检索结果-内蒙古大学图书馆

An Attention-Based Deep Network for Plant Disease Classification

Machine Graphics and Vision 2024年第1期33卷 47-67页

作者： Bera, Asish Bhattacharjee, Debotosh Krejcar, Ondrej Department of Computer Science and Information Systems Birla Institute of Technology and Science Rajasthan Pilani India Department of Computer Science and Engineering Jadavpur University West Bengal Kolkata India Center for Basic and Applied Science Faculty of Informatics and Management University of Hradec Králové Czech Republic Škoda Auto University Mladá Boleslav Czech Republic Universiti Teknologi Malaysia Kuala Lumpur Malaysia

Plant disease classification using machine learning in a real agricultural field environment is a difficult task. Often, an automated plant disease diagnosis method might fail to capture and interpret discriminatory information due to small variations among leaf sub-categories. Yet, modern Convolutional Neural Networks (CNNs) have achieved decent success in discriminating various plant diseases using leave images. A few existing methods have applied additional pre-processing modules or sub-networks to tackle this challenge. Sometimes, the feature maps ignore partial information for holistic description by part-mining. A deep CNN that emphasizes integration of partial descriptiveness of leaf regions is proposed in this work. The efficacious attention mechanism is integrated with high-level feature map of a base CNN for enhancing feature representation. The proposed method focuses on important diseased areas in leaves, and employs an attention weighting scheme for utilizing useful neighborhood information. The proposed Attention-based network for Plant Disease Classification (APDC) method has achieved state-of-the-art performances on four public plant datasets containing visual/thermal images. The best top-1 accuracies attained by the proposed APDC are: PlantPathology 97.74%, PaddyCrop 99.62%, PaddyDoctor 99.65%, and PlantVillage 99.97%. These results justify the suitability of proposed method. © 2024 Institute of Information Technology, Warsaw University of Life Sciences - SGGW. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Bad channel detection in EEG recordings

Bad channel detection in EEG recordings

引用

作者： Komosar, Milana Fiedler, Patrique Haueisen, Jens Institute of Biomedical Engineering and Informatics Faculty of Computer Sciences and Automation Technische Universität Ilmenau Ilmenau Germany

Electroencephalography (EEG) is widely used in clinical applications and basic research. Dry EEG opened the application area to new fields like self-application during gaming and neurofeedback. While recording, the signals are always affected by artefacts. Manual detection of bad channels is the gold standard in both gel-based and dry EEG but is time-consuming. We propose a simple and robust method for automatic bad channel detection in EEG. Our method is based on the iterative calculation of standard deviations for each channel. Statistical measures of these standard deviations serve as indications for bad channel detection. We compare the new method to the results obtained from the manually identified bad channels for EEG recordings. We analysed EEG signals during resting state with eyes closed and datasets with head movement. The results showed an accuracy of 99.69 % for both gel-based and dry EEG for resting state EEG. The accuracy of our new method is 99.38 % for datasets with the head movement for both setups. There was no significant difference between the manual gold standard of bad channel identification and our iterative standard deviation method. Therefore, the proposed iterative standard deviation method can be used for bad channel detection in resting state and movement EEG recordings. © 2022 The Author(s), published by De Gruyter.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Using Self-Sovereign-Identity principles to prove your worth in Decentralized Autonomous Organizations 9

Using Self-Sovereign-Identity principles to prove your worth...

引用

9th Workshop on Software Quality Analysis, Monitoring, Improvement, and Applications, SQAMIA 2022

作者： Keršič, Vid Vrečko, Andraž Vidovič, Urban Domajnko, Martin Turkanović, Muhamed Faculty of Electrical Engineering and Computer Science University of Maribor Institute of Informatics Blockchain Lab:UM Maribor Slovenia

Decentralized autonomous organizations (DAO) have many use cases and are becoming increasingly more popular in recent years. The paper analyses the disadvantages and problems of current DAOs (i.e., the Plutocracy problem) and presents a solution, in which the existing implementations of DAO are combined with the Self-Sovereign Identity (SSI) ecosystem to solve those issues. The solution is presented in the form of an extension to the crypto wallet MetaMask, using Snaps, which enables DAO users to create SSI-based identifiers (DID) and manage verifiable credentials (VC), which are later on used as a voting ticket in a DAO. We validate the solution by presenting the prototype of the SSI Snap and demonstrating its usage on the Snapshot decentralized voting system. © 2022 Copyright for this paper by its authors.

关键词： DAO decentralized decentralized autonomous organization MetaMask proof of concept self-sovereign identity Snaps SSI Veramo verifiable credential

来源：评论

学校读者我要写书评

暂无评论

Improved Accuracy of Decision Tree with XGBoost Technique in Cat Skin Disease Diagnosis

Improved Accuracy of Decision Tree with XGBoost Technique in...

引用

Science and Information Technology in Smart Administration (ICSINTESA), International Conference of

作者： Nanda Safrina Maya Silvi Lydia Benny Benyamin Nasution Master of Informatics Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia Department of Computer Engineering and Informatics Politeknik Negeri Medan Medan Indonesia

ISBN: (数字)9798350376111

ISBN: (纸本)9798350376128

This research aims to develop an expert system for initial diagnoses of skin diseases in cats using the Decision Tree method. It assists cat owners in identifying skin diseases based on observed symptoms. Data from expert veterinarian drh. Ismi Azima, including various types of cat skin diseases and their symptoms, were used. The research employs 80% training data and 20% testing data to develop the classification model. Testing results indicate the Decision Tree model achieves up to 90% average accuracy in diagnosing cat skin diseases based on 50 datasets. This expert system aids in diagnosis and provides treatment and prevention solutions, beneficial for cat owners, especially in areas with limited veterinary access. In conclusion, this Decision Tree-based expert system effectively provides initial diagnoses of skin diseases in cats with high accuracy.

关键词： Accuracy Prevention and mitigation Training data Skin Decision trees Medical diagnosis Expert systems Diseases Testing Python

来源：评论

学校读者我要写书评

暂无评论

MatrikalinDiabetes: User-Centered Design of a mHealth App for Gestational Diabetes Mellitus Management and Education Among Bangladeshi Women 26th

MatrikalinDiabetes: User-Centered Design of a mHealth App ...

引用

26th International Conference on Human-computer Interaction, HCII 2024

作者： Ratul, Mohammad Arshad Hossain Yanoor Bristy, Tunisha Sayeed, Noorjahan Islam, Ashraful Chaudhry, Beenish Moalla Center for Computational and Data Sciences Independent University Bangladesh Dhaka Bangladesh Department of Computer Science and Engineering Independent University Bangladesh Dhaka Bangladesh School of Computing and Informatics University of Louisiana at Lafayette Louisiana United States

ISBN: (纸本)9783031768088

This study employs the User-Centered Design (UCD) methodology to develop a mobile health (mHealth) application (app) specifically tailored for Bangladeshi women with Gestational Diabetes Mellitus (GDM). GDM affects approximately 10% of pregnant women globally and around 35% within Bangladesh, as reported by the World Health Organization (WHO). Despite its high prevalence, there is a significant lack of awareness and education about GDM in Bangladesh, compounded by language barriers that make existing digital solutions less accessible. The MatrikalinDiabetes mHealth app aims to overcome these barriers by providing comprehensive management and educational resources for GDM in the Bangla language, addressing both pre-pregnancy and post-pregnancy needs. To ensure the app meets the actual needs of potential users, personas were created based on a literature review, and a survey was conducted. This process informed the development of both a low-fidelity, paper-based prototype and a high-fidelity digital prototype. Key features of the MatrikalinDiabetes app include tracking of food and water intake, physical activity monitoring, reminders, GDM education, chat forums for community support, blood glucose level (BGL) monitoring, an SOS button for emergency contacts, and quizzes for user engagement. Preliminary feedback indicated that 53.8% of participants favored the integrated features and expressed willingness to use and recommend the app. The survey of the high-fidelity prototype yielded positive responses, with 57.9% of participants strongly agreeing and 42.1% agreeing that the features were beneficial. The user-friendly design of the high-fidelity prototype ensures intuitive interaction, aiding in health management, enhancing GDM understanding, and promoting a healthier lifestyle among pregnant women in Bangladesh. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Obstetrics

来源：评论

学校读者我要写书评

暂无评论

Lightweight Deep Learning for Human Activity Recognition in Ambient Assisted Living

Lightweight Deep Learning for Human Activity Recognition in ...

引用

Multimedia University engineering Conference (MECON)

作者： Ahsanul Bari Fahmid Al Farid Md. Tanjil Sarker Sarina Mansor Hezerul Abdul Karim Md Roman Bhuiyan Hasanul Bannah Faculty of Engineering Multimedia University Cyberjaya Malaysia Faculty of Computer Science and Informatics Berlin School of Business and Informatics Berlin Germany

ISBN: (数字)9798331530747

ISBN: (纸本)9798331530754

This Lightweight Deep Learning (LDL) for Multi-View Human Activity Recognition in Ambient Assisted Living Systems can significantly improve the conditions of daily activities for people living with the elderly, disabled, or simply needing assistance. Human Activity Recognition (HAR) is essential for these systems; currently, the task of identifying the wide array of human activities remains complicated. This study introduces an improved deep learning solution for recognizing human activity from multiple viewpoints in AAL environments. By utilizing skeleton data from various perspectives, such as the RHM-HAR-SK dataset, we demonstrate useful improvements in accuracy for activity recognition when compared with single-view methods. Our LeNet and Vision Transformer models have been carefully designed to excel with skeletal data, delivering outstanding performance while keeping computational requirements to a minimum. In this research study also highlights the benefits of multi-view human activity recognition in ambient assisted living and emphasizes the effectiveness of efficient deep learning models in enabling assistive technologies that are real-time and resource friendly. These advancements support more independence and safety by supporting the development of AAL systems that are more sensitive and intelligent.

关键词： Deep learning Ambient assisted living Computational modeling Soft sensors Assistive technologies Transformers Data models Skeleton Human activity recognition Older adults

来源：评论

学校读者我要写书评

暂无评论

Enhance Low-Resolution Face Recognition Accuracy Using Median and Mean Filtering Techniques Based on Convolutional Neural Networks (CNN) 18

Enhance Low-Resolution Face Recognition Accuracy Using Media...

引用

18th International Conference on Telecommunication Systems, Services, and Applications, TSSA 2024

作者： Kurnia, Dian Ade Risnanto, Slmaet Sugiyatno Kusuma, Ajeng Nisa Naufal, Yogacitra Bin Mohd, Othman Sekolah Tinggi Manajemen Informatika Dan Komputer Ikmi Departemen of Computer Science Cirebon Indonesia Unversitas Sangga Buana Faculty of Engineering Departemen of Informatics Engineering Bandung Indonesia Universitas Bhayangkara Jakarta Raya Fakulti Informatics Jakarta Indonesia Unversitas Sangga Buana Bandung Indonesia Universiti Teknikal Malaysia Fakulti Teknologi Maklumat Dan Komunikasi Melaka Malaysia

ISBN: (纸本)9798331527686

The aim of this study is to evaluate the effectiveness of median and mean filtering techniques in enhancing the performance of deep learning-based face recognition systems on low-resolution images. The main challenge in face recognition lies in the low quality of images due to various factors such as lighting, distance, and camera resolution. Median filtering replaces each pixel with the median value of its neighbors, effectively removing salt-and-pepper noise, while mean filtering replaces each pixel with the average value of its neighbors, resulting in smoother images but potentially blurring important details. The results show that median filtering is more effective in preserving edge details and reducing speckle noise, whereas mean filtering excels at producing overall smoother images. The combination of these techniques is expected to enhance the accuracy of face recognition on low-resolution images, contributing to the development of more reliable and precise face recognition systems © 2024 IEEE.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

Distributed Denial of Service (DDoS) Mitigation: Security Awareness Domain and Resources (SADAR) 22

Distributed Denial of Service (DDoS) Mitigation: Security Aw...

引用

10th International Conference on computer and Communications Management, ICCCM 2022

作者： Hidayat, Taufik Safar Fadillah, Yoga Lubis, Muharman Lubis, Arif Ridho Department of Information System Telkom University Indonesia Department of Computer Engineering and Informatics Politeknik Negeri Medan Indonesia

ISBN: (纸本)9781450396349

Information security is a constantly evolving field to safeguard confidentiality, integrity and assets with defensive measures should be developed and planned to improve information security. Therefore, it is very important for a company to update its security system and defense techniques from attacks that occur. Furthermore, Distributed Denial of Service (DDoS) attack is a major threat that can disrupt and hinder legitimate service requests on a network. They were first reported in 1996 and until now the complexity and sophistication of these attacks is increasing, which are usually used to force a site or service to go offline, that is, by passing high data traffic until the server cannot work. Meanwhile, In August 2021, Microsoft claimed to have succeeded in overcoming the largest DDoS attack reaching 2 TBps. Moreover, with the increasing number of DDoS attacks, a mitigation scenario is needed to deal with the complexity and technical development of this DDoS. In the network world, detecting a DDoS somehow, is extremely difficult because the attempt should distinguish between normal traffic and DDoS attacks. Thus, some recommended security solutions will be compiled in this paper to deliver solution involving the mitigation. © 2022 ACM.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

QG-SKI: Question Classification and MCQ Question Generation Using Sequential Knowledge Induction 22nd

QG-SKI: Question Classification and MCQ Question Generation ...

引用

22nd International Conference on Hybrid Intelligent Systems, HIS 2022 and the 18th International Conference on Information Assurance and Security, IAS 2022

作者： Dhanvardini, R. Deepak, Gerard Santhanavijayan, A. Health Care Informatics Domain Optum-United Health Groups Hyderabad India Department of Computer Science Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of Computer Science Engineering National Institute of Technology Tiruchirappalli India

ISBN: (纸本)9783031274084

E-Learning has emerged as the most effective way of getting information in a range of sectors in the contemporary age. The utilisation of electronic content to provide education and development is referred to as e-learning. While the broadening internet has a plethora of e-learning tools, knowledge acquisition is not just an aspect that adds to an individual's enrichment. Assessment and evaluation are crucial parts of every learning system. Due to more complex assessments and quicker inspection, multiple choice questions are becoming extremely prevalent in current evaluations. However, establishing a diversified pool of MCQs relevant to a certain subject matter presents a hurdle. Manually creating high-quality MCQ exams is a time-consuming and arduous procedure that demands skill. As a result, research has concentrated on the automated construction of well-structured MCQ-based tests. This paper presents a paradigm using natural language processing based on semantic similarity and dynamic ontology. The proposed QG-SKI model uses LOD Cloud and Wiki Data to generate Ontologies dynamically and Knowledge reservoir is performed. The dataset is analysed using TF-IDF algorithm and the Semantic Similarity and Semantic Dissimilarity are computed using Shannon’s entropy, Jaccard Similarity and Normalised Google Distance. These algorithms are executed for a multitude of degrees and levels to generate a similar of similar instances. The suggested model has a 98.15% accuracy and outperforms previous baseline models by dampening resilience. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： E-learning

来源：评论

学校读者我要写书评

暂无评论

Novel replaceable EEG electrode system

Novel replaceable EEG electrode system

引用

作者： Warsito, Indhika Fauzhan Fiedler, Patrique Komosar, Milana Haueisen, Jens Institute of Biomedical Engineering and Informatics Faculty of Computer Science and Automation Technische Universität Ilmenau Ilmenau Germany

Due to the direct contact between electrode and scalp, dry EEG electrodes are exposed to increased mechanical wear compared to conventional gel-based electrodes. However, state-of-the-art commercial cap systems commonly use permanently fixated electrodes which can lead to downtime of the EEG cap during professional repair and replacement as well as reduced overall lifetime. An easily replaceable EEG electrode would furthermore improve hygiene, especially for newborn and infant applications. We propose a novel replaceable electrode system, consisting of an electrode holder, a snap top, a contact ring fixated inside the electrode holder, and a replaceable electrode. The production process consists of 3D printing, silicone molding, resin casting, and electroless plating. The replaceable electrode system is integrated into a multichannel EEG cap system. A verification study is conducted with 30 volunteers. The operators experienced that the new electrode holder eases adjustment of the electrode to have proper contact with the scalp. During the study, defective electrodes can be replaced without a soldering process. Furthermore, all electrodes stayed in the holder and did not fall off the cap for the whole session. In conclusion, the novel replaceable electrode system is suitable for EEG measurements. © 2022 The Author(s), published by De Gruyter.

关键词： Electroencephalography

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：