检索结果-内蒙古大学图书馆

International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)

作者： Jezreel Kosasih Marlinda Vasty Overbeek Niknik Mediyawati Rudi Sutomo Samiaji Bintang Nusantara Informatics Study Program Universitas Multimedia Indonesia Tangerang Indonesia Digital Journalism Study Program Universitas Multimedia Nusantara Tangerang Information System Study Program Universitas Multimedia Nusantara Tangerang

ISBN: (数字)9798331519643

ISBN: (纸本)9798331519650

The research on standardized word error detection and correction is based on technological advances and artificial intelligence as well as the problem of errors that are common in writing journalistic articles due to time constraints and work demands. The research on standardized word error detection and correction is also based on previous research, namely U-Tapis research. The research is a development of U-Tapis research to create a text-based application machine learning to detect and correct word or sentence errors in Indonesian. The research uses the Levenshtein Distance algorithm as the main algorithm for processing input articles. This algorithm will match each character in a word and produce a ratio or similarity value. The research shows success with the accuracy of nonstandard word detection up to 99% and F1 score reaching 92.5%. The research proved to be effective in detecting nonstandard words in Bahasa news articles and was able to replace the word with a standard word.

关键词： Seminars Machine learning algorithms Accuracy Machine learning Writing Natural language processing Time factors Intelligent systems Standards Testing

来源：评论

学校读者我要写书评

暂无评论

Comparison of Machine Learning Text Classification for Intent Sentiment Analysis 7

Comparison of Machine Learning Text Classification for Inten...

引用

7th International Conference on Information Technology, Information Systems and Electrical Engineering, ICITISEE 2023

作者： Muhammad, Abulwafa Defit, Sarjon Cahyo, Gunadi Widi Nur Universitas Putra Indonesia Yptk Padang Faculty of Computer Science Department of Informatics Technology Padang Indonesia Universitas Putra Indonesia Yptk Padang Doctoral Program in Information Technology Padang Indonesia

ISBN: (纸本)9798350382266

Tourist destination reviews on Google Maps have become a valuable point of reference for visitors seeking enjoyable spots to visit. Additionally, users can gain insight into the reasons for writing reviews. Text classification is used to determine the motivation behind these reviews. The aim of this study is to compare machine learning (ML) text classification techniques for identifying the intent behind sentiments expressed as complaints (0), suggestions (1), opinions (2), statements(3), and awards (4). The ML techniques assessed are Multinomial Naive Bayes (MNB), Support Vector Machine (SVM), and K-Nearest Neighbor (KNN). To achieve this, tourist destination review data sets, comprising 738 reviews, were collected using web scraping from the Google Maps website. Preprocessing stages, including case-folding, tokenisation, filtering and stemming, are executed prior to the data being prepped for feature extraction with TF-IDF. The employed classification models perform well with KNN achieving 1.00 accuracy on a 90:10 data split, and SVM obtaining 0.90 on the same data split. Although, the Multinomial Naive Bayes algorithm with 0.70 accuracy on a 90:10 data split is classified as fair. Comparison of methods was conducted by means of a Receiver Operating Characteristic (ROC) diagram. The testing accuracy for the SVM method was found to be 95%, MNB at 91%, and KNN at 84%. © 2023 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Coevolution of Myoelectric Hand Control under the Tactile Interaction among Fingers and Objects

引用

Cyborg and Bionic Systems 2022年第1期2022卷 285-302页

作者： Yuki Kuroda Yusuke Yamanoi Shunta Togo Yinlai Jiang Hiroshi Yokoi Joint Doctoral Program for Sustainability Research Graduate School of Informatics and Engineering The University of Electro-CommunicationsTokyoJapan Department of Mechan ical and Intelligent System Engineering Graduate School of Informatics and Engineering The University of Electro Communications TokyoJapan Center for Neuroscience and Biomedical Engineering The University of Electro Communications TokyoJapan Bejing Innovation Center for Inelligent Robots and Systems BeijingChina

The usability of a prosthetic hand difers significantly from that of a real ***,the complexity of manipulation increases as the number of degrees of freedom to be controlled increases,making manipulation with biological signals extremely *** overcome this problem,users need to select a grasping posture that is adaptive to the object and a stable grasping method that prevents the object from *** previous studies,these have been left to the operating skills of the user,which is extremely difficult to *** this study,we demonstrate how stable and adaptive grasping can be achieved according to the object regardless of the user's operation *** required grasping technique is achieved by determining the correlation bet ween the motor output and each sensor through the interaction between the prosthetic hand and the surrounding stimuli,such as myoelectricity,sense of touch,and grasping *** agents of the 16 DOF robot hand were trained with the myoelectric signals of six participants,including one child with a congenital forearm ***,each agent could open and close the hand in response to the myoeletric stimuli and could accomplish the object pickup *** the tasks,the agents successfully identified grasping patterns suitable for practical and stable positioning of the *** addition,the agents were able to pick up the object in a similar posture regardless of the partiipant,suggesting that the hand was optimized by evolutionary computation to a posture that prevents the object from being dropped.

关键词： robot Objects overcome

来源：评论

学校读者我要写书评

暂无评论

Smart Electrical Devices Control with Intrusion Detection Alert

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2022年第5期16卷 139-152页

作者： Achmad, Andani Muliadi Areni, Intan Sari Palantei, Elyas Hadis, Muhammad Sabirin Department of Electrical Engineering Faculty of Engineering Universitas Hasanuddin Gowa Indonesia Department of Electrical Engineering Education Faculty of Engineering Universitas Negeri Makassar Indonesia Study Program of Informatics STMIK AKBA Makassar Indonesia

The consumption profile of electrical energy always increases every year due to the highly consumptive and inappropriate lifestyles of modern society. A bad lifestyle such as forgetting to turn off the unused electronic devices when they are leaving home is one of the factors influenced the increasing consumption of electrical energy. This is off course contributing in wasting energy. In the paper, an IoT-based electronic device control system has been successfully constructed. Monitoring and control tasks could be performed remotely and in real time mode using an interface application installed on a smartphone. The system built is equipped with a device operational condition monitoring featured by placing light, temperature, thermal and current sensors, respectively. Through the utilization of the implemented system, users can monitor and control electronic devices easily and can figure out the condition of the device remotely in a real time mode. The control test on the system was successful with an average response time of approximately 3.32 seconds and the accuracy of sensor readings above 89%. With the implementation of this system, users can easily monitor and control electronic devices anywhere and anytime so that the opportunities for efficient and effective use of electrical energy could be further optimized. © 2022. All Rights Reserved.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

ConvNeXt Model for Breast Cancer Image Classification 6

ConvNeXt Model for Breast Cancer Image Classification

引用

6th International Conference on Cybernetics and Intelligent System, ICORIS 2024

作者： Setiawan, Devin Karnyoto, Andrea Stevens Intan, Indo Pardamean, Bens Department of Electrical Engineering and Computer Science University of Kansas Lawrence United States Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Department of Informatics Engineering Universitas Dipa Makassar Makassar Indonesia Computer Science Department BINUS Graduate Program Computer Science Program Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9798331539603

Breast cancer is an occurrence of cancer that attacks breast tissue and is the most common cancer among women worldwide, affecting one in eight women. In this modern world, breast cancer image classification simplifies the process of analyzing, providing objective and accurate results. By leveraging machine learning algorithms and computer vision techniques, we developed breast cancer detection. The dataset is histopathology dataset from BreakHis and UNHAS Hospital. We chose the ConvNeXt-Tiny model then modified the classifier head as the proposed method. Before the dataset is processed by the model, we augment the images by applying random horizontal and vertical flips, adjustments to brightness, contrast, saturation, and hue using color jitter. The augmentation process simulates real-world variance and enhances the model's ability to generalize to unseen data. Our proposed model gained better performance (accuracy, F1-Score) results compared two other techniques to VGG16 and SVM. According to our experiments, the F1-Score for the ConvNeXt-Tiny model with classifier head modification is higher at 0.9516, than the gain for VGG16 at 0.9292, and the gain for the SVM at 0.83. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Training Swinging Door Trending Compression Algorithm for IoT devices 10

Training Swinging Door Trending Compression Algorithm for Io...

引用

10th IEEE World Forum on Internet of Things, WF-IoT 2024

作者： Correa, Juan David Arias Pinto, Alex Sandro Roschildt Montez, Carlos Post-graduate Program of Automation Systems Engineering Florianópolis Brazil Dept. of Informatics and Statistic Dept. of Automation and Systems Engineering Florianópolis Brazil Dept. of Automation and Systems Engineering Florianópolis Brazil

ISBN: (纸本)9798350373011

The communication system is essential for the devices used in IoT. Nevertheless, the consumption caused by transmitting and receiving data is a concern in many scenarios. That is due to these devices commonly having limited energy and computational capacities. Transmission of redundant or irrelevant samples frequently wastes the device's resources. Furthermore, Storing a large amount of redundant data could consume storage space and not offer any benefit. Data Compression (DC) methods are a potential solution. DC could reduce communication usage and storage demand. This research proposes the Training Swing Door Trending (TSDT) for being implemented in IoT Devices. TSDT is a new algorithm that improves the classic Swing Door Trending (STD). They represent the data by trend lines and have a constant computational complexity. TSDT has a training step for the automatic configuration of its parameters. This article additionally presents the Compression Factor (C-Score), a new quality metric to analyze the compression results in lossy DC methods. C-Score takes as a basis the F-Score, a measure of predictive performance. The C-Score uses the Compression and Error metrics to evaluate the compression performance in Lossy Algorithms. © 2024 IEEE.

关键词： Data compression ratio

来源：评论

学校读者我要写书评

暂无评论

Effective Alzheimer's Stage Classification Using Transfer Learning Based on MRI Images 7

Effective Alzheimer's Stage Classification Using Transfer Le...

引用

7th International Conference on Vocational Education and Electrical Engineering, ICVEE 2024

作者： Hamdani, Hamdani Septiarini, Anindita Pawitra, Theresia Amelia Sumampouw, Aldion Tejawati, Andi Kurniawan, Tri Basuki Mulawarman University Dept. of Informatics Faculty of Engineering Samarinda Indonesia Mulawarman University Dept. of Industrial Engineering Faculty of Engineering Samarinda Indonesia Universitas Bina Darma Magister Information of Technology Postgraduate Program Palembang Indonesia

ISBN: (纸本)9798331505103

Alzheimer's disease (AD) is a progressive neurodegenerative disorder and the most prevalent cause of dementia, significantly impacting cognitive functions and daily activities. Accurate and timely classification of AD stages is of paramount importance for the effective treatment and management of the disease. The aim of this research is to employ transfer learning in a convolutional neural network (CNN) to classify the stages of AD using magnetic resonance imaging (MRI) brain images, building on the aforementioned foundational principles. The CNN model employed in this study is MobileNetV3-Small, which has been trained on a comprehensive dataset of labeled MRI scans with the objective of accurately distinguishing the various stages of AD. The dataset, referred to as the 'Augmented Alzheimer MRI Dataset,' comprises 3 3, 9 8 4 augmented and 6, 4 0 0 original MRI images, which have been categorized into four stages: Very Mild Demented, Moderate Demented, Mild Demented, and NonDemented. The methodology comprises three principal stages: data preparation, model training, and model evaluation. A systematic assessment of various hyperparameters, including split ratio, learning rate, batch size, and dropout rate, was conducted to optimize model performance. The results demonstrate that fine-tuning the model significantly enhances classification accuracy, achieving a maximum accuracy of 9 6 % compared to 7 2 % without fine-tuning. A smaller learning rate was found to improve performance metrics by preventing the model from converging to local minima. These findings highlight the potential of transfer learning and hyperparameter optimization in developing robust models for the early detection and classification of AD, contributing to better patient outcomes and advancing the field of medical image analysis. © 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

Quantitative Assessment of Gait in Spinocerebellar Ataxia Using Deep Learning 4

Quantitative Assessment of Gait in Spinocerebellar Ataxia Us...

引用

4th IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2024

作者： Lai, Ming-Hui Liu, Don-Gey Cheng, Ching-Hwa Lai, Chung-Yu Master's Program of Biomedical Informatics and Biomedical Engineering Feng Chia University Taichung Taiwan Feng Chia University Department of Electronic Engineering Taichung Taiwan Hungkuang University Department of Medical Equipment Development and Application Taichung Taiwan

ISBN: (纸本)9798350360721

Spinocerebellar ataxia is a neurological disorder characterized by impaired neural coordination, leading to unstable gait, coordination difficulties, and other motor abnormalities. This disease significantly impacts patients' daily lives, making it challenging for them to maintain balance, walk smoothly, and even perform fine motor skills. The causes of spinocerebellar ataxia are diverse, including genetic factors, brain injuries, or certain diseases. Many patients with spinocerebellar ataxia require specialized medical care and ongoing monitoring to manage its effects. This study aims to utilize Human Posture Estimation to detect the gait patterns of patients with spinocerebellar ataxia and integrate it with a deep learning model to distinguish between normal and affected individuals. The outcomes offer physicians an objective diagnostic tool and facilitate early detection and intervention for patients with impaired gait, thereby supporting the enhancement or preservation of their quality of life. The current prediction accuracy for the risk of ataxia gait is 80%, with an F1 score of 78.26%. It is necessary to conduct a detailed quantitative assessment by analyzing the gait of patients with spinocerebellar ataxia. Quantitative evaluation of the data allows for an objective assessment of the patient's gait, which helps healthcare professionals to more accurately understand and assess the gait status of patients with spinocerebellar ataxia. © 2024 IEEE.

关键词： Gait analysis

来源：评论

学校读者我要写书评

暂无评论

A VAE-Based Data Augmentation Method for Fall Detection System using Wearable Sensor 10

A VAE-Based Data Augmentation Method for Fall Detection Syst...

引用

10th International Conference on Applied System Innovation, ICASI 2024

作者： Tu, Yu-Chen Wang, Hsuan-Chih Liu, Chien-Pin Hsieh, Chia-Yeh Chan, Chia-Tai National Yang Ming Chiao Tung University Department of Biomedical Engineering Taipei City112 Taiwan Bachelor's Program in Medical Informatics and Innovative Applications Fu Jen Catholic University New Taipei City242062 Taiwan

ISBN: (纸本)9798350394924

Fall incidents among the elderly represent a significant global concern, often resulting in physical injuries and psychological distress. It is crucial to develop reliable fall detection systems which are capable of identifying fall events immediately and triggering alerts for assistance. However, real-world fall occurrences are infrequent, leading to a highly imbalanced class situation. Training a model with imbalanced datasets may result in biased models with poor performance in fall detection. To address this challenge, various techniques such as data transformation and Synthetic Minority Oversampling Technique (SMOTE) have been proposed. However, these methods are constrained by issues such as limitations in input data size or sensitivity to outliers. Compared to other methods, variational autoencoder (VAE) can generate data with a similar probability distribution to the original input data while constraining the latent representation in a Gaussian distribution. This study proposes a VAE-based data augmentation method for wearable-based fall detection system. The proposed method is validated on the FallAllD public dataset, achieving a F-score of 99.46%. The performance has been increased by 2.21%. The results demonstrate the effectiveness of VAE-based data augmentation technique in enhancing fall detection systems and its superior performance compared with other traditional data augmentation methods. © 2024 IEEE.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Bibliometric Analysis of Trends and Directions in Machine Learning Applied to FinTech 4

Bibliometric Analysis of Trends and Directions in Machine Le...

引用

4th International Conference on Electronic and Electrical Engineering and Intelligent System, ICE3IS 2024

作者： Arif, Erman Suherman, Suherman Widodo, Aris Puji Doctoral Program of Information System School of Postgraduate Studies Diponegoro University Semarang Indonesia Diponegoro University Faculty of Engineering Department of Chemical Engineering Semarang Indonesia Diponegoro University Faculty of Science and Mathematics Department of Informatics Semarang Indonesia

ISBN: (纸本)9798350378368

Our article presents a comprehensive analysis of trends and directions in the application of machine learning in the FinTech sector. By utilizing data from academic databases such as Scopus, our objective is to showcase the advancements in this interdisciplinary research area. The study identifies key trends, influential authors, leading journals, and significant collaborative networks that shape the field. The methodology employed involves quantitative bibliometric analysis to evaluate publications from the past five years. The results indicate a substantial increase in the number of studies during this period, highlighting the importance of machine learning in addressing critical financial challenges, including fraud detection, algorithmic trading, credit scoring, and risk management. Additionally, we delve into the main themes, countries, and institutions that dominate the current research agenda. This analysis provides valuable insights into the present state and future direction of machine learning in FinTech, serving as a resource for researchers and practitioners seeking to comprehend and contribute to this dynamic and rapidly evolving field. We also discuss implications for future research, emphasizing the necessity for continuous innovation and interdisciplinary collaboration to maximize the potential of machine learning in transforming financial services. © 2024 IEEE.

关键词： Adversarial machine learning

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：