检索结果-内蒙古大学图书馆

4th International Conference on computer, Communication, Control and Information technology, C3IT 2024

作者： Paul, Ankit Guchait, Chiranjit Bhukta, Priyanath Computer Science Engineering Academy of Technology Adisaptagram India Mechanical Engineering Academy of Technology Adisaptagram India

ISBN: (纸本)9798350389128

The world is changing day by day and the expectations of every individual are also becoming high. Out of all the expectations, one of them is to buy a car. But all are not able to always buy a new car, so they will prefer a used one. In this study, we have conducted an analysis to help individuals make informed decisions about used car prices. By using supervised learning algorithms like multiple linear regressions and random forest regression along with Python, we have developed a model which can predict the price of resale vehicles. The dataset used here for prediction has been taken from *** and the final accuracy (R2) of multiple linear regression is 0.93464 and for random forest regression is 0. 93907. © 2024 IEEE.

关键词： Multiple linear regression

来源：评论

学校读者我要写书评

暂无评论

Assessing the Effectiveness of Anomaly Detection in IoT Data Streams with Machine Learning 4

Assessing the Effectiveness of Anomaly Detection in IoT Data...

引用

4th International Conference on computer, Communication, Control and Information technology, C3IT 2024

作者： Panja, Subir Das, Suman Pal, Arindrajit Computer Science and Engineering Academy of Technology Adisaptagram Hooghly India Adisaptagram Hooghly India

ISBN: (纸本)9798350389128

The proliferation of cyber-attacks and network infiltration has emerged as significant apprehensions in the contemporary utilization of the Internet of Things (IoT). Researchers have introduced several machine learning algorithms, which exhibit deficiencies in terms of binary classification accuracy or multi-class classification performance. This study presents an anomaly-based approach that encompasses major eight distinct machine learning algorithms, (i) Decision Tree (DT), (ii) SVMPolynomial Kernal (SVM-P) (iii) SVM- RBF Kernel(SVM-R) (iv) SVM-Linear Kernal (SVM-L) (v) K-Nearest Neighbours (KNN) (vi) Gaussian Naive Bayes (GNB) (vii) Bernoulli Naive Bayes (BNB) and (viii) AdaBoost with Decision Tree (Ada-DT). The experiment utilized the dataset 'UNSW 2018 IoT Botnet Final 10 best Testing' for our research. Performance measures, including as accuracy, precision, recall, and F1-Score are employed to assess and evaluate the performance of the each machine learning algorithm. The DT Classifier demonstrated exceptional accuracy of 99.99%, surpassing expectations in terms of precision, recall, and f1-score for both classes. The significant macro-average Receiver Operating Characteristic Area Under the Curve (ROCAUC) score of 0.91 exhibited by the model reveals its robust overall performance. In contrast, the GNB and BNB models had limits, as evidenced by their lower ROC-AUC scores. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A Deep Neural Network Based Holistic Approach for Optical Character Recognition of Handwritten Documents

引用

SN computer science 2024年第4期5卷 347页

作者： Mukherjee, Jayati Department of Computer Science and Engineering Academy of Technology West Bengal Adisaptagram 712121 India

Optical Character Recognition of handwritten document has been a research topic for last few decades now. Different type of classification schemes starting from template matching, structural analysis to deep neural network have been proposed by researchers. In this paper, a novel holistic approach is proposed for recognition of handwritten words. The approach is a hybrid model combining CNN and BLSTM layers which are responsible for extraction of spatial and temporal features respectively from the word images. Both the features are combined by compact bi-liner pooling. The CBP layer highlights the fine grained details which in turn help to achieve high recognition accuracy. The extracted feature is recognized by a connectionist temporal classification layer. The weights are learnt based on the database using the back propagation algorithm. The hybrid model is trained using three public databases CMATERdb2.1.2, IIIT-HW-Dev and IIIT-HW-Telugu containing Bengali, Devanagari and Telegu handwritten words respectively. The proposed model has achieved 96.42%, 94.79%, 95.07% accuracy on the Bengali, Devanagari and Telegu databases respectively. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2024.

关键词： computer vision Document analysis Handwriting recognition Image analysis Optical character recognition Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A Message Digest Based Secured APUF Model to Prevent Machine Learning Attacks 4

A Message Digest Based Secured APUF Model to Prevent Machine...

引用

4th International Conference on computer, Communication, Control and Information technology, C3IT 2024

作者： Das, Prasenjit Giri, Chandan Computer Science and Engineering Academy of Technology Adisaptagram Hooghly India Indian Institute of Engineering Science and Technology Department of Information Technology Shibpur Howrah India

ISBN: (纸本)9798350389128

In the era of the Internet of Things (IoT), cloud computing huge amounts of data are generated by machines, humans and it is communicated over the internet. We need a stringent security to protect information as well as the devices also from the intruder. The electronic devices such as RFID, smart card and different sensors are used in different applications like smart automation and health monitoring but they are small and resource limited. The devices are placed in public places and exposed to the adversary for physical and cloning attacks. Hardware-based security using Physical unclonable function (PUF) overcomes such a problem but it is vulnerable to machine learning attacks with high precision. A variety of PUF designs have been proposed by the different researchers to provide energy-efficient, cost-effective and machine learning attack re-sistant such as Arbiter PUF(APUF), double APUF, XOR-PUF and multi-PUF(M-PUF) but either they have low reliability or they are not fully machine learning attack resistant. In this paper, we propose a message digest based APUF (MD-PUF) model which is energy-efficient, cost-effective and better machine learning attack resistant compare to other APUF models. We have added a message digest module which changes the input challenges to an arbitrary random challenges its make the intruder confuse to predict the response for unknown challenges and then it is fed into the APUF. We design the message digest module using columnar transposition which requires a very less amount hardware cost of n-bit registers for n-stages PUF. We mathematically prove that the prediction probability of MD-PUF is less than the classical APUF. We evaluate and compare the quality metrics of MD-PUF and APUF. The prediction accuracy of the proposed model is less compare to APUF against the machine learning algorithm LR, SVM and using evolutionary strategy CMA-ES. © 2024 IEEE.

关键词： Smart cards

来源：评论

学校读者我要写书评

暂无评论

Adaptive Sensor Fault Detecting Cyber-Physical Security System for Automated Carriers 4

Adaptive Sensor Fault Detecting Cyber-Physical Security Syst...

引用

4th International Conference on computer, Communication, Control and Information technology, C3IT 2024

作者： Banerjee, Projat Das, Subhashis Blockchain Researcher and Developer Ibm India Private Limited India Academy of Technology Computer Science and Engineering Adisaptagram India

ISBN: (纸本)9798350389128

Security is a vital facet for any automatic carrier, supported by the detected situation, the carrier should respond consequently to make sure that the environment is secure. Hence, the carrier should be expedited with a cyber-physical atmosphere. We tend to showcase a cyber-physical security mechanism for a carrier in low light environments. Detection of vulnerability via optical device, supersonic (US), infrared (IR), motion sensors and dynamic higher cognitive process with applicable response via the actuators of the carrier is the stress of the present proposal. Focus is given to running on practical hardware and code faults of the sensors and actuators which can dynamically occur with time, with appropriate bypass and remedial actions to be taken at runtime to ensure security. Finally, with the aid of cloud infrastructure, we broadcast the matter situation to different carriers and forestall congestion blockchain infrastructure to make certain that the information once kept in the ledger cannot be tampered with. © 2024 IEEE.

关键词： Motion sensors

来源：评论

学校读者我要写书评

暂无评论

An efficient schedulability analysis based on worst-case interference time for real-time systems

引用

science China(Information sciences) 2024年第9期67卷 88-104页

作者： Hongbiao LIU Mengfei YANG Lei QIAO Xi CHEN Jian GONG School of Computer Science and Technology Xidian University China Academy of Space Technology Beijing Institute of Control Engineering

Real-time systems are widely implemented in the Internet of Things(IoT) and safety-critical systems, both of which have generated enormous social value. Aiming at the classic schedulability analysis problem in real-time systems, we proposed an exact Boolean analysis based on interference(EBAI) for schedulability analysis in real-time systems. EBAI is based on worst-case interference time(WCIT), which considers both the release jitter and blocking time of the task. We improved the efficiency of the three existing tests and provided a comprehensive summary of related research results in the field. Abundant experiments were conducted to compare EBAI with other related results. Our evaluation showed that in certain cases, the runtime gain achieved using our analysis method may exceed 73% compared to the stateof-the-art schedulability test. Furthermore, the benefits obtained from our tests grew with the number of tasks, reaching a level suitable for practical application. EBAI is oriented to the five-tuple real-time task model with stronger expression ability and possesses a low runtime overhead. These characteristics make it applicable in various real-time systems such as spacecraft, autonomous vehicles, industrial robots, and traffic command systems.

关键词： five-tuple real-time task model real-time system spacecraft Internet of Things exact schedulability analysis worst-case interference time

来源：评论

学校读者我要写书评

暂无评论

DALR: A Dynamically Adjustable Linear Regression Model for Handling Stream Data 4

DALR: A Dynamically Adjustable Linear Regression Model for H...

引用

4th International Conference on computer, Communication, Control and Information technology, C3IT 2024

作者： Mondal, Rishita Mandal, Sourab Dutta, Paramartha Pal, Arindrajit Visva-Bharati Department of Computer & System Sciences WB Santiniketan India Academy of Technology Department of Computer Science and Engineering Adisaptagram WB India

ISBN: (纸本)9798350389128

In response to the escalating demand for machine learning techniques capable of handling real-time data streams, particularly in applications like stock markets, this research dives deep into the domain of stream regression. The objective is to adeptly navigate challenges posed by evolving data over time, differentiating it from conventional static regression. Existing models, such as Fast and Incremental Model Trees with Drift Detection (FIMT-DD), k-Nearest Neighbours (KNN), and Adaptive Linear Regression (ALR) and some other studies, though competent, exhibit certain limitations like learning based on certain portions of data, using a significantly large memory and not capable of handling each data in every timestamp it arrives. We propose the Dynamically Adjustable Linear Regression Model (DALR) to address these shortcomings. DALR introduces an adaptive regression model that dynamically evolves based on historical knowledge and newly acquired data, providing an innovative solution to the intricacies of dynamic data streams. This endeavor has also highlighted that the DALR algorithm consistently demonstrates strong performance across various datasets according to the RMSE metric, surpassing other state-of -the-art algorithms in most instances. © 2024 IEEE.

关键词： Financial markets

来源：评论

学校读者我要写书评

暂无评论

AsyCo: an asymmetric dual-task co-training model for partial-label learning

引用

science China(Information sciences) 2025年第5期68卷 332-347页

作者： Beibei LI Yiyuan ZHENG Beihong JIN Tao XIANG Haobo WANG Lei FENG College of Computer Science Chongqing University State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences University of Chinese Academy of Sciences School of Software Technology Zhejiang University School of Computer Science and Engineering Nanyang Technological University

Partial-label learning(PLL) is a typical problem of weakly supervised learning, where each training instance is annotated with a set of candidate labels. Self-training PLL models achieve state-of-the-art performance but suffer from error accumulation problems caused by mistakenly disambiguated instances. Although co-training can alleviate this issue by training two networks simultaneously and allowing them to interact with each other, most existing co-training methods train two structurally identical networks with the same task, i.e., are symmetric, rendering it insufficient for them to correct each other due to their similar limitations. Therefore, in this paper, we propose an asymmetric dual-task co-training PLL model called AsyCo,which forces its two networks, i.e., a disambiguation network and an auxiliary network, to learn from different views explicitly by optimizing distinct tasks. Specifically, the disambiguation network is trained with a self-training PLL task to learn label confidence, while the auxiliary network is trained in a supervised learning paradigm to learn from the noisy pairwise similarity labels that are constructed according to the learned label confidence. Finally, the error accumulation problem is mitigated via information distillation and confidence refinement. Extensive experiments on both uniform and instance-dependent partially labeled datasets demonstrate the effectiveness of AsyCo.

关键词： machine learning weakly supervised learning partial-label learning co-training models candidate label sets

来源：评论

学校读者我要写书评

暂无评论

An Encoding-Decoding Framework Based on CNN for circ RNA-RBP Binding Sites Prediction

引用

Chinese Journal of Electronics 2024年第1期33卷 256-263页

作者： Yajing GUO Xiujuan LEI Yi PAN School of Computer Science Shaanxi Normal University Faculty of Computer Science and Control Engineering Shenzhen Institute of Advanced TechnologyChinese Academy of Sciences Department of Computer Science Georgia State University

Predicting RNA binding protein(RBP) binding sites on circular RNAs(circ RNAs) is a fundamental step to understand their interaction mechanism. Numerous computational methods are developed to solve this problem, but they cannot fully learn the features. Therefore, we propose circ-CNNED, a convolutional neural network(CNN)-based encoding and decoding framework. We first adopt two encoding methods to obtain two original matrices. We preprocess them using CNN before fusion. To capture the feature dependencies, we utilize temporal convolutional network(TCN) and CNN to construct encoding and decoding blocks, respectively. Then we introduce global expectation pooling to learn latent information and enhance the robustness of circ-CNNED. We perform circ-CNNED across 37 datasets to evaluate its effect. The comparison and ablation experiments demonstrate that our method is superior. In addition, motif enrichment analysis on four datasets helps us to explore the reason for performance improvement of circ-CNNED.

关键词： Circular RNAs (circRNAs) RNA binding proteins Convolutional neural network Temporal convolutional network Encoder-decoder network

来源：评论

学校读者我要写书评

暂无评论

Price Prediction of Resale Vehicle Through Supervised Learning Approaches

Price Prediction of Resale Vehicle Through Supervised Learni...

引用

International Conference on computer, Communication, Control and Information technology (C3IT)

作者： Ankit Paul Chiranjit Guchait Priyanath Bhukta Computer Science Engineering Academy of Technology Adisaptagram India Mechanical Engineering Academy of Technology Adisaptagram India

ISBN: (数字)9798350389128

ISBN: (纸本)9798350389135

关键词： Accuracy Input variables Supervised learning Linear regression Organizations Predictive models Prediction algorithms Automobiles Information technology Random forests

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：