检索结果-内蒙古大学图书馆

Innovative Data Communication Technologies and Application (ICIDCA), International Conference on

作者： Mahima Yadav Ishan Kumar Ayush Kumar Department of Computer Science and Engineering Lovely Professional University Phagwara India Software engineer Noida India

Accessing information because of language barriers has grown more crucial as globalization accelerates. The field of study called machine transliteration transforms words from one language to another while preserving their phonetic properties. With the rise of the Internet and the rapid expansion of online data, Information Retrieval (IR) has become a more significant field. Foreign terms are increasingly being incorporated into languages due to the development of new technologies and the flood of information available online. This generally indudes changing the adopted word's orthographical form as well as its original pronunciation to match the phonological norms of the target language. Transliteration describes this phonetic “translation” of a foreign language. Machine translation and cross-language information retrieval both benefit from transliteration. Ambiguity, variability, and out-of-vocabulary (OOV) words are a few of the crucial challenges that transliteration systems must deal with. This paper represents the transliteration models of the last decade used for transliteration-related research carried out by researchers.

关键词： Training Support vector machines Hidden Markov models Training data Transforms Phonetics Information retrieval

来源：评论

学校读者我要写书评

暂无评论

A First Look at the Inheritance-Induced Redundant Test Execution

A First Look at the Inheritance-Induced Redundant Test Execu...

引用

International Conference on software engineering (ICSE)

作者： Dong Jae Kim Tse-Hsun Peter Chen Jinqiu Yang Software PErformance Analysis and Reliability (SPEAR) Lab Concordia University Montreal Quebec Canada Department of Computer Science and Software Engineering Concordia University Montreal Quebec Canada

ISBN: (数字)9798400702174

ISBN: (纸本)9798350382143

Inheritance, a fundamental aspect of object-oriented design, has been leveraged to enhance code reuse and facilitate efficient software development. However, alongside its benefits, inheritance can introduce tight coupling and complex relationships between classes, posing challenges for software maintenance. Although there are many studies on inheritance in source code, there is limited study on using inheritance in test code. In this paper, we take the first step by studying inheritance in test code, with a focus on redundant test executions caused by inherited test cases. We empirically study the prevalence of test inheritance and its characteristics. We also propose a hybrid approach that combines static and dynamic analysis to identify and locate inheritance-induced redundant test cases. Our findings reveal that (1) inheritance is widely utilized in the test code, (2) inheritance-induced redundant test executions are prevalent, accounting for 13% of all execution test cases, (3) bypassing these redundancies can help reduce 14% of the test execution time, and finally, (4) our study highlights the need for careful refactoring decisions to minimize redundant test cases and identifies the need for further research on test code quality.

关键词： Couplings software maintenance Java Codes Source coding Redundancy Maintenance

来源：评论

学校读者我要写书评

暂无评论

Adaptive High-Frequency Transformer for Diverse Wildlife Re-Identification

arXiv

引用

arXiv 2024年

作者： Li, Chenyue Chen, Shuoyi Ye, Mang National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Hubei Luojia Laboratory Wuhan University Wuhan China

Wildlife ReID involves utilizing visual technology to identify specific individuals of wild animals in different scenarios, holding significant importance for wildlife conservation, ecological research, and environmental monitoring. Existing wildlife ReID methods are predominantly tailored to specific species, exhibiting limited applicability. Although some approaches leverage extensively studied person ReID techniques, they struggle to address the unique challenges posed by wildlife. Therefore, in this paper, we present a unified, multi-species general framework for wildlife ReID. Given that high-frequency information is a consistent representation of unique features in various species, significantly aiding in identifying contours and details such as fur textures, we propose the Adaptive High-Frequency Transformer model with the goal of enhancing high-frequency information learning. To mitigate the inevitable high-frequency interference in the wilderness environment, we introduce an object-aware high-frequency selection strategy to adaptively capture more valuable high-frequency components. Notably, we unify the experimental settings of multiple wildlife datasets for ReID, achieving superior performance over state-of-the-art ReID methods. In domain generalization scenarios, our approach demonstrates robust generalization to unknown species. Code is available at https://github. com/JigglypuffStitch/***. Copyright © 2024, The Authors. All rights reserved.

关键词： Invertebrates

来源：评论

学校读者我要写书评

暂无评论

CNN channel pruning via gradient integration and knowledge distillation

CNN channel pruning via gradient integration and knowledge d...

引用

International Conference on Signal Processing Proceedings (ICSP)

作者： Suyun Lian Yang Zhao Jiajian Cai Jihong Pei The Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (数字)9798350387384

ISBN: (纸本)9798350387391

With the advancement of artificial intelligence technology, intelligent applications have permeated all aspects of human life, including automatic driving, intelligent security, and face recognition. Convolutional neural networks (CNNs) are essential models for AI, but their complexity increases with more available data. The complex models are unsuitable for edge devices like wearables and smartphones due to high memory and computational requirements. In this paper, the compact model is achieved by pruning some redundant output channels. To effectively measure the validity of the output channels, this paper proposes a channel pruning algorithm based on gradient integration, which combines the gradient of the channel with the model output and the channel’s values. This pruning could destroy model accuracy, so knowledge distillation is introduced during fine-tuning to leverage the original model’s reasoning ability. Experiments show that our approach improves accuracy by 0.51% while reducing parameters by 30.1% and FLOPs by 26% in the VGG16 model.

关键词： Training Accuracy Computational modeling Signal processing algorithms Signal processing Cognition Convolutional neural networks Security Wearable devices Smart phones

来源：评论

学校读者我要写书评

暂无评论

Current-induced Néel order switching facilitated by magnetic phase transition

Current-induced Néel order switching facilitated by magneti...

引用

2023 IEEE International Magnetic Conference - Short Papers, INTERMAG Short Papers 2023

作者： Wu, Hao Zhang, Hantao Wang, Baomin Guo, Yaqin Cheng, Ran Wang, Kang L. Songshan Lake Materials Laboratory Dongguan523808 China University of California Department of Electrical and Computer Engineering Los AngelesCA90095 United States University of California Department of Electrical and Computer Engineering RiversideCA92521 United States Ningbo University School of Physical Science and Technology Ningbo315211 China Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Cas Key Laboratory of Magnetic Materials and Devices Ningbo315201 China

ISBN: (纸本)9798350338362

Antiferromagnetic materials (AFMs), which have zero-stray field and the THz-range magnetic resonance frequency, are promising candidates for the next-generation magnetic memory technology. Here, we report an electrical writing of antiferromagnetic orders through a record-low current density on the order of 106 A cm-2 facilitated by the unique AFM-ferromagnetic (FM) phase transition in FeRh. The spin-orbit torque can switch the AFM order parameter by 90° with a reduced writing current density by introducing a transient FM state via current-induced Joule heating. This work demonstrates the exciting possibility of writing operations in AFM-based devices with a lower current density, opening a new pathway toward pure AFM memory applications. © 2023 IEEE.

关键词： Magnetic resonance

来源：评论

学校读者我要写书评

暂无评论

Review Study on Blockchain Frameworks for Security Issues in IoT Devices 6

Review Study on Blockchain Frameworks for Security Issues in...

引用

6th International Symposium on Multidisciplinary Studies and Innovative Technologies, ISMSIT 2022

作者： Sille, Roohi Mahdi, Hussain Falih Choudhury, Tanupriya Sahoo, Samyukta Kapoor, Akshita Nanda, Ishita Sharma, Arnav University of Petroleum and Energy Studies Department of Systemics Dehradun248007 India University of Diyala Department of Computer and Software Engineering Baquba Iraq University of Petroleum and Energy Studies Department of Informatics Dehradun248007 India University of Petroleum and Energy Studies Computer Science and Engineering Dehradun248007 India

ISBN: (数字)9781665470131

ISBN: (纸本)9781665470131

A coalition of IoT devices, such as the smart houses, smart health care system, the smart device and many more, can share resources through communication lines. The Internet is integrated with the physical world over existing network infrastructure, allowing intelligent devices to share data more efficiently. As IOT devices have specific characteristics such as having low processing power, limited memory and energy, securing access to them requires special requirements. Because of their complex management of access, and their incredulity due to centralized control, conventional access control systems do not offer the security of data that IoT systems need. Blockchain technology is expected to enhance the IoT technology by ensuring trust and reducing overall overhead. We can address IoT's architectural shortcomings by including transparency, data encryption, auditable data, operational resilience, and immutability. In this paper, the most relevant findings are presented in the area of understanding blockchain applications to solve authorization and access control issues in IoT environments. Additionally, future suggestions and ideas are discussed in an effort to improve authentication and access control solutions over time. © 2022 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Violence Detection in Surveillance: The Role of Transfer Learning and Pre-Trained Models

Deep Learning for Violence Detection in Surveillance: The Ro...

引用

Information Technology (ACIT)

作者： Anum Ilyas Surayya Obaid Narmeen Zakaria Bawany Department of Computer Science and Software Engineering Center for Computing Research Jinah University for Women Karachi Pakistan

In recent years, the use of CCTV footage for proactive crime prevention has surged, particularly in public places like airports, train stations, and malls. However, the efficacy of these surveillance systems becomes questionable for their substantial reliance on human resources which may lead to erroneous or delayed responses. This research takes a comprehensive approach for violence detection which was previously limited to binary classification, by categorizing violence into four distinct classes: abuse, arson, assault, and fight. It employs transfer learning combined with computer vision techniques for violence detection and classification in video footages. The study compares the performance of four pre-trained neural networks, namely DenseNet121, VGG16, MobileNet, and Xception. The dataset created for this research is compiled from three datasets available on Kaggle. The results reveal that the Xception model performed comparatively better achieving the highest AUC score of 98.39%, while the VGG16 model attained the lowest AUC score of 96%. In addition to the AUC score, precision, recall, and fl-score are employed as performance metrics. Transfer learning with convolutional neural networks (CNN) significantly reduced computational requirements and time. Automating the detection and categorization of violent behavior through the employed approach has the potential to reduce the risk of fatalities and injuries in public areas. It also improves the speed and accuracy of threat detection, enabling swift preventive actions by authorities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Characterizing Static Analysis Alerts for Terraform Manifests: An Experience Report

Characterizing Static Analysis Alerts for Terraform Manifest...

引用

IEEE Cybersecurity Development (SecDev)

作者： Hanyang Hu Yani Bu Kristen Wong Gaurav Sood Karen Smiley Akond Rahman Company A CA USA Department of Computer Science and Software Engineering Auburn University Auburn AL USA

While Terraform has gained popularity to implement the practice of infrastructure as code (IaC), there is a lack of characterization of static analysis for Terraform manifests. Such lack of characterization hinders practitioners to assess how to use static analysis for their Terraform development process, as it happened for Company A, an organization who uses Terraform to create automated software deployment pipelines. In this experience report, we have investigated 491 static analysis alerts that occur for 10 open source and one proprietary Terraform repositories. From our analysis we observe: (i) 10 categories of static analysis alerts to appear for Terraform manifests, of which five are related to security, (ii) Terraform resources with dependencies to have more static analysis alerts than that of resources with no dependencies, and (iii) practitioner perceptions to vary from one alert category to another while deciding on taking actions for reported alerts. We conclude our paper by providing a list of lessons for practitioners and toolsmiths on how to improve static analysis for Terraform manifests.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Data Leakage with Label Reconstruction in Distributed Learning Environments 1

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Zhang, Xiaoxue Zhou, Xiuhua Chen, Kongyang School of Computer Science and Cyber Engineering Guangzhou University Guangzhou China Institute of Artificial Intelligence and Blockchain Guangzhou University Guangzhou China Pazhou Lab Guangzhou China Jiangsu Key Laboratory of Media Design and Software Technology Jiangnan University Wuxi China

ISBN: (数字)9783031200960

ISBN: (纸本)9783031200953

Distributed learning is commonly applied for the high demands of computation resources while training models with large-scale data. However, existing solutions revealed that it may lead to information leakage of private data. Attackers are able to reconstruct data via minimizing the difference between shared gradients and fake gradients that are produced by themselves. This is so-called data leakage attack from gradients. We find that, in many cases, such attack can only obtain random noises or extreme fuzzy information, which are quite different from the raw data. To deal with this problem, we exploit the gradient updates as well as their labels during the parameter-server training, and discover significant information losses during the label coding. Thus, in our method, we reconstruct the labels of samples with a fine-grained method, and we recover the raw inputs with these processed labels. We test our method on different datasets (i.e. CIFAR100 dataset and solid color images) and obtained the reconstructed results which are obviously clearer than the ones of the state-of-the-arts. The results prove the effectiveness of our algorithm in fixing defects to some extent as well. Extensive experiments are also conducted to explore defense strategies against data leakage. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

IOT based prediction of rainfall forecast in coastal regions using deep reinforcement model

引用

Measurement: Sensors 2023年 29卷

作者： Nithyashri, J. Poluru, Ravi Kumar Balakrishnan, S. Ashok Kumar, M. Prabu, P. Nandhini, S. Department of Computing Technologies School of Computing SRM Institute of Science and Technology Chengalpet District Kattankulathur603203 India Department of Information Technology Institute of Aeronautical Engineering Hyderabad India Department of Computer Science and Business Systems Sri Krishna College of Engineering and Technology Coimbatore India Faculty of Computer Science Department of Computer Science and Software Engineering Skyline University Nigeria Kano Nigeria Bengaluru560029 India Department of Computer Science and Engineering Karpagam Academy of Higher Education Tamilnadu Coimbatore India

This research proposes an IoT based technique for predicting rainfall forecast in coastal regions using a deep reinforcement learning model. The proposed technique utilizes Long Short-Term Memory (LSTM) networks to capture the temporal dependencies between the rainfall data collected from the coastal regions and the prediction model parameters. The proposed technique is evaluated on a dataset of rainfall data collected from the coastal regions of India and compared to traditional methods of rainfall forecasting. The accuracy and reliability of these models are evaluated by comparing them to prior models. Precipitation in coastal locations may be predicted with an average accuracy of 89% using the suggested model, as shown by the results. The suggested framework is computationally efficient and can be trained with little input. The results of this research give strong evidence that the proposed model is an effective tool for coastal precipitation forecasting. © 2023 The Authors

关键词： Internet of things

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：