检索结果-内蒙古大学图书馆

IEEE International Symposium on Biomedical Imaging

作者： Alexandros Gkillas Dimitris Ampeliotis Kostas Berberidis Dept. of Computer Engineering & Informatics University of Patras Greece Dept. of Digital Media and Communication Ionian University Greece

ISBN: (数字)9798350313338

ISBN: (纸本)9798350313345

In this work, we study the problem of skin cancer diagnosis from images by employing a network of collaborating institutions (e.g, hospitals) that cooperate under the emerging federated learning protocol. In such a scenario, the problems of not exposing sensitive patient information as well as the heterogeneity of the participating devices are of paramount importance. To this end, we propose the use of deep equilibrium models, in place of some other "traditional" deep neural network model, that offer a natural means of dealing with devices that have different computational resources. Furthermore, to prevent the leakage of sensitive information, the models exchanged in the proposed approach are homo-morpically encrypted. Numerical results indicate that the proposed approach offers the same accuracy as compared to the state-of-the-art federated learning case that "traditional" deep-learning models, but with three significant advantages: (a) increased privacy, (b) support of heterogeneous devices, and (c) significantly reduced communication requirements.

关键词： Adaptation models Privacy Accuracy Protocols Federated learning Computational modeling Biological system modeling

来源：评论

学校读者我要写书评

暂无评论

Electricity Consumption by ICT: Facts, trends, and measurements

引用

Ubiquity 2023年第8期2023卷 1-15页

作者： Gelenbe, Erol Institute of Theoretical and Applied Informatics Polish Academy of Sciences Gliwice44100 Poland Université Côte d'Azur CNRS I3S Nice06000 France Dept. of Computer Engineering Yaşar University Bornova Izmir Turkey

This paper considers key issues surrounding energy consumption by information and communication technologies (ICT), which has been steadily growing and is now attaining approximately 10% of the worldwide electricity consumption with a significant impact on greenhouse gas emissions. The perimeter of ICT systems is discussed, and the role of the subsystems that compose ICT is considered. Data from recent years is used to understand how each of these sub-systems contribute to ICT's energy consumption. The quantitatively demonstrated positive correlation between the penetration of ICT in the world's different economies and the same economies' contributions to undesirable greenhouse gas emissions is also discussed. The paper also examines how emerging technologies such as 5G, AI, edge computing, and cryptocurrencies are contributing to the worldwide increase in electricity consumption by ICT, despite the increases in ICT efficiency, in terms of energy consumed per bit processed, stored, or transmitted. The measurement of specific ICT systems' electricity consumption is also addressed, and the manner in which this consumption can be minimized in a specific edge computing context is discussed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence of Things;Remote Robot System Interacts with Humans and Vice Versa During Pandemic 5

Artificial Intelligence of Things;Remote Robot System Intera...

引用

5th World Symposium on Communication engineering, WSCE 2022

作者： Metallidou, Chrysi Psannis, Kostas E. Sarigiannidis, Panagiotis Michalas, Angelos Vergados, Dimitrios D. Goudos, Sotirios University of Macedonia Dept. of Applied Informatics Thessaloniki Greece Dept of Economics/Computer Science University of Western Macedonia Kastoria Greece University of Western Dept. of Electrical & Computer Engineering Kozani Greece University of Piraeus Dept. of Informatics Piraeus Greece Aristotle University Dept. of Physics Thessaloniki Greece

ISBN: (数字)9781665450577

ISBN: (纸本)9781665450577

Nowadays., the advancement of artificial intelligence has led to the application of robotic systems in the industry, especially in the hotel industry, with a view to providing intelligent, automated and luxury services. At the same time, the knowledge gained from the Covid19 pandemic outbreak that convulses the world community, highlights the issue of sustainability in the hotel industry, solved by utilizing artificial intelligence achievements, remote robot systems, so as to guarantee reliability and security of a hotel's functionality, by providing not only convenient accommodation to guests, but safety, as well. In this paper, we focus on the development of a remote robot system, utilizing the Internet of Things, that has various kinds of sensors and cameras. Both the owners of the hotel and the guests can collaborate with the robot efficiently and accurately, since the robot is able to react with them. Specifically, the developed robot is able to serve clients, by providing them with hotel supplies and by giving them any requested information. In return, the guests are requested to give feedback to the robot upon check out. In addition, the robot browses throughout the hotel to inspect the normal and efficient functionality of all technical systems. The developed robot is also a Covid19 inspector, since it inspects whether one's pandemic measures are applied among guests in public areas and in case of a patient, the robot detects people connected to the patient, isolates the patient and gives medical care, food and supplies, so as to prevent humans from closely contacting the patient. © 2022 IEEE.

关键词： Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Gender Detection Using Short Speech Utterances: A Deep Learning Approach with Wavelet Cepstral Coefficients

Gender Detection Using Short Speech Utterances: A Deep Learn...

引用

International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)

作者： Syahroni Hidayat Budi Sunarko Uswatun Hasanah Faila Nadhifatul Aryza Dept. of Electrical Engineering Universitas Negeri Semarang Semarang Indonesia Dept. of Informatics and Computer Engineering Education Universitas Negeri Semarang Semarang Indonesia Dept. of Computer Engineering Universitas Negeri Semarang Semarang Indonesia

ISBN: (数字)9798331519643

ISBN: (纸本)9798331519650

The human voice is critical in recognizing the speaker’s identity and gender. This study aims to develop an effective gender detection system using short utterances of less than one second. Wavelet Cepstral Coefficient (WCC) features were used for feature extraction, and a Long Short-Term Memory (LSTM) model was applied for classification. Primary and secondary short voice datasets, including syllables and the Audio MNIST dataset, underwent acoustic pretreatment and were trained using LSTM architectures with 32, 64, and 128 units. Results indicated that the LSTM model achieved high accuracy, with the syllable dataset reaching 0.99 accuracy and the Audio MNIST dataset showing perfect accuracy (1.00) using a 32-unit configuration. The findings demonstrate that combining WCC features and LSTM models can efficiently handle short-duration speech for accurate gender detection.

关键词： Seminars Accuracy Cepstral analysis Memory architecture Speech recognition Feature extraction Speaker recognition Intelligent systems Information technology Long short term memory

来源：评论

学校读者我要写书评

暂无评论

The Correlation Between Architecture Smells, Package Stability and Reusability: A Case Study 4

The Correlation Between Architecture Smells, Package Stabili...

引用

4th IEEE International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and computer engineering, MI-STA 2024

作者： Benidris, Mrwan Elfallah, Ehab A. Omar Cheema, Marwa Aslam Alsma, Mohammed Salah Addin Kadiki, Tareq Ziad Elbarsha, Abdelfattah University of Benghazi Faculty of Information Technology Dep. of Computer Science Libya Libyan International Medical University Faculty of Information Technology Dept. of Software Engineering Libya University of Benghazi Faculty of Public Health Health Informatics Department Libya

ISBN: (纸本)9798350372632

the design decisions made in the architecture of a software system are essential to its maintainability, and thus its quality is of great importance. Architecture smells (ASs) can be used to identify any quality issues within the system. To further explore the relationships between ASs, stability, and reusability, Spearman correlation coefficients will be calculated. This paper seeks to examine the connection between architecture smells, software stability, and reusability. To do this, we utilized a dataset created by other researchers and conducted an empirical study of the associations between five types of architecture smells and software stability and reusability. This research is necessary as there is a lack of in-depth research on architecture smells and their relationship to software stability and reusability. We found a relationship between the presence of Feature Concentration in package and the stability and reusability of the package. Also, package's stability is affected by both Cyclic Dependency and Unstable Dependency. A slight positive correlation has been found between God Class and stability, as well as a very weak negative correlation between Unstable Dependency and reusability. Finally, we found a slight negative correlation between package stability and reusability. © 2024 IEEE.

关键词： Reusability

来源：评论

学校读者我要写书评

暂无评论

Indonesian Hate Speech and Abusive Tweets Classification with Deep Learning Pre-trained Language Models

Indonesian Hate Speech and Abusive Tweets Classification wit...

引用

International Conference of computer and informatics engineering (IC2IE)

作者： Bagus Tri Yulianto Darmawan Bassamtiano Renaufalgi Irnawan Yoshimi Suzuki Dept. of Computer and Informatics Engineering Politeknik Negeri Jakarta Depok Indonesia Dept. of Computer Science and Engineering University of Yamanashi Kofu Japan

Hate speech and abusive language on social media can spread massively and escalate into conflict between two or more individuals or parties. Previous studies about multi-label classification to identify whether the tweet contains hate speech, abusive language, or not have been conducted with machine learning techniques. They applied machine learning with a combination of feature extraction and achieved a good result in recognizing the tweet with hate speech content. In this research, we apply two approaches: first, we use vanilla pre-trained models of IndoBERT, IndoBERTweet, and Indonesian RoBERTa; second, we combine the three previous models with CNN. Our experiment shows that our proposed method has better results compared to previous research with the best performance achieved by IndoBERTweet+CNN with 93.9% Accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RadioModRec-l: A Large Scale Radio Frequency Dataset for Automatic Modulation Recognition Research 4

RadioModRec-l: A Large Scale Radio Frequency Dataset for Aut...

引用

4th International Conference on Emerging Trends in Networks and computer Communications, ETNCC 2024

作者： Adetiba, Emmanuel Olasina, Jamiu R. Obiyemi, Obiseye Covenant University Covenant Applied Informatics and Communication Africa Center of Excellence Dept. of Electrical and Information Engineering Ota Nigeria HRA Institute for Systems Science Durban University of Technology Durban4001 South Africa Federal Polytechnic Ilaro Dept. of Computer Engineering Ilaro Nigeria Durban University of Technology Space Science Centre Dept. of Electrical Power Engineering Durban South Africa

ISBN: (纸本)9798350353266

Access to well-curated large datasets remains a significant bottleneck in AI-based research within wireless communication. Rapid advancements in neighbouring fields, such as computer vision and natural language processing, are largely due to the availability of extensive open-access datasets. However, similar progress has not been observed in wireless communication. To address this gap, we curated a comprehensive dataset for fifteen digital modulation schemes, including 4QAM, 16QAM, 64QAM, 256QAM, 8PSK, 16PSK, 32PSK, 64PSK, 128PSK, 256PSK, CPFSK, DBPSK, DQPSK, GFSK, and GMSK. Our dataset considers Rayleigh and Rician channel models under Additive White Gaussian Noise (A WGN) with SNRs ranging from -20dB to + 20dB in 5dB increments. The data samples were converted to constellation signal images and carefully pre-processed. Named RadioModRec, this dataset provides a valuable resource for researchers to train and evaluate AI models. It is freely accessible on Kaggle, promoting further innovation in the wireless communication domain. © 2024 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

A Game Theoretic Approach to Enhance DCF Performance in Full Duplex Ad-hoc WLANs

A Game Theoretic Approach to Enhance DCF Performance in Full...

引用

International Conference on Modern Circuits and Systems Technologies (MOCAST)

作者： Anastasios C. Politis Hristos T. Anastassiu Constantinos S. Hilas Dept. of Computer Informatics and Telecommunications Engineering International Hellenic University Serres Greece

Physical Full Duplex (FD) operation in WLANs is a promising technology aiming at substituting the traditional Half Duplex (HD) functionality. An increased performance is expected which, theoretically, can be expressed as a double increase in system throughput. However, due to the initial design of the basic access method in WLANs, known as Distributed Coordination Function (DCF), this performance boost is poorly exhibited. Game theory is an invaluable tool to model the performance of Medium Access Control (MAC) protocols used in WLANs. In this paper, we exploit game theory to propose a simple enhancement to the DCF access method, in order to increase the benefit received when the FD capability is enabled in ad-hoc WLANs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

To Split or not to Split? A Simulation Study on the Network Convergence Duration of Multi-Area OSPF

To Split or not to Split? A Simulation Study on the Network ...

引用

International Conference on Telecommunications and Signal Processing (TSP)

作者： Theofilos Sachinidis Anastasios C. Politis Constantinos S. Hilas Dept. of Computer Informatics and Telecommunications Engineering International Hellenic University Serres Greece

Internetworks with a large number of routing devices that utilise the Open Shortest Path First (OSPF) routing protocol, benefit greatly if they are designed in a hierarchical manner. The multi-area feature of OSPF leads to reduced network overhead, low processing and memory requirements and smaller routing tables. This, however, comes at the cost of increased configuration complexity, especially at the Area Border Routers. The threshold after which splitting the OSPF domain into multiple areas, is an ongoing debate among network administrators. A well known rule-of-thumb is recommended by large vendors of networking devices setting that threshold to 50 routing devices. The objective of this preliminary work is to investigate that threshold by conducting a simulation-based study using the OPNET network simulation tool. To assess the network performance, we select the network convergence duration as the quantitative Key Performance Indicator (KPI) of our study. Results indicate that the above mentioned threshold does not appear to be appropriate and a revision of that empirical rule should be considered.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GAN vs. LSTM: Network State Prediction 17

GAN vs. LSTM: Network State Prediction

引用

17th International Conference on Ubiquitous Information Management and Communication, IMCOM 2023

作者： Byun, Gyurin Raza, Syed M. Yang, Huigyu Kim, Moonseong Choo, Hyunseung Sungkyunkwan University Dept. of Superintelligence Engineering Suwon Korea Republic of College of Computing and Informatics Sungkyunkwan University Suwon Korea Republic of Seoul Theological University Dept. of It Convergence Software Bucheon Korea Republic of Sungkyunkwan University Dept. of Electrical and Computer Engineering Suwon Korea Republic of

ISBN: (纸本)9781665453486

Network Traffic prediction is the prerequisite for proactive traffic management, where a longer duration and high accuracy of prediction ensures a more effective solution. This paper exploits Generative Adversarial Network (GAN) architecture to propose a model that utilizes spatiotemporal features in network traffic data for extended prediction of future traffic. The generator in GAN consists of a Convolutional Long Short-Term Memory (ConvLSTM) model for predicting network traffic, while the discriminator uses Convolutional Neural Network (CNN) model that provides feedback to the generator for training. The experiments based on network traces show that the proposed model reduces the error by 12% compared to the baseline model while predicting next 48 mins of network traffic. © 2023 IEEE.

关键词： Generative adversarial networks

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：