检索结果-内蒙古大学图书馆

2024 Innovations in Intelligent Systems and Applications Conference, ASYU 2024

作者： Tufan, Elif Arslan, Sibel Computer Engineering Department Sivas Cumhuriyet University Sivas Turkey Software Engineering Department Sivas Cumhuriyet University Sivas Turkey

ISBN: (纸本)9798350379433

Nowadays, with the increasing number of metaheuristic, different strategies for solving engineering problems have been introduced. In this study, the Crayfish Optimizer Algorithm (COA), Spider Wasp Optimizer (SWO) and Goose Algorithm (Goose) are compared among the current metaheuristics inspired by the unique behaviors and survival functions of different animals in nature. To the best of our knowledge, this is the first study to compare the performance of these algorithms on three popular engineering problems (pressure vessel design, welded beam design and tension-compression design problems). When the experimental results and convergence rates are evaluated, it is observed that all metaheuristics exhibit very high performance. SWO, inspired by the hunting and nesting behavior strategies of spider wasps, is the most successful metaheuristic. SWO is followed by COA, modeled from the natural behavior of crayfish, and Goose, developed by imitating the flocking behavior of goose. The statistical significance of the results was assessed using t-tests, which demonstrate the superiority of SWO. In future studies, it is aimed that other metaheuristics, especially SWO, can be used in solving different engineering problems. © 2024 IEEE.

关键词： Invertebrates

来源：评论

学校读者我要写书评

暂无评论

A Study on Identifying, Categorizing and Reporting Usability Bugs and Challenges 4

A Study on Identifying, Categorizing and Reporting Usability...

引用

4th International Conference on Communication Technologies, ComTech 2023

作者： Ain, Qurat Ul Rana, Tauseef Aamana Department of Computer Science Islamabad Pakistan NUST Military College of Signals Department of Computer Software Engineering Islamabad Pakistan Department of Software Engineering Rawalpindi Pakistan

ISBN: (纸本)9798350337211

To assess the quality, acceptability and user experience of interactive applications, usability is one of the most integral quality attributes. However, significant number of usability bugs are being experienced by the end users of interactive applications thus creating a gap between users and technology. To bridge this gap and to overcome those usability bugs and challenges, it is significantly important to clearly identify the those usability bugs along with the gaps and challenges causing them. This research study aims to identify the usability bugs being experienced by users of interactive applications and proposes a categorization taxonomy for the identified bugs. Moreover, to reach the cause of emergence of usability bugs, the study attempts to identify and report the usability gaps and challenges in existing usability practices. Furthermore, this study performs a mapping between the identified gaps and challenges in existing practices to that of the recommendations to address the identified gaps. Index Terms - Usability, interactive applications, usability bugs, user experience, user satisfaction, usability testing, user interface. © 2023 IEEE.

关键词： User interfaces

来源：评论

学校读者我要写书评

暂无评论

Multimodal Classifier for Disaster Response 2nd

Multimodal Classifier for Disaster Response

引用

2nd International Conference on Advanced engineering, Technology and Applications, ICAETA 2023

作者： Alqaraleh, Saed Sirin, Hatice Computer Engineering Department Hasan Kalyoncu University Gaziantep Turkey Software Engineering Department Hasan Kalyoncu University Gaziantep Turkey

ISBN: (纸本)9783031509193

Data obtained from social media has a massive effect on making correct decisions in time-critical situations and natural disasters. Social media content generally consists of messages, images, and videos. In situations of disasters, using multimedia files such as images can significantly help in understanding the damage caused by disasters compared to using text only. In other words, the exact situation and the effect of disaster are better understood using visual data. So far, researchers widely use text datasets for building efficient disaster management systems, and a limited number of studies have focused on using other content, such as images and videos. This is due to the lack of available multimodal datasets. We addressed this limitation in this work by introducing a new Turkish multimodal dataset. This dataset was created by collecting disaster-related Turkish texts and their related images from Twitter. Then, by three evaluators and the majority voting, each sample was annotated as a disaster or not a disaster. Next, multimodal classification studies were carried out with the late fusion technique. The BERT embedding approach and a pre-trained LSTM model are used to classify the text, and a pre-trained CNN model is used for the visual content (images). Overall, concatenating both inputs in a multimodal learning architecture using late fusion achieved an accuracy of 91.87% compared to early fusion, which achieved 86.72%. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Disaster Management Image Classification Multimodal Classifier Turkish language Tweet Text Classification

来源：评论

学校读者我要写书评

暂无评论

Handwriting Analysis for Alzheimer's Diagnosis: Feature Enrichment and Machine Learning Classification 8

Handwriting Analysis for Alzheimer's Diagnosis: Feature Enri...

引用

8th International Artificial Intelligence and Data Processing Symposium, IDAP 2024

作者： Anacur, Cansu Akyurek Yilmaz, Asuman Gunay Aykut, Murat Karadeniz Technical University Department of Computer Engineering Trabzon Turkey Karadeniz Technical University Department of Software Engineering Trabzon Turkey

ISBN: (纸本)9798331531492

Alzheimer's is an incurable neurodegenerative disease that causes cognitive impairment. Various treatment methods are applied to slow the progression of the disease and improve the quality of patient's life. However, early diagnosis and treatment are of great importance. Due to motor coordination difficulties and decline in cognitive functions, abnormalities can be observed in the handwriting of Alzheimer's patients. Therefore, handwriting analysis is considered as an important tool for the early diagnosis of the disease. This study aims to detect Alzheimer's disease through handwriting analysis. Features extracted from different handwriting tasks of both healthy and diseased individuals were classified using machine learning methods. In addition to the existing features in the original dataset, two features were added, and the impact of these fetaures on the classification performance was evaluated. The results of the experiments and analyses revealed that the new features significantly improved the classification performance. The highest accuracy rate, 85.86 %, was achieved using the Logistic Regression method. © 2024 IEEE.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

Feature Selection Using Automatic Programming Methods in Hypertension Risk Prediction 8

Feature Selection Using Automatic Programming Methods in Hyp...

引用

8th International Artificial Intelligence and Data Processing Symposium, IDAP 2024

作者： Yagmurcu, Merve Arslan, Sibel Sivas Cumhuriyet University Computer Engineering Department Sivas Turkey Sivas Cumhuriyet University Software Engineering Department Sivas Turkey

ISBN: (纸本)9798331531492

Hypertension is a condition where the pressure in the blood vessels is higher than normal. It can lead to serious problems such as heart attack, stroke, heart failure, kidney disease and vision problems. Therefore, early diagnosis and treatment is important to find appropriate treatment strategies for the disease. In this study, automatic programming (AP) methods, were used and compared to analyze the risk of hypertension. These methods are Artificial Bee Colony Programming developed from the behavior of honeybees, Genetic Programming (GP) inspired by genetic selection and Immune Plasma Programming (IPP) based on immune plasma therapy. According to the performance evaluations obtained from the methods, GP and IPP were the most successful methods with test success rates of 0.91% and 0.89% respectively. In future research, Due to the success of the AP methods, we aim to develop different versions for health problems. © 2024 IEEE.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

Feature Selection and Detection of COPD Using Automatic Programming Methods 8

Feature Selection and Detection of COPD Using Automatic Prog...

引用

8th International Artificial Intelligence and Data Processing Symposium, IDAP 2024

作者： Karaca, Huseyin Arslan, Sibel Sivas Cumhuriyet University Computer Engineering Department Sivas Turkey Sivas Cumhuriyet University Software Engineering Department Sivas Turkey

ISBN: (纸本)9798331531492

Chronic obstructive pulmonary disease (COPD) is a serious lung disease that severely limits patients' quality of life and can lead to further health complications if it is not diagnosed and treated in time. In this study, various Automatic Programming (AP) methods, including Genetic Programming (GP) and Multi-Gene Genetic Programming (MGGP), are used to achieve highly accurate predictions for diagnosis. Among the methods, MGGP stands out with a prediction accuracy of 100%. The results highlight the potential of AP methods in modeling complex nonlinear relationships in COPD data and identifying key features that influence the diagnosis of the disease. In addition, the effectiveness and efficiency of AP methods suggest that they can contribute to the development of early diagnosis and treatment strategies. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

VR-Based Promotion and Training of Electric Vehicles 8

VR-Based Promotion and Training of Electric Vehicles

引用

8th International Symposium on Multidisciplinary Studies and Innovative Technologies, ISMSIT 2024

作者： Koç, Hamza Eren Başarslan, Muhammet Sinan Canli, Hikmet Istanbul Medeniyet University Department of computer Engineering Istanbul Turkey Istanbul Gedik University Department of software Engineering Istanbul Turkey

ISBN: (纸本)9798350354423

This study presents an innovative application that showcases electric vehicles using Unity-based virtual reality (VR) technology. In addition to acting as a virtual showroom for electric vehicles, this application provides a range of simulation capabilities, including color selection and interior accessories such as steering wheels. Users can gain new experiences in a simulation environment by interacting with customizable features and exploring various aspects of electric vehicles in an immersive setting. This study has brought a new perspective to the automotive industry as a prototype for human-computer interaction (HCI). © 2024 IEEE.

关键词： Automotive industry

来源：评论

学校读者我要写书评

暂无评论

UNiFY-ESSL: UNIfied Framework for Yielding EEG-Based Emotion Recognition Model with Self-Supervised Learning

UNiFY-ESSL: UNIfied Framework for Yielding EEG-Based Emotion...

引用

2024 International Conference on Brain computer Interface and Healthcare Technologies, iCon-BCIHT 2024

作者： Ahuja, Chirag Sethia, Divyashikha Delhi Technology University Department of Computer Engineering Delhi India Delhi Technology University Department of Software Engineering Delhi India

ISBN: (纸本)9798331540067

Electroencephalography (EEG) based emotion recognition shows promise in human-computer interaction and mental health monitoring, but faces challenges in cross-dataset generalization. This study introduces the Unified Framework for EEG-based Emotion Recognition with Self-Supervised Learning (UNiFY-ESSL), combining self-supervised learning (SSL) and advanced sampling techniques to integrate multiple EEG datasets. UNiFY-ESSL utilizes a unified 14-channel setup across all datasets (SEED, DEAP, and DREAMER), allowing consistent preprocessing and feature extraction. This approach adapts datasets with varying initial channel counts (62 for SEED, 32 for DEAP, and 14 for DREAMER) to a common configuration based on DREAMER's channels. The framework explores contrastive learning methods, specifically Simple Contrastive Learning (Sim-CLR) and Contrastive Predictive Coding (CPC), enhanced by a novel stratified sampling scheme. Experiments yield impressive results: SimCLR achieves F1-scores of 82.62%, 87.83%, and 89.05% for SEED, DEAP, and DREAMER respectively, while CPC attains 81.35%, 82.27%, and 91.23%. It demonstrates improved cross-dataset generalization, with a 1-2% performance gain on DREAMER and maintained performance on DEAP despite channel reduction. However, SEED experiences a 3% F1-score drop due to significant channel reduction. These findings highlight the potential of our sampling method in advancing EEG-based emotion recognition while underscoring the need for future work on efficient channel combination strategies, particularly for datasets with higher initial channel counts. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Generating Robust Adversarial Images in Medical Image Classification using GANs

Generating Robust Adversarial Images in Medical Image Classi...

引用

2024 Innovations in Intelligent Systems and Applications Conference, ASYU 2024

作者： Kanca, Elif Gulsoy, Tolgahan Kablan, Elif Baykal Ayas, Selen Department of Software Engineering Karadeniz Technical University Trabzon Turkey Department of Computer Engineering Karadeniz Technical University Trabzon Turkey

ISBN: (纸本)9798350379433

Rapid advancements in artificial intelligence and deep learning technologies have greatly improved the accurate classification of medical images, resulting in earlier diagnosis of disease. However, these advancements have also brought attention to the challenge of ensuring the resilience of models against adversarial medical images. In this study, we propose an adversarial attack algorithm that utilizes generative adversarial networks for medical image classification. This algorithm seamlessly integrates the target classifier into the attack generation framework, enabling it to learn the distribution of adversarial examples closely resembling real data. Through extensive experiments across various medical image classification datasets including fundoscopy, chest x-ray, skin lesion, and breast histology, the proposed attack algorithm achieves impressive attack success rates. Specifically, rates of 81.36%, 95.23%, 77.75%, and 51.67% are reported for each dataset, respectively. These findings underscore the critical importance of addressing adversarial vulnerabilities in medical image classification, ensuring the reliability and trustworthiness of diagnostic systems in clinical settings. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Power of Deep Learning: A Comparative Study of LSTM, BERT, and GRU for Disaster Tweet Classification

引用

IEIE Transactions on Smart Processing and Computing 2023年第6期12卷 526-534页

作者： Ullah, Ihsan Jamil, Anum Ul Hassan, Imtiaz Kim, Byung-Seo Department of Software and Communication Engineering Hongik University Korea Republic of Department of Physics NED University of Engineering & Technology Karachi Pakistan Department of Computer Science and Information Technology NED University of Engineering & Technology Karachi Pakistan

Disasters have serious effects on people's lives and buildings. Therefore, social media platforms, such as Twitter, have become more critical. They are crucial tools for responding to and managing disasters effectively. This study examined the effectiveness of various deep learning models, such as bidirectional encoder representations from transformers (BERT), gated recurrent units (GRU), and long short-term memory (LSTM) for classifying disaster-related tweets. Twitter data related to different disasters were collected using hashtags. The data were then cleaned, preprocessed, and manually annotated by a team. The annotated data were divided into training, validation, and testing sets. The data were used to train three models based on BERT, GRU, and LSTM for the categorical classification of disaster tweets. Finally, the three models were evaluated and compared using the test data. BERT achieved an accuracy of 96.2%, making it the most effective model. In contrast, the LSTM and GRU models achieved an accuracy of 93.2% and 88.4%, respectively. These findings underscore the potential effectiveness of deep learning models in classifying disaster-related tweets, offering insights that could enhance disaster management strategies, refine social media monitoring processes, bolster public safety, and provide directions for future research. © 2023 Institute of Electronics and Information Engineers. All rights reserved.

关键词： Disasters

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：