检索结果-内蒙古大学图书馆

A Novel Deep Learning Approach Toward Efficient and Accurate Recommendation Using Improved Alternating Least Squares in Social Media

引用

Journal of The Institution of Engineers (India): Series B 2024年第3期105卷 657-675页

作者： Dhawan, Sanjeev Singh, Kulvinder Batra, Amit Choi, Anthony Choi, Ethan Department of Computer Science and Engineering University Institute of Engineering and Technology Kurukshetra University Haryana India Department of Electrical and Computer Engineering Mercer University MaconGA United States

The increasing number of electronic transactions on the Internet has given rise to the design of recommendation systems. The main objective of these systems is to give recommendations to the users about the items (i.e., movies, music, books, etc.) they are likely to purchase in near future. These recommendations are on the foundation of the response provided by the other individuals about these products in the terms of ratings, which are in the form of a five-star rating system. Plenty of algorithms have been proposed in the past for building recommender systems. The most popular of these algorithms comprise content-centered and collaborative filtering recommendation methodologies. Recently, matrix factorization has appeared as a technique in recommender systems. Several algorithms centered on matrix factorization have been suggested in the recent past. In this paper, an improved alternating least squares algorithm has been proposed for building more efficient and accurate recommender systems which improves the performance of matrix factorization. The performance of the model has been evaluated using metrics like root-mean-square-error and execution time. However, in general, the time complexity of both algorithms is O(n^3), where n is the number of users or items. This is because both IALS and ALS involve iteratively solving a system of linear equations, and the time complexity of solving a system of linear equations is O(n^3). However, IALS can achieve significant performance improvements over ALS, particularly for large datasets, due to its incorporation of stochastic gradient descent and parallelization techniques. © The Institution of Engineers (India) 2024.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Context Awareness by Noise-Pattern Analysis of a Smart Factory

引用

computers, Materials & Continua 2023年第8期76卷 1497-1514页

作者： So-Yeon Lee Jihoon Park Dae-Young Kim Department of Software Convergence Soonchunhyang UniversityAsan31538Korea Department of Computer Software Engineering Soonchunhyang UniversityAsan31538Korea

Recently,to build a smart factory,research has been conducted to perform fault diagnosis and defect detection based on vibration and noise signals generated when a mechanical system is driven using deep-learning technology,a field of artificial *** of the related studies apply various audio-feature extraction techniques to one-dimensional raw data to extract sound-specific features and then classify the sound by using the derived spectral image as a training ***,compared to numerical raw data,learning based on image data has the disadvantage that creating a training dataset is very ***,we devised a two-step data preprocessing method that efficiently detects machine anomalies in numerical raw *** the first preprocessing process,sound signal information is analyzed to extract features,and in the second preprocessing process,data filtering is performed by applying the proposed *** efficient dataset was built formodel learning through a total of two steps of data *** addition,both showed excellent performance in the training accuracy of the model that entered each dataset,but it can be seen that the time required to build the dataset was 203 s compared to 39 s,which is about 5.2 times than when building the image dataset.

关键词： Noise-pattern recognition context awareness deep learning fault detection smart factory

来源：评论

学校读者我要写书评

暂无评论

SkinMultiNet: Advancements in Skin Cancer Prediction Using Deep Learning with Web Interface

引用

Biomedical Materials and Devices 2025年第1期3卷 621-637页

作者： Likhon, Md Nur Hosain Rana, Sahab Uddin Akter, Sadeka Ahmed, Md. Shorup Tanha, Khadiza Akter Rahman, Md. Mahbubur Nayeem, Md Emran Hussain Department of Computer Science and Engineering Dhaka International University Dhaka Bangladesh Department of Computer Science and Engineering Dhaka University of Engineering and Technology Gazipur Bangladesh Department of Computer Science and Engineering Bangladesh University of Business and Technology Dhaka Bangladesh

Cancer remains the leading cause of death worldwide, significantly impacting individuals and healthcare systems alike. In recent decades, skin cancer has surged in prevalence compared to other major cancer types. Various factors such as texture, color, morphological characteristics, and structure are employed in categorizing different forms of skin cancer. However, traditional methods of identification often prove time-consuming and costly. Skin cancer classification predominantly relies on machine learning, with the primary method being convolutional neural networks (CNNs). Our ‘SkinMultiNet’ framework, presented in this study and based on transfer learning principles, integrates the InceptionV3 and Xception CNN models for predicting skin cancer using image data. While other machine learning models such as ResNet50, NasNet, and MobileNet were explored, the 'SkinMultiNet' framework demonstrated the most promising outcomes. Utilizing a publicly available dataset comprising 6086 skin images, we trained, tested, and evaluated our models extensively. Proposed system employed a train generator to feed image data into our deep learning CNN models, followed by implementing a learning rate reducer on the datasets within the model. Through rigorous testing and validation procedures, our models successfully processed a substantial volume of skin image data. In contrast to conventional approaches, our proposed architecture offers the potential for more reliable diagnoses, achieving an optimal accuracy rate of 94% in skin cancer prediction. This advancement holds promise for early detection and improved patient outcomes following therapy. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Convolutional neural network Deep learning Django Skin cancer Web interface

来源：评论

学校读者我要写书评

暂无评论

OCRBench: on the hidden mystery of OCR in large multimodal models

引用

science China(Information sciences) 2024年第12期67卷 23-35页

作者： Yuliang LIU Zhang LI Mingxin HUANG Biao YANG Wenwen YU Chunyuan LI Xu-Cheng YIN Cheng-Lin LIU Lianwen JIN Xiang BAI School of Artificial Intelligence and Automation Huazhong University of Science and Technology School of Electronic and Information Engineering South China University of Technology Microsoft Research School of Computer & Communication Engineering University of Science and Technology Beijing Institute of Automation Chinese Academy of Sciences School of Software Engineering Huazhong University of Science and Technology

Large models have recently played a dominant role in natural language processing and multimodal vision-language learning. However, their effectiveness in text-related visual tasks remains relatively unexplored. In this paper, we conducted a comprehensive evaluation of large multimodal models, such as GPT4V and Gemini, in various text-related visual tasks including text recognition, scene text-centric visual question answering(VQA), document-oriented VQA, key information extraction(KIE), and handwritten mathematical expression recognition(HMER). To facilitate the assessment of optical character recognition(OCR) capabilities in large multimodal models, we propose OCRBench, a comprehensive evaluation benchmark. OCRBench contains 29 datasets, making it the most comprehensive OCR evaluation benchmark available. Furthermore, our study reveals both the strengths and weaknesses of these models, particularly in handling multilingual text, handwritten text, non-semantic text, and mathematical expression *** importantly, the baseline results presented in this study could provide a foundational framework for the conception and assessment of innovative strategies targeted at enhancing zero-shot multimodal *** evaluation pipeline and benchmark are available at https://***/Yuliang-Liu/Multimodal OCR.

关键词： large multimodal model OCR text recognition scene text-centric VQA document-oriented VQA key information extraction handwritten mathematical expression recognition

来源：评论

学校读者我要写书评

暂无评论

Fractional Processing Based Adaptive Beamforming Algorithm

引用

computers, Materials & Continua 2023年第7期76卷 1065-1084页

作者： Syed Asghar Ali Shah Tariqullah Jan Syed Muslim Shah Ruhul Amin Khalil Ahmad Sawalmeh Muhammad Anan Department of Electrical Engineering University of Engineering and TechnologyPeshawar25120Pakistan Department of Electrical Engineering Capital University of Science and TechnologyIslamabad44000Pakistan Department of Computer Science Northern Border UniversityArar91431Saudi Arabia Department of Software Engineering Alfaisal UniversityRiyadh11533Saudi Arabia

Fractional order algorithms have shown promising results in various signal processing applications due to their ability to improve performance without significantly increasing *** goal of this work is to inves-tigate the use of fractional order algorithm in the field of adaptive beam-forming,with a focus on improving performance while keeping complexity *** effectiveness of the algorithm will be studied and evaluated in this *** this paper,a fractional order least mean square(FLMS)algorithm is proposed for adaptive beamforming in wireless applications for effective utilization of *** algorithm aims to improve upon existing beam-forming algorithms,which are inefficient in performance,by offering faster convergence,better accuracy,and comparable computational *** FLMS algorithm uses fractional order gradient in addition to the standard ordered gradient in weight *** derivation of the algorithm is provided and supported by mathematical convergence *** is evaluated through simulations using mean square error(MSE)minimization as a metric and compared with the standard LMS algorithm for various *** results,obtained through Matlab simulations,show that the FLMS algorithm outperforms the standard LMS in terms of convergence speed,beampattern accuracy and scatter *** outperforms LMS in terms of convergence speed by 34%.From this,it can be concluded that FLMS is a better candidate for adaptive beamforming and other signal processing applications.

关键词： Adaptive beamforming adaptive array fractional processing least mean square fractional least mean square

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Characteristic Aware Index Structure Optimized for Real-world Datasets

引用

ACM Transactions on Storage 2025年第2期21卷 1-32页

作者： Yang, Jin Yoon, Heejin Yun, Gyeongchan Noh, Sam H. Choi, Young-Ri Computer Science and Engineering Unist Ulsan Korea Republic of Department of Computer Science Virginia Tech Blacksburg United States

Many datasets in real life are complex and dynamic, that is, their key densities are varied over the whole key space and their key distributions change over time. It is challenging for an index structure to efficiently support all key operations for data management, in particular, search, insert, and scan, for such dynamic datasets. In this article, we present DyTIS (Dynamic dataset Targeted Index Structure), an index that targets dynamic datasets. DyTIS, although based on the structure of Extendible hashing, leverages the CDF of the key distribution of a dataset, and learns and adjusts its structure as the dataset grows. The key novelty behind DyTIS is to group keys by the natural key order and maintain keys in sorted order in each bucket to support scan operations within a hash index. We also define what we refer to as a dynamic dataset and propose a means to quantify its dynamic characteristics. Our experimental results show that DyTIS provides higher performance than the state-of-the-art learned index for the dynamic datasets considered. We also analyze the effects of the dynamic characteristics of datasets, including sequential datasets, as well as the effect of multiple threads on the performance of the indexes. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Dynamic datasets index structure key distribution

来源：评论

学校读者我要写书评

暂无评论

Improved security with novel M-Log chaos steganography algorithm for huffman compressed english text

引用

Multimedia Tools and Applications 2025年第2期84卷 665-688页

作者： Raghuvanshi, Devvrat Joshi, Kamaldeep Nandal, Rainu Sehrawat, Harkesh Singh, Surender Singh, Srishti Department of Computer Science and Engineering University Institute of Engineering and Technology Maharshi Dayanand University Rohtak Haryana India

This paper addresses the underexplored landscape of chaotic functions in steganography, existing literature when examined under PRISMA-ScR framework it was realized that most of the studies predominantly focuses on utilizing chaotic functions for either concealing or diffusing messages within cover images. This study explored a different direction of using chaotic function as guards for concealed data by proposing the M-Log chaos algorithm which employs logarithmic chaotic function to drive a unique bomb generator equation, strategically placing bomb bits in the image. These bombs act as sentinels, safeguarding the concealed message. Successful retrieval involves diffusing the bombs before extracting data from the rest of the image. Failure to defuse these bombs prior to access results in irreversible damage to concealed information, thwarting unauthorized access. Our proposed method demonstrates notable advancements across quantitative performance metrics, including a 40% increase in payload capacity, a mean PSNR of 45.8981, and a mean SSIM of 0.9931. Future avenues include exploring multi-dimensional chaotic functions and employing nature-based searching algorithms such as genetic algorithms or particle swarm optimization for optimal chaos bomb placement. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

A Hybrid P&O-Fuzzy-Based Maximum Power Point Tracking (MPPT) Algorithm for Photovoltaic Systems under Partial Shading Conditions

引用

IEEE Access 2025年 13卷 86046-86056页

作者： Karimi, Hamed Siadatan, Alireza Rezaei-Zare, Afshin Khatam University Department of Electrical Engineering Tehran Iran York University Department of Electrical Engineering and Computer Science Toronto Canada

Photovoltaic arrays receive varying levels of solar radiation due to factors such as shadows created by clouds, surrounding buildings, and other obstructions. Therefore, an effective Maximum Power Point Tracking (MPPT) algorithm should be used to maximize power generation from non-uniform arrays. Most MPPT algorithms do not perform well during partial shadow conditions, as they can become trapped in local maxima and fail to identify the absolute global maximum point (GP). This paper proposes a new MPPT approach that combines Perturb & Observe (P&O) and Fuzzy Logic Controller (FLC) with the Particle Swarm Optimization (PSO) algorithm. The FLC algorithm is then used to maximize search accuracy. The configurations of this system and the study results demonstrate the dynamic and promising performance of the proposed method under various environmental and shading conditions. In addition to its simplicity and ease of implementation, the proposed algorithm exhibits high accuracy in tracking the maximum power point. This has been evidenced through both simulation and laboratory results of the hardware. © 2025 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Fine-Tuning Cyber Security Defenses: Evaluating Supervised Machine Learning Classifiers for Windows Malware Detection

引用

computers, Materials & Continua 2024年第8期80卷 2917-2939页

作者： Islam Zada Mohammed Naif Alatawi Syed Muhammad Saqlain Abdullah Alshahrani Adel Alshamran Kanwal Imran Hessa Alfraihi Department of Software Engineering International Islamic UniversityIslamabad25000Pakistan Information Technology Department Faculty of Computers and Information TechnologyUniversity of TabukTabuk71491Saudi Arabia Department of Computer Science and Artificial Intelligence College of Computer Science and EngineeringUniversity of JeddahJeddah21493Saudi Arabia Department of Cybersecurity College of Computer Science and EngineeringUniversity of JeddahJeddah21493Saudi Arabia Department of Computer Science University of PeshawarPeshawar25121Pakistan Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia

Malware attacks on Windows machines pose significant cybersecurity threats,necessitating effective detection and prevention *** machine learning classifiers have emerged as promising tools for malware ***,there remains a need for comprehensive studies that compare the performance of different classifiers specifically for Windows malware *** this gap can provide valuable insights for enhancing cybersecurity *** numerous studies have explored malware detection using machine learning techniques,there is a lack of systematic comparison of supervised classifiers for Windows malware *** the relative effectiveness of these classifiers can inform the selection of optimal detection methods and improve overall security *** study aims to bridge the research gap by conducting a comparative analysis of supervised machine learning classifiers for detecting malware on Windows *** objectives include Investigating the performance of various classifiers,such as Gaussian Naïve Bayes,K Nearest Neighbors(KNN),Stochastic Gradient Descent Classifier(SGDC),and Decision Tree,in detecting Windows *** the accuracy,efficiency,and suitability of each classifier for real-world malware detection *** the strengths and limitations of different classifiers to provide insights for cybersecurity practitioners and *** recommendations for selecting the most effective classifier for Windows malware detection based on empirical *** study employs a structured methodology consisting of several phases:exploratory data analysis,data preprocessing,model training,and *** data analysis involves understanding the dataset’s characteristics and identifying preprocessing *** preprocessing includes cleaning,feature encoding,dimensionality reduction,and optimization to prepare the data for *** training utilizes various

关键词： Security and privacy challenges in the context of requirements engineering supervisedmachine learning malware detection windows systems comparative analysis Gaussian Naive Bayes K Nearest Neighbors Stochastic Gradient Descent Classifier Decision Tree

来源：评论

学校读者我要写书评

暂无评论

ANovel Light Weight CNN Framework Integrated with Marine Predator Optimization for the Assessment of Tear Film-Lipid Layer Patterns

引用

computer Modeling in engineering & sciences 2023年第7期136卷 87-106页

作者： Bejoy Abraham Jesna Mohan Linu Shine Sivakumar Ramachandran Department of Computer Science and Engineering College of Engineering MuttatharaThiruvananthapuramKerala695008India Department of Computer Science and Engineering Mar Baselios College of Engineering and TechnologyThiruvananthapuramKerala695015India Department of Electronics and Communication Engineering College of Engineering TrivandrumKerala695016India

Tear film,the outermost layer of the eye,is a complex and dynamic structure responsible for tear *** tear film lipid layer is a vital component of the tear film that provides a smooth optical surface for the cornea and wetting the ocular *** eye syndrome(DES)is a symptomatic disease caused by reduced tear production,poor tear quality,or excessive *** diagnosis is a difficult task due to its multifactorial *** of several clinical tests available,the evaluation of the interference patterns of the tear film lipid layer forms a potential tool for DES *** instrument known as Tearscope Plus allows the rapid assessment of the lipid layer.A grading scale composed of five categories is used to classify lipid layer *** reported work proposes the design of an automatic system employing light weight convolutional neural networks(CNN)and nature inspired optimization techniques to assess the tear film lipid layer patterns by interpreting the images acquired with the Tearscope *** designed framework achieves promising results compared with the existing state-of-the-art techniques.

关键词： Dry-eye syndrome tearscope plus tear film deep neural 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：