检索结果-内蒙古大学图书馆

7th International Conference on Applied Informatics, ICAI 2024

作者： Ajagbe, Sunday Adeola Computer Engineering Department Ladoke Akintola University of Technology Ogbomoso210214 Nigeria Computer Science Department University of Zululand Kwadlangezwa3886 South Africa Department of Computer Engineering Abiola Ajimobi Technical University Ibadan Ibadan Nigeria

ISBN: (纸本)9783031751462

Nigerian native languages can still be classified as under-resourced concerning the text and speech resources required for technology development. This limitation strikes all human endeavor facets, including healthcare. The study aims to develop multilingual Nigerian speech resources (English, Yorùbá, and Pidgin languages speech) for antenatal orientation. We collected the dataset from LTH in six (6) different Antenatal clinics using an 8 GB Sony digital voice recorder Midget system, along with a language expert. Each clinic had about an hour of orientation before the nurses began to attend to the pregnant women one after the other. The collected dataset was aligned with the World Health Organisation standard on antenatal. The dataset collected was transcribed into English language and later annotated into Yorùbá (Yorùbá Oyo) and Pidgin languages. The speech version was also developed for the three languages. The project uses the English, Yorùbá, and Pidgin language datasets in text and speech. The word count is 2639, 3202, and 2521 for English, Yorùbá, and Pidgin languages, respectively. These were produced (Speech) in 59880, 70380, and 69840 for English, Yorùbá, and Pidgin languages, respectively. The size of the speech dataset was 15.6, 17.9, and 18.3KB for English, Yorùbá, and Pidgin languages, respectively. The dataset was harvested with a higher level of annotation used as a baseline from under-resourced multilingual Nigeria speech for antenatal orientation and out-of-domain speech data. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Real-Time Myanmar Hand Gestures Recognition Using Deep Learning Models 8th

Real-Time Myanmar Hand Gestures Recognition Using Deep Learn...

引用

8th International Conference on Intelligent Technologies, ICIT 2023

作者： Kyaw, Nwe Ni Mitra, Pabitra Sinha, G.R. Department of Computer Science and Engineering Indian Institute of Technology Kharagpur West Bengal721302 India Indian Knowledge System Lab International Institute of Information Technology Bangalore Karnataka Bengaluru560100 India

ISBN: (纸本)9789819738588

The proposed system for recognizing Myanmar sign language between individuals who are deaf. The aim of this study is to develop deep learning models for the purpose of accurately identifying dynamic hand gesture images depicting 14 classes of Myanmar words and numbers. The present system utilizes a new dataset comprising 7834 images for 14 classes obtained through Webcam. The objective of this study is to enhance the robustness of the new model. Next, we proceed to evaluate the proposed model by comparing them to those of existing convolutional neural network models. These models are generally recognized as effective deep-learning approaches for recognition tasks. The proposed model exhibits a performance level of 96% for both validation and testing accuracies. Furthermore, the experimental finding demonstrates that the model, convolutional layers, achieved an accuracy of 100% in recognizing Myanmar Sign Language (MSL). © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Architecting Space Microdatacenters: A System-level Approach

Architecting Space Microdatacenters: A System-level Approach

引用

IEEE Symposium on High-Performance computer Architecture

作者： Nathan Bleier Rick Eason Michael Lembeck Rakesh Kumar Department of Electrical Engineering & Computer Science University of Michigan Ann Arbor MI Department of Electrical and Computer Engineering University of Illinois Urbana IL Department of Aerospace Engineering University of Illinois Urbana IL

ISBN: (数字)9798331506476

ISBN: (纸本)9798331506483

Server-based computing in space has been recently proposed due to potential benefits in terms of capability, latency, security, sustainability, and cost. Despite this, there has been no work asking the question: how should we architect systems for server-based computing in space when considering overall cost. This paper presents a Total Cost of Ownership (TCO)-based approach to architecture of server-based computing systems for space (Space Microdatacenters - SμDC) for processing data produced by low Earth orbit (LEO)-based Earth observation (EO) satellites. We show that power of compute is the primary factor in determining SμDC TCO, though the dependence is sublinear. Second, the impact of compute mass, monetary cost, and communication on TCO is relatively insignificant. Third, architectures with the highest $\frac{\text { FLOPs }}{{\mathrm {W}}}$ provide much higher performance per TCO ${\$}$ even if they have poor $\frac{\mathrm{FLOPs}}{\$}$. We leverage these insights to advocate extreme heterogeneity designs for SμDCs. These designs reduce SμDC TCO by 116× in spite of poor $\frac{\mathrm{FLOPs}}{\$}$ characteristics. We also show that (a) collaborative compute constellations — constellations in which EO satellites are also equipped with compute hardware — further improve SμDC TCO by 1.31 to 1.74×, (b) a distributed architecture reduces TCO by 10% over a monolithic architecture, and (c) low monetary cost of compute can be leveraged to provide near zero cost compute overprovisioning which improves an SμDC’s availability significantly and supports graceful degradation. Overall, this is the first paper on cost-aware architecture and optimization of a SμDC.

关键词： Space vehicles Earth Costs Satellites Low earth orbit satellites computer architecture Hardware Security Sustainable development Optimization

来源：评论

学校读者我要写书评

暂无评论

Enhanced Speech Emotion and Gender Recognition Using Hybrid CNN-LSTM Models

Enhanced Speech Emotion and Gender Recognition Using Hybrid ...

引用

Sentiment Analysis and Deep Learning (ICSADL), International Conference on

作者： S Priyadharshini G. Naveen Sundar D. Narmadha Senthil Kumar Thangavel Adeyemi Abel Ajibesin Selvanayaki Kolandapalayam Shanmugam Department of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India Department of Computer Science and Engineering Amrita School of Computing Coimbatore India Department of Information Technology Faculty of Informatics and Design Cape Peninsula University of Technology South Africa Department of Mathematics and Computer Science Ashland University USA

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

The current paper proposes a new approach for peripheral speech emotion analysis and gender estimation incorporating the best machine learning architectures such as CNNs and LSTMs. Its correct depiction of emotions and the variation of the gendered speech to indicate manifold signal-to-noise ratio make the approach accommodate the difficulty inherent in recognizing emotions from the recording of voices as well as predicting the gender of a speaker. It is then able to ally with preprocessing and collection of a vast range of different speech samples, feature extraction of pitch, tone and spectral data. These features serve as input to the CNNs and LSTMs: LSTMs work well at temporal regular features and the CNNs work well in feature extraction by location (spatio feature). The approach is tested on the RAVDESS and IEMOCAP datasets and establishes a near perfect match to prior approaches with reference to recognition accuracy of emotion analysis and gender prediction. Thus, applying the identified dual method approach, which could be described by such characteristics as highly accurate data pre-preprocessing, clear indication of the features of interest, a different CNN-LSTM model joint training, it offers a reasonably good platform to gain certain insights into such characteristics of the speech as our experiment demonstrates. This work offers satisfactory configurations on concerns such as human computer relation, customer relation and mental health surveillance to suggest that other applications could be achieved in future.

关键词： Training Emotion recognition Accuracy Computational modeling Speech recognition Speech enhancement Predictive models Feature extraction Data models Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An Algorithmic Approach to Intrusion Detection in Ad Hoc Wireless Networks Based on Artificial Intelligence

An Algorithmic Approach to Intrusion Detection in Ad Hoc Wir...

引用

Intelligent Control, Computing and Communications (IC3), International Conference on

作者： Shrikant V. Sonekar Pravin R. Kshirsagar Bhuvan Unhelkar Prasun Chakrabarti Balajee Maram Kamal Upreti Department of Computer Science & Engineering J D College of Engineering & Management Nagpur India Department of Electronics & Telecommunication Engineering J D College of Engineering & Management Nagpur India Department of Infornation Systems and Decision Sciences Muma College of Business University of South Florida Sarasata USA Department of Computer Science & Engineering Sir Padampat Singhania University Udaipur Rajasthan India Department of Computer Science and Artificial Intelligence SR University Warangal Telangana Department of Computer Science Christ University Ghaziabad India

ISBN: (数字)9798331527495

ISBN: (纸本)9798331527501

The self-configured, autonomous, and framework-free modes of communication that mobile adhoc networks (MANETs) offer have revolutionized our culture. As a result, efforts have been made to explore ways to maximize the potential of MANETs through increased and improved utilization. Standards for AI have been developed thanks to the most recent release of new machine learning technologies. Different security-related issues from malware assaults affect mobile ad hoc networks (MANETs). Any node operates as a router to move data without centralized control, making nodes more vulnerable to threats from other nodes or attackers because of their brief existence. Because of this, MANET needs particular security policies to detect the incorrect entrance of misbehaving nodes. If all nodes are self-assured and correctly collaborate, the networks function better. The paper presents a practical artificial intelligence algorithm-based security system that uses AdaBoost and DT algorithms to recognize and identify packet falling nodes, classify information packets as normal or abnormal, and detect insider threats in real-time. The results showed that DT performed better than AdaBoost, with a 98% accurate prediction rate. Consequently, DT is better able to recognize damaging attacks in MANETs.

关键词： Accuracy Wireless networks Computational modeling Prediction algorithms Throughput Ad hoc networks Mathematical models Classification algorithms Security Mobile computing

来源：评论

学校读者我要写书评

暂无评论

Development and implementation of an autonomous vehicle prototype with ADAS

Development and implementation of an autonomous vehicle prot...

引用

International Conference on Energy, Power, Environment, Control and Computing (ICEPECC 2025)

作者： Ahmed Mohamed Hassan Ahmed Fatima N. Al-Aswadi Ghassan Saleh AlDharhani Osama M. I. Hamad Zahid Iqbal Institute of Computer Science & Digital Innovation UCSI University Kuala Lumpur 56000 Malaysia Electronics & Computer Systems Engineering University of Science and Technology Khartoum Sudan Department of Computer Science Air University Kharian Pakistan

ISBN: (数字)9781837243150

Road traffic accidents are a significant global issue, resulting in considerable fatalities and injuries each year. The United Nations aims to decrease such incidences by 50% by 2030. Advanced Driver Assistance Systems (ADAS) provide a revolutionary solution; yet, their implementation is predominantly restricted to high-priced electric vehicles, limiting their influence to affluent markets. This study advocates for a paradigm shift by showcasing the viability of an economical autonomous vehicle prototype integrated with ADAS capabilities, created using cost-efficient and readily available technology. The prototype used a Raspberry Pi as the core computing unit, incorporating ultrasonic sensors for obstacle detection, a GPS module for navigation, and a camera for traffic signal recognition. These components, while more basic and far less costly than those in premium automobiles, effectively provide essential functions such as automated braking, GPS navigation, and adherence to traffic signals. The project employs an Agile approach, enabling iterative development and swift responsiveness to input. This research demonstrates the potential of democratising ADAS technology to provide safer, smarter automobiles to under-represented socioeconomic groups. Future developments could enhance the system’s precision by integrating advanced sensors, such as LiDAR and radar, while maintaining cost-effectiveness, fostering inclusive innovation in vehicle safety.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Quantum Analysis of LESCA

Quantum Analysis of LESCA

引用

International Conference on VLSI Design

作者： Sumanta Chakraborty Debajyoti Mandal SK Hafizul Islam Department of Computer Science and Engineering Techno International New Town Kolkata West Bengal India Department of Computer Science and Engineering Indian Institute of Information Technology Kalyani Kalyani West Bengal India

ISBN: (数字)9798331522445

ISBN: (纸本)9798331522452

This paper explores the complexity measurements of applying Grover's search algorithm on a dynamic, key-dependent, lightweight stream cipher, LESCA (LightwEight Stream Cipher Algorithm). For this purpose, we present our algorithms to implement LESCA in quantum paradigm, probably the first, to the best of our knowledge. After that, we provide the cost measurements of the quantum implementation of LESCA and the quantum cost for applying Grover's search on LESCA. We show that LESCA meets the quantum security levels 1, 3, and 5 defined by National Institute of Standards and Technology (NIST).

关键词： Ciphers Costs Quantum computing Embedded systems Heuristic algorithms NIST Very large scale integration Complexity theory Security

来源：评论

学校读者我要写书评

暂无评论

Advanced Course Equivalence Certification Using NLP Technology through Word Mover's Distance in Global Academic Credit Transfers

Advanced Course Equivalence Certification Using NLP Technolo...

引用

International Conference on Electronics, Materials engineering and Nano-Technology (IEMENTech)

作者： Sumathy Krishnan Surendran R Poornima Jayaraman Sathish Kumar P. J Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Department of Electronics and Communication Engineering Chennai Institute of technology Chennai India Department of Computer Science and Engineering Panimalar Engineering College Chennai India

ISBN: (数字)9798331520762

ISBN: (纸本)9798331520779

As the competition for higher education and professional employment intensifies globally, the proper evaluation and translation of academic credits and qualification systems has taken on a key significance. Most classic techniques for evaluating the contents of equivalence course certificates, such as Jaccard Index or Cosine, are too simplistic and do not reveal differences in educational credentials or course materials that are found at a semantically deeper structure. These techniques are primarily based on the surface-level characteristics of the texts, ignoring their inherent pictures. To overcome these challenges, this paper considers the possibility of using methods of Natural Language Processing (NLP), especially Word Mover's Distance, in the context of higher education and professional qualification, academic credit and course equivalency evaluation. WMD, or Word Mover's Distance, is a more sophisticated method of NLP, which describes the food transport distance problem and searches for the optimal distance between two different documents. The advantages of this methodology lie in comparing the course description and qualifications from a different perspective without losing the true meaning of these words in relation to course equivalence certificate comparison. On the basis of our study, we can state that WMD implements better than other conventional approaches and is an appealing solution for credit system transfer, the degree equivalence process evaluation in higher education, and employment clearance services. In this way, WMD applications for NLP purposes will allow for the sustainable recognition of the international qualifications of professionals and students, thus enhancing their movement across borders.

关键词： Translation Text analysis Education Employment Semantics Search problems Natural language processing Reliability Surface treatment Qualifications

来源：评论

学校读者我要写书评

暂无评论

Converging to a Lingua Franca: Evolution of Linguistic Regions and Semantics Alignment in Multilingual Large Language Models 31

Converging to a Lingua Franca: Evolution of Linguistic Regio...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Zeng, Hongchuan Han, Senyu Chen, Lu Yu, Kai X-LANCE Lab Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence SJTU AI Institute Shanghai Jiao Tong University Shanghai China Suzhou Laboratory Suzhou China

ISBN: (纸本)9798891761964

Large language models (LLMs) have demonstrated remarkable performance, particularly in multilingual contexts. While recent studies suggest that LLMs can transfer skills learned in one language to others, the internal mechanisms behind this ability remain unclear. We observed that the neuron activation patterns of LLMs exhibit similarities when processing the same language, revealing the existence and location of key linguistic regions. Additionally, we found that neuron activation patterns are similar when processing sentences with the same semantic meaning in different languages. This indicates that LLMs map semantically identical inputs from different languages into a "Lingua Franca", a common semantic latent space that allows for consistent processing across languages. This semantic alignment becomes more pronounced with training and increased model size, resulting in a more language-agnostic activation pattern. Moreover, we found that key linguistic neurons are concentrated in the first and last layers of LLMs, becoming denser in the first layers as training progresses. Experiments on BLOOM and LLaMA2 support these findings, highlighting the structural evolution of multilingual LLMs during training and scaling up. This paper provides insights into the internal workings of LLMs, offering a foundation for future improvements in their cross-lingual capabilities. The codes are available at: https://***/X-LANCE/LinguaFranca. © 2025 Association for Computational Linguistics.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

ValidCertify: an effective blockchain-based domain certificate authentication and verification scheme

引用

Peer-to-Peer Networking and Applications 2025年第4期18卷 1-18页

作者： Kadam, Priyanka Amol Bhushan, Shashi Rishiwal, Vinay Yadav, Mano Yadav, Preeti Agarwal, Udit Department of Computer Engineering Smt. Kashibai Navale College of Engineering Pune India Department of Computing Universiti Teknologi PETRONAS Seri Iskandar Malaysia Department of CSIT MJP Rohilkhand University Bareilly India Department of Computer Science Bareilly College Bareilly India

Certificate verification is a fundamental component of Public Key Infrastructure (PKI), ensuring that digital certificates provided by Certificate Authorities (CAs) are both valid and trustworthy. The process involves authenticating a certificate by tracing it through a "chain of trust, " which ultimately leads to a trusted root CA. A certificate is deemed valid when it successfully chains back to a recognized root authority, allowing users to trust the information provided by the certificate holder. PKI relies on a centralized trust model where CAs are responsible for issuing and managing certificates. If a CA is compromised, attackers can issue fraudulent certificates, enabling them to impersonate legitimate entities or intercept sensitive communications. This breach could disrupt the integrity of the entire trust model, highlighting the risks associated with the centralized nature of PKI systems. As a result, ensuring the security and reliability of the certificate issuance process is crucial to maintaining the overall trustworthiness of digital communications and transactions within PKI frameworks. In this research, the authentication and verification of the certificate using the blockchain-based domain, named the ValidCertify approach, are proposed, which illustrates the reliable and effective method for the certificate authentication of users. The four significant phases of blockchain-based secured domain certificate authentication and verification are user registration, domain authentication, certificate issuance, and token generation. The certificate authority plays a vital role between the domain and the block header, and the new blocks generated during every communication are placed in the block header through blockchain technology. After verifying the domain request for certificate authentication, the certificate authority verifies the security factor of both the validator and the user for acceptance. Compared to the state-of-the-art, the ValidCertify met

关键词：

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：