检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Tiwari, Abhisek Bera, Shreyangshu Saha, Sriparna Bhattacharyya, Pushpak Ghosh, Samrat Dept. of Computer Science and Engineering Indian Institute of Technology Patna India Dept. of Computer Science and Engineering Indian Institute of Technology Bombay India

Over the past few years, the use of the Internet for healthcare-related tasks has grown by leaps and bounds, posing a challenge in effectively managing and processing information to ensure its efficient utilization. During moments of emotional turmoil and psychological challenges, we frequently turn to the internet as our initial source of support, choosing this over discussing our feelings with others due to the associated social stigma. In this paper, we propose a new task of multi-modal medical concern summary (MMCS) generation, which provides a short and precise summary of patients' major concerns brought up during the consultation. Nonverbal cues, such as patients' gestures and facial expressions, aid in accurately identifying patients' concerns. Doctors also consider patients' personal information, such as age and gender, in order to describe the medical condition appropriately. Motivated by the potential efficacy of patients' personal context and visual gestures, we propose a transformer-based multi-task, multi-modal intent-recognition, and medical concern summary generation (IR-MMCSG) system. Furthermore, we propose a multitasking framework for intent recognition and medical concern summary generation for doctor-patient consultations. We construct the first multi-modal medical concern summary generation (MM-MediConSummation) corpus, which includes patient-doctor consultations annotated with medical concern summaries, intents, patient personal information, doctor's recommendations, and keywords. Our experiments and analysis demonstrate (a) the significant role of patients' expressions/gestures and their personal information in intent identification and medical concern summary generation, and (b) the strong correlation between intent recognition and patients' medical concern summary generation3 © 2024, CC BY-NC-ND.

关键词： Multitasking

来源：评论

学校读者我要写书评

暂无评论

A catalogue of game-specific anti-patterns 2022

A catalogue of game-specific anti-patterns

引用

15th Innovations in Software engineering Conference, ISEC 2022

作者： Agrahari, Vartika Chimalakonda, Sridhar Lab Dept. of Computer Science and Engineering Indian Institute of Technology Tirupati India

ISBN: (纸本)9781450396189

With the ever-increasing use of games, game developers are expected to write efficient code and support several aspects such as security, maintainability, and performance. However, the continuous need to update the features of games in shorter duration might compel the developers to use anti-patterns, code smells and quick-fix solutions that may affect the functional and non-functional requirements of the game. These bad practices may lead to technical debt, poor program comprehension, and can cause several issues during software maintenance. While there exists empirical research on games, we are not aware of any work on understanding and cataloguing these anti-patterns in the domain of games. Thus, in this paper, we propose a catalogue of game-specific anti-patterns by mining and analyzing 892 commits, 189 issues, and 104 pull requests from 100 open-source GitHub game repositories. We use regular expressions and thematic analysis on this dataset and present a catalogue of ten game-specific anti-patterns along with examples. We see this catalogue as a first step for further empirical research in the domain of games and can help game developers to improve quality of games. © 2022 ACM.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Runtime Detection of Time-Delay Security Attack in System-An-Chip 15

Runtime Detection of Time-Delay Security Attack in System-An...

引用

15th IEEE/ACM International Workshop on Network on Chip Architectures, NoCArc 2022

作者： Rajan, Manju Choksey, Mayank Jose, John Indian Institute of Technology Dept. of Computer Science and Engineering Assam Guwahati India

ISBN: (数字)9781665455893

ISBN: (纸本)9781665455893

Soft real-Time applications, including multimedia, gaming, and smart appliances, rely on specific architectural characteristics to deliver output in a time-constrained fashion. Any violation of application deadlines can lower the Quality-of-Service (QoS). The data sets associated with these applications are distributed over cores that communicate via Network-on-Chip (NoC) in multi-core systems. Accordingly, the response time of such applications depends on the worst-case latency of request/reply packets. A malicious implant such as Hardware Trojan (HT) that initiates a delay-of-service attack can tamper with the system performance. We model an HT that mounts a time-delay attack in the system by violating the path selection strategy used by the adaptive NoC router. Our analysis shows that once activated, the proposed HT increases the packet latency by 17% and degrades the system performance (IPC) by 18% over the Baseline. Furthermore, we propose an HT detection framework that uses packet traffic analysis and path monitoring to localise the HT. Experiment results show that the proposed detection framework exhibits 4.8% less power consumption and 6.4% less area than the existing technique. © 2022 IEEE.

关键词： Network-on-chip

来源：评论

学校读者我要写书评

暂无评论

ARIA: Augmented Reality and Artificial Intelligence enabled mobile application for Yield and grade prediction of tomato crops 2

ARIA: Augmented Reality and Artificial Intelligence enabled ...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Balaji Prabhu, B.V. Shashank, R. Shreyas, B. Jois Narsipura, Omkar Subbaram Malnad College of Engineering Hassan Visvesvaraya Technological University Belagavi573202 India Dept. of Computer Science Viterbi School of Engineering University of Southern California Los Angeles90007 United States Dept. of Computer Science and Engineering RNS Institute of Technology Bangalore560098 India Dept. of Aerospace Engineering Indian Institute of Science Bangalore560012 India

Agriculture is the most crucial sector of the indian economy. Lately, there has been a surge in the usage of technologies like deep learning and computer vision to make the process of agriculture modern and consequently, lessening the mistakes related to conventional processes. This work delivers a user-friendly, accessible, and novel approach for the detection, counting, and grading of tomatoes found on a farm. An Augmented Reality (AR) based mobile application is developed to obtain the images efficiently from a tomato farm in the pre-harvest stage subjected to open situations. The proposed approach uses Faster RCNN, a convolutional neural network model for detection of tomatoes from the input image on a large scale. The proposed model is trained and tested using 2083 images. The results are then analyzed for the overall performance of detection, segmentation, and classification of tomatoes. The results have examined the efficiency of the proposed mobile application and demonstrate the robustness it exhibits for the detection, grading and yield prediction of Tomatoes. © 2024 Elsevier B.V.. All rights reserved.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Image Denoising based on Multi Domain Feature Inspired Convolutional Neural Network

Image Denoising based on Multi Domain Feature Inspired Convo...

引用

2022 IEEE Region 10 International Conference, TENCON 2022

作者： Thakur, Ramesh Kumar Maji, Suman Kumar Indian Institute of Technology Patna Dept. of Computer Science and Engineering Patna India

ISBN: (数字)9781665450959

ISBN: (纸本)9781665450959

Blind Gaussian denoising is the process of removing noise from an image affected by additive white Gaussian noise (AWGN) of unknown variance. This paper proposes a multi domain feature inspired deep neural network for blindly (noise variance unknown) denoising AWGN corrupted images. The proposed network uses features of the noisy image in both spatial domain as well as frequency (discrete cosine transform) domain. Spatial and frequency domain features are concatenated to get a combined feature map from which we generate the residual noisy image. The residual noise is then subtracted from the input noisy image to obtain the final denoised image. By restricting the number of layers and trainable parameters in the proposed network, we ensure that it is lightweight in nature and provides fast denoising capability. Comparison with classical state-of-the-art methods and recent CNN based denoising approaches show that the proposed network gives superior denoising results both visually and quantitatively. Our code is uploaded at https://***/RTSIR/MDFBGDN. © 2022 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Dynamic Fencing for Interference Mitigation in Integrated Satellite-Terrestrial Networks

Dynamic Fencing for Interference Mitigation in Integrated Sa...

引用

2022 IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2022

作者： Khan, Aman Kherani, Nomaan Alam Baswade, Anand M. Indian Institute of Technology Dept. of Electrical Engineering and Computer Science Bhilai India

ISBN: (纸本)9781665473408

Integrated Satellite-Terrestrial Network (ISTN) is one of the promising approaches for global wireless connection in 5th Generation (5G) and beyond networks. The integration of terrestrial and non-terrestrial networks open a wide range of opportunities in the networking domain. Though the integrated system has numerous benefits, it also has various challenges including the interference caused by the different networks, (satellite and terrestrial) sharing the same frequency band. The interference between both the networks degrades the performance of integrated network communication systems. This paper presents a scenario for integrated satellite and terrestrial networks (ISTN) and proposes a novel solution for interference management by coordinating satellite and terrestrial networks in order to minimize interference and enhance the overall throughput of the integrated network. To address this issue, a dynamic fencing mechanism is applied where a fence is created for a time slot to provide fairness to the victim users getting affected by the severe interference. © 2022 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

YOLO Dietician

YOLO Dietician

引用

Applied Artificial Intelligence and Computing (ICAAIC), International Conference on

作者： Sirikonda Vaishnavi Sanne Hruthika Shetty M Maheswari J.L. Jany Shabu J. Refonaa Department of CSE Sathyabama Institute of Science and Technology Chennai India Dept.of Computer Science and Engineering Sathyabama Institute of Science and Technology

ISBN: (数字)9798350375190

ISBN: (纸本)9798350375206

In recent years, the integration of Artificial Intelligence (AI) in healthcare has attracted a lot of attention, particularly in the domain of personalized nutrition. With the rising prevalence of diet-related health issues such as obesity, diabetes, and cardiovascular diseases, the primary objective of this research study is to design and implement a platform capable of analyzing individual preferences, nutritional needs, health goals, and lifestyle factors to offer customized dietary guidance and management. This research study proposes a AI Dietician by utilizing AI algorithms to provide personalized dietary recommendations. This study also covers the technical aspects and methods used in creating a AI dietician, including feature extraction, algorithm selection, data gathering strategies, and model training by ultimately contributing to the prevention of diet-related health issues and promoting long-term health outcomes.

关键词： YOLO Training Obesity Medical services Feature extraction Data models Diabetes

来源：评论

学校读者我要写书评

暂无评论

Synchrosqueezed Wavelet transform Based Power Quality Disturbance Detection and Monitoring of Solar Integrated Micro-Grid 2

Synchrosqueezed Wavelet transform Based Power Quality Distur...

引用

2nd International Conference on Power Electronics and Energy, ICPEE 2023

作者： Pattanaik, Debasish Swain, Sarat Chandra Samanta, Indu Sekhar Rout, Ullash Kumar Dash, Ritesh Swain, Kunjabihari Kiit Deemed to Be University School of Electrical Engineering Bhubaneswar India Iter Soa University Dept.of Computer Science and Engineering Bhubaneswar India Odisha University of Technology and Research Dept. of Electrical Engineering Bhubaneswar India Reva University Dept.of Electrical and Electronics Engineering Bangalore India Nist Institute of Science and Technology Dept. of Electrical and Electronics Engineering Berhampur India

ISBN: (纸本)9781665470582

Microgrid monitoring has gained popularity in recent years, owing to their popularity and the power quality disturbances (PQD) caused by renewable energies. Many artificial intelligence-based PQD monitoring strategies have been proposed by researchers. This paper presents a novel method for detecting, classifying and monitoring the power quality disturbances in solar integrated microgrids. Power quality events are detected by analysing the frequency signal with the wavelet synchro-squeezing transform (WSST). The features of power quality disturbances are used to classify them. For PQD classification, the retrieved features are fed into a Convolutional neural network (CNN) classifier, using GoogLeNet and SqueezeNetfier. Thus the accuracy was found to be 99.90% and 93.76% respectively. © 2023 IEEE.

关键词： Artificial Neural Network Convolutional Neural Network GoogLeNet neural network Innovation Micro Grid Power Quality Disturbances Renewable Energy Sources Wavelet synchro-squeezing transform

来源：评论

学校读者我要写书评

暂无评论

FReNG: Federated Optimization by Using Regularized Natural Gradient Descent 22

FReNG: Federated Optimization by Using Regularized Natural G...

引用

22nd IEEE International Conference on Machine Learning and Applications, ICMLA 2023

作者： Sen, Mrinmay Gayatri, C. Indian Institute of Technology Hyderabad Dept. of Artificial Intelligence Hyderabad India Mahindra University Dept. of Computer Science and Engineering Hyderabad India

ISBN: (纸本)9798350345346

Federated learning (FL) is an important area in machine learning that addresses the challenges of distributed data by collaboratively training a global model. One major issue with FL is the increased communication rounds or FL iterations between the server and the participating data sources or clients, which is caused by the presence of heterogeneous data across all the clients. To address this issue, this paper introduces FReNG, which utilizes regularized natural gradient descent with exponential moving average of the global gradient on the server. The server-based utilization of regularized natural gradient descent and exponential moving average of the global gradient leads to faster convergence of the global model in heterogeneous settings without additional local space and computational complexities, resulting in comparatively fewer communication rounds, while achieving the targeted accuracy from the global model. As FReNG uses regularized natural gradient descent, it can directly compute the update step without calculating and storing the full Fisher information matrix (FIM), which is one of the key advantage of FReNG. Extensive experimental results on image classification tasks using various heterogeneously partitioned datasets show that FReNG outperforms existing state-of-the-art FL algorithms such as FedProx, SCAFFOLD & FedInit and can compete with other state-of-the-art FL algorithms, FedGA, & DONE (with less per FL iteration communication cost & less local time complexity) in terms of reduced communication rounds, while achieving a certain precision of convergence and a targeted test accuracy from the global model. © 2023 IEEE.

关键词： exponential moving average of gradient federated learning increased communication rounds natural gradient descent slow convergence

来源：评论

学校读者我要写书评

暂无评论

Face Recognition Using openCV- use case on student attendance system

Face Recognition Using openCV- use case on student attendanc...

引用

International Conference on Computing and Networking technology (ICCNT)

作者： Anjan Kumar Kamalapur Begari Srikanth Asari Shivadeep Yadav Bachhanaboni Yashwanth Vivek Duraivelu Dept.of Computer Science Engineering B V Raju Institute of Technology Narsapur Telangana

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

This is a modern approach to student attendance management using face recognition technology, powered by advanced techniques including Convolutional Neural Network (CNN) and Haar Cascade frontalface default algorithm. By leveraging OpenCV and these cutting-edge face recognition methods, the system offers a reliable and efficient solution for tracking attendance in educational institutions. Real-time face detection and recognition, support for multiple face recognition, and smooth interaction with current attendance management systems are some of the key characteristics. Additionally, the system incorporates deep learning algorithms to enhance its accuracy and robustness in identifying students’ faces. Through practical implementation, the project demonstrates the effectiveness of using OpenCV and deep learning for automated student attendance management. By providing accurate and efficient attendance tracking, while improving operational efficiency in educational settings, this innovative solution marks a significant advancement in modernizing attendance management practices.

关键词： Deep learning Privacy Accuracy Face recognition Neural networks Real-time systems Robustness Convolutional neural networks Face detection Character recognition

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：