检索结果-内蒙古大学图书馆

International Conference on Electronics, computers and Artificial Intelligence (ECAI)

作者： Sama Hussein Al-Gburi Kanar Alaa Al-Sammak Khattab M. Ali Alheeti George Suciu Abedulqader Gailan Abdulqader Faculty of Electronics Telecommunications and Information Technology National University of Science and Technology Politehnica Bucharest (UNSTPB) Bucharest Romania Faculty of Department of Computer Networking System College of Computer Sciences and Information Technology University of Anbar Ramadi Iraq Faculty of Electronics Telecommunications and Information Technology National University of Science and Technology Politehnica Bucharest (UNSTPB) and BEIA Consult International Bucharest Romania Karkh Second Directorate of Education Ministry of Education Baghdad Iraq

ISBN: (数字)9798350371154

ISBN: (纸本)9798350371161

Ensuring road safety is becoming more and more significant for researchers and for all the society. One of the main issues in this area considers driver drowsiness. Therefore, the focus of this paper is the comprehensive analysis and comparison of four distinct machine learning models: Logistic Regression, Random Forest, Support Vector Machine (SVM), and Gradient Boosting. The ultimate goal is to gain insights into the intricate factors that shape driver behavior. When assessing the effectiveness of each model, four key metrics are taken into account: precision, recall, F1 score, and accuracy. In this study, we used a “TRYOUT” dataset. The study yielded several significant findings regarding the performance of the machine learning models employed. Remarkably, the accuracy scores for all models were notably high, falling within a range of 0.8651 to 0.9999. Among all the models, the Random Forest model stood out as the most effective, displaying an impressive accuracy score of 0.9999 on the merged data. The SVM model, while not as proficient as the Random Forest, still managed a respectable performance, particularly on the MPM39 dataset where it achieved an accuracy of $\mathbf{7 5. 0 6 \%}$. The Logistic Regression model demonstrated its strength on the CVD08 dataset, although its performance was comparatively weaker on the other datasets. Lastly, the Gradient Boosting model demonstrated consistent competency across all datasets, underscoring its reliability in a range of circumstances.

关键词： Support vector machines Logistic regression Accuracy Shape Computational modeling Brain modeling Boosting

来源：评论

学校读者我要写书评

暂无评论

Tomato Leaf Disease Detection and Classification using MobileNetV2 and Extreme Learning Method: A Hybrid Approach

Tomato Leaf Disease Detection and Classification using Mobil...

引用

International Conference on Soft Computing and Machine Intelligence (ISCMI)

作者： Meenakshi Srivastava Varsha Sisaudia Jasraj Meena Department of Information Technology Delhi Technological University Delhi India School of Computer and System Sciences Jawaharlal Nehru University Delhi India

Tomatoes are one of the most essential vegetables in the world. It is regarded as a pillar of many countries' economies. However, tomato leaf is susceptible to a variety of diseases that can reduce or eliminate production, and for this reason, early and precise detection of tomato leaf disease is very important. As a result, various deep learning methods and extreme learning machines for tomato leaf disease diagnosis have been constructed. Extreme Learning Machine (ELM), with its short learning time and excellent generalization capabilities, has been used in feature-based sickness diagnosis approaches. This paper initially proposes a hybrid method for classifying tomato leaf diseases using transfer learning and ELM. TLMV2-ELM model includes MobileNetV2 for feature extraction that generates efficient feature vectors, which are then categorized using ELM. The TLMV2-ELM method is validated using a tomato leaf dataset, and the results of the experiment show that it outperforms current approaches with 0.99% accuracy and 0.06 loss in terms of disease detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Secure Multiparty Quantum Homomorphic Encryption Scheme

引用

computers, Materials & Continua 2022年第11期73卷 2835-2848页

作者： Jing-Wen Zhang Xiu-Bo Chen Gang Xu Heng-Ji Li Ya-Lan Wang Li-Hua Miao Yi-Xian Yang Information Security Center State Key Laboratory of Networking and Switching TechnologyBeijing University of Posts and TelecommunicationsBeijing100876China School of Information Science and Technology North China University of TechnologyBeijing100144China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Sichuan610025China Quantum Technology Lab&Applied Mechanics Group University of MilanMilan20133Italy Department of Computer Science Faculty of Engineering and Physical SciencesUniversity of SurreyGuildfordSurreyGU27XHUnited Kingdom Huawei Technologies Co.Ltd Shenzhen518129China

The significant advantage of the quantum homomorphic encryption scheme is to ensure the perfect security of quantum private *** this paper,a novel secure multiparty quantum homomorphic encryption scheme is proposed,which can complete arbitrary quantum computation on the private data of multiple clients without decryption by an almost dishonest ***,each client obtains a secure encryption key through the measurement device independent quantum key distribution protocol and encrypts the private data by using the encryption operator and ***,with the help of the almost dishonest server,the non-maximally entangled states are preshared between the client and the server to correct errors in the homomorphic evaluation of T gates,so as to realize universal quantum circuit evaluation on encrypted ***,from the perspective of the application scenario of secure multi-party computation,this work is based on the probabilistic quantum homomorphic encryption scheme,allowing multiple parties to delegate the server to perform the secure homomorphic *** operation and the permission to access the data performed by the client and the server are clearly pointed ***,a concrete security analysis shows that the proposed multiparty quantum homomorphic encryption scheme can securely resist outside and inside attacks.

关键词： Quantum homomorphic encryption secure multiparty computation almost dishonest server security

来源：评论

学校读者我要写书评

暂无评论

ICON: An IR Drop Compensation Method at OU Granularity with Low Overhead for eNVM-based Accelerators

ICON: An IR Drop Compensation Method at OU Granularity with ...

引用

IEEE International Conference on computer Design: VLSI in computers and Processors, (ICCD)

作者： Jinpeng Liu Wei Tong Bing Wu Huan Cheng Chengning Wang Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System (School of Computer Science and Technology) Huazhong University of Science and Technology Ministry of Education of China

Processing at operating unit (OU) granularity can alleviate the program variation effect and ADC conversion overhead in emerging non-volatile memory (eNVM) based accelerators. However, our experiments show that the IR drop effect can severely decrease computing accuracy when processing at OU granularity. Moreover, the IR drop effect on the entire array differs from the IR drop effect on OUs, meaning compensating at OU granularity is necessary. We also notice that the IR drop effect differs among OUs, and previous IR drop mitigation methods introduce more latency, area, and power overhead to adapt to these differences. Compensation modules from their methods calibrated for one OU do not apply to other OUs and need to be configured for each OU compensation using configuration modules. This paper proposes ICON, an IR drop compensation method at OU granularity with low overhead for eNVM-based accelerators. In order to decrease compensation latency, area, and power overhead, we perform several optimizations. First, the designed compensation circuit is simplified and does not compensate for the IR drop effect caused by parasitic resistances inside an OU. This simplification is based on our observation that the parasitic wire resistances inside an OU can be ignored using the OU size mentioned in previous works. Second, the compensation circuit is designed without the help of configuration circuits. We take the IR drop differences among OUs as input parameters of the compensation circuit so that it can apply to all OUs. Furthermore, the compensation circuit is pipelined into six stages to increase throughput. Experiments show that our compensation method can overcome the IR drop problem when processing in the eNVM-based crossbar array at OU granularity, with 1.3× ~ 13× lower latency, 1.5× ~ 33.1× lower area, and 1.4× ~ 8.4× lower power overhead compared with state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MAML MOT: Multiple Object Tracking based on Meta-Learning

arXiv

引用

arXiv 2024年

作者： Chen, Jiayi Deng, Chunhua School of Computer Science and Technology Wuhan University of Science and Technology Wuhan430065 China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System Wuhan430065 China

With the advancement of video analysis technology, the multi-object tracking (MOT) problem in complex scenes involving pedestrians is gaining increasing importance. This challenge primarily involves two key tasks: pedestrian detection and re-identification. While significant progress has been achieved in pedestrian detection tasks in recent years, enhancing the effectiveness of re-identification tasks remains a persistent challenge. This difficulty arises from the large total number of pedestrian samples in multi-object tracking datasets and the scarcity of individual instance samples. Motivated by recent rapid advancements in meta-learning techniques, we introduce MAML MOT, a meta-learning-based training approach for multi-object tracking. This approach leverages the rapid learning capability of meta-learning to tackle the issue of sample scarcity in pedestrian re-identification tasks, aiming to improve the model’s generalization performance and robustness. Experimental results demonstrate that the proposed method achieves high accuracy on mainstream datasets in the MOT Challenge. This offers new perspectives and solutions for research in the field of pedestrian multi-object tracking. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Moodle-based Learning Management system Design as a Learning Media at SMKN 40 Jakarta

Moodle-based Learning Management System Design as a Learning...

引用

Conference on New Media Studies (CoNMedia)

作者： Oktaviano Nanda Prima Setya Widodo Murien Nugraheni Informatics and Computer Engineering Education State Jakarta University Jakarta Indonesia Information System and Technology State Jakarta University Jakarta Indonesia

Indonesia is currently in the final stages of the COVID-19 pandemic, which has changed the world of the online learning. Online learning has many benefits, one of which students can learn anywhere and anytime. SMK Negeri 40 Jakarta is one of the vocational high schools located in DKI Jakarta. Based on observation at SMKN 40 Jakarta, teachers use a learning management system for daily learning. Therefore, a Moodle-based learning management system is needed. Learning Management system is a web application to manage various learning activities automatically, which is built using Moodle platform with RAD (Rapid Application Development) methodology. The result is a Moodle-based learning management system application that can be useful in supporting the teaching and learning process at school. Based on the results of black box testing and user acceptance testing, the learning management system created is very good, therefore it can be concluded this application can be accepted and implemented at SMK Negeri 40 Jakarta.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Anti-3CLpro Molecular Design Based on the Model Constrained by Specific DTIs

Anti-3CLpro Molecular Design Based on the Model Constrained ...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Xiaoli Lin Xuan Liu Xiaolong Zhang Hubei Key Laboratory of Intelligent Information Processing and Real-Time Industrial System School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China

computer-aided drug design and artificial intelligence-driven drug design have accelerated drug discovery. However, how to design effective drugs that have strong interaction ability with target proteins to further improve the efficacy of drugs in treating diseases remains a key issue. This paper proposes a new target-specific drug generative model 3CLpro2mol to generate new drug molecules, which uses features of drug-target interactions (DTIs) to constrain the correlation between the drug and the target protein. To obtain as many drug-target interaction features as possible from a small amount of data, a small molecule extraction strategy is proposed to ensure the diversity of small molecules in the training samples. To improve the efficiency and accuracy of the generative model, a TOP K sampling strategy is used to generate tokens, which can improve the rationality and diversity of the generated molecules. The experimental results show that the proposed model has the potential to generate small molecules that interact better with the target protein.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of Public Opinion on Twitter about the Implementation of the Merdeka Curriculum Using the Support Vector Machine Algorithm

Sentiment Analysis of Public Opinion on Twitter about the Im...

引用

Modeling & E-information Research, Artificial Learning and Digital Applications (ICMERALDA), International Conference on

作者： Intan Ramadhanti Widodo Murien Nugraheni Informatics and Computer Engineering Education Universitas Negeri Jakarta Jakarta Indonesia Information System and Technology Universitas Negeri Jakarta Jakarta Indonesia

In 2022 the Head of Standards, Curriculum, Education Assessment (BSKAP) No. 0441HIKR/2022 issued a Decree (SK) regarding Education Units for the Implementation of the Merdeka Curriculum in 140 thousand educational units in Indonesia. The implementation of this new curriculum raises various public opinions on social media Twitter. Therefore, research on the analysis of public sentiment on the implementation of the Merdeka Curriculum was carried out. The tweets taken are tweets with positive and negative sentiments. This study aims to see whether the SVM algorithm is good at carrying out text classification for sentiment analysis of the Merdeka Curriculum by looking at the accuracy value and describing how the public's sentiment on Twitter is about the Merdeka Curriculum. The data used is a dataset of 1,186 tweets, that is 363 positive tweets and 823 negative tweets. The results showed that the accuracy of the Support Vector Machine algorithm with linear, polynomial, and sigmoid kernels was 91.82% and the RBF kernel was 89.88%. As well as seen from the results of the sentiment analysis of implementing the Merdeka Curriculum there were more negative responses, one of which was regarding too many assignments and projects that made students feel tired and stressed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Generating Molecules Conditional on 3D Protein Pockets with HGAF

Generating Molecules Conditional on 3D Protein Pockets with ...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Qinglian Zhu Xiaoli Lin Xiaolong Zhang Hubei Key Laboratory of Intelligent Information Processing and Real-Time Industrial System School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China

Most current representations of protein pockets are the atom-pair graph, which ignore the global structural information of amino acids. Therefore, we propose a new molecular generation model, which uses the hypergraph to represent protein pocket structure, and combines the structural features obtained by atom-pair graph representation. These two levels of graphs are more capable of representing the complex structural information of protein pockets. Then, the graphs of the two levels of the protein pockets are input into the improved network model, which is named Hypergraph Graph Attention Fusion (HGAF), to obtain the embedding representation of the protein pockets, which is used as a condition to constrain the molecule generation. The molecules sampled by HGAF are subjected to quality assessment and docking targeting validation. Experimental results show that the molecules generated by proposed method can achieve better results in both of these assessment approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Att-TCN: An Advertising Attribution Method Based on Temporal Convolutional Network with Attention Mechanism 8

Att-TCN: An Advertising Attribution Method Based on Temporal...

引用

8th IEEE International Conference on computer and Communications, ICCC 2022

作者： Xie, Bowen Sun, Yi Lin, Zhaowen Ma, Baoquan Beijing University of Posts and Telecommunications Beijing China National Engineering Laboratory for Mobile Network Technologies Beijing China National Engineering Laboratory for Industry Control System Information Security Technology Beijing China National Computer System Engineering Research Institute of China Beijing China

ISBN: (纸本)9781665450515

Advertising attribution is an effective method to measure the effect of various advertisements in the era of Internet advertising. It enables scientific tracking back and refined operation of advertising by quantitatively evaluating the contribution of different advertising channels to reach the target. It is challenging to predict conversion results based on users' journey data accurately, reflect the impact of ads on user conversions, and appropriately assign attribution values to advertising channels. To achieve the above objectives, we propose an advertising attribution method based on a temporal convolutional network with an attention mechanism (Att-TCN). By mining the hidden information in time and attribution channels using the attention mechanism, our proposed method can improve the accuracy of conversion prediction and thus more rationally assign attribution values across channels. Experimental validation on a real dataset obtained from an operational commercial advertising monitoring company shows that our proposed attribution method has better accuracy than other state-of-the-art attribution methods and gives an open-ended approach to attribution value assignment. © 2022 IEEE.

关键词： Marketing

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：