检索结果-内蒙古大学图书馆

Behavioral insights into compression: a study of Move-to-Front-or-Middle deterministic online algorithm through sequence classification and characterization

引用

International Journal of Information technology (Singapore) 2025年第1期17卷 189-203页

作者： Baisakh Mohapatra, Hitesh Guru, Abhishek Department of Computer Science and Engineering Sambalpur University Institute of Information Technology Sambalpur India Computer Science and Engineering GMR Institute of Technology Andhra Pradesh Rajam India School of Computer Engineering KIIT Deemed to Be University Bhubanseswar India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India

Since the list update problem was applied to data compression as an effective encoding technique, numerous deterministic algorithms have been studied and analyzed. A powerful strategy, Move-to-Front (MTF), involves moving an accessed item to the front of the list immediately. Theoretical analysis has demonstrated MTF’s potential, showing it to be 2-competitive through competitive analysis. This success has inspired researchers to develop various intriguing MTF variants and assess their performance both theoretically and experimentally. One such variant, Move-to-Front-or-Middle (MFM), has been experimentally shown that MFM performed better than the classic MTF on Calgary and Cantebury Datasets. However, the experimental performance alone does not provide sufficient insight into the internal behavior of the algorithm or explain why its performance surpasses MTF on certain datasets. Therefore, in this paper, we conduct a detailed behavioral study of MFM through sequence classification and characterization to gain deeper understanding of the algorithm and aims to reconcile the disparity between theoretical and experimental outcomes. This paper also by classifying and characterizing MFM’s performance across various request sequences, considering both the presence and absence of locality of reference. © Bharati Vidyapeeth's institute of computer Applications and Management 2024.

关键词： Competitive analysis Deterministic list update algorithm List update problem Sequence classification

来源：评论

学校读者我要写书评

暂无评论

Document Summarizer: A Machine Learning approach to PDF summarization 4

Document Summarizer: A Machine Learning approach to PDF summ...

引用

4th International Conference on Evolutionary Computing and Mobile Sustainable Networks, ICECMSN 2024

作者： Peddarapu, Rama Krishna Anogna, Sudagoni Harshini, M.N.S. Sri Sireesha, J. Rathna, K. Guna Department of Computer Science and Engineering Faculty of Computer Sciences and Engineering VNR Vignana Jyothi Institute of Engineering and Technology Telangana Hyderabad India Department of Computer Science and Engineering VNR Vignana Jyothi Institute of Engineering and Technology Telangana Hyderabad India

To address the need for summarizing and extracting information efficiently, this paper highlights the growing challenge posed by the increasing number of PDF files. Reading lengthy documents is a tedious and time-consuming task. To save time and quickly comprehend the key points of a PDF, a PDF summarizer tool has been developed to tackle these issues. In today's professional environments, gathering and managing data from documents is critical. This article introduces an innovative solution called DocSum, which automates the process of summarizing extracted data. Powered by *** Core, the DocSum system allows users to upload PDF documents for processing and receive concise summaries in return. The system features a user-friendly interface that encourages interaction and engagement, utilizing AI and machine learning techniques to streamline document handling. Users can request specific summaries, enabling efficient document management workflows. By empowering users to seamlessly interact with vast amounts of information, DocSum enhances productivity and explores new ways to optimize document management. This solution is ideal for professionals seeking to stay informed and manage data effectively, while also keeping track of advancements in document handling technologies across multiple industries. It is not only helpful for professionals but also helpful for students who need quick revision or examinations, teachers to gain brief knowledge on the concepts. © 2025 The Authors. Published by Elsevier B.V.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

Deep ensemble model for skin cancer classification with improved feature set

引用

Multimedia Tools and Applications 2025年第10期84卷 7599-7626页

作者： Burada, Sreedhar Manjunathswamy, B.E. Kumar, M. Sunil Department of Computer Science and Engineering Don Bosco Institute of Technology Karnataka Bengaluru560074 India Department of Computer Science and Engineering School of Computing Mohan Babu University Sree Vidyanikethan Engineering College Andhra Pradesh Tirupati517102 India

Early identification of skin cancer is mandatory to minimize the worldwide death rate as this disease is covering more than 30% of mortality rates in young and adults. Researchers are in the move of proposing advanced models for the accurate classification of skin disease. This paper introduces a novel skin cancer detection model under the stages of preprocessing, feature extraction, classification as well as segmentation. The given input is first preprocessed via Gaussian filtering. Subsequently, the Deep learning model termed as ‘U-net’ is used for the segmentation process. Afterward, the extraction of the feature set including features like Improved Center symmetric Local Binary Pattern (ICS-LBP), Local Gradient Pattern (LGP), Median binary pattern (MBP) is performed. Classification takes place using Deep Ensemble Model based on the extracted features, that includes BiGRU, Deep Maxout, and Improved Deep Convolutional Neural Network (CNN), respectively. Also, as the hyperparameter tuning of the classification model enhances the performance, this work introduces a new Hybrid Atom and Arithmetic Operation Algorithm (HAAOA) algorithm for tuning the optimal weights of the Bi-GRU (Bi-directional Gated Recurrent Unit) and Deep Maxout model. At last, the validation of the proposed work is performed through different performance measures by comparing it with different algorithms. Accordingly, accuracy of the adopted method at 90th learning percentage is 93.56%, which is (~) 82.63%, 85.15%, 84.98%, 83.66% and 83.42% better than AOA, ASO, BWO, BMO and DO, respectively. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Enhancing real time object detection for autonomous driving using YOLO-NAS algorithm with CLEO optimizer

引用

International Journal of Information technology (Singapore) 2025年第3期17卷 1321-1328页

作者： Nandal, Priyanka Pahal, Sudesh Malik, Sunesh Sehrawat, Neetu Mamta Department of Computer Science and Engineering Maharaja Surajmal Institute of Technology New Delhi India Department of Electronics and Communication Engineering Maharaja Surajmal Institute of Technology New Delhi India Department of Information Technology Maharaja Surajmal Institute of Technology New Delhi India Department of Computer Science and Engineering Panipat Institute of Engineering & Technology New Delhi India

For autonomous driving to operate in a safe and effective manner, efficient and precise object detection is essential. The efficacy of the network model is heavily challenged because of the high-speed movement of vehicles and the dynamic nature of the surrounding environment that need the detection of objects of various scales. With notable improvements over earlier iterations, the You Only Look Once-Neural Architecture Search (YOLO-NAS) algorithm is a strong contender for improving real-time object recognition in autonomous vehicles. YOLO-NAS integrated with chimpanzee leader election optimization (CLEO) has the potential to greatly enhance the safety and dependability of autonomous driving systems by utilizing its sophisticated capabilities and skill fully combining it with the vehicle’s perception system. The BDD100K dataset serves as the training and evaluation set for our suggested technique. The YOLO-NAS model with CLEO optimizer achieves mean average precision (mAP) of 83%, which is significantly higher than the mAP of 65.7% attained by the YOLO-NAS model without the optimizer. This improvement highlights the effectiveness of the CLEO optimizer in enhancing detection precision. The proposed approach was compared with existing algorithms and demonstrated remarkable performance in terms of recall, precision, and mAP. It is seen that our proposed model is better by striking equilibrium between detection speed and accuracy. Based on our findings, object detection performance for autonomous driving applications is much enhanced when utilizing our suggested approach. © Bharati Vidyapeeth's institute of computer Applications and Management 2024.

关键词： Autonomous vehicles Deep learning Object detection YOLO-NAS

来源：评论

学校读者我要写书评

暂无评论

An Automated Approach to Discovering Software Refactorings by Comparing Successive Versions

引用

IEEE Transactions on Software engineering 2025年第05期51卷 1358-1380页

作者： Liu, Bo Liu, Hui Niu, Nan Zhang, Yuxia Li, Guangjie Jiang, He Jiang, Yanjie University of Cincinnati Department of Electrical Engineering and Computer Science CincinnatiOH United States National Innovation Institute of Defense Technology Beijing China School of Software Dalian University of Technology Dalian China Beijing Institute of Technology School of Computer Science and Technology Beijing China Peking University School of Computer Science Beijing China

Software developers and maintainers frequently conduct software refactorings to improve software quality. Identifying the conducted software refactorings may significantly facilitate the comprehension of software evolution, and thus facilitate software maintenance and evolution. Besides that, the identified refactorings are also valuable for data-driven approaches in software refactoring. To this end, researchers have proposed a few approaches to identifying software refactorings automatically. However, the performance (especially precision) of such approaches deserves substantial improvement. To this end, in this paper, we propose a novel refactoring detection approach, called REEXTRACTOR+. At the heart of REEXTRACTOR+ is a reference-based entity matching algorithm that matches coarse-grained code entities (e.g., classes and methods) between two successive versions, and a context-aware statement matching algorithm that matches statements within a pair of matched methods. We evaluated REEXTRACTOR+ on a benchmark consisting of 400 commits from 20 real-world projects. The evaluation results suggested that REEXTRACTOR+ significantly outperformed the state of the art in refactoring detection, reducing the number of false positives by 59.6% and improving recall by 19.2%. We also evaluated the performance of the proposed matching algorithms that serve as the cornerstone of refactoring detection. The evaluation results suggested that the proposed algorithms excel in matching code entities, substantially reducing the number of mistakes (false positives plus false negatives) by 67% compared to the state-of-the-art approaches. © 2025 IEEE.

关键词： Software quality

来源：评论

学校读者我要写书评

暂无评论

Domain generalization with semi-supervised learning for people-centric activity recognition

引用

Science China(Information Sciences) 2025年第1期68卷 171-188页

作者： Jing LIU Wei ZHU Di LI Xing HU Liang SONG Academy for Engineering & Technology Fudan University Shanghai East-bund Research Institute on Networking Systems of AI School of Optoelectronic Information and Computer Engineering University of Shanghai for Science & Technology

People-centric activity recognition is one of the most critical technologies in a wide range of real-world applications,including intelligent transportation systems, healthcare services, and brain-computer interfaces. Large-scale data collection and annotation make the application of machine learning algorithms prohibitively expensive when adapting to new tasks. One way of circumventing this limitation is to train the model in a semi-supervised learning manner that utilizes a percentage of unlabeled data to reduce the labeling burden in prediction tasks. Despite their appeal, these models often assume that labeled and unlabeled data come from similar distributions, which leads to the domain shift problem caused by the presence of distribution gaps. To address these limitations, we propose herein a novel method for people-centric activity recognition,called domain generalization with semi-supervised learning(DGSSL), that effectively enhances the representation learning and domain alignment capabilities of a model. We first design a new autoregressive discriminator for adversarial training between unlabeled and labeled source domains, extracting domain-specific features to reduce the distribution gaps. Second, we introduce two reconstruction tasks to capture the task-specific features to avoid losing information related to representation learning while maintaining task-specific consistency. Finally, benefiting from the collaborative optimization of these two tasks, the model can accurately predict both the domain and category labels of the source domains for the classification task. We conduct extensive experiments on three real-world sensing datasets. The experimental results show that DGSSL surpasses the three state-of-the-art methods with better performance and generalization.

关键词： activity recognition deep learning domain generalization semi-supervised learning adversarial training

来源：评论

学校读者我要写书评

暂无评论

Semi supervised K–SVCR for multi-class classification

引用

Multimedia Tools and Applications 2025年第9期84卷 6737-6753页

作者： Srivastava, Vivek Prakash Kapil Department of Computer Applications National Institute of Technology Haryana Kurukshetra136119 India

In recent developments, the traditional binary class SVM has evolved into a multi-class classifier utilizing a ‘1-versus-1-versus-rest’ approach named K−SVCR. This innovative version efficiently categorizes multi-class data samples, generating ternary mode outputs {-1,0,+1}, enabling simultaneous classification into three distinct classes. However, the availability of labelled data is scarce as it requires human effort for labelling it. But, the availability of unlabelled samples is easier as these are devoid of explicit class labels. This unlabelled data can be utilized by augmenting graph Laplacian regularisation term, evolving it into a semi-supervised learning approach for mode training. Thus, the model can capture samples’ distribution information available with abundant unlabeled data. Now, even a few labelled samples can elevate the effectiveness of the trained model on out-of-sample data. This article’s primary objective is to harness the potential of unlabeled data. To understand the intuition behind the proposed model two artificial datasets are considered. Further, the experiments were conducted on several real-world datasets from the UCI machine learning repository and the Flavia dataset for plant identification from leaf images, to evaluate the performance of the Semi-supervised graph Laplacian K−SVCR (Lap−KSVCR) model in terms of accuracy, precision, recall, and F-score of classification. It was observed that the model could achieve 63% accuracy by training on a single labelled sample per class in case of non-linear three class artificial datasets. Additionally, on UCI real-world dataset and Flavia dataset an improvement of up to 17.5%, 17.3%, 30.1%, and 17.2% was observed in accuracy, precision, recall, and f-score, respectively when compared to K−SVCR. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Extraction of road using semi-supervised deep learning method 4th

Extraction of road using semi-supervised deep learning metho...

引用

4th International Conference on Computational Methods in Science and technology, ICCMST 2024

作者： Mishra, Jalaj Khan, Mohd Jawed Negi, Himanshi Alam, Jitendra Alam, Junaid Singh, Pankaj Pratap Department of Computer Science & Engineering Greater Noida Institute of Technology Greater Noida India Department of Computer Science & Engineering Central Institute of Technology Assam Kokrajhar India

ISBN: (纸本)9781032911571

Detection of road networks using high-resolution aerial or remote sensing imagery constitutes a significant focus within modern research efforts. Currently, deep learning models demonstrate efficiency to a certain degree, they are constrained by a notable reliance on annotated datasets, a practice divergent from optimal methodologies due to the scarcity of extensive, high-quality labeled data. The precision of road prediction is additionally influenced by the latent information embedded within pixels exhibiting diminished confidence values. These pixels play a crucial role in discriminating between road and non-road regions within the images, yet their utilization by deep learning models is suboptimal. To handle these two different issues, opted U-Net as our base model with a sole generator paired with twin dis-criminators and presented this combined setup of U-Net on the Generative Adversarial Network (GAN). At the base of the U-Net architecture, a bottleneck module is incorporated to augment the functionalities of the proposed model. This proposed model attains 98% accuracy on DeepGlobe Road Dataset. Comparative and quantitative assessment demonstrates the enhanced efficiency of our model compared to similar methodologies. © 2025 the Author(s).

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Optimizing Parkinson’s Disease Detection: Hybrid S-transform-EEG Feature Reduction Through Trajectory Analysis

引用

SN computer Science 2025年第2期6卷 1-14页

作者： Afonso, Melina Maria Edla, Damodar Reddy Reddy, R. Ravinder Department of Computer Science and Engineering National Institute of Technology Goa Kottamoll Plateau Goa Cuncolim 403703 India Department of Computer Engineering Goa College of Engineering Farmagudi Goa Ponda 403401 India Department of Computer Science and Engineering Chaitanya Bharathi Institute of Technology Telangana Hyderabad 500075 India

With Parkinson’s disease (PD) becoming more common, there is an increasing demand for accurate technology-driven PD detection. This research attempts to address this requirement. Because of its accessibility, use, and non-invasiveness, electroencephalography (EEG) has shown to be a potential technique for detection. Extraction of a wide range of features from the intricate EEG signals of Parkinson’s disease patients has been made possible by utilizing deep learning algorithms and transformation methods, enabling comprehensive analysis. But this data is enormous and presents computational difficulties, particularly when developing accessible and detection systems. To address this, the research proposes a feature reduction model that uses a hybrid approach to cut down the computational complexity. This approach combines four different feature scoring methods-ANOVA F-value, Mutual Information, Chi-square, and linear regression F-value-to generate a unified ranking score for each feature extracted from S-transformed EEG images. This score is thus generated leveraging the strengths of the diverse mechanisms and used to sort the features. The model decreases the feature set depending on these scores and utilizes a deep neural network to detect PD. This methodically lowers the feature count while monitoring the impact on the accuracy of the neural network. Finding the ideal feature combination is the goal, but maintaining the capacity to detect between people who have and don’t have Parkinson’s disease is a must. By balancing diagnostic accuracy and computational efficiency, the suggested technique ultimately yields accuracy rates of 95.94% and 97.31% on two different datasets with the reduced features, which outperforms other state-of-the art optimization algorithms compared in this research. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Brain computer interface Deep learning Electroencephalography Feature reduction Parkinson’s disease Stockwell-transform

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Reliability in Request-segregated Clouds through Remiadiations Predicting Hardware Failure Scheme

引用

Recent Patents on engineering 2025年第1期19卷 112-127页

作者： Sharma, Rohit Yadav, Vibhash Singh, Raghuraj Department of Computer Science and Engineering Dr. Ambedkar Institute of Technology for Handicapped U.P. Kanpur208024 India Department of Information Technology Rajkiya Engineering College Banda210201 India Department of Computer Science and Engineering Harcourt Butler Technical University Kanpur208002 India

Background: Cloud services have become a popular approach for offering efficient services for a wide range of activities. Predicting hardware failures in a cloud data center can minimize downtime and make the system more reliable and fault-tolerant. Objective: This research aims to analyze a predictive hardware failure model based on machine learning that anticipates the required remediations for undiagnosed failures in a cloud computing system serving multiclass requests. Methods: The model is tested on a carefully designed cloud data center that categorizes incoming requests as web, compute, storage, and dedicated server requests. To demonstrate improved reliability, a carefully designed test case is run on ReliaCloud-NS, which is a simulator for creating a CCS and computing its reliability. Results: The work found that using this model considerably enhanced the reliability of cloud computing systems when compared to not using the model. Conclusion: Although various estimation methods are patented to evaluate the system reliability of a cloud computing network, the emphasis of this study was mostly on improving the reliability of request-segregated clouds upon failing hardware resources like CPU, memory, bandwidth, and hard disc. Moreover, the prediction model might potentially be expanded to other system resources such as GPUs, software, and database packages. © 2025 Bentham Science Publishers.

关键词： Cloud platforms

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：