检索结果-内蒙古大学图书馆

International Conference on Contemporary Computing and Informatics (IC3I)

作者： S P Sreeja D Sreenivasulu Alok Jain R. Akhilesh Reddy Fatimah Dhari Jabbar V. Keerthi Master of Computer Application New Horizon College of Engineering Bangalore India Computer Science and Engineering (Data Science) Institute of Aeronautical Engineering Dundigal Hyderabad India Lovely Professional University Phagwara India Department of CSE-AI&ML MLR Institute of Technology Hyderabad Telangana India Radiology Techniques Department College of Medical Technology The Islamic University Najaf Iraq Department of CSE GRIET Bachupally Hyderabad Telangana India

ISBN: (数字)9798350350067

ISBN: (纸本)9798350350074

The phenomena of data explosion in different areas of life require enhanced methods to performing big data analysis. This paper proposes the Hybrid Intelligent Machine Learning System (HIMLS) which work through the combination of multiple machine learning approaches to improve the efficacy of big data analysis. HIMLS applies the benefits of both supervised and unsupervised learning, integrates deep learning models and ensemble methods to solve the difficulties which are from high-dimension learning and heterogeneous data. As a result of combining feature selection with the process of dimensionality reduction HIMLS moderates the curse of dimensionality which enhances the models’ predictive capability while lowering the computational requirements. It is proved that the system works on actual big data implementation, exhibits a better solution in terms of the accuracy of the model, size, and stability aspects in contrast to the conventional machine learning approaches. This research also analyses the effects that different techniques of hyperparameters optimization select and the involvement of distributed computing systems for speeding up analytics. Thus the study infers HIMLS as a suitable solution to the shortcomings characterized by current big data analytical techniques, giving an efficient method for harnessing big data solutions.

关键词： Dimensionality reduction Accuracy Computational modeling Distributed databases Big Data Feature extraction Data models Stability analysis Ensemble learning Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

A New Debleeding Algorithm for Image colorization

A New Debleeding Algorithm for Image colorization

引用

Consumer Electronics and computer engineering (ICCECE), 2021 IEEE International Conference on

作者： Lianrong Chen Naidan Mei Lianjie Wang Jianhong Li Department of Computer Science and Technology Guangdong University of Foreign Studies (GDUFS) Guangzhou China Department of Software Engineering Guangdong University of Foreign Studies (GDUFS) Guangzhou China

Colorization is the process of adding color to grayscale images using computer algorithms. There are several approaches to color an image, including precise image segmentation algorithms, deep learning algorithms, and manually colored local color expansion methods. However, one common problem with these approaches is the occurrence of “color bleeding”, where colors from one region of the image spill over into adjacent regions. In this paper, we propose a new manually colored local color expansion algorithm that considers the intensity value difference and distance difference between the central pixel in the window and its neighbor pixels comprehensively. Combined with side window filtering, our algorithm significantly reduces the occurrence of colors bleeding at the edges of the colored image. The experiments demonstrate the effectiveness of the proposed algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modeling and Performance Analysis of Spiral Fishbone Network Using NS-2

引用

Journal of computer and Communications 2022年第3期10卷 125-140页

作者： Pronab Biswas Md Maruf Islam Sayed Asaduzzaman Nazrul Islam M. Raihan Department of Software Engineering Daffodil International University Dhaka Bangladesh Department of Information and Communication Technology Mawlana Bhashani Science and Technology University Tangail Bangladesh Department of Computer Science and Engineering North Western University Khulna Bangladesh

In this research, we have projected and carried out a novel fishbone network that shows better performance in the term of minimizing the packet delay with respect to sink speed. Previous study implies that sector angle affects greatly on designing fishbone network. Finite Set of nodes arranges to sense the physical condition of any system is called wireless sensor. Our designed fishbone network can be potentially applied for a wireless sensing system to formulate a whole network. The network is a novel design which has been finalized by comparing sector angle. Analysis takes place by varying packet delay according to sink speed. Future analysis takes place for Quality of Service (QoS) and Quality of Experience (QoE). Latency of Packet and its size is the measurement criteria of any network or service is called Quality of Service (QoS). On the other hand the user experience of using the designed network is called Quality of Experience (QoE). Our designed network has been analyzed in TCP Tracer to find out the latency or packet delay for different users. The user data has been shorted and equated among them for latency with different no of packets. Our proposed spiral fishbone network shows better QoS and QoE. In future more nodes can be added to design extended fishbone network for wireless.

关键词： Fishbone Network Network Modelling Performance Analysis NS-2

来源：评论

学校读者我要写书评

暂无评论

A Novel Hybrid Scheme for Time Series Prediction Using LMS Filter and ISSA-based LSTM

A Novel Hybrid Scheme for Time Series Prediction Using LMS F...

引用

Symposia and Workshops on Ubiquitous, Autonomic and Trusted Computing, UIC-ATC

作者： Pei Heng Li Dong Xia Chen Han Yao Huang Xiao Tong Wu Hua Wei Jiang Gen Lin Ji School of Computer Science and Technology Nanjing Normal University Nanjing China Department of Computer and Software Engineering Nanyang Institute of Technology Nanyang China Department of Computer Science Engineering Sungkyunkwan Univeristy Suwon Korea

In the era of Internet of Everything (IoE), there is an explosive growth in data volumes and the data usually with time series characteristics. Therefore, how to deal with time series data to improve prediction accuracy remains a critical issue. In this paper, an efficient hybrid scheme combining linear and nonlinear models is proposed to greatly improve the prediction performance and simplify the hyperparameter selection process. Gradient-based least mean square (GD-LMS) is introduced for adaptive linear section, while a hyperparameter-determined long short-term memory (LSTM) is used for nonlinear section. In particular, an improved sparrow search algorithm combining opposition-based learning and Cauchy variance (ISSA) is used to construct the optimal hyperparameters for the two-layer LSTM. computer simulations with the UMass weather dataset reveal that the proposed scheme considerably outperforms three benchmarking methods in terms of data prediction accuracy and robustness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GRASSMARLIN-based Metadata Extraction of Cyber-Physical Systems Intrusion Detection in CyberSCADA Networks

GRASSMARLIN-based Metadata Extraction of Cyber-Physical Syst...

引用

International Conference on Computational science and Computational Intelligence (CSCI)

作者： John E. Efiong Bodunde O. Akinyemi Emmanuel A. Olajubu Ganiu A. Aderounmu Department of Computer Science & Engineering Obafemi Awolowo University lIe-Ife Nigeria Department of Computer Science & Engineering African Centre of Excellence in Software Engineering Obafemi Awolowo University Ile-Ife Nigeria

Cyber-Physical Systems such as those in the SCADA architecture and the entire industrial control system networks have now become essential components of the cyberspace due to their integration with modern IT networks. Cyber attackers have taken advantage of these vulnerable critical assets that have suddenly found themselves in an unprepared situation enabled by the Internet of Things Paradigm. Intrusions into the new CyberSCADA networks seem to go unabated as the proprietary communication protocols in these systems lack security mechanisms to help intrusion detection and analysis. In addition, existing network analyzers are weak in identifying granular details from traffic in these legacy networks that could help track, detect and investigate intrusions. This study performed a passive fingerprinting exercise on captured network data using Grassmarlin and identified useful metadata of critical network devices. The results demonstrate that fingerprints, metadata and critical assets' inventory on Grassmarlin would help industry-based cybersecurity personnel improve intrusion detections on CyberSCADA networks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Do bugs propagate? an empirical analysis of temporal correlations among software bugs 35

Do bugs propagate? an empirical analysis of temporal correla...

引用

35th European Conference on Object-Oriented Programming, ECOOP 2021

作者： Gu, Xiaodong Han, Yo-Sub Kim, Sunghun Zhang, Hongyu School of Software Shanghai Jiao Tong University China Department of Computer Science Yonsei University Seoul Korea Republic of Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong The University of New Castle Australia

ISBN: (纸本)9783959771900

The occurrences of bugs are not isolated events, rather they may interact, affect each other, and trigger other latent bugs. Identifying and understanding bug correlations could help developers localize bug origins, predict potential bugs, and design better architectures of software artifacts to prevent bug affection. Many studies in the defect prediction and fault localization literature implied the dependence and interactions between multiple bugs, but few of them explicitly investigate the correlations of bugs across time steps and how bugs affect each other. In this paper, we perform social network analysis on the temporal correlations between bugs across time steps on software artifact ties, i.e., software graphs. Adopted from the correlation analysis methodology in social networks, we construct software graphs of three artifact ties such as function calls and type hierarchy and then perform longitudinal logistic regressions of time-lag bug correlations on these graphs. Our experiments on four open-source projects suggest that bugs can propagate as observed on certain artifact tie graphs. Based on our findings, we propose a hybrid artifact tie graph, a synthesis of a few well-known software graphs, that exhibits a higher degree of bug propagation. Our findings shed light on research for better bug prediction and localization models and help developers to perform maintenance actions to prevent consequential bugs. © 2021 Schloss Dagstuhl- Leibniz-Zentrum fur Informatik GmbH, Dagstuhl Publishing. All rights reserved.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Optimizing Network Navigation: A Comparative Analysis of Genetic Algorithm Efficacy Against Traditional Shortest Path Paradigms

Optimizing Network Navigation: A Comparative Analysis of Gen...

引用

Technological Advancements in Computational sciences (ICTACS), International Conference on

作者： Jeetendra Kumar Rashmi Gupta Tejinder Kaur Department of Computer Science and Application Atal Bihari Vaipayyee Vishwavidyalya Bilaspur C.G. India Chitkara University Institute of Engineering and Technology Chitkara University Punjab India

it then selects the node with the smallest distance and adds it to the set of visited nodes. The heuristic function estimates the distance between each node and the goal node, allowing the algorithm to explore nodes that are likely to lead to the goal node first.. Once the graph is constructed, you can apply Dijkstra algorithm. Traditional algorithms, such as Dijkstra and Floyd-War shall, have been used to solve this problem efficiently, but their performance can be affected by the complexity and size of the network.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A deep learning-based approach for predicting ubiquitination sites using word embedding techniques

A deep learning-based approach for predicting ubiquitination...

引用

International Conference on computer and Information Technology (ICCIT)

作者： Md. Faruk Hosen Md. Abul Basar Md. Samim Hossain Sakib Sarker Md. Suhag Ali Monir Morshed Muhammad Shahin Uddin Department of Information and Communication Technology Mawlana Bhashani Science and Technology University Tangail Bangladesh Department of Computing and Information System Daffodil International University (DIU) Ashulia Dhaka Bangladesh Department of Computer Science and Engineering Uttara University Dhaka Department of Software Engineering Daffodil International University (DIU) Ashulia Dhaka Bangladesh

ISBN: (数字)9798331519094

ISBN: (纸本)9798331519100

Ubiquitination is a prevalent and reversible post-translational modification (PTM) that controls apoptosis and plays a crucial role in protein breakdown and cell disorders. Ubiquitination also involved in the control of a number of physiological mechanisms such as cellular proliferation, gene transcription, intracellular signaling, DNA correction, and synthesis. However, experimental identification of ubiquitination sites prediction is time-consuming and costly, so it is an urgent need to construct effective predictors. In this paper, a novel predictor called UbiSite-DeepWET has been developed to accurately predict ubiquitination sites from sequences using a convolutional neural network (CNN) model. First, we perform nine feature extraction method, namely Amino Acid Composition (AAC), Dipeptide Compostion (DPC), Composition of k-spaced Amino Acid Pairs (CKSAAP), Pseudo-Amino Acid Composition (PAAC), Amino Acid index (AAindex) database, Word2Vec, GloVe and fastText, to represent protein sequence patterns. Secondly, SHapley Additive exPlanations (SHAP) are used to remove unnecessary and irrelevant features for predicting ubiquitination sites. Finally, the best features are fed into the CNN classifier to build the UbiSite-DeepWET model for identifying the protein ubiquitination sites. Five-fold cross validation shows that the AUC values of Set1-Set6 datasets are 0.8846, 0.7764, 0.7881, 0.7740, 0.6870 and 0.7238, respectively. The Adaptive synthetic sampling approach (ADASYN) is applied in Set4 to Set6 unbalanced datasets, and the AUC values are 0.9929, 0.9975 and 0.9971, respectively. Additionally, we have created three independent test (IT) datasets which the AUC values are 0.8529, 0.6215 and 0.6001, respectively. The results demonstrate that the proposed technique UbiSite-DeepWET outperforms conventional ubiquitination prediction methods and offers new guidance for the identification of ubiquitination sites.

关键词： Protein engineering Additives Predictive models Amino acids Feature extraction Physiology Robustness Protein sequence Convolutional neural networks Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

MoMa: A Modular Deep Learning Framework for Material Property Prediction

arXiv

引用

arXiv 2025年

作者： Wang, Botian Ouyang, Yawen Li, Yaohui Wang, Yiqun Cui, Haorui Zhang, Jianbing Wang, Xiaonan Ma, Wei-Ying Zhou, Hao Tsinghua University China Department of Computer Science and Technology Tsinghua University China School of Artificial Intelligence National Key Laboratory for Novel Software Technology Nanjing University China Department of Chemical Engineering Tsinghua University China

Deep learning methods for material property prediction have been widely explored to advance materials discovery. However, the prevailing pre-train then fine-tune paradigm often fails to address the inherent diversity and disparity of material tasks. To overcome these challenges, we introduce MoMa, a Modular framework for Materials that first trains specialized modules across a wide range of tasks and then adaptively composes synergistic modules tailored to each downstream scenario. Evaluation across 17 datasets demonstrates the superiority of MoMa, with a substantial 14% average improvement over the strongest baseline. Few-shot and continual learning experiments further highlight MoMa’s potential for real-world applications. Pioneering a new paradigm of modular material learning, MoMa will be open-sourced to foster broader community collaboration. © 2025, CC BY-NC-SA.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Design of an E-Administration Platform and Its Cryptography-Based Security Model

引用

Journal of computer and Communications 2023年第4期11卷 166-189页

作者： Ohwobeno Omohwo Iwasokun Gabriel Babatunde Boyinbode Olutayo Kehinde Gabriel Junior Arome Department of Computer Science Delta State University Asaba Nigeria Department of Software Engineering Federal University of Technology Akure Nigeria Department of Information Technology Federal University of Technology Akure Nigeria Department of Cybersecurity Federal University of Technology Akure Nigeria

E-administration is performing administrative works via computer and its associated technologies such as the Internet. It is administrative efforts that center on the exchange of information and providing services to people and the business sector at high speed and low cost through computers and networks with the assurance of maintaining information security. It is based on the positive investment in information technology and communication in administrative practices. This paper presents the design of the e-administration platform that adopts the concept of cryptography for identity management. The architectural framework of the platform comprises subcomponents for service and forms identification, business process redesign, service architecture, amalgamation, and deployment. The cryptography model for securing the platform was designed based on the combination of authentication criteria presented in the Rijndael-Advanced Encryption Standard (AES), Lattice-based cryptography (LBC), and Secure Hash Algorithm (SHA512). It is required that a record be encrypted prior to its commitment to the database via a double encryption method. The AES algorithm-based encryption’s output will form the input to the LBC algorithm to obtain the final output.

关键词： E-Administration Cryptography Management System Encryption and Decryption

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：