检索结果-内蒙古大学图书馆

2nd IEEE International Conference on Big Data, Artificial Intelligence and Internet of Things engineering, ICBAIE 2021

作者： Ai, Xingfang Cao, Min Li, Xuechen Information Engineering College Jiangmen Polytechnic Jiangmen China Guangzhou Panyu Sanatorium Radiology Department Guangzhou China Shenzhen University College of Computer Science and Software Engineering Shenzhen China

ISBN: (纸本)9780738131221

Lung diseases remain to be fatal even in the modern and technologically advanced world. When using artificial intelligent (AI) methods for lung disease diagnosis, it is better to give the location of the lesion areas, which makes the AI diagnosis more convincing. However, compared with general objects detection or segmentation, the annotation of medical images requires professional knowledges and more time, which limited the application of deep learning technology in medical image analysis. In this work, we proposed a pseudo lesion generation method, which can use annotated lesion CXR and normal CXR to create new annotated lesion CXRs. Two publicly available datasets, i.e. RSNA and ChestX-Det10 were employed for performance evaluation. The experimental results showed that the proposed pseudo lesion generation method can improved about 4% of the network performances. © 2021 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Method of Multidimensional software Aging Prediction Based on Ensemble Learning: A Case of Android Os

SSRN

引用

SSRN 2023年

作者： Nie, Yuge Chen, Yulei Jiang, Yujia Wu, Huayao Yin, Beibei Cai, Kai-Yuan Beihang University School of Automation Science and Electrical Engineering Beijing100083 China Nanjing University State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing210023 China

Context: software aging refers to the phenomenon of performance degradation, increasing failure rate, or system crash due to resource consumption and error accumulation in software systems running for a long time. Precisely predicting software aging is crucial for enabling proactive measures before the situation substantially deteriorates. Previous machine learning (ML) methods for predicting aging predominantly rely on a single ML modeland a single labeling metric to attain their objectives. Furthermore, a common limitation shared by these methods is that training and prediction data stem from identical operational profiles. This could pose challenges for these models in delivering the desired performance when confronted with diverse user scenarios. Objective: In this paper, we aim to find a method that can both consistently and precisely predict aging trends across a wide range of application scenarios. Method: We propose a method of multidimensional software aging prediction based on ensemble learning called MSAP. Unlike the previous full-process single-threaded approaches, in the framework of MSAP, five dimensions including datasets, labeling metrics, labeling thresholds, algorithms, and model decisions are extracted and diversified to protest against diverse user scenarios and aging situations. Results: When subjected to identical workloads, MSAP demonstrates comparable performance to the majority of unidimensional models, albeit without significant prominence. Under different workloads, MSAP consistently outperforms unidimensional models whose performance drops dramatically in terms of precision, maintaining a notable lead while exhibiting minimal fluctuations. Conclusion: MSAP exhibits exceptional stability while concurrently upholding outstanding prediction precision across a spectrum of user scenarios. Therefore, it has better generalization characteristics and application prospects. © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Hadiyyissa Automatic Speech Recognition Using Deep Learning Approach

Hadiyyissa Automatic Speech Recognition Using Deep Learning ...

引用

Information and Communication Technology for Development for Africa (ICT4DA), International Conference on

作者： Selamu Shamore Amin Tuni Gure Mohammed Abebe Yimer Department of Computer Science Wachemo University Hossana Ethiopia Department of Information System Arsi University Arsi Ethiopia Faculty of Computing and Software Engineering Arba Minch University Arba Minch Ethiopia

Speech Recognition focuses on developing advanced technologies that can recognize and translate spoken language into text. Automatic Speech Recognition (ASR) is an Artificial Intelligence (AI) technology that captures human voice from a mi-crophone and analyzes it based on spoken words to comprehend natural language. In Ethiopia, ASR models have been developed for specific local languages such as Amharic, Tigrigna, Wolaytta, and Afaan Oromo, but there has been a lack of research on ASR models for the Hadiyyisa language, which is also spoken in Ethiopia. The research study designed and developed an ASR model for the Hadiyyisa language. The researchers collected data from native speakers of the Hadiyyisa language and used Python programming to design and develop the deep learning model for the Hadiyissa ASR model. Different methods and techniques were used in the study to achieve the research objectives and complete the entire research process. The proposed model utilized deep learning algorithms including RNN, LSTM, BiLSTM, and CNN, along with suitable feature extraction techniques such as Mel Frequency Cepstral Coefficients (MFCC). The accuracy of the proposed ASR model was evaluated through experimentation, which demonstrated that the BiLSTM model outperformed the other deep learning models with an overall accuracy of 90.95 % Based on the experimental evidence, the proposed model was found to be better suited for ASR for the Hadiyyisa language.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Next-Generation Human Activity Recognition Using Locality Constrained Linear Coding Combined With Machine Learning (NG-HAR-LCML)

引用

Healthcare Technology Letters 2025年第1期12卷

作者： Shabbir, Maryam Ahmad, Fahad Alanazi, Saad Awadh Khan, Muhammad Hassan Li, Jianqiang Mahmood, Tariq Naseem, Shahid Anwar, Muhammad Department of Computer Sciences Bahria University Punjab Lahore Pakistan Department of Computer Science Faculty of Computing & Information Technology University of the Punjab Lahore Pakistan School of Computing Faculty of Technology University of Portsmouth Portsmouth United Kingdom University of Portsmouth Portsmouth United Kingdom Department of Computer Science College of Computer and Information Sciences Jouf University Aljouf Sakaka Saudi Arabia The School of Software Engineering Beijing University of Technology Beijing China Lab CCIS Prince Sultan University Riyadh Saudi Arabia Department of Information Sciences University of Education Vehari Pakistan Faculty of Information Sciences Division Science &Technology University of Education Lahore Pakistan

Accurate Human Activity Recognition (HAR) is a critical challenge with wide-ranging applications in healthcare, assistive technologies, and human-computer interaction. Traditional feature extraction methods often struggle to capture the complex spatial and temporal dynamics of human movements, leading to suboptimal classification performance. To address this limitation, this study introduces a novel encoding approach using Locality-Constrained Linear Coding (LLC) to enhance the discriminative power of hand-crafted features extracted from low-cost wearable sensors—an accelerometer and a gyroscope. The proposed LLC-based encoding scheme enables robust feature representation, improving the accuracy of HAR models. The encoded features are classified using a diverse set of Machine Learning (ML) and Deep Learning (DL) algorithms, including Support Vector Machine (SVM), Logistic Regression (LR), Naive Bayes (NB), K-Nearest Neighbours (KNN), AdaBoost, Gradient Boosting Machine (GBM), and Deep Belief Network (DBN). Extensive quantitative evaluations demonstrate that LLC significantly outperforms conventional feature encoding techniques, leading to improved classification accuracy. Among the tested models, DBN achieves a state-of-the-art accuracy of 99%, highlighting its superiority for HAR tasks. The contributions of this research are threefold: (1) it establishes the necessity of an advanced encoding scheme (LLC) for feature enhancement in HAR, (2) it provides a rigorous comparative analysis of multiple ML and DL classifiers, and (3) it introduces a scalable and cost-effective HAR framework suitable for real-world applications. Performance is comprehensively assessed using robust evaluation metrics such as Area Under the Curve (AUC), Classification Accuracy (CA), F1 Score, Precision, Recall, and Matthews Correlation Coefficient (MCC). The findings of this study offer new insights into feature encoding for HAR, setting a foundation for future advancements in sensor-based act

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Multi-branch Person Re-identification Net

Multi-branch Person Re-identification Net

引用

Image Processing, computer Vision and Machine Learning (ICICML), International Conference on

作者： Zhihao Chen Yiyuan Ge Ji Zhang Xiang Gao Computer School Beijing Information Science & Technology University Beijing China Department of Software Engineering Jilin University Changchun China School of Instrument Science and Opto-Electronics Engineering Beijing Information Science & Technology University Beijing China School of Mechanical Science and Engineering Xihua University Chengdu China

Person ReID is a complex and important problem within the domain of computer vision. Its objective is to identify and match individuals in video sequences, often captured from different camera viewpoints. By comparing visual characteristics, poses, and clothing of pedestrians, Person ReID enables the tracking and recognition of the same person across various scenarios. This paper introduces a Multi-Branches Person Re-identification Net (MPRN), a novel framework for person re-identification. MPRN leverages OSNet as the backbone and establishes a multi-branch structure on top of it, effectively integrating both local and global features. Experimental results demonstrate that the combination of OSNet and the multi-branch structure yields highly competitive results. Specifically, it achieves a mean average precision (mAP) of 90.5% and a rank-1 accuracy of 96% on the Market-1501 dataset, as well as an mAP of 85.5% and a rank-1 accuracy of 87.7% on the CHUK03-L dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On the Educational and Professional Implications of Integrating Mind Mapping in software Testing

On the Educational and Professional Implications of Integrat...

引用

International Conference on Computational science and Computational Intelligence (CSCI)

作者： Pankaj Kamthan Nazlie Shahmir Department of Computer Science and Software Engineering Concordia University Montreal Canada IS Quality Engineering Canadian Pacific Railway Limited Calgary Canada

The increasing societal dependence on software, and the negative consequences of undesirable behavior of software, calls for ever more attention to software quality. The purpose of software quality control is activities that support the achievement of desirable levels of software quality, and software testing is one such activity. In order to preserve the intent of software testing, it must be deliberated carefully, and given necessary time and due diligence, before being acted upon. In that regard, this paper adopts a human-centered approach to software testing, embraces mind mapping as a lightweight technique for early software testing-related commitments, provides elements of a theoretical basis for mind mapping, and offers a guided tour of software testing-related mind maps using practical examples relevant in academia as well as industry.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A High-Gain DC-DC Boost Converter for Solar Microgrid Systems Using a Switching Inductor and a Capacitor

A High-Gain DC-DC Boost Converter for Solar Microgrid System...

引用

Advances in computer science, Electrical, Electronics, and Communication Technologies (CE2CT), International Conference on

作者： S. Prasanth S. Priyadarsini R. Lakshmi G. Sneha S. S. Ajitha R. Saravanakumar Konnaiah Gari Narendra Department of Computer Science and Engineering Unnamalai Institute of Technology Kovilpatti Tamil Nadu India Department of Computer Science and Engineering PSR Engineering College Sivakasi Tamil Nadu India Department of Elecrical and Electroncis Engineering Siddharth Institute of Engineering and Technology Puttur India Department of Electronics and Communication Engineering St. Joseph's Institute of Technology Chennai Tamil Nadu India Department of Electronics and Communication Engineering Vel Tech Multi Tech Dr. Rangarajan Dr. Sakunthala Engineering College Chennai Tamil Nadu India Iconix Software Solution Tirunelveli Tamil Nadu India Department of Electonics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India

ISBN: (数字)9798331518578

ISBN: (纸本)9798331518585

This paper outlines the design and implementation of a solar microgrid-specific high-gain DC-DC booster converter that makes use of a variable inductor and capacitors. To improve the suitability of photovoltaic (PV) panels for incorporation into microgrids, the proposed converter efficiently increases their low-voltage outputs. Conventional boost converters can't offer that kind of voltage increase because they lose too much performance and put too much strain on their internal components. The converter increases the voltage gain dramatically while maintaining a high degree of efficiency thanks to a switching inductor-capacitor network. The main breakthrough is an inventive multi-stage energy transfer and storage device that cleverly employs a switching inductor and capacitor. This configuration increases the output voltage while decreasing the voltage and current ripples, which in turn reduces the amount of electromagnetic interference (EMI) and increases the life of the components. Thorough assessments of the converter's working via theoretical modeling and simulation studies confirm its performance across several load and input situations common to solar microgrids. The prototype's testing findings show a significant voltage increase and a peak efficiency of over 95% when compared to traditional boost converters. Moreover, the converter's reliable performance over a wide range of voltage sources and workload scenarios proves its suitability for practical solar applications. As a result, the proposed high-gain boost converter will greatly improve the efficiency and reliability of solar microgrids, leading to a rise in the use of renewable energy sources in DGS.

关键词： Photovoltaic systems Renewable energy sources Capacitors Electromagnetic interference Voltage Switches Microgrids DC-DC power converters Inductors Switching circuits

来源：评论

学校读者我要写书评

暂无评论

An n-MOSFET Layout with Multi-Finger Z Gate for Radiation Tolerance 5

An n-MOSFET Layout with Multi-Finger Z Gate for Radiation To...

引用

5th IEEE International Conference on Knowledge Innovation and Invention, ICKII 2022

作者： Shan, Chan Liu, Ying Chen, Huan Huo, Dong-Yang Xu, Tian-Rong Jimei University College of Ocean Information Engineering Xiamen China Xiamen Institute of Software Technology Department of Software Technology Xiamen China Minjiang University School of Journalism and Communication Fuzhou China Universiti Malaya Faculty of Computer Science and Information Technology Department of Information Systems Kuala Lumpur Malaysia Universiti Malaya Planning Faculty of Built Environment Department of Urban and Regional Kuala Lumpur Malaysia

ISBN: (数字)9781665479295

ISBN: (纸本)9781665479295

In this paper, a new n-MOSFET layout with multi-finger Z gate is proposed to reduce the total ionizing dose (TID) effect. In addition to the proposed layout, multi-finger single gate layout is also simulated using Sentaurus TCAD in 3D. Firstly, drain current - gate voltage curves of both layouts are compared in order to verify the radiation hardening ability of the proposed layout. Secondly, we compare TID responses by extracting threshold voltages and leakage currents from both layouts. Thirdly, the finger number is investigated for both layouts because it is an important factor for multi-finger layout. The results have indicated that the finger number significantly affects the multi-finger single gate layout, whereas the proposed multi-finger Z gate layout is relatively little affected by the finger number in radiation environment. © 2022 IEEE.

关键词： Drain current

来源：评论

学校读者我要写书评

暂无评论

Effectively Generating Vulnerable Transaction Sequences in Smart Contracts with Reinforcement Learning-guided Fuzzing 22

Effectively Generating Vulnerable Transaction Sequences in S...

引用

Proceedings of the 37th IEEE/ACM International Conference on Automated software engineering

作者： Jianzhong Su Hong-Ning Dai Lingjun Zhao Zibin Zheng Xiapu Luo School of Software Engineering Sun Yat-sen University China and Ant Group China Department of Computer Science Hong Kong Baptist University China School of Software Engineering Sun Yat-sen University China The Hong Kong Polytechnic University China

ISBN: (纸本)9781450394758

As computer programs run on top of blockchain, smart contracts have proliferated a myriad of decentralized applications while bringing security vulnerabilities, which may cause huge financial losses. Thus, it is crucial and urgent to detect the vulnerabilities of smart contracts. However, existing fuzzers for smart contracts are still inefficient to detect sophisticated vulnerabilities that require specific vulnerable transaction sequences to trigger. To address this challenge, we propose a novel vulnerability-guided fuzzer based on reinforcement learning, namely RLF, for generating vulnerable transaction sequences to detect such sophisticated vulnerabilities in smart contracts. In particular, we firstly model the process of fuzzing smart contracts as a Markov decision process to construct our reinforcement learning framework. We then creatively design an appropriate reward with consideration of both vulnerability and code coverage so that it can effectively guide our fuzzer to generate specific transaction sequences to reveal vulnerabilities, especially for the vulnerabilities related to multiple functions. We conduct extensive experiments to evaluate RLF’s performance. The experimental results demonstrate that our RLF outperforms state-of-the-art vulnerability-detection tools (e.g., detecting 8%-69% more vulnerabilities within 30 minutes).

关键词： Reinforcement learning Fuzzing Smart contract

来源：评论

学校读者我要写书评

暂无评论

HierarchyNet: Learning to Summarize Source Code with Heterogeneous Representations

arXiv

引用

arXiv 2022年

作者： Nguyen, Minh Huynh Bui, Nghi D.Q. Son, Hy Truong Thanh, Long Tran Nguyen, Tien N. FPT Software AI Center Department of Computer Science Fulbright University Viet Nam Department of Computer Science University of Chicago IL United States Department of Computer Science University of Warwick United Kingdom School of Engineering and Computer Science The University of Texas Dallas United States

We propose a novel method for code summarization utilizing Heterogeneous Code Representations (HCRs) and our specially designed HierarchyNet. HCRs effectively capture essential code features at lexical, syntactic, and semantic levels by abstracting coarse-grained code elements and incorporating fine-grained program elements in a hierarchical structure. Our HierarchyNet method processes each layer of the HCR separately through a unique combination of the Heterogeneous Graph Transformer, a Tree-based CNN, and a Transformer Encoder. This approach preserves dependencies between code elements and captures relations through a novel Hierarchical-Aware Cross Attention layer. Our method surpasses current state-of-the-art techniques, such as PA-Former, CAST, and NeuralCodeSum. Copyright © 2022, The Authors. All rights reserved.

关键词： Semantics

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：