检索结果-内蒙古大学图书馆

2024 International Conference on Innovation and Intelligence for Informatics, computing, and Technologies, 3ICT 2024

作者： Sharif, MhD Saeed Tamang, Madhav Theeng Nepal, Anup Elmedany, Wael Intelligent Technologies Research Group School of Architecture Computing and Engineering UEL London United Kingdom College of Information Technology University of Bahrain Bahrain

ISBN: (纸本)9798331533137

Retail management requires accurate sales forecasting for strategic planning, inventory control, and revenue maximisation. In this research, we are predicting sales using PySpark-built ML models and the Big Mart dataset. We evaluate and demonstrate the prediction skills of numerous machine learning algorithms, concentrating on XGBoost. Big Mart offers item weight, visibility, type, and outlet data. We use these properties as prediction model features. PySpark, a strong distributed computing platform, manages massive datasets for analysis and model training. In massive trials, we test decision trees (DT), XGBoost, linear regressions (LR), and random forests (RF). Training and testing enhance model accuracy. RMSE and R-squared measure our model quality. Our metrics evaluate the model’s data fit and prediction accuracy. XGBoost performed best with an RMSE of 1081 and an R-squared of 0.59. The XGBoost algorithm accurately predicts Big Mart sales. The model performs well because of its ensemble learning and understanding of intricate dataset links. We also used Power BI to present analytical insights, helping decision-makers design sales-estimated business plans. This study employed several machine learning algorithms, XGBoost gave the best performance. This research provides insights into how organisations might use these technologies to improve resource allocation and inventory management decision-making. ©2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection Landscape: Exploring Progress and Confronting Challenges in Security Advances 2

Intrusion Detection Landscape: Exploring Progress and Confro...

引用

2nd IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2024

作者： Usman, Mohammed Pavan, S. Suhas, M.R. Yogesh, B. Surendra Babu, K.N. Akash Thirumala, K. Ahmed, Mohammed Riyaz Reva University School of Computing and Information Technology Bengaluru India Dxc Technology Analyst i Infrastructure Services Bengaluru India Hkbk College of Engineering Bengaluru India

ISBN: (纸本)9798350317558

In the face of escalating cyber-attacks marked by increasing sophistication, the accurate detection of intrusions has become a paramount challenge in the realm of computer security. Failure to prevent these intrusions can have far-reaching consequences, affecting data confidentiality, integrity, and availability, ultimately eroding the trust in security services. This comprehensive survey explores the intricate landscape of intrusion detection methods, a cornerstone of defense against cybersecurity threats. The paper categorizes intrusion detection methods into two main types: Signature-based Intrusion Detection Systems (SIDS) and Anomaly-based Intrusion Detection Systems (AIDS). With meticulous detail, the paper presents a taxonomy of contemporary IDS, providing a systematic understanding of their diverse approaches. Additionally, the paper conducts a thorough review of recent ground breaking works, highlighting the cutting-edge advancements in intrusion detection techniques. Moreover, the paper delves into the crucial role of datasets commonly used for evaluation, emphasizing their impact on the effectiveness of intrusion detection systems. Beyond the current state of IDS, the paper critically examines the evasion techniques employed by attackers to evade detection, emphasizing the need for robust countermeasures. Finally, the paper contemplates the future of intrusion detection, outlining the research challenges that lie ahead. These challenges serve as essential focal points for strengthening computer systems and enhancing their resilience against evolving cyber threats. © 2024 IEEE.

关键词： Cyber-attacks Cybersecurity Intrusion Detection Systems Machine Learning

来源：评论

学校读者我要写书评

暂无评论

Ultrasensitive textile strain sensors redefine wearable silent speech interfaces with high machine learning efficiency

引用

npj Flexible Electronics 2024年第1期8卷 664-674页

作者： Chenyu Tang Muzi Xu Wentian Yi Zibo Zhang Edoardo Occhipinti Chaoqun Dong Dafydd Ravenscroft Sung-Min Jung Sanghyo Lee Shuo Gao Jong Min Kim Luigi Giuseppe Occhipinti Electrical Engineering Division Department of EngineeringUniversity of CambridgeCambridgeUK Department of Electronic and Electrical Engineering University College LondonLondonUK UKRI Centre for Doctoral Training in AI for Healthcare Department of ComputingImperial College LondonLondonUK School of Materials Science and Engineering Kumoh National Institute of Technology(KIT)GumiSouth Korea School of Instrumentation Science and Optoelectronic Engineering Beihang UniversityBeijingChina

This work introduces a silent speech interface(SSI),proposing a few-layer graphene(FLG)strain sensing mechanism based on thorough cracks and AI-based self-adaptation capabilities that overcome the limitations of state-of-the-art technologies by simultaneously achieving high accuracy,high computational efficiency,and fast decoding speed while maintaining excellent user *** demonstrate its application in a biocompatible textile-integrated ultrasensitive strain sensor embedded into a smart choker,which conforms to the user’s *** to the structure of ordered through cracks in the graphene-coated textile,the proposed strain gauge achieves a gauge factor of 317 with<5%strain,corresponding to a 420%improvement over existing textile strain sensors fabricated by printing and coating technologies reported to *** high sensitivity allows it to capture subtle throat movements,simplifying signal processing and enabling the use of a computationally efficient neural *** resulting neural network,based on a one-dimensional convolutional model,reduces computational load by 90%while maintaining a remarkable 95.25%accuracy in speech *** synergy in sensor design and neural network optimization offers a promising solution for practical,wearable SSI systems,paving the way for seamless,natural silent communication in diverse settings.

关键词： strain wear neural

来源：评论

学校读者我要写书评

暂无评论

Application of Clustering Algorithms to enhance Personalized Learning through Recommendation Model

Application of Clustering Algorithms to enhance Personalized...

引用

2024 International Conference on Innovation and Intelligence for Informatics, computing, and Technologies, 3ICT 2024

作者： Sharif, Mhd Saeed Tamang, Madhav Theeng Mani, Dyuthi Elmedany, Wael Intelligent Technologies Research Group School of Architecture Computing and Engineering UEL London United Kingdom College of Information Technology University of Bahrain Bahrain

ISBN: (纸本)9798331533137

technology and education have recently changed student involvement with learning resources and educational experiences. It is very important to have a platform which can provide personalized learning resources and group students by learning patterns. The research develops recommendation systems and grouping algorithms to help students with their learning patterns and performance measures. To record multidimensional student learning experiences, demographics, learning activities, problem-solving behaviours, and performance measures are extracted and processed. This system makes personalised student suggestions via collaborative filtering, especially Alternating Least Squares (ALS). The model predicts learning materials and problem sets based on student preferences and ability levels by analysing historical student interactions with learning resources. The research also uses clustering methods like K-means clustering to group students with similar learning and performance patterns. Clustering analysis lets instructors discover student group traits and tailor interventions and support techniques. This research also examines temporal relationships in student learning sequences using sequential models. Sequential learning activities and problem-solving behaviour of students help recurrent neural networks (RNNs), or sequential pattern mining algorithms predict their next activities. This research used a huge dataset of over sixteen million exercise logs and applied collaborative filtering (ALS) and K-means clustering to find learning patterns. The ALS-based recommendation system achieved a Mean Squared Error (MSE) of 0.23, showed excellent predictive accuracy. Clustering grouped students by learning behaviours, enabling targeted interventions. This research improves personalised learning using machine learning and data analytics in education. The recommendation system can help instructors tailor training, give individualised support, and boost academic success for various

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Advancing the Future of Agricultural Sustainability: Utilizing Deep Learning for Plant Disease Detection 2

Advancing the Future of Agricultural Sustainability: Utilizi...

引用

2nd IEEE International Conference on Advances in Information technology, ICAIT 2024

作者： Vinodh Kumar, S. Reshmy, A.K. Senthil Pandi, S. Kumar, P. Department of CSE Rajalakshmi Engineering College Chennai India Department of CINTEL School of Computing SRM Institute of Science and Technology Kattankulathur Chennai India

ISBN: (数字)9798350383867

ISBN: (纸本)9798350383867

In the complex agricultural environment, precisely detecting plant diseases is the first and most important step in preventing them. This identification process has changed drastically, moving in the direction of digitalization and data-driven techniques, due to the rapid advancement of technology in farming. As a result of this development, smart farming can incorporate complex analytical tools, strategic planning, and decision-making support systems. A major step forward in contemporary farming is the digitization and data-driven revolution in plant disease detection. Sustainable agriculture in the face of complicated environmental difficulties is possible when farmers use technology and data to their advantage in the fight against diseases. This will increase crop yields while decreasing losses. The present research study presents an innovative framework designed to improve the detection and recognition of plant diseases by utilizing deep learning techniques. This framework is specifically created to enhance the precision, comprehensiveness, and effectiveness of diagnosing plant diseases in agricultural environments. At first, the framework utilises a region proposal network (RPN) to accurately identify and locate leaves in challenging environmental conditions. This phase is essential for separating the pertinent sections of the image for further investigation. After localizing the leaves, the images are inputted into a classification system, such as a fine-tuned convolutional neural network (CNN) known as MobileNet-V2, to identify and recognize diseases. The execution of this framework yielded highly accurate findings, with an impressive accuracy rate of 97.97%. The level of precision exceeds that of conventional techniques, demonstrating a substantial enhancement in illness detection capability. The suggested framework effectively reduces the negative effects of plant diseases on agricultural production, leading to sustainable development in *** imp

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Loan Approval: Harnessing the Power of K-Nearest Neighbors for Predictive Eligibility

Revolutionizing Loan Approval: Harnessing the Power of K-Nea...

引用

2024 International Conference on Innovation and Intelligence for Informatics, computing, and Technologies, 3ICT 2024

作者： Sharif, Mhd Saeed Tamang, Madhav Theeng Hussain, Niyas Jaheer Elmedany, Wael Intelligent Technologies Research Group School of Architecture Computing and Engineering UEL London United Kingdom College of Information Technology University of Bahrain Bahrain

ISBN: (纸本)9798331533137

A bank has become a basic need of our daily lives. People use banks for several tasks, such as depositing or withdrawing money and borrowing loans. The number of loan applications is rising significantly. It is crucial for the bank and financial sectors to determine loan eligibility and approve loans to suitable applicants only. This study attempts to design a system which can easily predict loan eligibility with the application of several machine learning (ML) algorithms. We employed the five different machine learning algorithms to achieve this research’s aim. These algorithms were trained using the pre-processed dataset to create predictive models. F1 score, accuracy, Recall and Precision are used to evaluate the performance of the proposed approaches. The result showed that K-nearest neighbor (KNN) demonstrated outstanding performance, with an accuracy rate of 88.89%. The Random Forest (RF) model had an accuracy of 84.44%, whereas the Support Vector Machine (SVM) and Linear regression (LR) models achieved 82.22% and 80% accuracy, respectively. The Decision Tree (DT) algorithms showed the worst performance among the five algorithms, with an accuracy of 79.88%. The achievement of this research focuses on the possibility of machine learning algorithms as an efficient method for predicting loan eligibility in banks, contributing to the advancement of financial technology by automating and optimizing key banking processes, reducing processing times, and enhancing overall bank efficiency. ©2024 IEEE.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Two-step Runge–Kutta methods for Volterra integro-differential equations

引用

International Journal of Computer Mathematics 2024年第1期101卷 37-55页

作者： Wen, Jiao Huang, Chengming Guan, Hongbo College of Mathematics and Information Science Zhengzhou University of Light Industry Zhengzhou China School of Mathematics and Statistics Huazhong University of Science and Technology Wuhan China Hubei Key Laboratory of Engineering Modeling and Scientific Computing Huazhong University of Science and Technology Wuhan China

In this paper, we investigate two-step Runge–Kutta methods to solve Volterra integro-differential equations. Two-step Runge–Kutta methods increase the order of convergence in comparing the classical Runge–Kutta method without extra computational cost. First, the local order conditions and convergence theorem are derived. Then, stability properties of two-step Runge–Kutta methods corresponding to the basic and convolution test equations are analysed. Furthermore, one-stage method with order four and two-stage method with order six are constructed and we plot the stability regions. Numerical examples are presented to confirm the theoretical analyses. © 2024 Informa UK Limited, trading as Taylor & Francis Group.

关键词： Stability

来源：评论

学校读者我要写书评

暂无评论

Intelligent Guitar Chord Recognition Using Spectrogram-Based Feature Extraction and AlexNet Architecture for Categorization

引用

International Journal of Advanced Computer Science and Applications 2025年第4期16卷 758-767页

作者： Korade, Nilesh B. Salunke, Mahendra B. Bhosle, Amol A. Sangve, Sunil M. Joshi, Dhanashri M. Asalkar, Gayatri G. Kadu, Sujata R. Sarwade, Jayesh M. Department of Computer Engineering JSPM’s Rajarshi Shahu College of Engineering Tathawade Maharashtra Pune411033 India Department of Computer Engineering PCET’s Pimpri Chinchwad College of Engineering and Research Ravet Maharashtra Pune412101 India Department of Computer Science and Engineering School of Computing MIT Art Design and Technology University Loni Kalbhor Maharashtra Pune412201 India Department of Artificial Intelligence and Data Science Vishwakarma Institute of Technology Bibwewadi Pune411037 India Department of Computer Engineering Terna Engineering College Maharashtra Mumbai India Department of Information Technology JSPM’s Rajarshi Shahu College of Engineering Tathawade Maharashtra Pune411033 India

Chord prediction plays a key role in the advancement of musical technological innovations, such as automatic music transcription, real-time music tutoring, and intelligent composition tools. Accurate chord prediction can assist musicians, educators, and developers in constructing tools that help in learning, playing, and composing music. Background noise and audio distortions may have an impact on chord prediction accuracy, particularly in real-world situations. Chords can have distinct voicings or finger positions on the guitar, resulting in slight variations in audio representation. This study focuses on the classification of guitar chords using techniques of deep learning. There are eight major and minor guitar chords in the dataset. They have been turned into spectrograms, chromagrams, and Mel Frequency Cepstral Coefficients (MFCC) so that features can be extracted. Various deep learning architectures, including CNN, ResNet50, AlexNet, and VGG, were employed to classify the chords. Experimental results demonstrated that the spectrogram-based AlexNet model outperforms others, achieving good accuracy and robustness in chord classification. The proposed study demonstrates the efficiency of spectrograms and advanced deep learning models for audio signal processing in music applications. By automating chord detection, this study provides beneficial resources for music learners as well as educators, enabling more efficient learning and real-time feedback during practice sessions. © (2025), (Science and Information Organization). All Rights Reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

AI-Powered Demand Response Mechanisms for Sustainable Smart Grids 5

AI-Powered Demand Response Mechanisms for Sustainable Smart ...

引用

5th International Conference on Electronics and Sustainable Communication Systems, ICESC 2024

作者： Krishnan, R. Santhana Ashokkumar, C. Nithila, Ezhil E. Soundiraraj, N. Malar, P.Stella Rose Rani, P. Alice Scad College of Engineering and Technology Department of Electronics and Communication Engineering Cheranmahadevi India School of Computing College of Engineering and Technology Srm Institute of Science and Technology Department of Computing Technologies Chennai Kattankulathur India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Electronics and Communication Engineering Chennai Avadi India Psna College of Engineering and Technology Department of Electronics and Communication Engineering Dindigul India Jp College of Engineeringology Department of Electronics and Communication Engineering Thenkasi India Sarah Tucker College Department of Tamil Tirunelveli India

ISBN: (纸本)9798350379945

The integration of renewable energy sources into smart grids is a critical strategy for achieving sustainable energy systems. This necessitates effective management of energy resources, demand, and grid operations to fully exploit the potential of renewables while ensuring grid stability and reliability. Demand response (DR) mechanisms play a key role in optimizing energy use and grid stability within smart grids. This research explores the application of artificial intelligence (AI) for developing advanced DR mechanisms. The proposed approach leverages machine learning techniques to analyze energy consumption patterns and predict future demand. This enables the implementation of intelligent DR programs that incentivize consumers to adjust their energy usage during peak demand periods. By optimizing energy consumption in response to grid conditions, AI-powered DR mechanisms can significantly contribute to the integration of renewable energy sources and the creation of a sustainable energy future. The research investigates the design and implementation of these AI-powered DR mechanisms. In the proposed research, Machine learning algorithms are employed to analyze historical energy consumption data and predict future demand with high accuracy. This enables the development of DR programs that are tailored to anticipated grid conditions. Also, AI algorithms continuously monitor grid conditions and dynamically adjust DR incentives in real-time. This ensures that DR programs effectively address fluctuations in energy demand and supply. The research explores methods to incentivize consumer participation in DR programs. This may involve offering rebates or other benefits to consumers who adjust their energy consumption during peak demand periods. The effectiveness of the proposed AI-powered DR mechanisms will be evaluated through extensive simulations. The simulations will compare the performance of the proposed approach with existing DR methods. Key metrics such as forecas

关键词： Demand response

来源：评论

学校读者我要写书评

暂无评论

Improving Existing VANETs by Incorporating UAVS Using Ant Colony and PSO Algorithms 4

Improving Existing VANETs by Incorporating UAVS Using Ant Co...

引用

4th IEEE International Conference on Data engineering and Communication Systems, ICDECS 2024

作者： Thangam, S. Dixit, Aniket Karn, Alok Kumar Thakur, Arnav Arunbalaji, Cg Jesy Janet Kumari, J. Saleem Raja, A. Amrita School of Computing Amrita Vishwa Vidyapeetham Dept. of Computer Science and Engineering Bengaluru India University of Technology and Applied Sciences-Shinas College of Computing and Information Sciences It Department Oman

ISBN: (纸本)9798350393354

Vehicular Ad Hoc Networks (VANETs) are a type of wireless communication network that enable vehicles to communicate with each other and with roadside infrastructure in a peer-to-peer fashion;despite their vast applications, they come with several shortcomings. The key challenges in their real-world implementation include scalability, connectivity, and coverage issues. Unmanned Aerial Vehicles (UAVs), also known as drones, can complement existing VANETs in several ways to enhance their functionality and address some of their limitations. This paper studies the incorporation of UAVs in VANETs to overcome the challenges faced by the present networks. The approach is based on the dynamic deployment of UAVs in the most optimal positions, found by utilizing Particle Swarm Optimization (PSO) and Ant Colony algorithms which analyze the vehicle density, and previous coverage information in the network. The deployment of UAVs is intended to provide a seamless network coverage for ground vehicles. The impact of dynamic UAV mobility in communicating VANETs is comparatively studied. The simulation is done using Network Simulator-3 (NS3) simulator to evaluate the performance of 4 VANET protocols, AODV, DSR, OLSR, and DSDV, in terms of packet delivery ratio (PDR), Average End-to-End Delay, Throughput, Average Throughput per Packet, Packet Drop Rate, and Normalized Routing Load after incorporating the proposed modification designs. The paper concludes that the incorporation of Ant Colony is better suited to enhance VANETs than PSO. © 2024 IEEE.

关键词： Vehicular ad hoc networks

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：