检索结果-内蒙古大学图书馆

3rd IEEE Delhi Section Flagship Conference, DELCON 2024

作者： Javid, Sajid Saim, Mohammad Islam, Saiful Indraprastha Institute of Information Technology Delhi Dept. of Computer Science & Engineering Delhi India University of Cincinnati Dept. of Computer Science & Engineering CincinnatiOH United States Zakir Husain College of Engineering & Technology Aligarh Muslim University Dept. of Computer Engineering Aligarh India

ISBN: (纸本)9798331518592

In the era of rapid advancements in technology, the efficient digitization of paper-based documents remains a crucial challenge across various domains. The traditional approach to document scanning often struggles with accurate extraction of critical information from unstructured or diverse document formats. This paper presents the development of a web-based document scanner application that leverages Named Entity Recognition (NER) to extract entities from scanned business cards efficiently. The study aims to address the challenge of digitizing and organizing physical documents, with a focus on precise entity extraction. The methodology involves creating a custom dataset of scanned business cards, preprocessing the data, and training an NER model using machine learning techniques. The application is built using the Flask framework and integrates OpenCV for text extraction and SpaCy for NER. The key findings include the model's high F1 score in identifying entities such as names, organizations, designations, emails, and contact details. The application streamlines document digitization by automatically extracting and tagging relevant metadata, minimizing the need for manual data entry. This research contributes to enhancing document management and demonstrates broader applicability for other document types apart from business cards. The implications highlight improvements in workflow automation, data accuracy, and the potential for integrating with larger document management systems. © 2024 IEEE.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

DFT-based Channel Estimation with Multiple Windows for ATSC 3.0 Receiver 13

DFT-based Channel Estimation with Multiple Windows for ATSC ...

引用

13th IEEE Global Conference on Consumer Electronic, GCCE 2024

作者： Liu, Yu-Sun Li, Yin-Shan You, Shingchern D. National Taipei University of Technology Dept. of Electronic Engineering Taipei Taiwan National Taipei University of Technology Dept. of Computer Science and Information Engineering Taipei Taiwan

ISBN: (纸本)9798350355079

This study introduces a novel method for Discrete Fourie Transform (DFT)-based interpolation for channel estimation through the application of multiple windows in the channel impulse response. Utilizing a genetic algorithm, we determine the optimal positions and lengths of these windows. Our simulation results demonstrate that this approach has lower channel's Mean Squared Error (MSE) than other high-performance estimation approaches. © 2024 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Reconsider Time Series Analysis for Insider Threat Detection

Reconsider Time Series Analysis for Insider Threat Detection

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Chen, Chia-Cheng Pao, Hsing-Kuo National Taiwan University of Science and Technology Dept. of Computer Science and Information Engineering Taipei Taiwan

ISBN: (纸本)9798350362480

Insider threat detection (ITD) presents a significant challenge in cybersecurity, particularly within large and complex organizations. Traditionally, ITD has been overshadowed by the focus of external threats, resulting in less attention and development in this critical area. Conventional ITD approaches often rely heavily on event-driven approaches. On top of that, researchers developed various rule-based methods to conquer the tasks. Based on that, we often ignore the intrinsic temporal relationships that are naturally built in between events that occur in different moments. For instance, we may easily understand events with causality such as one anomalous event followed by another specific event to complete a malicious action;however, may not be aware of events that occur around 9 am every morning during working hours. In our opinion, we attempt to re-consider the temporal behavior to extract the information hidden in cyberspace activities. Specifically, some effective sentence embeddings can assist us in providing informative internal representations to summarize temporal behaviors in the temporal activity sequences to make the right judgment on insider threat detection. In this paper, we propose a novel methodology for insider threat detection that emphasizes temporal relationship modeling on top of already-matured event sequence analysis to effectively catch insider threats. The proposed approach leverages contrastive sentence embeddings to learn users' intentions in sequences, followed by the deployment of a user-level and event-level Contrastive Learning (euCL) model to incorporate temporal behaviors with user behavior embeddings. To validate the proposed methodology, we conduct extensive analyses and experiments using the publicly available CERT dataset. The results demonstrate the effectiveness and robustness of the proposed method in detecting insider threats and identifying malicious scenarios, highlighting its potential for enhancing cybersecurity measur

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

WellBe: An Intelligent Elderly Care and Well-Being Monitoring System Using Deep Learning 4

WellBe: An Intelligent Elderly Care and Well-Being Monitorin...

引用

4th International Conference on Intelligent Technologies, CONIT 2024

作者： Raotole, Atharv Shirodkar, Sailee Sanjay Shukla, Rahul Sisodia, Jignesh Devadkar, Kailas Patel Institute of Technology Dept. of Information Technology Sardar Mumbai India Patel Institute of Technology Dept. of Computer Science and Engineering Sardar Mumbai India

ISBN: (纸本)9798350349900

Deep Learning refers to a subset of Machine Learning that utilizes deep neural networks to simulate the complex decision-making process of the human brain. In recent years, DL has made remarkable progress in addressing multiple unique challenges faced by most elderly individuals. While there have been significant contributions to independent systems catered for the elderly, there is the existence of an overall integrated AI platform that unifies the use of individual modules for an optimized solution. This paper introduces 'WellBe,' an innovative AI system that encompasses an alarm-based fall detection component, a facial emotion recognition (FER) system and a built-in personalized chatbot all under a user-friendly website. The novelty of the work extends beyond the aforementioned components, owing to the implementation of an optimized FER system able to handle wrinkles and changes in skin texture, thereby tailored exclusively for the elderly demographic. The system leverages a custom feature extraction module, fusing facial and wrinkle features, in addition to extending a convolutional neural network (CNN) architecture for accurate emotion classification, achieving promising performance with precision, recall, and F1-scores of 0.87, 0.91, and 0.89 for the 'Happy' (one of the predicted emotions) class, respectively. The fall detection component, on the other hand, utilizes a pre-trained YOLOv7 Pose model for the real-time identification of falls, sitting at a performance accuracy of 95.3%. Finally, the personalized chatbot is implemented using a rule-based approach enhanced with the Jaccard similarity algorithm, to facilitate prompt assistance and a sense of companionship to the end user. Overall, the integration of these components into a cohesive website offers a comprehensive solution for enhancing the quality of life for elderly individuals living alone, addressing loneliness, safety, and overall well-being. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhanced Adaptive Video Streaming for Resource-Constrained UAVs through Dynamic Region-of-Interest Tile Swapping 10

Enhanced Adaptive Video Streaming for Resource-Constrained U...

引用

10th International Conference on Applied System Innovation, ICASI 2024

作者： Hsu, Tz-Heng Ju, Rui-Han Horng, Gwo-Jiun Southern Taiwan University of Science and Technology Dept. of Computer Science and Information Engineering Tainan Taiwan

ISBN: (纸本)9798350394924

Real-time video transmission via unmanned aerial vehicles (UAVs) is significantly impacted by latency issues. Using Region of Interest (ROI) tile segmentation methods, video streaming techniques can dynamically adjust the encoding bitrate, assign various priorities to distinct video tiles, and specify different quality quantization factors. High-efficiency video tile encoding techniques, combined with ROI-based streaming methods, can meet various Quality of Service (QoS) criteria. However, dynamically assigning quantization factors for different tiles has the disadvantage of increasing the encoding system's complexity. This study presents a method to dynamically swap ROI tiles to lower the complexity of the encoding system, making it suitable for UAVs with limited computational capacities. By adopting the proposed adaptive video streaming transmission method with tile-swapping strategy, it is feasible to enhance the visual quality in critical areas for resource-constrained UAV devices. © 2024 IEEE.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

Leveraging XAI and Breakthrough Machine Learning Techniques for Trigeminal Neuralgia Severity Classification

Leveraging XAI and Breakthrough Machine Learning Techniques ...

引用

2024 IEEE Region 10 Symposium, TENSYMP 2024

作者： Abhijna, M.B. Akul, P. Kodipalli, Ashwini Global Academy of Technology Dept. of Information Science and Engineering India Global Academy of Technology Dept. of Computer Science and Engineering India Global Academy of Technology Dept. of Artificial Intelligence and Data Science India

ISBN: (纸本)9798350364866

Trigeminal Neuralgia (TN) is a debilitating chronic pain disorder that significantly diminishes overall well-being, making diagnosis and therapy more challenging. The quick and precise categorization of TN severity is critical to therapy effectiveness. To assess the severity of TN, this study makes use of advanced machine learning techniques and explainable AI (XAI) approaches. We use a range of bagging and boosting strategies, including AdaBoost, Random Forest, Decision Tree, K-Nearest Neighbours (KNN), Gradient Boosting, and Logistic Regression. Random Forest was 95.2% accurate, whereas AdaBoost and Gradient Boosting were 92% and 97.2% in terms of their accuracy. The Decision Tree classifier obtained an accuracy of 84.62%, while K-Nearest Neighbours and Logistic Regression also achieved 92.31% accuracy. F1- score, precision, and recall metrics were used to assess performance on a dataset that included patient demographics and medical histories. XAI techniques, such as LIME and SHAP values, were used to improve the models' readability and transparency, which helped to progress the creation of cutting-edge diagnostic tools and increase clinician and researcher confidence. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Design and Development of Cognitive Training Systems Based on Extended Reality and BCI technology 7

Design and Development of Cognitive Training Systems Based o...

引用

7th IEEE Eurasian Conference on Educational Innovation, ECEI 2024

作者： Lin, Pei-Jung Ku, Hsiu-Chien Lin, Li-Lun Feng Chia University Dept. of Information Engineering and Computer Science Taichung Taiwan Hungkuang University Dept. of Computer Science and Information Engineering Taichung Taiwan

ISBN: (纸本)9798350307207

Dementia is considered a Mild Cognitive Impairment (MCI), representing a blurred transition from normal cognitive function to dementia. MCI might be a precursor to dementia being caused by various neurodegenerative diseases, including Alzheimer's disease, stroke, metabolic disorders, and mental health conditions. According to the World Health Organization (WHO), over 55 million people worldwide are suffering from dementia, with nearly 10 million new cases each year. This number is expected to rise to 78 million by 2030. Numerous studies have proposed various training methods targeting specific cognitive domains in dementia. For instance, reminiscence therapy encourages individuals to recall buried memories, while reality orientation therapy focuses on strengthening orientation cues to help patients with dementia establish a stronger sense of control. With aging, changes occur in cognitive and physical functions. Research suggests that memory functions can be improved through training. Therefore, the primary goal of this study was to develop an Extended Reality (XR) cognitive system to assist MCI patients in enhancing logical thinking, increasing independence in daily life, and improving response accuracy. The application of extended reality technology in the medical field is expanding, covering areas such as surgical assistance, medical consultation, disease treatment, and medical training. We integrated mixed reality devices with brain-computer interface (BCI) equipment. By detecting brainwave signals in the frontal region of the brain through sensors, neural activity was quantified, and digital brainwave data was transmitted to the system. This data was then visualized on screen in real-time to analyze changes in brainwave data during training. Through multifaceted task training, the system enhanced cognitive response and sensory perception, stimulating brain activity with the goal of strengthening cognitive functions. © 2024 IEEE.

关键词： Mixed reality

来源：评论

学校读者我要写书评

暂无评论

Fuzzy-rule-decided small cell offloading for rate-adaptive SVC-DASH video streaming over the vehicle environment

引用

computer Communications 2023年 212卷 1-20页

作者： Huang, Chung-Ming Wang, Han-I Dept. of Computer Science and Information Engineering National Cheng Kung University Tainan Taiwan

This paper proposed an SVC-DASH video streaming method over the vehicular environment based on the Multi-access Edge Computing (MEC) architecture. For the streaming concern, a control scheme using the Segment-Set-based buffer-aware bitrate adaptation with the backward quality's increment control was proposed;for the mobility concern, a Small Cell Video Streaming Offloading (SC–VSO) control scheme adopting the multiple attribute fuzzy-based decision for deciding whether it can offload the video streaming traffic from a macro cell to a small cell or not was proposed. To have the suitable bitrate adaptation and stable quality variation, three factors that the proposed streaming control scheme considers are (i) estimated bandwidth, (ii) buffer occupancy and (iii) quality variation. Since the vehicle is moving across many types of Base Stations (BSs), the proposed mobility control scheme can decide whether to have SC-VSO or not before vehicle X entering into the ahead small cell's signal coverage based on (i) the network situations of the corresponding macro and small cell and (ii) the reported context from vehicle X using the proposed fuzzy logic mechanism. The performance evaluation results shown that the proposed method has the higher video quality and better quality stability for video streaming over the vehicle environment. © 2023 Elsevier B.V.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

Resilient Fog-Based Adaptive Traffic Control System 14

Resilient Fog-Based Adaptive Traffic Control System

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Matange, Ashwini Taneja, Varun Chaumal, Aarya Buwa, Pallavi Abraham, Jibi Coep Tech Dept. of Computer Engineering and Information Technology Pune India

ISBN: (纸本)9798350335095

Traffic congestion is a growing problem in India, largely caused by the increasing number of vehicles. To address this, creating an adaptive traffic control system has become essential. To present a solution, this paper aims to create a resilient, adaptive traffic control system that dynamically adjusts signal timings based on the current traffic density. The paper proposes introducing a Fog layer at each traffic junction to capture real-time video feeds and process them locally, with the final decision about dynamic signal control being taken in the Cloud. The validity of the solution is tested through simulations in SUMO. A Machine Learning model is trained in the Cloud to predict expected vehicle numbers to set adaptive signal times for contingency situations. The paper aims to demonstrate the resilience and performance of the system with the adaptive traffic signal control algorithm, potentially offering a solution to traffic congestion in India. © 2023 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Tourist Place Classification Using Topic Modeling Algorithms 56

Tourist Place Classification Using Topic Modeling Algorithms

引用

56th International Carnahan Conference on Security technology, ICCST 2023

作者： Wadhe, Apeksha Arun Suratkar, Shraddha S. Vjti Mumbai Dept. of Computer Engineering & Information Technology 400019 India

ISBN: (纸本)9798350315875

Today social media is one of the most powerful and popular tool which is expanding rapidly in the world. Many tourism websites publish tourist places data for describing places in the form of Description. Over this data, Analysis can be performed and meaningful insights can be drawn. By analyzing this data we can find the subject or topic discussed in Description. By performing topic modeling over these data we can predict the category of tourist place. Also topic Modeling can help to cluster textual content into groups as per the subject of the text. In research study, Comparative analysis of topic modeling algorithms has been performed which will find a category of tourist places. Tourist place description blog data was gathered from tourism websites. Using tourist place Description dataset, comparative study of Topic modeling algorithms i.e. LDA Variational Inference(VI) algorithm and LDA Gibbs Sampling(GS) algorithm has been performed. Results of experiments has been analyzed with performance evaluation using various factors such as coherence score, perplexity, training execution time and accuracy percentage. LDA Gibbs Sampling(GS) algorithm outperforms LDA Variational Inference (VI) algorithm in terms of coherence score, perplexity, accuracy percentage. Whereas, LDA Variational Inference(VI) algorithm requires less execution time as compared to the LDA Gibbs Sampling(GS) algorithm © 2023 IEEE.

关键词： Websites

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：