检索结果-内蒙古大学图书馆

computer science, Information Technology and Engineering (ICCoSITE), International Conference on

作者： Rissa Rahmania Harco Leslie Hendric Spits Warnars Benfano Soewito Ford Lumban Gaol Computer Science Department BINUS Graduate Program Computer Science Bina Nusantara University Jakarta Indonesia

The ability to differentiate various products in the retail store plays an essential role to provide effectiveness to customers and reduce or even eliminate long queues. However, traditional machine learning algorithms are incapable of recognizing many subordinate categories in various retail product. This paper aims to recognize the retail product recognition algorithm based on the YOLOv7 model in terms of intra-class variations, with the sub-categories of brand and size. We used two schemes of the dataset to compare recognition performance between them. Firstly, the YOLOv7 is applied in the two schemes of the dataset that is annotated with the subordinate category to detect the brand as meta category. Secondly, the proposed method is applied by adding the object size classification into the YOLOv7 model where the square area of the bounding box was calculated to classify the product according to size. Confidence score and square area are used to verify the object and to obtain the product size, which represents sub-category of the product. The experimental results show that our proposed method achieves higher recall compared to baseline object detection.

关键词： computer science Machine learning algorithms Automation Transfer learning Object detection computer architecture Information technology

来源：评论

学校读者我要写书评

暂无评论

Analysis of Feature Selection Methods On Clove Quality Classification

Analysis of Feature Selection Methods On Clove Quality Class...

引用

International Conference on Information Technology (INCIT)

作者： Firman Tempola Aina Musdholifah Retantyo Wardoyo Doctoral Program Department of Computer Science and Electronics Universitas Gadjah Mada Yogyakarta Indonesia Department of Computer Science and Electronics Universitas Gadjah Mada Yogyakarta Indonesia

ISBN: (数字)9798350366303

ISBN: (纸本)9798350366310

Proper feature selection is becoming increasingly important in the context of clove quality classification in Indonesia; effective feature selection can identify the most relevant attributes of clove quality. This study investigates 3 famous feature selection methods, namely mutual information, recursive feature selection, and lasso regression, for classifying clove quality using various models, i.e. Naïve Bayes, K-NN, and Decision Tree. The study results showed that the mutual information feature selection method impacted the K-NN method by 1.05%; for naïve Bayes and decision trees, the accuracy did not increase. For the recursive feature elimination (RFE) feature selection method, the accuracy of K-NN increased by 2.16%, the decision tree by 0.37%, and naïve Bayes accuracy did not increase. In addition, using Lasso Regression feature selection, the accuracy of naïve Bayes increased by 2.97%, K-NN by 2.28%, and decision tree accuracy decreased.

关键词： Analytical models Accuracy Lighting Machine learning Nearest neighbor methods Feature extraction Bayes methods Information technology Mutual information Regression tree analysis

来源：评论

学校读者我要写书评

暂无评论

Multiclassifier for Aspect-Based Sentiment Analysis on Indonesian Reviews of Kredit Pintar Online Lending App

Multiclassifier for Aspect-Based Sentiment Analysis on Indon...

引用

International Conference of Information and Communication Technology (ICoICT)

作者： Nanda Yuniar Aina Musdholifah Undergraduate Program in Computer Science Universitas Gadjah Mada Yogyakarta Indonesia Department of Computer Science and Electronics Universitas Gadjah Mada Yogyakarta Indonesia

ISBN: (数字)9798350363432

ISBN: (纸本)9798350363449

Aspect-based sentiment analysis is carried out to determine user sentiment's polarity while still considering the aspects of the discussion so that all information in the reviews can be represented. The multiclassifier in this research means that two classifiers are used, the first is an aspect classifier to perform aspect classification, and the second is a sentiment classifier to perform sentiment classification based on its aspect. Two approaches were studied according to their classification work, namely, individual model in the form of an aspect classification and sentiment classification based on the aspects individually and sequentially model by testing the aspect and sentiment models sequentially. This study evaluates the performance of Support Vector Machine (SVM) and Naïve Bayes Classifier (NBC) algorithms and their combination in sequential testing. In addition, to overcome imbalance dataset, the use of oversampling types is also compared. In the individual approach, the SVM model with random oversampling showed the best performance with average accuracy, precision, recall, and f1 score of 92%, 86%, 80%, and 83% for the aspect model and 86%, 81%, 80%, and 80% for the sentiment model, respectively. While in the sequential approach, the combination of SVM-SVM with oversampling shows the best performance with an average accuracy, precision, recall, and f1-score of 79%, 56%, 50%, and 53%, while the performance of other model combinations is only in the maximum range of 77% accuracy, 55% precision, 51% recall, and 52% f1-score.

关键词： Support vector machines Sentiment analysis Accuracy Reviews Vectors Bayes methods Information and communication technology Classification algorithms Testing

来源：评论

学校读者我要写书评

暂无评论

Q-Learning Energy Management System (Q-EMS) in Wireless Sensor Network

Q-Learning Energy Management System (Q-EMS) in Wireless Sens...

引用

2024 International Conference on Smart Computing, IoT and Machine Learning, SIML 2024

作者： Ardiansyah, Deden Mustafid Mantoro, Teddy Universitas Diponegoro Doctoral Program of Information Systems School of Postgraduate Central Java Semarang Indonesia Universitas Pakuan Vocational School Computer Engineering Department West Java Bogor Indonesia Sampoerna University Media-Tech-Lab Computer Science Department DKI Jakarta Indonesia

ISBN: (纸本)9798350364101

The energy control of a Wireless Sensor Network (WSN) often leads to an unbalanced state between the battery storage system, energy extraction through photovoltaic systems energy, and energy utilization in the WSN. These disparities result in suboptimal wireless sensor network performance. The reliance on batteries is a major factor contributing to this problem. The Q-Learning Energy Management System (Q-EMS) is designed to address these challenges and improve energy management strategies. The Q-EMS algorithm used a learning process resulting in optimal actions for sensor nodes in different situations. The rewards or punishments nodes receive determine their decisions, which are determined by the Q-EMS algorithm. The Q-learning model approach is aimed at reducing energy consumption and supply in WSNs. Energy supply is categorized into battery-based, transfer-based, and harvesting, while energy consumption can be classified into task-cycle, mobility-based, and data-driven. The development of the Q Learning algorithm model has three scenarios: determining energy needs for WSN, effective energy harvesting strategy, and effective energy transfer. As a result, effective energy demand, harvesting and transfer using the Q-learning algorithm are balanced. However, it needs to be studied in more depth using real data in the field. In future research, I will use real data and optimize the use of the Q-Learning algorithm. © 2024 IEEE.

关键词： Energy management systems

来源：评论

学校读者我要写书评

暂无评论

Cross-Modal Knowledge Distillation With Multi-Stage Adaptive Feature Fusion for Speech Separation

IEEE Transactions on Audio, Speech and Language Processing

引用

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 935-948页

作者： Cunhang Fan Wang Xiang Jianhua Tao Jiangyan Yi Zhao Lv Anhui Province Key Laboratory of Multimodal Cognitive Computation School of Computer Science and Technology Anhui University Hefei China Department of Automation Tsinghua University Beijing China

Although audio-visual speech separation has achieved significant advancements, it is relatively difficult to obtain audio and visual modalities simultaneously in real scenarios, often leading to the issue of missing visual modality. Actually, during the training phase of the speech separation network, the developed audio and video datasets can be fully utilized to obtain an effectual audio-visual speech separation. However, enhancing the performance of unimodal models during testing using multimodal approaches poses a challenge. To address the problem, this paper proposes a cross-modal knowledge distillation method for speech separation, which leverages a multimodal model to enhance the unimodal model via knowledge distillation. Specifically, during the training phase, a pre-trained audio-visual network is used as the teacher and the audio-only network is used as the student. Then the teacher with the additional visual input transfers knowledge to the student to enhance the performance of the student model. During the test phase, the audio-only network only conducts speech separation. In addition, to further improve the performance of the teacher model, a multi-stage adaptive feature fusion method is proposed. The global and local perspectives are used to effectively capture deep audio-visual correlations. We have conducted extensive experiments with audio-visual datasets LRS2, LRS3, and VoxCeleb2. Experimental results demonstrate that our proposed method effectively improves the student model by 15% $\sim$ 25% relative improvements over the baseline in terms of SI-SNRi and SDRi.

关键词： Visualization Training Knowledge engineering Adaptation models Correlation Testing Data models Neural networks Feature extraction Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

Mobile Application for Haircut Art Community 2

Mobile Application for Haircut Art Community

引用

2nd International Conference on Artificial Intelligence and Smart Energy, ICAIS 2022

作者： Fahmi, Hilal Nugroho, Muhammad Ivan Setiawan, Kristian Daniel Gary, Vittorio Moedjiono, Sardjoeni Warnars, Harco Leslie Hendric Spits School of Information Systems Bina Nusantara University Information Systems Department Jakarta11480 Indonesia Budi Luhur University Faculty of Information Technology Computer Science Department Jakarta Indonesia Bina Nusantara University Binus Graduate Program - Computer Science Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9781665400527

The haircut art community is a community that is interested in the art of hair or hair-related issues and information. This haircut art community has several members, but they need the application of technology to support their hobby as a community. In this mobile application, a system where users can make transactions connected to the haircut community has been proposed. Users can make online appointments with barbers' haircuts, make online payments, engage with forums, and get information about the barbershop community. In addition, this mobile app will allow people in the community to sell and buy anything related to haircuts. In addition, it is hoped that it can be used as an income opportunity for people who have expertise in the art of barbering. This application is implemented using visual studio and MySQL database for the database. This application is modeled using use case diagrams to describe its business processes and class diagrams to describe the database design. © 2022 IEEE.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Representations of emotion concepts: Comparison across pairwise, appraisal feature-based, and word embedding-based similarity spaces 44

Representations of emotion concepts: Comparison across pairw...

引用

44th Annual Meeting of the cognitive science Society: cognitive Diversity, CogSci 2022

作者： Kwon, Mijin Wager, Tor D. Phillips, Jonathan Department of Psychological and Brain Sciences Dartmouth College United States Program in Cognitive Science Dartmouth College United States Department of Philosophy Dartmouth College United States

A question that has long interested cognitive scientists is how to best represent the different emotions we experience and attribute to others. For example, constructionist and appraisal theories propose that differences between emotions can be captured in part by their variation along a set of appraisal dimensions. More recently, researchers have used language models to capture the differences across different emotion terms. Both approaches allow us to represent emotions as occupying different locations in high-dimensional representational spaces. To ask how well these different approaches capture the similarity between emotion concepts, we collected pairwise similarity and appraisal feature ratings for 58 different emotion concepts and then employed representational similarity analysis to investigate the overlap between people's pairwise similarity judgments and emotion similarity in a 14-dimensional appraisal space and three word embedding spaces from two word2vec models (300 dimensions) and the newer GPT-3 model (12288 dimensions). The results indicate that while there is a high correlation between appraisal feature-based similarity and pairwise similarity judgments, word embedding-based similarity exhibits lower correlations, though GPT-3 showed much better performance than the word2vec models. Finally, characterizing the errors made by word embedding models showed that they can be largely attributed to an over-reliance on the valence of emotion concepts. © 2022 The Author(s). This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY)

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Individual Performance of Students in Online Learning Environments: Study of User Satisfaction 10

Individual Performance of Students in Online Learning Enviro...

引用

10th International Conference on Information Technology, computer, and Electrical Engineering, ICITACEE 2023

作者： Alamsyah, Doni Purnama Indriana Utomo, Satrio Matin Siswanto, Boby Susanti, Leni Morika, Doni Bina Nusantara University BINUS Business School Entrepreneurship Department Jakarta11480 Indonesia Bina Nusantara University Management Program BINUS Business School Jakarta11480 Indonesia Bina Nusantara University Computer Science Study Program School of Computer Science Jakarta11480 Indonesia Bina Nusantara University Interior Design Study Program School of Design Jakarta11480 Indonesia

ISBN: (纸本)9798350322729

Investigation on e-learning is important, especially user satisfaction in support of student academic performance. Evaluation of user satisfaction can be measured by evaluating perceived quality on the user's side, so this research aims to investigate the role of perceived quality over online learning on User satisfaction. Users of online learning targeted are students because students have experience and knowledge of the implementation of online learning at the university. Collected data and information from students related to satisfaction with online learning through online questionnaires. 615 students filled out questionnaires, then questionnaire data was processed quantitatively through SPSS with statistical testing based on research hypotheses. Three factors essentially increase user satisfaction in online learning, regarding the system, service, and information. Student satisfaction can be improved when supported by information on the platform. The role of a platform regarding information in the online learning context is important, a measure that explains the quality of information among other things useful, understandable, interesting, and reliable. Research findings provide important information for universities as organizers of education, aimed at attaining information quality related to online learning. © 2023 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

DARTS-Drone and Artificial Intelligence Reconsolidated Technological Solution for Increasing the Oil and Gas Pipeline Resilience

引用

International Journal of Disaster Risk science 2022年第5期13卷 810-821页

作者： Premkumar Ravishankar Seokyon Hwang Jing Zhang Ibrahim X.Khalilullah Berna Eren-Tokgoz Department of Industrial and Systems Engineering Lamar UniversityBeaumontTX 77710USA Construction Management Program Lamar UniversityBeaumontTX 77710USA Department of Computer Science Lamar UniversityBeaumontTX 77710USA

The need for safe operation and effective maintenance of pipelines grows as oil and gas demand ***,it is increasingly imperative to monitor and inspect the pipeline system,detect causes contributing to developing pipeline damage,and perform preventive maintenance in a timely ***,pipeline inspection is performed at pre-determined intervals of several months,which is not sufficiently robust in terms of *** research proposes a drone and artificial intelligence reconsolidated technological solution(DARTS) by integrating drone technology and deep learning *** solution is aimed to detect the targeted potential root problems-pipes out of alignment and deterioration of pipe support system-that can cause critical pipeline failures and predict the progress of the detected problems by collecting and analyzing image data *** test results show that DARTS can be effectively used to support decision making for preventive pipeline maintenance to increase pipeline system s afety and resilience.

关键词： Artifcial intelligence Asset management Drone application Midstream industry Pipeline resilience Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

Dynamic Terrain Data Exchange in a Collaborative Terrain Editor

引用

Informatica (Slovenia) 2022年第4期46卷 575-582页

作者： Tarigan, Jos Timanta Sitompul, Opim Salim Zarlis, Muhammad Nababan, Erna Budhiarti Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia Information Systems Management Department BINUS Graduate Program Bina Nusantara University Jakarta Indonesia

In a computer supported cooperative work (CSCW), data consistency between collaborating users is a crucial issue. Based on the type of the application, ensuring data consistency can be a lengthy process that takes time and affects the system’s performance. In most 3D application, terrain data are massive due to its size. Exchanging this data may be expensive and may cause significant delay. In a real-time collaborative terrain editor, this issue becomes more significant due to terrain data exchange is consistently occurred between collaborating users. We present a solution to perform a conflict-free dynamic terrain data exchange in a real-time collaborative terrain editor. Our objective is to develop a method that able to ensure data consistency amongst collaborating peers in real-time manner. The main idea of our method is to split the terrain into smaller patches and synchronize the changes efficiently by only exchanging the modified patches. We applied our solution to a collaborative terrain editor application to test its performance in a real-time collaborative editing session. The tests were done in multiple scenarios, using different patch model, brush size (in the terrain editor), and connection setup between server and collaborating clients. The result shows that our protocol is capable to maintain data consistency between collaborating clients in a real-time terrain edition session. The delay is varied and highly depends on the data size and client-server environment setup. The overall test shows that it is possible to perform a collaborative terrain editing with an acceptable response time delay. In this paper, we present our proposed method, the implementation, and the result data from the test. © 2022 Slovene Society Informatika. All rights reserved.

关键词： Electronic data interchange

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：