检索结果-内蒙古大学图书馆

2022 International Conference on Smart Information Systems and Technologies, SIST 2022

作者： Tereikovskyi, Ihor Tereikovska, Liudmyla Kryvoruchko, Olena Tereikovskyi, Oleh Tyshchenko, Dmytro Franchuk, Tamara National Technical University Of Ukraine Igor Sikorsky Kyiv Polytechnic Institute Dept. Of System Programming And Specialized Computer Systems Kyiv Ukraine Kyiv National University Of Construction And Architecture Dept. Of Information Technology For Design And Applied Mathematics Kyiv Ukraine Kyiv National University Of Trade And Economics Dept. Of Software Engineering And Cyber Security Kyiv Ukraine National Technical University Of Ukraine Igor Sikorsky Kyiv Polytechnic Institute Dept. Of Department Of Computer Engineering Kyiv Ukraine

ISBN: (数字)9781665467902

ISBN: (纸本)9781665467902

The article is devoted to the development of means for recognition of the emotions of the speaker, based on the neural network analysis of fixed fragments of the voice signal. The possibility of improving recognition tools through the use of a convolutional neural network of the GoogLeNet type is shown. The expediency of training the network on the examples of the TESS database is determined. A procedure for representing a voice signal in the form of a square grayscale image has been developed. Based on the use of the specified database, the modification of the GoogLeNet network was carried out. The architecture and software implementation of the recognition module have been developed. With the help of computer experiments, it has been established that after 150 epochs of training on a fairly limited training sample, the modified GoogLeNet makes it possible to achieve an accuracy of recognition of the speaker's emotions of approximately 0.97 on test examples. The obtained accuracy is comparable to the accuracy of the best modern systems of this purpose and confirms the promise of using neural network models like GoogLeNet for emotion recognition based on voice signal analysis. The need for further research aimed at reducing the resource intensity of the neural network model is shown. © 2022 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Machine Learning based Cybersecurity Technique for Detection of Upcoming Cyber Attacks 8

Machine Learning based Cybersecurity Technique for Detection...

引用

8th International Conference on Communication and Electronics Systems, ICCES 2023

作者： Lakshmi, Kanchi Lohitha Shobana, S. Kumar, Bathula Prasanna Glory, K.B. Kumar, Bonda Kiran Rani, Sandya Vasireddy Venkatadri Institute of Technology Department of Computer Science and Engineering Guntur India R.M.K Engineering College Department of It India Kkr & Ksr Institute of Technology and Sciences Department of Computer Science and Engineering AP Guntur India Koneru Lakshmaiah Education Foundation Department of Engineering English Andhra Pradesh State Vaddeswaram522302 India Kl Deemed to Be University Kl School of Architecture Department of Architecture Guntur District Vaddeswaram522302 India St. Martin's Engineering College Dept. of It Telangana Secunderabad India

ISBN: (纸本)9798350396638

Cyberattacks are prevalent in the age of the Internet. Each year, both the quantity and severity of cybercrimes increase. Protection against cyber-attacks has become a primary responsibility, Significant in the internet society of today. However, providing cyber security is a highly difficult task that requires experience in the field of attacks and the ability to evaluate the possibility of threats. The continual evolution of cyberattacks is the biggest challenge in this industry. This article describes the significance of cyber security and enumerates the hazards that exist in the present digital environment. The statistics and evaluation of cyberattacks demonstrate the seriousness of these occurrences. Several sorts of cyber security threats are outlined, along with the machine learning approaches that may be used to detect these attacks. © 2023 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

CDP: Selective Influential Nodes Based on Cliques in the Diffusion Process in Social Networks

CDP: Selective Influential Nodes Based on Cliques in the Dif...

引用

International Conference on Web Research (ICWR)

作者： Fatemeh Yazdanifar Hamid Ahmadi Beni Nikoo Salimi Asgarali Bouyer Dept. of Mathematics and Computer Science Amirkabir University of Technology Tehran Iran Dept. Software Engineering Azarbijan Shahid Madani University Tabriz Iran Dept. of the Electrical Electronics Electronics and Telecommunication Engineering and Naval Architecture University of Genoa Genoa Italy Dept. of Computer Engineering Azarbaijan Shahid Madani University Tabriz Iran

Influence maximization techniques emphasize selecting a set of influential nodes in order to maximize influence. Because the algorithms presented in this field ignore the topology of cliques for diffusion, there are two major challenges in influence maximization algorithms: optimal diffusion and computational overhead reduction. As a result, the CDP algorithm is presented in this article to address these issues. This algorithm first selects suitable cliques for diffusion based on their position and strategy in social networks. Furthermore, for each clique, a score is calculated based on the topological criteria of the clique, and suitable cliques are selected for diffusion by applying a threshold limit. The seed nodes are chosen from the cliques in the second step. To avoid the rich club phenomenon, only a few nodes from each clique are chosen as seed candidate nodes. Finally, the seed nodes are chosen based on the node’s topology and the strength of the node’s level one neighbor. In the experiment section, the CDP algorithm significantly outperforms the best algorithms presented in recent years in terms of influence spread rate and execution time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

BC4ECO - Using Visual Tools for a Shared Understanding and Pedagogical Approach across an Interdisciplinary Consortium

BC4ECO - Using Visual Tools for a Shared Understanding and P...

引用

IEEE Annual International computer Software and Applications Conference (COMPSAC)

作者： Andy Peruccon Roisin Lyons Amalia de Gotzen Tiziana Margaria Luca Simeone dept. of Architecture Design and Media Technology Aalborg University Copenhagen Denmark Kemmy Business School University of Limerick Limerick Ireland Dept. of Computer Science and Information Systems University of Limerick Limerick Ireland

Effective communication is crucial when working on complex or wicked problems in interdisciplinary, international teams. Developing a shared understanding of critical concepts and aligning knowledge, focus, and resources can be problematic when stakeholders speak different languages, span several disciplines and work within different national or industry-based norms. Using visual tools to represent critical concepts and their relations, and map out our strategic goals has greatly helped combat such issues. This paper recounts the use and impact of adopting visual tools within the transnational and interdisciplinary collaborative environment in the BC4ECO project's international consortium. The Miro Board and the canvas approach greatly helped represent, visualise, and thus concretise the structure and contents of our collaboration, which takes place within a 3 years ERASMUS+ framework that builds and delivers Summer School, MOOCS as well as teacher and multiplier events about harnessing the potential of Distributed Ledger Technologies (DLTs) for environmental sustainability. As the materials and MOOCS are expected to become Open Education Resources and have a wide impact, it is particularly crucial to get the contents as well as the pedagogy right, in spite of the team's differences in almost any dimension of background and culture.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Concept of an Optical Distance and Speed Sensor Using Novel Offsetless Spatial Frequency Filters in the Area of Functional Safety

Concept of an Optical Distance and Speed Sensor Using Novel ...

引用

IEEE International Symposium on Industrial Electronics (ISIE)

作者： Frank Wasinski Werner Bonath Ubbo Ricklefs Josef Börcsök Michael Schwarz Eike Hahn Dept. of Electrical Engineering and Information Technology THM University of Applied Sciences Giessen Germany ICAS Institute for Computer Architecture and System Programming University of Kassel Kassel Germany

Optical speed sensors based on the spatial frequency filter method are a proven technology that offer high measurement accuracy over a wide speed range. Newly developed variants also enable measurements at very low speeds and increase the robustness of the method [1]. This makes the sensor very suitable for use in the area of functional safety. A measurement chain up to safety integrity level 3 (SIL3) should be feasible via a combination with a safety system on a chip (SoC) for evaluating the measurement data and an extension of the sensor module to include safety-related elements [2], [3]. By integrating the sensor at IC level, a compact overall solution is to be made possible. After the first successful tests with the safety SoC, further examinations of the measuring method with regard to functional safety are now necessary.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Light up that Droid! On the Effectiveness of Static Analysis Features against App Obfuscation for Android Malware Detection

arXiv

引用

arXiv 2023年

作者： Molina-Coronado, Borja Ruggia, Antonio Mori, Usue Merlo, Alessio Mendiburu, Alexander Miguel-Alonso, Jose The Dept. of Computer Architecture and Technology University of the Basque Country UPV/EHU Donostia Spain The Dept. of Computer Science and Artificial Intelligence University of the Basque Country UPV/EHU Donostia Spain The Dept. of Informatics Bioengineering Robotics and Sytems Engineering University of Genoa Genoa Italy The CASD - Centre for Advanced Defense Studies Rome Italy

Malware authors have seen obfuscation as the mean to bypass malware detectors based on static analysis features. For Android, several studies have confirmed that many anti-malware products are easily evaded with simple program transformations. As opposed to these works, ML detection proposals for Android leveraging static analysis features have also been proposed as obfuscation-resilient. Therefore, it needs to be determined to what extent the use of a specific obfuscation strategy or tool poses a risk for the validity of ML malware detectors for Android based on static analysis features. To shed some light in this regard, in this article we assess the impact of specific obfuscation techniques on common features extracted using static analysis and determine whether the changes are significant enough to undermine the effectiveness of ML malware detectors that rely on these features. The experimental results suggest that obfuscation techniques affect all static analysis features to varying degrees across different tools. However, certain features retain their validity for ML malware detection even in the presence of obfuscation. Based on these findings, we propose a ML malware detector for Android that is robust against obfuscation and outperforms current state-of-the-art detectors. © 2023, CC BY-NC-SA.

关键词： Static analysis

来源：评论

学校读者我要写书评

暂无评论

Towards a Fair Comparison and Realistic Evaluation Framework of Android Malware Detectors based on Static Analysis and Machine Learning

arXiv

引用

arXiv 2022年

作者： Molina-Coronado, Borja Mori, Usue Mendiburu, Alexander Miguel-Alonso, Jose The Dept. of Computer Architecture and Technology University of the Basque Country UPV EHU Donostia Spain The Dept. of Computer Science and Artificial Intelligence University of the Basque Country UPV EHU Donostia Spain

z As in other cybersecurity areas, machine learning (ML) techniques have emerged as a promising solution to detect Android malware. In this sense, many proposals employing a variety of algorithms and feature sets have been presented to date, often reporting impresive detection performances. However, the lack of reproducibility and the absence of a standard evaluation framework make these proposals difficult to compare. In this paper, we perform an analysis of 10 influential research works on Android malware detection using a common evaluation framework. We have identified five factors that, if not taken into account when creating datasets and designing detectors, significantly affect the trained ML models and their performances. In particular, we analyze the effect of (1) the presence of duplicated samples, (2) label (goodware/greyware/malware) attribution, (3) class imbalance, (4) the presence of apps that use evasion techniques and, (5) the evolution of apps. Based on this extensive experimentation, we conclude that the studied ML-based detectors have been evaluated optimistically, which justifies the good published results. Our findings also highlight that it is imperative to generate realistic experimental scenarios, taking into account the aforementioned factors, to foster the rise of better ML-based Android malware detection solutions. © 2022, CC BY.

关键词： Static analysis

来源：评论

学校读者我要写书评

暂无评论

Condition monitoring of industrial exhaust motor-fan assembly using statistical feature optimization with nature-inspired optimizers

Condition monitoring of industrial exhaust motor-fan assembl...

引用

International Conference on Control, Instrumentation, Energy and Communication (CIEC)

作者： Abhrodeep Das Ayushman Agrawal Nishkarsh Kundoliya Ananta Dutta Surjya K Pal Rishi Kumar Dept. of Computer Science and Engineering Jalpaiguri Government Engineering College WB India Dept. of Mechanical Engineering Indian Institute of Technology Kharagpur WB India Dept of Ocean Engg & Naval Architecture Indian Institute of Technology Kharagpur WB India Research & Development Centre for Iron & Steel Steel Authority of India Limited (SAIL) Ranchi Jharkhand India

Exhausters are very crucial components in sinter plant of steel manufacturing industries. Problems in fan or motor side of the exhausters lead to machine stoppages or reduced speed, resulting in stoppage of the system and decreased sinter production. Common issues include imbalance, misalignments, looseness, eccentricity, and motor bearing failure. The proposed IoT-based system aims to continuously analyze vibration signals, predict issues, and prevent sudden stoppages and exhauster tripping, thereby enhancing overall plant efficiency. This study focuses on online monitoring and health prediction of industrial exhausters by selection of statistical features extracted from triaxial time-series vibration data by using multiple optimizers, followed by implementation of machine learning classifiers. By incorporating a novel feature selection process based on nature-inspired optimizers, this methodology aims to enhance the overall generalization performance of classification. The retrained models with cross-validation were evaluated with real-time industrial data, which shows 99.5% cross-validation accuracy and 95.83% real-time prediction accuracy. The proposed methodology holds great potential for detecting machine faults in industrial applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Energy efficiency in Edge TPU vs. embedded GPU for computer-aided medical imaging segmentation and classification

arXiv

引用

arXiv 2023年

作者： Corral, José María Rodríguez Civit-Masot, Javier Luna-Perejón, Francisco Díaz-Cano, Ignacio Morgado-Estévez, Arturo Domínguez-Morales, Manuel 10 Spain Architecture and Computer Technology Dept. E.T.S. Ingeniería Informática University of Seville Avda. Reina Mercedes s/n Sevilla Spain

In this work, we evaluate the energy usage of fully embedded medical diagnosis aids based on both segmentation and classification of medical images implemented on Edge TPU and embedded GPU processors. We use glaucoma diagnosis based on color fundus images as an example to show the possibility of performing segmentation and classification in real time on embedded boards and to highlight the different energy requirements of the studied implementations. Several other works develop the use of segmentation and feature extraction techniques to detect glaucoma, among many other pathologies, with deep neural networks. Memory limitations and low processing capabilities of embedded accelerated systems (EAS) limit their use for deep network-based system training. However, including specific acceleration hardware, such as NVIDIA’s Maxwell GPU or Google’s Edge TPU, enables them to perform inferences using complex pre-trained networks in very reasonable times. In this study, we evaluate the timing and energy performance of two EAS equipped with Machine Learning (ML) accelerators executing an example diagnostic tool developed in a previous work. For optic disc (OD) and cup (OC) segmentation, the obtained prediction times per image are under 29 and 43 ms using Edge TPUs and Maxwell GPUs, respectively. Prediction times for the classification subsystem are lower than 10 and 14 ms for Edge TPUs and Maxwell GPUs, respectively. Regarding energy usage, in approximate terms, for OD segmentation Edge TPUs and Maxwell GPUs use 38 and 190 mJ per image, respectively. For fundus classification, Edge TPUs and Maxwell GPUs use 45 and 70 mJ, respectively. © 2023, CC BY-NC-ND.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Sixteen years of sound and music computing: A look into the history and trends of the conference and community 17

Sixteen years of sound and music computing: A look into the ...

引用

17th Sound and Music Computing Conference, SMC 2020

作者： Mauro, Davide Andrea Avanzini, Federico Baraté, Adriano Ludovico, Luca Andrea Ntalampiras, Stavros Dimitrov, Smilen Serafin, Stefania Dept. of Computer & Information Technology Marshall University United States Dept. of Computer Science University of Milano Italy Dept. of Architecture Design and Media Technology Aalborg University Copenhagen Denmark

ISBN: (纸本)9788894541502

This contribution provides an overview of the Sound and Music Computing conference and community over the course of its sixteen years. As a sequel to a previous corresponding contribution investigating the community ten years ago, here we analyze the proceedings of the past editions, as well as the changes in the organization of the conference itself. The analysis reveals the growth of the SMC community in terms of attendees and countries represented at the conference, highlights the changes in trends and topics, and provides insights on the directions of the conference. A reflection is made with regards to the SMC roadmap originally conceived in 2004. Motivated by similar initiatives in "sister"communities, this resource is made available to the community at http://***/. Copyright © 2020 Davide Andrea Mauro et al.

关键词： computer programming

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：