检索结果-内蒙古大学图书馆

Advances in Signal Processing, Power, Communication, and Computing (ASPCC), IEEE International Conference on

作者： Prasandika Balage Nuwan Jayawardene School of Computer Science and Engineering University of Westminster London United Kingdom Department of Computing Informatics Institute of Technology Colombo Sri Lanka

ISBN: (数字)9798350355093

ISBN: (纸本)9798350355109

Visual impairment is characterized by the loss of vision, encompassing both complete blindness and partial vision loss. Studies reveal a notable prevalence of visual impairment among school-aged children. The significance of colors in acquiring and discerning visual information is crucial, aiding children in effectively perceiving and comprehending their surroundings. This study presents an Internet of Things (IoT) system designed for teaching colors to visually impaired children. The system achieved an accuracy rate surpassing 77.8%, and it is operated effectively regardless of surrounding lighting conditions. Given that the target users of the system are visually impaired children, this research was conducted in close alignment with Human-computer Interaction (HCI) principles.

关键词： Human computer interaction Visualization Accuracy Visual impairment Education Lighting Color Blindness Signal processing Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis of Game Reviews on STEAM using BERT, BiLSTM, and CRF

Sentiment Analysis of Game Reviews on STEAM using BERT, BiLS...

引用

International Conference on Electrical engineering and informatics, ICEEI

作者： Jalaluddin Al Mursyidy Fadhlurrahman Neng Ayu Herawati Hayyu Rachma Widya Aulya Ira Puspasari Nugraha Priya Utama School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia Computer Engineering Department Dinamika University Surabaya Indonesia

The Steam platform releases thousands of games almost every week, providing customers with many options, which require various considerations to make a purchase decision. Steam has features that can help consumers consider purchasing games, such as the help dashboard that provides information on game reviews and ratings. However, based on user input reviews, game ratings are still manual, which may cause human error and inaccurate results. To help gamers get the desired game information and increase customer purchasing power towards available games, sentiment analysis is one technique for classifying opinions. This study focuses on sentiment analysis of game reviews, which will result in classification into two classes, positive and negative. It will be measured for its performance based on the f1 score evaluation results. The proposed model that we created is to compare sentiment analysis models using the baseline Bi-directional Long-short Term Memory (BiLSTM), Bidirectional Gated Recurrent Unit (BiGRU), and fine-tuning Bidirectional Encoder Representations from Transformer (BERT). We then propose another model, BiLSTM-CRF, by examining the effect of using the last four hidden states of BERT and comparing it with the last one hidden state of BERT to be used in the BiLSTM-CRF model. Based on the results of sentiment analysis models we developed for the ten most reviewed games on Steam, the BiLSTM model combined with CRF on the last four hidden states yielded the best performance, with an Fl score of 95.2 %. This score exceeds the baseline transformer-based model's Fl score of 88.0%. This is because combining BiLSTM and CRF allows the log-likelihood of the BiLSTM emission sample to be obtained more accurately so the model does not lose its context.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning from Multi-Omics Networks to Enhance Disease Prediction: An Optimized Network Embedding and Fusion Approach

Learning from Multi-Omics Networks to Enhance Disease Predic...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Hussein, Sundous Ramos, Vicente Liu, Weixuan Kechris, Katerina J. Lange, Leslie Bowler, Russell P. Banaei-Kashani, Farnoush University of Colorado Denver Department of Computer Science and Engineering DenverCO United States University of Colorado Anschutz Medical Campus Department of Biostatistics and Informatics AuroraCO United States University of Colorado Anschutz Medical Campus Division of Biomedical Informatics and Personalized Medicine AuroraCO United States Cleveland Clinic Main Campus Genomic Medicine Institute ClevelandOH United States

ISBN: (纸本)9798350386226

Understanding complex diseases hinges on a profound understanding of intricate biomolecular interactions unfolding within a complex, multidimensional landscape, challenging traditional methods to extract meaningful insights. While multi-omics networks capture the richness of biological data, providing a basis for predicting relationships between biomolecules and various phenotypic traits of complex diseases, their inherent complexity limits their predictive power. To address this challenge, we introduce a novel pipeline that leverages the power of Graph Neural Networks (GNNs) to extract and integrate meaningful information from multi-omics networks. By generating informative node embeddings and seamlessly incorporating them into the original subject-level data, our approach captures both local and global network dependencies, leading to substantial improvements in disease prediction accuracy. The proposed pipeline optimizes the embedding generation process for the specific prediction task, enabling the model to learn task-relevant representations. Through rigorous experimentation, we demonstrate the superior performance of our approach, surpassing existing methods by a substantial margin on nine real-world multi-omics datasets. With remarkable increases in accuracy ranging approximately from 8% to 10% over the best-performing baseline, particularly when the multi-omics networks are moderately dense, striking a balance between capturing complex relationships and avoiding excessive noise. Our findings underscore the potential of GNNs to significantly improve disease prediction by effectively extracting and representing knowledge embedded within multi-omics networks. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Mechanical Ventilator Control System Using Low-Cost Pressure Sensors

Mechanical Ventilator Control System Using Low-Cost Pressure...

引用

2021 International Conference on computer Science, Information Technology, and Electrical engineering, ICOMITEE 2021

作者： Haq, Endi Sailul Suwardiyanto, Devit Rini, Eka Mistiko Sigit, Riyanto Kristanto, Sepyan Purnama State Polytechnic of Banyuwangi Informatics Engineering Banyuwangi Indonesia Electronic Engineering Polytechnic Institute of Surabaya Computer Engineering Surabaya Indonesia

ISBN: (纸本)9781665401470

The increasingly active cases of people with the COVID- 19 viruses have reached a very worrying level in most countries globally. The availability of ventilators in hospitals is one factor that increases the number of deaths in Indonesia. In this study, we present a control system on a mechanical ventilator using an inexpensive pressure sensor to control pressure, flow rate, and volume during the process of inspiration and expiration. The implemented method uses the venturi meter concept by comparing two air pressure sensors flowed by the Ambu bag. The control system on this ventilator uses a microcontroller and MPX5050DP sensor. The system tries to maintain the PEEP value of 5 cmH2O, and the feedback obtained ranges from 2.7-5.16 cmH2O. At the same time, the expected flowrate value of 55 L/min can be maintained at a value of 53.9 - 59.5 L/min. The tidal volume, which functions as a limiter for inspiration and expiration, is set at a value of 400 ml;the feedback given by the sensor varies between 416 ml - 436 ml. Nevertheless, on the other hand, this system needs to be developed further because there are problems with sensor precision. © 2021 IEEE.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Innovative Urban Solutions with IoT-Driven Traffic and Pollution Control

Innovative Urban Solutions with IoT-Driven Traffic and Pollu...

引用

2024 IEEE International Conference on Automation and Computation, AUTOCOM 2024

作者： Yogi, Kottala Sri Sharma, Avinash Dankan Gowda, V. Saxena, Rini Barua, Tarkeshwar Mohiuddin, Khalid Dept of Operations Symbiosis Institute of Business Management Hyderabad Symbiosis International University Pune Telangana Hyderabad India Chandigarh Engineering College Chandigarh Group of Colleges Jhanjeri Department of Computer Science and Engineering Punjab Mohali140307 India Bms Institute of Technology and Management Department of Electronics and Communication Engineering Karnataka Bangalore India King Khalid University College of Business Department of Business Informatics PO Box-3247 Abha61471 Saudi Arabia

ISBN: (纸本)9798350382723

The Internet of Things (IoT) is rethinking the model for building the smart cities, and this paper makes just such a step in that direction. It then examines various ways of cutting urban pollution. Under increasing pressure from rising urbanization, smart cities represent a huge leap forward in regard to efficiency, scalability and livability. The key is IoTtechnology, which collects and analyzes data in real time and allows for more quick-witted and intelligent urban governance. This paper combines literature review, case study analysis and data-driven methods to focus on the opportunities offered by IoT applications for restructuring urban traffic systems and pollution control. This study explains what is missing in modern smart city initiatives, and offers a road map for bringing Internet of things solutions to municipal systems. The results can also serve as some answers to cope with the dilemma and bring more intelligence, cleanness, efficiency in making a city into a smart metropolis. The article ends by highlighting the significance of IoT for future urban development, and ideas for further research into this complex yet rapidly evolving area. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Vessels Segmentation in Angiograms Using Convolutional Neural Network: A Deep Learning Based Approach

引用

computer Modeling in engineering & Sciences 2023年第7期136卷 241-255页

作者： Sanjiban Sekhar Roy Ching-Hsien Hsu Akash Samaran Ranjan Goyal Arindam Pande Valentina E.Balas School of Computer Science and Engineering Vellore Institute of TechnologyVellore632014India Department of Computer Science and Information Engineering Asia UniversityTaichung41354Taiwan Department of Medical Research China Medical University HospitalChina Medical UniversityTaichung406Taiwan Guangdong-Hong Kong-Macao Joint Laboratory for Intelligent Micro-Nano Optoelectronic Technology School of Mathematics and Big DataFoshan UniversityFoshan528000China Medica Superspecialty Hospital Kolkata700099India Automation and Applied Informatics Aurel Vlaicu University of AradArad310130Romania

Coronary arterydisease(CAD)has become a significant causeof heart attack,especially amongthose 40yearsoldor *** is a need to develop new technologies andmethods to deal with this *** researchers have proposed image processing-based solutions for CADdiagnosis,but achieving highly accurate results for angiogram segmentation is still a *** different types of angiograms are adopted for CAD *** paper proposes an approach for image segmentation using ConvolutionNeuralNetworks(CNN)for diagnosing coronary artery disease to achieve state-of-the-art *** have collected the 2D X-ray images from the hospital,and the proposed model has been applied to *** augmentation has been performed in this research as it’s the most significant task required to be initiated to increase the dataset’s ***,the images have been enhanced using noise removal techniques before being fed to the CNN model for segmentation to achieve high *** the output,different settings of the network architecture undoubtedly have achieved different accuracy,among which the highest accuracy of the model is 97.61%.Compared with the other models,these results have proven to be superior to this proposed method in achieving state-of-the-art results.

关键词： Angiogram convolution neural network coronary artery disease diagnosis of CAD image segmentation

来源：评论

学校读者我要写书评

暂无评论

Big Five Personality Prediction Based on Indonesian Tweets and Personality Test

Big Five Personality Prediction Based on Indonesian Tweets a...

引用

International Conference on Electrical engineering and informatics, ICEEI

作者： Made Arbi Parameswara Farrel Satya Putra Mahendra Muhammad Randy Cahya Mardika Ira Puspasari Nugraha Priya Utama School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia Computer Engineering Department Dinamika University Surabaya Indonesia

The integration of human resources and artificial intelligence has shown a growing interest in automatically predicting personality traits, particularly in recruitment. To contribute to this field, we propose a new method to assist human resource professionals in Indonesia to identify candidates' personality traits. Biases come from personality tests due to their question format and susceptibility to manipulation on this research, we propose an approach that combines personality tests using the BFI form, which measures OCEAN personality traits, with personality trait predictions derived from Twitter data. This research aims to create a personality prediction model and system that efficiently and effectively screens candidate personality traits in human resources. This research has developed a novel model that combines personality test results with tweets personality prediction with an impressive F1-macro performance of 98%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Traffic Classification in Software-Defined Networking (SDN): Application of Machine Learning Models for Flooding DDoS Attack Detection 3

Traffic Classification in Software-Defined Networking (SDN):...

引用

3rd IEEE Industrial Electronics Society Annual On-Line Conference, ONCON 2024

作者： Bosi, Lucas Leal Mendes, Andre Chaves Guedes, Raphael Melo Salles, Ronaldo Moreira Defense Engineering Military Institute of Engineering Rio de Janeiro Brazil VALORIZA - Research Centre for Endogenous Resource Valorization Campus Politécnico Portalegre7300-555 Portugal State University of Rio de Janeiro Campus Maracanã Informatics and Computer Science Department Rio de Janeiro Brazil CIICESI ESTG Polytechnic of Porto Porto Portugal

ISBN: (纸本)9798331540319

Among the advantages offered by the SDN paradigm over traditional networks is the centralized implementation of comprehensive security policies. From this perspective, this study develops, trains, and tests several machine learning algorithms for traffic classification, distinguishing between legitimate traffic and three types of DDoS flooding attacks (HTTP, UDP, and TCP). The dataset used for training was employed both in its raw and preprocessed forms, and was generated in a reference study. The Random Forest and Gradient Boosting algorithms achieved the highest results in terms of accuracy and F1-score. Additionally, a comparison of the results of the studies is conducted. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Novel End-to-End Ensemble UNet Network Based on Edge Computing for Tool Wear Detection 24

A Novel End-to-End Ensemble UNet Network Based on Edge Compu...

引用

3rd Asia Conference on Algorithms, Computing and Machine Learning, CACML 2024

作者： Chen, Jianwen Tsai, Meng-Shiun Lin, Wan-Ju Hung, Che-Lun Department of Computer Science National Tsing Hua University Hsinchu300044 Taiwan Department of Mechanical Engineering National Taiwan University Taipei106319 Taiwan Department of Mold and Die Engineering National Kaohsiung University of Science and Technology Kaohsung807618 Taiwan Institute of Biomedical Informatics National Yang Ming Chiao Tung University Taipei11221 Taiwan

ISBN: (纸本)9798400716416

Automated tool wear condition monitoring is essential for ensuring product quality. However, achieving both high detection precision and utilizing edge computing are critical for advancing intelligent manufacturing. Consequently, this article develops a tool wear detection system utilizing edge computing techniques. Firstly, a novel end-to-end ensemble UNet-based model is proposed. Through end-to-end feature fusion training, it effectively addresses the robustness and accuracy issues inherent in single models. Secondly, multiple neural computing sticks are involved to reduce the need for cloud transmission and preserve data privacy, thereby enabling scalability and flexibility in deployment. Experiments demonstrate that mean intersection over union (mIoU) and mean dice coefficient (mDice) in tool wear detection can be improved by over 3% and 2%, respectively. Furthermore, the execution time can be accelerated by a factor of 4. © 2024 ACM.

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

Dynamic Day and Night Cycle Impact in a Serious VR Game

Dynamic Day and Night Cycle Impact in a Serious VR Game

引用

Virtual Reality (ICVR), IEEE International Conference on

作者： Fardani Annisa Damastuti Kenan Firmansyah Yunifa Miftachul Arif Ali Ridho Barakbah Mochamad Hariadi Department of Electrical Engineering Institut Teknologi Sepuluh Nopember Surabaya Indonesia Department of Creative Multimedia Technology Electronic Engineering Polytechnic Institute of Surabaya Surabaya Indonesia Department of Informatics Engineering Universitas Islam Negeri Maulana Malik Ibrahim Malang Indonesia Department of Informatics and Computer Engineering Electronic Engineering Polytechnic Institute of Surabaya Surabaya Indonesia Department of Computer Engineering Institut Teknologi Sepuluh Nopember Surabaya Indonesia

ISBN: (数字)9798350364231

ISBN: (纸本)9798350364248

The immersive nature of virtual reality (VR) gaming is significantly improved by the implementation of dynamic environmental systems. This paper focuses on the development and impact of a dynamic day and night cycle in a serious VR game. This feature is intended to simulate a full 24-hour cycle within a 10-minute gameplay session, resulting in a seamless transition between different times of day that impacts both the visual aesthetics and gameplay mechanics. The day and night cycle introduces strategic depth by requiring players to adjust their management strategies according to the time of day, which affects resource availability, operational efficiency, and conditions. This system not only enhances visual fidelity but also directly impacts gameplay, necessitating that player modify their strategies in response to the changing environment. Visual aesthetics are expected to increase by 15%, strategic profundity will be improved by 20%, and player immersion will be enhanced by 25%, according to the research findings. This investigation underscores the importance of natural cycles in enhancing the strategic complexity, interactivity, and realism of virtual reality environments, thereby offering valuable insights for the creation of future virtual reality games.

关键词： Visualization Accuracy Virtual reality Games Immersive experience Hardware Complexity theory

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：