.e., the number of parameters). We also investigate how these models behave with different levels of supervision, ranging from having all the information to no evidence at all. Furthermore, we compare the two primary methods of teaching these LLMs, fine-tuning, and few-shot learning, using the Chain-of-Thought approach. We provide a detailed case study highlighting the most common limitations of these models. While our results imply that these models may have a long journey ahead to reach human-level reasoning, our work can be considered a robust baseline for the community to strive toward achieving this ambitious goal. Our code is available on GitHub https://***/MostafaRahgouy/LLMs_for_FPs for the community. © 2023 Copyright for this paper by its authors.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

SKDLog: Self-Knowledge Distillation-based CNN for Abnormal Log Detection 19

SKDLog: Self-Knowledge Distillation-based CNN for Abnormal L...

引用

2022 IEEE SmartWorld, 19th IEEE International Conference on Ubiquitous Intelligence and Computing, 2022 IEEE International Conference on Autonomous and Trusted Vehicles Conference, 22nd IEEE International Conference on Scalable Computing and Communications, 2022 IEEE International Conference on Digital Twin, 8th IEEE International Conference on Privacy Computing and 2022 IEEE International Conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022

作者： Han, Ningning Lu, Siyang Wang, Dongdong Wang, Mingquan Tan, Xiaoman Wei, Xiang Beijing Jiaotong University School of Computer and Information Technology Beijing China University of Central Florida Department of Computer Science OrlandoFL United States Beijing Jiaotong University School of Software Engineering Beijing China Southwest University College of Computer and Information Science College of Software Chongqing China

ISBN: (纸本)9798350346558

System logs are critical to system health diagnosis, especially for big data distributed systems. To detect anomalies in logs, log analysis has become a popular and practical approach. However, with the increasing complexity of system logs in real-world systems, more noisy data are generated. The noise disturbs the regular detection procedure and decreases the detection quality. Hence, it is more difficult to improve detection performance under such uncertain circumstance. To tackle this challenge, we propose SKDLog, a novel and effective log anomaly detection method equipped with self-knowledge distillation. This approach leverages the knowledge from soft labels and refined feature maps through knowledge distillation. Moreover, it helps the detection model better acquire latent information. To better exploit feature maps, an auxiliary self-teacher branch is incorporated into the framework. After the integration, the model achieves performance gain in log anomaly detection. To demonstrate the effectiveness, we compare SKDLog with the state-of-the-art log-based anomaly detection approaches on HDFS and Hadoop Application datasets. Our model outperforms other approaches on both recall and F1-score. Furthermore, we challenge problem solving by performing experiments on an industry dataset and an unstable dataset. The experimental results show that SKDLog more accurately detects abnormal logs from noisy data with high recall and F1-score. © 2022 IEEE.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Overlooked Aspects of Data Governance: Workflow Framework for Enterprise Data Deduplication

Overlooked Aspects of Data Governance: Workflow Framework fo...

引用

2023 International Conference on Intelligent Computing, Communication, Networking and Services, ICCNS 2023

作者： Azeroual, Otmane Nikiforova, Anastasija Sha, Kewei Berlin Germany University of Tartu Faculty of Science and Technology Institute of Computer Science Chair of Software Engineering Tartu Estonia European Open Science Cloud Task Force 'Fair Metrics and Data Quality' Brussels Belgium University of Houston Clear Lake College of Science and Engineering Houston United States

ISBN: (纸本)9798350339291

Data quality in companies is decisive and critical to the benefits their products and services can provide. However, in heterogeneous IT infrastructures where, e.g., different applications for Enterprise Resource Planning (ERP), Customer Relationship Management (CRM), product management, manufacturing, and marketing are used, duplicates, e.g., multiple entries for the same customer or product in a database or information system, occur. There can be several reasons for this, but the result of non-unique or duplicate records is a degraded data quality. This ultimately leads to poorer, inefficient, and inaccurate data-driven decisions. For this reason, in this paper, we develop a conceptual data governance framework for effective and efficient management of duplicate data, and improvement of data accuracy and consistency in large data ecosystems. We present methods and recommendations for companies to deal with duplicate data in a meaningful way. © 2023 IEEE.

关键词： Ecosystems

来源：评论

学校读者我要写书评

暂无评论

Data and Ensemble Machine Learning Fusion Based Intelligent software Defect Prediction System

引用

computers, Materials & Continua 2023年第6期75卷 6083-6100页

作者： Sagheer Abbas Shabib Aftab Muhammad Adnan Khan Taher MGhazal Hussam Al Hamadi Chan Yeob Yeun School of Computer Science National College of Business Administration&EconomicsLahore54000Pakistan Department of Computer Science Virtual University of PakistanLahore54000Pakistan Department of Software Faculty of Artificial Intelligence and SoftwareGachon UniversitySeongnam13120Korea Riphah School of Computing&Innovation Faculty of ComputingRiphah International UniversityLahore CampusLahore54000Pakistan School of Information Technology Skyline University CollegeUniversity City SharjahSharjahUAE Center for Cyber Security Faculty of Information Science and TechnologyUKMBangiSelangor43600Malaysia College of Engineering and IT University of Dubai14143UAE EECS Department Center for Cyber Physical SystemsKhalifa UniversityAbu Dhabi127788UAE

The software engineering field has long focused on creating high-quality software despite limited *** defects before the testing stage of software development can enable quality assurance engineers to con-centrate on problematic modules rather than all the *** approach can enhance the quality of the final product while lowering development *** defective modules early on can allow for early corrections and ensure the timely delivery of a high-quality product that satisfies customers and instills greater confidence in the development *** process is known as software defect prediction,and it can improve end-product quality while reducing the cost of testing and *** study proposes a software defect prediction system that utilizes data fusion,feature selection,and ensemble machine learning fusion techniques.A novel filter-based metric selection technique is proposed in the framework to select the optimum features.A three-step nested approach is presented for predicting defective modules to achieve high *** the first step,three supervised machine learning techniques,including Decision Tree,Support Vector Machines,and Naïve Bayes,are used to detect faulty *** second step involves integrating the predictive accuracy of these classification techniques through three ensemble machine-learning methods:Bagging,Voting,and ***,in the third step,a fuzzy logic technique is employed to integrate the predictive accuracy of the ensemble machine learning *** experiments are performed on a fused software defect dataset to ensure that the developed fused ensemble model can perform effectively on diverse *** NASA datasets are integrated to create the fused dataset:MW1,PC1,PC3,PC4,and *** to the results,the proposed system exhibited superior performance to other advanced techniques for predicting software defects,achieving a remarkable accuracy rate of 92.08%.

关键词： Ensemble machine learning fusion software defect prediction fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

DRRS-BC:Decentralized Routing Registration System Based on Blockchain

引用

IEEE/CAA Journal of Automatica Sinica 2021年第12期8卷 1868-1876页

作者： Huimin Lu Yu Tang Yi Sun College of Computer Science and Technology Qingdao UniversityQingdao 266071China School of Engineering Kyushu Institute of TechnologyKitakyushu 804-8550Japan School of Computer Science(National Pilot Software Engineering School) Beijing University of Posts and TelecommunicationsBeijing 100876China

The border gateway protocol(BGP)has become the indispensible infrastructure of the Internet as a typical inter-domain routing ***,it is vulnerable to misconfigurations and malicious attacks since BGP does not provide enough authentication mechanism to the route *** a result,it has brought about many security incidents with huge economic *** solutions to the routing security problem such as S-BGP,So-BGP,Ps-BGP,and RPKI,are based on the Public Key Infrastructure and face a high security risk from the centralized *** this paper,we propose the decentralized blockchain-based route registration framework-decentralized route registration system based on blockchain(DRRS-BC).In DRRS-BC,we produce a global transaction ledge by the information of address prefixes and autonomous system numbers between multiple organizations and ASs,which is maintained by all blockchain nodes and further used for *** applying blockchain,DRRS-BC perfectly solves the problems of identity authentication,behavior authentication as well as the promotion and deployment problem rather than depending on the authentication ***,it resists to prefix and subprefix hijacking attacks and meets the performance and security requirements of route registration.

关键词： Blockchain decentralized routing protocol routing registration

来源：评论

学校读者我要写书评

暂无评论

Tomato Leaf Diseases Prediction Using Deep Learning Algorithms

Tomato Leaf Diseases Prediction Using Deep Learning Algorith...

引用

Advances in Data engineering and Intelligent Computing Systems (ADICS), International Conference on

作者： P. Ananthi K. Nirmala Devi Gopinath D P. Shanmugapriya Gowtham S Department of Computer Technology Kongu Engineering College Perundurai Tamilnadu Department of Computer Science (PG) Kristu Jayanti College Bangaluru Department of Computer Science Kristu Jayanti College Bangaluru MSc Software Systems Kongu Engineering College Erode India

ISBN: (数字)9798350364828

ISBN: (纸本)9798350364835

In the realm of agriculture, infections on tomato leaves pose a worldwide danger to established tomato production, impacting a large number of farmers worldwide. To ensure healthy tomato plant growth and food security for the world's expanding population, early disease detection, treatment, and solution identification are essential. The use of computer-assisted technologies for disease detection in plant leaf is prevalent in modern agriculture. The goal was to develop an effective deep learning model for the detection of diseases in tomato plant leaf. To address memory and computational resource constraints, the proposed model incorporates a lightweight ‘Region Convolutional Neural Network (R-CNN)‘ head and conducted experiments with various neural network architectures, including Densenet-169, optimized Mobilenet-V2 and Resnet-50, to enhance detection accuracy and computational efficiency. The research extends the capabilities of these neural network architectures by optimizing anchor proportions in the Conventional Neural Network (CNN) and modifying feature extraction topologies. These optimizations resulted in improved detection accuracy and computational efficiency and compared proposed technique against cutting-edge models to evaluate its viability and robustness. The outcomes of the research were promising. Impressive outcomes were obtained by the proposed approach regarding accuracy, F1-score, recall, and precision.

关键词： Deep learning Plant diseases Computational modeling Neural networks Predictive models Reliability engineering Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

A Model Driven Framework Enabling the Development of Standardized Text-Free User Interface for Smartphones

A Model Driven Framework Enabling the Development of Standar...

引用

International Bhurban Conference on Applied sciences & Technology, IBCAST

作者： Uzair Rasheed Sadia Khalid Rabia Mehmood Muhammad Ahmad Mishal Muneer Department of Computer and Software Engineering College of Electrical and Mechanical Engineering NUST Islamabad Pakistan Department of Computer Science Lahore College for Women University Lahore Pakistan Department of Computer science International Univesity of Rostock Germany

ISBN: (数字)9798331516680

ISBN: (纸本)9798331516697

Smartphones offer a wide range of applications globally, and usability is a key factor in their quality. Human-computer Interaction (HCI) continuously evolves to enhance usability by improving user interface (UI) components. However, most UI trends are designed for literate users, neglecting a significant portion of the population who cannot read or write. These users often rely on others for assistance with smartphone applications, and text-based UIs hinder their learning and usage, reducing overall usability. This research addresses the limitations of text-based standards by introducing a standardized framework for developing text-free user interfaces for smartphones. The framework utilizes static and dynamic images instead of text to convey widget or button functions, aiming to enhance usability for illiterate users, including preschoolers. Developed with Obeo Designer and Sirius, the framework's Platform Independent Metamodel (PIM) was validated through case studies representing the target user groups. Future work involves Model to Text (M2T) transformation, and results show the framework's potential for automating applications with text-free UIs.

关键词： Human computer interaction Market research Usability Smart phones Standards

来源：评论

学校读者我要写书评

暂无评论

Novel Load Balancing Mechanism Based on Deep Reinforcement Learning for Human-Centric Applications in Data Centers

引用

Human-centric Computing and Information sciences 2025年 15卷

作者： Hu, Jinbin Luo, Wangqing He, Yi Rao, Shuying Alqahtani, Fayez Tolba, Amr Zhu, Min Wang, Jin School of Computer and Communication Engineering Changsha University of Science and Technology Changsha China Software Engineering Department College of Computer and Information Sciences King Saud University Riyadh Saudi Arabia Department of Computer Science Community College King Saud University Riyadh Saudi Arabia College of Information Science and Technology Zhejiang Shuren University Zhejiang China

Human-computer interaction applications require ultra-low response delays to achieve a better user experience. With the rapid growth of data center network (DCN) topologies, the number of equal-cost paths has increased dramatically. It is imperative to use load balancing between parallel paths to improve link utilization. However, the existing load balancing mechanisms cannot make appropriate forwarding decisions for reacting to the dynamic traffic and path congestion status in large-scale DCNs, resulting in poor network performance. In this paper, we have proposed a dynamic load balancing (DLB) mechanism that uses deep reinforcement learning (DRL) to monitor the status of parallel paths in real time and uses the depth deterministic policy gradient algorithm to make the path state weight (PSW) automatically adapt to different network load scenarios. It then automatically configures the PSW through the DRL agent to guide the switch to select the best forwarding path to balance the load. The experimental results show that DLB significantly reduces the average flow completion by up to 36% compared to state-of-the-art load balancing schemes such as DRILL, LetFlow, and RPS under the asymmetric topology scenario, the result of which significantly enhances the efficiency of human-centric interaction. © (2024), (Korea Information Processing Society). All Rights Reserved.

关键词： Reinforcement learning

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：