检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Friedbaum, Jesse Adiga, Sudarshan Tandon, Ravi Program in Applied Mathematics University of Arizona TucsonAZ United States Department of Electrical and Computer Engineering University of Arizona TucsonAZ United States

Counterfactuals, or modified inputs that lead to a different outcome, are an important tool for understanding the logic used by machine learning classifiers and how to change an undesirable classification. Even if a counterfactual changes a classifier's decision, however, it may not affect the true underlying class probabilities, i.e. the counterfactual may act like an adversarial attack and "fool" the classifier. We propose a new framework for creating modified inputs that change the true underlying probabilities in a beneficial way which we call Trustworthy Actionable Perturbations (TAP). This includes a novel verification procedure to ensure that TAP change the true class probabilities instead of acting adversarially. Our framework also includes new cost, reward, and goal definitions that are better suited to effectuating change in the real world. We present PAC-learnability results for our verification procedure and theoretically analyze our new method for measuring reward. We also develop a methodology for creating TAP and compare our results to those achieved by previous counterfactual methods. Copyright 2024 by the author(s)

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

LOCOS: A cosine based local gene expression pattern finding algorithm on time-series data

LOCOS: A cosine based local gene expression pattern finding ...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Suk, Youjeong Jeon, Jaemin Jung, Inuk Kyungpook National University School of Computer Science and Engineering Daegu Korea Republic of Seoul National University Interdisciplinary Program in Bioinformatics Seoul Korea Republic of

ISBN: (纸本)9798350362480

In gene expression analysis, understanding a biological event that is observed at some time instance often requires capturing genes whose expression levels modulate before and after the event. Such genes are expected to be the responders to the event and will exhibit similar expression patterns during the event. However, after the effect of the event fades, their expression levels may loose their correlation. Hence, it is a non-trivial task to identify genes that share highly similar local expression patterns nearby the event and also allowing some level of divergent expression patterns further away from the event's time point. Here, we propose LOCOS (LOcal COSine), a novel time-course clustering algorithm tailored to cluster genes exhibiting similar expression patterns within a specified time interval. LOCOS is an extension of the traditional Non-negative Matrix Factorization (NMF), which incorporates the cosine similarity and Euclidean distances in its update procedure. LOCOS maximizes the cosine similarity within an interval of interest, while allowing a relaxed minimization of Euclidean distance outside it. Using synthetic and non-biological time-course data, we showed that LOCOS was able to correctly detect the known local patterns within a specified interval. Furthermore, we used longitudinal single-cell RNA-seq samples from four patients showing deteriorating and recovering health conditions to identify genes related to each of the phenotype. As a result, LOCOS was able to capture gene clusters with distinct expression patterns that aligned with the intervals embedding the clinical deterioration and recovery events. © 2024 IEEE.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Developing an Expert System for Mobile-based Gastroenteritis Detection Using ESDLC and Best First Search Methods 8

Developing an Expert System for Mobile-based Gastroenteritis...

引用

8th International Conference on Informatics and Computing, ICIC 2023

作者： Isnanto, R. Rizal Widodo, Catur Edi Windasari, Ike Pertiwi Saputri, Misik Puspajati Diponegoro University Information Systems Doctoral Program Semarang Indonesia Diponegoro University Computer Engineering Department Semarang Indonesia

ISBN: (纸本)9798350342604

Gastroenteritis is a common gastrointestinal disorder with varying degrees of severity, including cases without dehydration, mild dehydration, moderate dehydration, and severe dehydration. This research focuses on the development of a mobile-based expert system for detecting gastroenteritis, capable of distinguishing between these different dehydration levels. The methodology employed integrates the Extreme Structure Development Life Cycle (ESDLC) and the Best First Search algorithm. The expert system is designed to provide swift and accurate responses to users inputting symptoms, categorizing gastroenteritis cases based on the severity of dehydration. The application of ESDLC ensures a structured and organized development process, while the Best First Search method enhances the efficiency of the diagnostic process, facilitating timely and precise recommendations. Accessible through mobile platforms, the system allows users to input symptoms conveniently and receive rapid recommendations. Rigorous testing and evaluation affirm the system's high accuracy in discerning dehydration levels in gastroenteritis patients. In conclusion, the developed mobile-based expert system exhibits promising potential for advancing diagnostic services, particularly in the categorization of dehydration levels in gastroenteritis cases. The successful implementation of ESDLC and Best First Search paves the way for similar solutions in other healthcare domains, contributing positively to early and accurate disease management efforts. This innovation marks a significant stride towards improving healthcare technology for enhanced decision support in gastroenteritis diagnosis. © 2023 IEEE.

关键词： Life cycle

来源：评论

学校读者我要写书评

暂无评论

Gastritis Diagnosis Expert System Using Android-Based Certainty Factor Method 6

Gastritis Diagnosis Expert System Using Android-Based Certai...

引用

6th International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2023

作者： Isnanto, R. Rizal Purwanto Windarto, Yudi Eko Setiawan, Annas Diponegoro University Information Systems Doctoral Program Semarang Indonesia Diponegoro University Computer Engineering Department Semarang Indonesia

ISBN: (纸本)9798350358346

In the modern era, an increasing number of diseases are emerging because of human lifestyle choices and bacterial transmission. Gastritis, characterized by inflammation in the stomach lining leading to frequent abdominal pain, is one such ailment. Recognizing the significance of addressing these health issues, there is a need for an expert system application specifically designed for diagnosing gastritis. The primary objective is to disseminate information to the public regarding the early symptoms of gastritis, promoting awareness from a young age. The research method used is the web-based Expert System Development Life Cycle (ESDLC). The diagnostic process employs the Certainty Factor (CF) method to ensure accurate results. By utilizing symptom CF values chosen by the user, the Certainty Factor approach facilitates a diagnosis based on calculations established by medical specialists. The research culminates in the development of an expert system application capable of accurately diagnosing the disease Android based. The accuracy rates for the first, second, and third test cases are reported as 98.848%, 99.8464%, and 99.99115264%, respectively. System testing, conducted through black-box testing, validates the application's functionality, demonstrating a 100% success rate for each component. © 2023 IEEE.

关键词： Expert systems

来源：评论

学校读者我要写书评

暂无评论

A Shoe Shopping System based on Convolutional Neural Network Image Recognition 5

A Shoe Shopping System based on Convolutional Neural Network...

引用

5th IEEE Eurasia Conference on IOT, Communication and engineering, ECICE 2023

作者： Chang, Chin-Chih Wei, Chi-Hung Chen, Chen-Sheng Chen, Jian-An Yeh, Shih-Hsien Hsiao, Sean Chung Hua University Department of Computer Science and Information Engineering Hsinchu Taiwan Chung Hua University Program in Engineering Science Hsinchu Taiwan Chang Gung University Department of Computer Science and Information Engineering Taoyuan Taiwan Chung Hua University Program in Applied Foreign Language and Smart Commerce Hsinchu Taiwan

ISBN: (纸本)9798350314694

In this article, we present an innovative approach to enhance the online shoe shopping experience. The convolutional neural network (CNN) image recognition technology was used to enhance shoe classification and recommendations. By training the CNN model on an extensive dataset, unique shoe features and styles were learned. Integrated into a user-friendly online platform, the system offers real-time image recognition, allowing users to snap a photo of a desired shoe for instant identification, including brand, price, and availability details. Moreover, the CNN-based recommendation engine provides personalized suggestions based on style, color, and customer preferences, enriching the shopping experience. Evaluation results confirmed the system's feasibility, and user feedback highlighted its effectiveness in simplifying the shopping process and enhancing satisfaction. This innovative system presents a significant leap in merging AI and e-commerce and shows the potential of image recognition to transform online marketplaces, benefiting consumers, offering valuable insights for retailers, and ultimately reshaping the future of online shoe shopping. © 2023 IEEE.

关键词： convolutional neural network (CNN) deep learning image recognition recommender system

来源：评论

学校读者我要写书评

暂无评论

Expert System for Diagnosis of Diphtheria Disease Using Fuzzy Logic 6

Expert System for Diagnosis of Diphtheria Disease Using Fuzz...

引用

6th International Seminar on Research of Information Technology and Intelligent Systems, ISRITI 2023

作者： Isnanto, R.Rizal Mustafid Prasetijo, Agung Budi Fitria Ali, Safira Isna Diponegoro University Information Systems Doctoral Program Semarang Indonesia Diponegoro University Computer Engineering Department Semarang Indonesia

ISBN: (纸本)9798350358346

Diphtheria is an infectious disease that affects the upper respiratory system and throat, arising suddenly and caused by Corynebacterium diphtheriae. The symptoms of diphtheria such as fever, swollen neck and slimy nose are often interpreted as influenza or laryngitis. Diphtheria is a contagious and deadly disease that requires specialized and rapid treatment and care. In today's technological era, it can be overcome with a system that can diagnose diphtheria like a doctor's diagnosis ability commonly called an expert system. This study describes the application of an expert system to diagnose diphtheria disease. The research method used is the web-based Expert System Development Life Cycle (ESDLC). The method used to process input values is Forward Chaining. Fuzzy Tsukamoto to calculate the input value from the user. The research has been tested with Blackbox testing showing the results that the expert system works well and accuracy testing with 92% results. The results show effectiveness with a satisfactory level of accuracy in detecting diphtheria disease. This research contributes to the development of expert systems in the health sector with a focus on diagnosing diphtheria disease using a fuzzy logic approach. © 2023 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Bioinformatics exploration into potential mechanisms of Calamus draco for colorectal cancer treatment 9th

Bioinformatics exploration into potential mechanisms of Cala...

引用

9th International Conference on computer Science and Computational Intelligence, ICCSCI 2024

作者： Kenneth, Christian Nirwantono, Rudi Pardamean, Bens Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta11480 Indonesia Biotechnology Department Faculty of Engineering Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program Computer Science Program Bina Nusantara University Jakarta11480 Indonesia

As one of the cancer types with the highest incidence rates, colorectal cancer (CRC) would benefit from treatments with fewer side effects and reduced treatment-resistant potential. One of the options is to harness the anti-CRC potential of natural products. Previous studies have shown that Calamus draco exudate, dragon's blood, has anticancer activity in liver cancer and acute myeloid leukemia, but its bioactivity has not been studied in CRC. Here we conduct a bioinformatics study based on network pharmacology to explore the anti-CRC potential and mechanism of C. draco-derived compounds. The bioinformatics pipeline is composed of compound and target collection, biological network evaluation, and enrichment analysis. We found that there are 43 bioactive compounds from C. draco targeting 91 CRC-related targets, of which most compounds target MEN1, PTGS2, and IDH1. Further analyses show that the targets of C. draco are involved in the cellular response to hypoxia. By inhibiting those targets, C. draco bioactive compounds can potentially hinder angiogenesis and increase treatment response efficacy. © 2024 The Authors.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

DanceOnStage: positioning training of dancing stage performance in virtual reality 6

DanceOnStage: positioning training of dancing stage performa...

引用

6th IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality, AIxVR 2024

作者： Wu, Ssu-Hsuan Wang, Kai-Ting Chiang, Chia-Chen Chang, Hsin-Yu Yeh, Cheng-Yun Hu, Min-Chun National Tsing Hua University International Intercollegiate Ph.D.Program Hsinchu Taiwan National Tsing Hua University Master of Computer Science Program Hsinchu Taiwan National Tsing Hua University Interdisciplinary Program of Electrical Engineering and Computer Science Hsinchu Taiwan National Tsing Hua University Interdisciplinary Program of Technology and Art Hsinchu Taiwan National Tsing Hua University Hsinchu Taiwan

ISBN: (纸本)9798350372021

This research aims to create a virtual reality-based practice system that simulates real-stage performance environments, assisting amateur dancers in overcoming stage fright and practicing group choreography that is difficult to achieve during individual practice. In this study, users can engage in performance simulations within the created system using the HTC VIVE virtual reality device. Within the system, we have developed a virtual stage space system that only requires a 2m x 3.5m physical area to simulate a large virtual stage experience. Users can also simulate choreographic positioning with virtual dance partners within this system, providing amateur dancers with group dance rehearsal practice opportunities that are not feasible during solo practice. Additionally, by creating three different audience modes, we aim to help users simulate various audience scenarios they may encounter during a performance. The system includes a recording feature that captures users' simulated performances, allowing them to review their actions and receive feedback after practice. © 2024 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Hybrid 1D and 2D CNN-Transformer Architectures for Multilabel 12-Lead EKG Anomaly Detection

Hybrid 1D and 2D CNN-Transformer Architectures for Multilabe...

引用

Annual Conference on Information Sciences and Systems (CISS)

作者： Ian DeTore John Samsundar Cleon Davis Electrical and Computer Engineering Program Johns Hopkins University Baltimore MD USA Electrical and Computer Engineering Program Johns Hopkins University Laurel MD USA

ISBN: (数字)9798331513269

ISBN: (纸本)9798331513276

This study introduces two novel hybrid machine-learning architectures for multilabel anomaly detection in electrocardiograms (EKGs): a 1D modified ResNet combined with a transformer encoder and an equivalent 2D ResNet-Transformer hybrid. This work is among the first to utilize two separate CNN-transformer architectures tailored specifically for temporal and spatial features in multilabel EKG data. Our models address the challenges of imbalanced data and multilabel classification by leveraging the PTB-XL dataset, containing over 21,000 annotated samples across five diagnostic superclasses, namely myocardial infarction, conduction disturbances, hypertrophy, ST-T wave changes, and normal EKGs. We applied advanced data augmentation techniques to mitigate class imbalance, including the Multilabel Synthetic Minority Over-Sampling Technique (ML-SMOTE). Additionally, we employed digital signal processing to denoise the EKG signals and convert time-series data into time-frequency representations for 2D modeling. Experimental results demonstrate the effectiveness of our approach, with the 1D model achieving an area under the curve (AUC) of 91.5% and the 2D model achieving an AUC of 87.2%. These findings demonstrate the potential of specialized architectures for comprehensive multilabel EKG anomaly detection.

关键词： Time-frequency analysis Multi label classification Machine learning Electrocardiography Myocardium Brain modeling Transformers Data models Electromyography Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Enhanced fault diagnosis of wind energy conversion systems using ensemble learning based on sine cosine algorithm

引用

Journal of engineering and Applied Science 2023年第1期70卷 56页

作者： Attouri, Khadija Dhibi, Khaled Mansouri, Majdi Hajji, Mansour Bouzrara, Kais Nounou, Hazem Higher Institute of Applied Sciences and Technology of Kasserine Kairouan University Kasserine1200 Tunisia Chemical Engineering Program Texas A&M University at Qatar 23874 Doha Qatar Electrical and Computer Engineering Program Texas A&M University at Qatar 23874 Doha Qatar Laboratory of Automatic Signal and Image Processing National Engineering School of Monastir University of Monastir Monastir5019 Tunisia

This paper investigates the problem of incipient fault detection and diagnosis (FDD) in wind energy conversion systems (WECS) using an innovative and effective approach called the ensemble learning-sine cosine optimization algorithm (EL-SCOA). The evolved strategy involves two primary steps: first, a sine-cosine algorithm is used to extract and optimize features in order to only select the most descriptive ones. Second, to further improve the capability, thereby providing the highest accuracy performance, the newly gathered dataset is introduced as input to an ensemble learning paradigm, which merges the benefits of boosting and bagging techniques with an artificial neural network classifier. The essential goal of the developed proposal is to discriminate between the diverse operating conditions (one healthy and six faulty conditions). Three potential and frequent types of faults that can affect the system behaviors including short-circuit, open-circuit, and wear-out are considered and thereby injected at diverse locations and sides (grid and generator sides) in order to evaluate the availability and performance of the proposed technique when compared to the conventional FDD methods. The diagnosis performance is analyzed in terms of accuracy, recall, precision, and computation time. The acquired outcomes demonstrate the efficiency of the suggested diagnostic paradigm compared to conventional FDD techniques (accuracy rate has been successfully achieved 98.35%). © 2023, This is a U.S. Government work and not under copyright protection in the US;foreign copyright protection may apply.

关键词： Failure analysis

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：