检索结果-内蒙古大学图书馆

1st IEEE International Conference on Applied Intelligence and Sustainable Computing, ICaiSC 2023

作者： Kumar, M Vinod Ramesh, G.P. Pareek, Piyush Kumar Deepak, H.A. Babu, J. Ananda St. Peter's Institute of Higher Education and Research Department of Electronics and Communication Engineering Chennai India Nitte Meenakshi Institute of Technology Department of AI & ML Bengaluru India Navkis College of Engineering Department of ECE Hassan India Malnad College of Engineering Department of Information Science and Engineering Hassan India

ISBN: (纸本)9798350323795

Facial recognition is one example of the ways in which computer vision is being applied in modern, people-oriented utility apps. Facial recognition technology has improved in recent years, but it still lags behind other biometric authentication methods such as fingerprint and iris scanning or Radio Frequency Identification (RFID) cards in terms of accuracy. However, it is still frequently utilised due to the fact that the recognition procedure does not involve touching the device in any way. This research takes advantage of advances in facial recognition technology to offer an embedded device integrated ai and IoT-based automated attendance solution for use in smart classrooms. This study uses the ResNet architecture to explore a deep learning classification method for identifying student attendance. In this research, we used facial photos from students to train ResNet-18 and ResNet-50. Models educated to differentiate regular from irregular student attendance. Our photos were evaluated on 20%, 25%, and 40% of simulated and real-world datasets, respectively. Results from three types of testing data show that ResNet-50 outperforms ResNet-18 in rapports of accuracy, F1-measure, and mean accuracy value. This study makes use of the FER2013 dataset for labelling faces, as well as real-time student faces. This study uses a deep learning approach to show how dependable and repeatable student image analysis © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Optimizing Brain Tumor Segmentation with Advanced Superpixel Techniques in Conjunction with Deep Learning Methods

Optimizing Brain Tumor Segmentation with Advanced Superpixel...

引用

2023 International Conference on Evolutionary Algorithms and Soft Computing Techniques, EASCT 2023

作者： Chythanya, Kanegonda Ravi Aruna, S. Karuppaiah, Jayakumar Arul, S. Benjamin Kumar Pareek, Piyush Sr University School of Computer Science & Artificial Intelligence Warangal India Srmist Dept. of Computational Intelligence Chennai India KIT- Kalaignarkarunanidhi Institute of Technology Department of Biomedical Engineering Coimbatore India School of Engineering and Technology Jeppiaar University Chennai India Nitte Meenakshi Institute of Technology Department of Ai and Ml Bengaluru India

ISBN: (纸本)9798350313413

Brain tumor segmentation in medical imaging is crucial for precise diagnosis and treatment planning. To address these issues, our research leverages deep learning techniques and introduces an innovative approach that combines various key components. Our methodology includes preprocessing, superpixel segmentation, feature extraction, and the use of a Convolutional Neural Network (CNN) to achieve precise brain tumor segmentation. This approach is driven by the necessity for improved accuracy and efficiency, especially with diverse clinical data and tumor types, like the challenging BraTS 2018 dataset, consisting of 1070 T1W-CE MRI images. This approach using metrics such as the Dice score, sensitivity, and specificity, which demonstrate the superior performance of our superpixel model in brain tumor segmentation. This proposed method yields exceptional results, with a Dice score of 97.06%, sensitivity of 99.05%, and specificity of 99.83%, highlighting its accuracy and effectiveness in tumor segmentation when compared to existing methods such as UNet, Kapur entropy, and rough set theory. This research significantly advances the state of the art and offers great promise for enhancing medical image analysis in this critical field. © 2023 IEEE.

关键词： Brain tumor Convolutional Neural Network Deep Learning Superpixel technique Tumor segmentation

来源：评论

学校读者我要写书评

暂无评论

Fake News Detection using Machine Learning Algorithms

Fake News Detection using Machine Learning Algorithms

引用

New Frontiers in Communication, Automation, Management and Security (ICCAMS), International Conference on

作者： Tina Babu Rekha R Nair Adithya Challa Rahul Srikanth Sri Sai Aravindan Suhas S Department of Computer Science and Engineering Alliance Univerity Bengaluru India Department of Computer Science & Engineering (Data Science) School of Engineering Dayananda Sagar Univerity Bengaluru India Department of Computer Science & Engineering (AI & ML) School of Engineering Dayananda Sagar Univerity Bengaluru India

ISBN: (数字)9798350317060

ISBN: (纸本)9798350317077

The spread of false news threatens news and information sources, especially in Indian politics. We present a machine learning-based strategy to identify false news by vectorizing and tokenizing news headlines using a pre-defined dataset of authentic and fraudulent news items. We want to create a model that can properly identify news stories by textual content, separating propaganda from real news. Our technique is tested on a benchmark dataset of news items. Our suggested technique outperforms various state-of-the-art false news detection algorithms in the literature. Our methodology can prevent false news and safeguard news and information sources in Indian politics. This technique is versatile and successful for identifying and reducing the impact of false news across several topics and languages.

关键词： Machine learning algorithms Limiting Detectors Forestry Graph theory Security Labeling

来源：评论

学校读者我要写书评

暂无评论

Future Communication Technology Using Huge Millimeter Waves - An Overview 1

Future Communication Technology Using Huge Millimeter Waves ...

引用

1st International Conference on Computational Intelligence, Communication Technology and Networking, CICTN 2023

作者： Salama, Ramiz Al-Turjman, Fadi Chaudhary, Preeti Banda, Latha Near East University Ai and Robotics Institute Research Center for Ai and IoT Department of Computer Engineering Nicosia Turkey Near East University Ai and Robotics Institute Artificial Intelligence Engineering Dept. Nicosia Turkey University of Kyrenia Research Center for Ai and IoT Faculty of Engineering Kyrenia Turkey Graphic Era Hill University Computer Science and Engineering Dehradun India Abes Engineering College Ghaziabad India

ISBN: (纸本)9798350338027

Frequency selective surface (FSS) was first created by G. Marconi and C. S. Franklin in 1919 and is known as the "Reflector for Wireless Telegraph and Telephone,"making a significant contribution to our way of life. In terms of the 1960s, it is impossible to overlook the success attained with the employment of regularly selective surfaces in military intelligence units. These structures, which were occasionally applied to land, air, and sea platforms, displayed low pass, high pass, band pass, or band stop characteristics for particular frequencies and served as electromagnetic filters. Many accomplishments have been made, particularly with platforms that are invisible to target detection systems. The geometry and arrangement of the unit cell in these structures, which are successfully used in many fields such as wireless communication systems, radars, and microwaves, allows for the reflection or transmission of the incoming electromagnetic wave. This is made possible by the advancement of technology. High-speed internet connectivity is possible using millimeter wave, a frequency spectrum between 30 GHz and 300 GHz. Its significance has grown in the fields of radio astronomy, radar, remote sensing, and wireless communications. © 2023 IEEE.

关键词： Millimeter waves

来源：评论

学校读者我要写书评

暂无评论

Adversarial learning for Mirai botnet detection based on long short-term memory and XGBoost

引用

International Journal of Cognitive Computing in engineering 2024年第1期5卷 153-160页

作者： Vajrobol, Vajratiya Gupta, Brij B. Gaurav, Akshat Chuang, Huan-Ming Institute of Informatics and Communication University of Delhi India International Center for AI and Cyber Security Research and Innovations. Asia University Taiwan Department of Computer Science and Information Engineering Asia University Taichung413 Taiwan Ronin Institute MontclairNJ United States Department of Information Management National Yunlin University of Science and Technology Yunlin Taiwan Symbiosis International University Pune India Department of Electrical and Computer Engineering Lebanese American University Beirut1102 Lebanon Dehradun India

In today's world, where digital threats are on the rise, one particularly concerning threat is the Mirai botnet. This malware is designed to infect and command a collection of Internet of Things (IoT) devices. The use of Mirai attacks has intensified in recent times, thus threatening the smooth operation of numerous devices that are connected to a network. Such attacks carry adverse consequences that include interference with services or the leakage of confidential information. To fight this growing threat, smart and flexible detection techniques are required to counter the new methods cyber attackers use. The aim of this research is to develop a resilient defense against Mirai botnet attacks. The Long Short Term Memory term (LSTM) and XGBoost combined have the best performance of 97.7% accuracy score. With this combination, the aim is to strengthen our cyber defenses against sophisticated and dynamically operating Mirai botnets to further enhance the security of our digital world. © 2024

关键词： Botnet

来源：评论

学校读者我要写书评

暂无评论

A Case Study on Context Encoding in Multi-Encoder based Document-Level Neural Machine Translation 19

A Case Study on Context Encoding in Multi-Encoder based Docu...

引用

19th Machine Translation Summit, MT Summit 2023

作者： Appicharla, Ramakrishna Gain, Baban Pal, Santanu Ekbal, Asif Department of Computer Science and Engineering Indian Institute of Technology Patna Patna India Wipro AI Lab45 London United Kingdom

Recent studies have shown that the multi-encoder models are agnostic to the choice of context, and the context encoder generates noise which helps improve the models in terms of BLEU score. In this paper, we further explore this idea by evaluating with context-aware pronoun translation test set by training multi-encoder models trained on three different context settings viz, previous two sentences, random two sentences, and a mix of both as context. Specifically, we evaluate the models on the ContraPro test set to study how different contexts affect pronoun translation accuracy. The results show that the model can perform well on the ContraPro test set even when the context is random. We also analyze the source representations to study whether the context encoder generates noise. Our analysis shows that the context encoder provides sufficient information to learn discourse-level information. Additionally, we observe that mixing the selected context (the previous two sentences in this case) and the random context is generally better than the other settings. © 2023 The authors. This article is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0)

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Epic-Sounds: A Large-Scale Dataset of Actions that Sound 48

Epic-Sounds: A Large-Scale Dataset of Actions that Sound

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Huh, Jaesung Chalk, Jacob Kazakos, Evangelos Damen, Dima Zisserman, Andrew University of Oxford Visual Geometry Group Department of Engineering Science United Kingdom University of Bristol Department of Computer Science United Kingdom Samsung Ai Center Cambridge United Kingdom

ISBN: (纸本)9781728163277

We introduce EPIC-SOUNDS, a large-scale dataset of audio annotations capturing temporal extents and class labels within the audio stream of the egocentric videos from EPIC-KITCHENS-100. We propose an annotation pipeline where annotators temporally label distinguishable audio segments and describe the action that could have caused this sound. We identify actions that can be discriminated purely from audio, through grouping free-form descriptions into classes. For actions that involve objects colliding, we collect human annotations of the materials of these objects (e.g. a glass object being placed on a wooden surface), which we verify from visual labels, discarding ambiguities. Overall, EPIC-SOUNDS includes 78.4k categorised segments of audible events and actions, distributed across 44 classes, as well as 39.2k non-categorised segments, totalling 117.6k segments spanning 100 hours of audio, capturing diverse actions that sound in home kitchens. We train and evaluate two state-of-the-art audio recognition models on our dataset, highlighting the importance of audio-only labels and the limitations of current models to recognise actions that ***-SOUNDS and baseline source code is available from: https://***/epic-sounds. © 2023 IEEE.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

CLEVA: Chinese Language Models EVAluation Platform

CLEVA: Chinese Language Models EVAluation Platform

引用

2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, EMNLP 2023

作者： Li, Yanyang Zhao, Jianqiao Zheng, Duo Hu, Zi-Yuan Chen, Zhi Su, Xiaohui Huang, Yongfeng Huang, Shijia Lin, Dahua Lyu, Michael R. Wang, Liwei Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Department of Information Engineering The Chinese University of Hong Kong Hong Kong Shanghai AI Laboratory China

With the continuous emergence of Chinese Large Language Models (LLMs), how to evaluate a model’s capabilities has become an increasingly significant issue. The absence of a comprehensive Chinese benchmark that thoroughly assesses a model’s performance, the unstandardized and incomparable prompting procedure, and the prevalent risk of contamination pose major challenges in the current evaluation of Chinese LLMs. We present CLEVA, a user-friendly platform crafted to holistically evaluate Chinese LLMs. Our platform employs a standardized workflow to assess LLMs’ performance across various dimensions, regularly updating a competitive leaderboard. To alleviate contamination, CLEVA curates a significant proportion of new data and develops a sampling strategy that guarantees a unique subset for each leaderboard round. Empowered by an easy-to-use interface that requires just a few mouse clicks and a model API, users can conduct a thorough evaluation with minimal coding. Large-scale experiments featuring 23 Chinese LLMs have validated CLEVA’s efficacy. Our GitHub repo is https://***/LaVi-Lab/CLEVA. © 2023 Association for Computational Linguistics.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Exploring Time-Frequency Domain Target Speaker Extraction For Causal and Non-Causal Processing

Exploring Time-Frequency Domain Target Speaker Extraction Fo...

引用

2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023

作者： Zhang, Wangyou Yang, Lei Qian, Yanmin Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence Ai Institute Department of Computer Science and Engineering Shanghai China China

ISBN: (纸本)9798350306897

In recent years, target speaker extraction (TSE) has drawn increasing interest as an alternative to speech separation in realistic applications. While time-domain methods have been widely used in recent studies to achieve high performance, the potential of time-frequency (T-F) domain methods have been less explored. In this paper, we try to fill this gap and propose to incorporate the top-performing T-F domain speech separation method into the TSE framework. We first explore different speaker information fusion methods for the proposed model. In addition to the commonly-used concatenation based fusion, we propose a novel speaker token-based fusion method to fuse the target speaker information. Second, we show that the proposed model can be easily extended for causal processing with strong performance. Experiments on the WSJ0-2mix and LibriMix benchmarks show that our proposed model outperforms the widely-used time-domain models in both causal and non-causal settings by a large margin. © 2023 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Skeletal Fragility Detection using Deep Learning

Skeletal Fragility Detection using Deep Learning

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： K. Rama Krishna Reddy V. Sravya Reddy V. Sriram Sathvik N. Muthukumaran Shaik Mahaboob Subhani Department of Computer Science and Engineering (AI & ML) Vignan Institute of Technology and Science Nalgonda Telangana Department of ECE Centre for Computational Imaging and Machine Vision Sri Eshwar College of Engineering Coimbatore Tamil Nadu India

ISBN: (数字)9798350359299

ISBN: (纸本)9798350359305

In the field of diagnosing health there has been a shift, in focus from simply identifying bone fractures to a broader evaluation of skeletal fragility. Skeletal fragility involves not detecting fractures but also assessing the health and resilience of the skeletal system, which is crucial for preventing future fractures. While an automated network (DNN) model has achieved impressive accuracy of 92.44% in distinguishing between healthy and fractured bones iti s important to consider additional factors when measuring skeletal fragility. These supplementary factors include bone density, composition, and comprehensive markers of bone health like vitamin D levels. To create a framework for assessing skeletal fragility and not just bone fractures it is necessary to expand the model’s scope by incorporating these essential additional factors and indicators. This holistic approach has the potential to provide a nuanced perspective, on bone health and the likelihood of future fractures. Ultimately this can significantly improve care by facilitating measures.

关键词： Deep learning Image processing Noise Surgery Manuals Bones Data augmentation

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：