检索结果-内蒙古大学图书馆

International Conference on Electronics, information and Communications (ICEIC)

作者： Sherin Sheela May Phu Piang Sakda Sakorntanant Suvit Poomrittigul Treesukon Treebupachatsakul Department of Biomedical Engineering School of Engineering King Mongkut's Institute of Technology Ladkrabang Thailand Department of Software Engineering and Information System Faculty of Science and Technology Pathumwan Institute of Technology Bangkok Thailand School of Information Technology King Mongkut's Institute of Technology Ladkrabang Thailand

Bacterial strains in the same genus share highly similar morphology, gram-staining characteristics, colony sizes, and spatial arrangements. Therefore, identifying them by deep learning can be quite challenging. This study aimed to assess the classification of 7 species of bacteria from 2 genera of Bacillus and Vibrio by using 8 Convolutional Neural Network (CNN) models. We implemented Python programming along with Keras API within the Jupyter Notebook. The models were constructed and evaluated under unbalanced and balanced datasets by augmentation (rotation, flip, etc.). Transfer learning with fine-tuning, and pre-processing of mixup and label smoothing were also applied to reduce overfitting and enhance generalization. Based on the experimental results on private dataset, the results of InceptionResNetV2 emerged as the top-performing model with a notable accuracy of 82.8%, 88.6% precision, 78.4% recall, and 78.0% F1-score when label smoothing was applied at 0.5 on balanced dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automatic Repeat Request Design in AoI-Aware Broadcast With Heterogeneous Direct and Relay-Assisted Users

引用

IEEE Internet of Things Journal 2025年

作者： Wang, Xueer Pan, Haoyuan Chan, Tse-Tin Li, Jianqiang Shenzhen University College of Computer Science and Software Engineering Shenzhen China The Education University of Hong Kong Department of Mathematics and Information Technology Hong Kong Shenzhen University National Engineering Laboratory for Big Data System Computing Technology The College of Computer Science and Software Engineering Shenzhen China

This paper investigates the design of automatic repeat request (ARQ) protocols in age of information (AoI)-aware broadcast systems with heterogeneous users, including both direct and relay-assisted users. In this setup, a direct user receives status updates directly via a single-hop link, while a relay-assisted user can receive status updates through either a direct single-hop link or a two-hop relay-assisted link. While ARQ is commonly used to ensure reliable transmission in error-prone wireless networks, previous studies suggest that ARQ does not improve the average AoI in single-hop networks. However, its impact on AoI in systems with relays, particularly those involving heterogeneous users, remains unclear. We address this gap by analyzing the average AoI under different ARQ strategies, introducing a transmission limit k ≥ 0 at the relay. Here, k = 0, k = 1, and k > 1 correspond to non-relay, non-ARQ-at-relay, and truncated-ARQ-at-relay strategies, respectively. Utilizing a unified Markov chain framework that models the transmission processes for each user type, we derive the theoretical average AoI. Our results show that the direct user benefits most from non-relay and non-ARQ strategies, similar to single-hop systems. In contrast, the relay-assisted user achieves optimal performance with truncated-ARQ-at-relay, leveraging both direct and relay-assisted links. For the overall system, applying a non-ARQ-at-relay approach strikes a balance in AoI between the direct and relay-assisted users, leading to a more stable and lower system-wide average AoI. © 2014 IEEE.

关键词： Mobile telecommunication systems

来源：评论

学校读者我要写书评

暂无评论

Simulative Investigations of Crowd Evacuation by Incorporating Reinforcement Learning Scheme 6

Simulative Investigations of Crowd Evacuation by Incorporati...

引用

6th International Conference on Algorithms, Computing and systems, ICACS 2022

作者： Sinpan, Nitinun Sasithong, Pruk Chaudhary, Sushank Poomrittigul, Suvit Leelawat, Natt Wuttisittikulkij, Lunchakorn Department of Electrical Engineering Chulalongkorn University Thailand Wireless Communication Ecosystem Research Unit Thailand Department of Software Engineering and Information System Pathumwan Institute of Technology Thailand Disaster and Risk Management Information Systems Research Unit Department of Industrial Engineering Chulalongkorn University Thailand

ISBN: (纸本)9781450397407

Safe and effective evacuation is very essential to decrease casualties in an emergency event. The social force model is used to simulate the movement of evacuee and leader crowd evacuation with leader in an experimental area. The a-star algorithm is used to find the evacuation routes of each evacuee from the initial location to the exit. In this paper, we proposed the application of reinforcement learning to train the agent to become an evacuation leader via the Unity ML-Agents Toolkit. This model is tested in three scenarios: an evacuation without a leader, an evacuation with a leader, and an evacuation with randomly located agent. They are considered for comparison purposes to show the impact of an agent that tries to tell an exit to all evacuees in the experimental area. The experimental results show that the proposed crowd evacuation agent could effectively evacuate all evacuees in the experimental area. © 2022 ACM.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Unveiling Fake News with an Attention-Based CNN Model Using Hybrid Features

Unveiling Fake News with an Attention-Based CNN Model Using ...

引用

information and Communication technology (ICICT), International Conference on

作者： Francis Rudra D Cruze Md. Faruk Hosen Md. Suhag Ali Mohammad Sarwar Hossain Mollah Muhammad Shahin Uddin Monir Morshed Department of Computing and Information System Daffodil International University (DIU) Ashulia Dhaka Bangladesh Department of Information and Communication Technology Mawlana Bhashani Science and Technology Univeristy Tangail Bangladesh Department of Software Engineering Daffodil International University (DIU) Ashulia Dhaka Bangladesh

ISBN: (数字)9798331508227

ISBN: (纸本)9798331508234

Sophisticated detection mechanisms are required to protect the integrity of information in the digital age, as the widespread dissemination of false news on social media platforms has become a critical challenge. To tackle the practical issue of spreading false information, there is an urgent need for reliable systems that can effectively identify and counteract the propagation of fake news. This work presents a novel method for identifying fake news by combining sophisticated encoding techniques and utilizing deep learning architectures. Our approach integrates TF-IDF, CountVectorizer (CV), and Word2Vec (W2V) techniques for encoding. These techniques are coupled sequentially to capture the subtle details in fake news content successfully. Through the utilization of attention-based Convolutional Neural Network (CNN) models, we improve the comprehension and categorization of intricate textual material. Our methodology prioritizes scalability to efficiently analyze big datasets while retaining high detection accuracy in many situations and languages. Our approach has been thoroughly tested and proven to be strong and applicable in a wide range of false news situations. We have attained a state-of-the-art level of precision, with an accuracy of 99.11 %, by employing an attention-based Convolutional Neural Network (CNN) coupled CountVectorizer and Word2Vec embeddings,

关键词： Deep learning Accuracy Social networking (online) Scalability Organizations Feature extraction Encoding Convolutional neural networks Reliability Fake news

来源：评论

学校读者我要写书评

暂无评论

Applications of Blockchain technology for Secure Transaction of Electronic Health Records 2

Applications of Blockchain Technology for Secure Transaction...

引用

2nd International Conference on Automation, Computing and Renewable systems, ICACRS 2023

作者： Kunduru, Arjun Reddy Thatikonda, Ramya Vaddadi, Srinivas A. Lakshmi, B. Durairaj, Yabesh Abraham Khirasaria, Vivek Software Developer OrlandoFL United States Information Technology University of the Cumberlands United States Principal System Reliability Architect Department - Risk & Reliability University of the Cumberlands United States MBA Department Panimalar Engineering College India School of Management SA College of Arts and Science India Faculty of Engineering and Technology Sharda University Uzbekistan

ISBN: (纸本)9798350340235

The healthcare industry is not immune to the trend of adopting new IT systems, and this includes hospitals and doctors' offices. To store a patient's medical history (including diagnoses and treatments), medical history (including diagnostic pictures), and financial data (including demographics and insurance details), a computerised database known as an "Electronic Health Record" (EHR) is used. Because medical records are typically private and must be shielded from prying eyes, ensuring their secure transfer is a top priority for healthcare systems. Electronic health records (EHRs) are used in the proposed study to ensure the security of all sent medical data, including the Chest X-ray MedPix images. This article describes a blockchain-based solution that patients can use to keep all their data in one secure location. This system was built with the Ganache tool on the Ethereum network, making use of Solidity and *** as well as other languages, tools, and approaches. In this study, a systematic method is described wherein blockchain smart contracts are used to record patient information and execute tasks in a distributed environment. After a smart contract has been deployed, all transactional communication occurs within its encrypted confines, protecting both the parties and their personal information. As an added bonus, the validated and broadcasted changes intended by the transaction can be checked. To ensure that government agencies have quick access to protected records, there is a cryptocurrency wallet (MetaMask) that stores the information in an encrypted, decentralised manner. Both patients and physicians can use the wallet to log in. In addition, the system will manage and protect all of the doctor and patient's information. Things like the following are in scope for the proposed system: Users may now access the same information at the same time because to blockchain's distributed ledger capabilities, which boosts productivity, establishes trust, and lowe

关键词： Blockchain Electronic health record Healthcare systems

来源：评论

学校读者我要写书评

暂无评论

On the Discriminability of Self-Supervised Representation Learning

arXiv

引用

arXiv 2024年

作者： Song, Zeen Qiang, Wenwen Zheng, Changwen Sun, Fuchun Xiong, Hui The University of Chinese Academy of Sciences Beijing China The Science & Technology on Integrated Information System Laboratory Institute of Software Chinese Academy of Sciences Beijing China The Science & Technology on Integrated Information System Laboratory Department of Computer Science and Technology Tsinghua University Beijing China The Hong Kong University of Science and Technology China

Self-supervised learning (SSL) has recently achieved significant success in downstream visual tasks. However, a notable gap still exists between SSL and supervised learning (SL), especially in complex downstream tasks. In this paper, we show that the features learned by SSL methods suffer from the crowding problem, where features of different classes are not distinctly separated, and features within the same class exhibit large intra-class variance. In contrast, SL ensures a clear separation between classes. We analyze this phenomenon and conclude that SSL objectives do not constrain the relationships between different samples and their augmentations. Our theoretical analysis delves into how SSL objectives fail to enforce the necessary constraints between samples and their augmentations, leading to poor performance in complex tasks. We provide a theoretical framework showing that the performance gap between SSL and SL mainly stems from the inability of SSL methods to capture the aggregation of similar augmentations and the separation of dissimilar augmentations. To address this issue, we propose a learnable regulator called Dynamic Semantic Adjuster (DSA). DSA aggregates and separates samples in the feature space while being robust to outliers. Through extensive empirical evaluations on multiple benchmark datasets, we demonstrate the superiority of DSA in enhancing feature aggregation and separation, ultimately closing the performance gap between SSL and SL. © 2024, CC BY.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Mudahnya BM: A Context-Aware Mobile Cloud Learning Application Using Semantic-Based Approach

Mudahnya BM: A Context-Aware Mobile Cloud Learning Applicati...

引用

7th International Conference on Advances in Visual Informatics, IVIC 2021

作者： Muhammad, Sufri Admodisastro, Novia Osman, Hafeez Mohd Ali, Norhayati Faculty of Computer Science and Information Technology Department of Software Engineering and Information System Universiti Putra Malaysia Seri Kembangan Selangor43400 Malaysia

ISBN: (纸本)9783030902346

A great potential of various learning environment in mobile learning application can clearly be seen in current pandemic situation. The accessibility of the learning resources needs to be available from anywhere anytime despite having strong or poor internet connection. It has motivated researchers to imply context-aware capability in improving the accessibility of the learning resources. This paper presents a development process of Mudahnya BM mobile application that follows a fundamental concept of Mobile Cloud Learning (MCL). Mudahnya BM is an application to learn basic Malay language for learner 7–12 years old. The injection of extrinsic and intrinsic context-aware help the application to improve the reasoning process for finding available learning resources from service providers. Semantic-based approach is applied in the reasoning process. This study involved the end users for evaluation purposes. 33 randomized scenarios have been tested using One-Sample Wilcoxon Signed Rank test. The result shows a positive impact to the population. © 2021, Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Cybersecurity Enhancement in IoT-Enabled Public Health information systems Using Deep Learning Techniques

Cybersecurity Enhancement in IoT-Enabled Public Health Infor...

引用

2025 AI-Driven Smart Healthcare for Society 5.0, AdSoc5.0 2025

作者： Mishra, Mahesh Kumar Trivedi, Lalit Mohan Farooq, Mansoor Nimma, Divya Alazzam, Malik Bader Kiran Bala, B. Delta System and Software Inc 2320 Grover Cleveland Dr McKinneyTX United States Department of ASH Moradabad Institute of Technology UP Moradabad India Department of Cybersecurity American University of Bahrain Bahrain University of Southern Mississippi Data Analyst in UMMC United States Faculty of Information Technology Jadara University Irbid Jordan Department of AI & DS K.Ramakrishnan College of Engineering Trichy India

ISBN: (纸本)9798331536336

The rising use of IoT devices in Public Health information systems (PHIS) has revolutionized the way patient surveillance and record keeping is being done in real-time, but this has exposed systems to serious cybersecurity threats. Generated by using traditional approaches, like rule-based detection and basic artificial neural network-based models, is not capable of dealing with the dynamic and diverse nature of threats in IoT networks. These approaches are often inadequate in providing a detailed analysis of the attack especially because they do not have the ability to learn from sequences of features. This work presents an improved predictive analytics model using CNN with BiLSTM to improve cybersecurity in IoT connected PHIS. The CNN component performs feature extraction on spatial elements in the data received while the BiLSTM uncovers temporal dependencies and sequence of attacks, which enhance threats identification accuracy. The process of the proposed methodology includes dataset acquisition and cleansing of IoT healthcare datasets and finally, the training and testing of the model with the help of relevant parameter such as accuracy, precision, and recall values. Qualitative comparison with the baseline models also shows that the proposed hybrid CNN-BiLSTM model performs better, and it has fewer false alarms to detect a range of cyber threats. Accordingly, the results point to a feasible solution for enhancing security and reliability of IoT-based healthcare applications to protect patients’ record from cyber threats. © 2025 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Empowering Deaf Children with Sinhala Sign Language, Emotion Detection, and Sound Recognition

Empowering Deaf Children with Sinhala Sign Language, Emotion...

引用

Advancements in Computing (ICAC), International Conference on

作者： W.H.K Fernando P.L.D.N Perera M.I.N Fernando P.T.E.W Gunasekara Harinda Fernando Rivoni De Zoysa Department of Information Technology Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Computer System Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka Department of Computer Science Software Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka

This study describes a broad endeavor to use cutting-edge technologies to empower deaf primary school students in Sri Lanka. Three key elements make up the study: a sound recognition and classification system, an Android software for translating gestures in Sinhala Sign Language (SSL), and a mobile app for emotion recognition and text-tospeech in Sinhala. By promptly alerting caregivers to potential dangers, the sound recognition technology secures the security of deaf children at home, providing an invaluable layer of security. The Android software bridges the communication gap and improves family interactions by translating SSL gestures captured by the device's camera into textual representations. This promotes successful communication between deaf children and their parents. Convolutional Neural Networks (CNNs) are used in the mobile application to detect and understand emotions based on facial expressions. This enables non-verbal youngsters to communicate successfully through Sinhala textto-speech output with adaptive tone modulation. This research aims to build a caring and inclusive atmosphere, enabling increased independence and enhanced communication skills in deaf children by combining these advances. The suggested solutions could significantly improve the lives of deaf kids, providing them with opportunities for better learning, social interaction, and emotional health.

关键词：

来源：评论

学校读者我要写书评

暂无评论

I-Police-An Intelligent Policing system Through Public Area Surveillance 12

I-Police-An Intelligent Policing System Through Public Area ...

引用

12th IEEE Annual information technology, Electronics and Mobile Communication Conference, IEMCON 2021

作者： Jayakody, Anuradha Lokuliyana, Shashika Dasanayaka, Kolitha Iddamalgoda, Ashvinda Ganepola, Isuri Dissanayake, Anupama Sri Lanka Institute of Information Technology Department of Computer System Engineering Malabe Sri Lanka Sri Lanka Institute of Information Technology Department of Software Engineering Malabe Sri Lanka

ISBN: (纸本)9781665400664

technology and law enforcement are now commonly used hand in hand to improve public safety. Most police departments only use CCTV cameras at a few major intersections for remote surveillance. The public is waiting too long for emergency response lines, therefore using new technologies to improve the current policing system has become one of the police's main goals. The paper presents a coordinated framework that could identify the subtleties of violations via an automated public area surveillance system, specifically the weapon-related crimes and vehicle accidents, which are then disassembled, analyzed, and stored for future inspections. The trained models are aimed to reduce the false positives of incident detection. The weapon detection system had the best average precision (93.8%) by using YOLOv5 while the vehicle accident detection system resulted in the best average precision (94.9%) by using YOLOv4. The system is tested against the collected set of CCTV footage and tested how long it takes to create a notification which is the main goal of this system. Notification is generated in less than 5 seconds after an incident is detected. The evidence collection engine developed with MATLAB delivered the expected with an accuracy of 97% making the extracted evidence reliable to both vehicle accidents and crime scenes. Additionally, the framework provides an effective and efficient communication channel through which the residents can report crimes to regular parties. © 2021 IEEE.

关键词： Crime

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：