检索结果-内蒙古大学图书馆

International Conference of computer and informatics engineering (IC2IE)

作者： Rizky Adi Fumiyo Fukumoto Bassamtiano Renaufalgi Irnawan Department of Computer and Informatics Engineering Politeknik Negeri Jakarta Depok Indonesia Department of Computer Science and Engineering University of Yamanashi Yamanashi Japan

Twitter is one of Indonesia's most used social media, with total visits reaching 192 million visits per month, making it the fifth most-visited website in Indonesia. Twitter users exchange information with each other daily. One of them is a traffic accident event. With over 100,000 cases every year from 2017–2021, it is not usual to see a tweet that contains traffic accident information. By implementing text classification, traffic accidents can be detected through tweets and used to send alert messages to emergency responders to respond as quickly as possible. Previous research used a machine learning approach to solve this text classification problem. The study resulted in the best accuracy of 85% from the SVM model, which leaves room for improvement using state-of-the-art deep learning models. This research proposes a transfer learning method using two BERT-based and two RoBERTa-based pre-trained models, namely IndoBERT, IndoBERTweet, Indonesian RoBERTa Base Wiki, and Indonesian RoBERTa Base OSCAR to create the best model to classify tweets that contain traffic accident information. We used two kinds of fine-tuning architecture: the vanilla version fine-tuning architecture and the modified version, which combines the pre-trained model with CNN. This study used 1,002 manually labeled tweets, where 360 were labeled as traffic accident tweets. The experiment found that transfer learning from a pre-trained model Indonesian RoBERTa OSCAR provided the best result with an f1-score of 88.73 % and an accuracy of 92%, which means a 7% accuracy improvement over the previous research's best model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Game Theory-Based IoT Efficient Power Control in Cognitive UAV

引用

computers, Materials & Continua 2022年第7期72卷 1561-1578页

作者： Fadhil Mukhlif Norafida Ithnin Omar B.Abdulghafoor Faiz Alotaibi Nourah Saad Alotaibi Information Assurance and Security Research Group(IASRG) School of ComputingFaculty of EngineeringUniversiti Teknologi MalaysiaJohorMalaysia Electronic and Telecommunication Department College of EngineeringThe American University of KurdistanIraq Faculty of Computer Science and Information Technology Universiti Putra MalaysiaSelangorMalaysia Computer Department Faculty of Applied CollegeImam Abdulrahman Bin Faisal UniversityDammamSaudi Arabia

With the help of network densification,network coverage as well as the throughput can be improved via ultra-dense networks(UDNs).In tandem,Unmanned Aerial Vehicle(UAV)communications have recently garnered much attention because of their high agility as well as widespread *** this paper,a cognitive UAV is proposed for wireless nodes power pertaining to the IoT ground ***,the UAV is included in the IoT system as the source of power for the wireless nodes as well as for resource *** quality of service(QoS)related to the cognitive node was considered as a utility function based on pricing scheme that was modelled as a non-cooperative game theory in order to maximise users’net utility ***,an energy efficiency non-cooperative game theory power allocation with pricing scheme(EE-NGPAP)is proposed to obtain an efficient power control within IoT wireless ***,uniqueness and existence of the Nash equilibrium have been demonstrated mathematically and through *** results show that the proposed energy harvest algorithm demonstrated considerable decrease in transmitted power consumption in terms of average power reduction,which is regarded to be apt with the 5Gnetworks’***,the proposed algorithm requires around 4 iterations only to converge to NE which makes the algorithm more suitable in practical heterogeneous scenarios.

关键词： UAV drones WSN IoT game theory energy efficiency 5G&B5G networks

来源：评论

学校读者我要写书评

暂无评论

M2SILENT: Enabling Multi-user Silent Speech Interactions via Multi-directional Speakers in Shared Spaces 25

M2SILENT: Enabling Multi-user Silent Speech Interactions via...

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI 2025

作者： Zhou, Juntao Ding, Dian Li, Yijie Lu, Yu Wang, Yida Zhang, Yongzhao Chen, Yi-Chao Xue, Guangtao Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China School of Computing National University of Singapore Singapore Singapore Shanghai Jiao Tong University Shanghai China School of Computer Science and Engineering University of Electronic Science and Technology of China Sichuan Chengdu China Computer Science and Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9798400713941

We introduce M2Silent, which enables multi-user silent speech interactions in shared spaces using multi-directional speakers. Ensuring privacy during interactions with voice-controlled systems presents significant challenges, particularly in environments with multiple individuals, such as libraries, offices, or vehicles. M2Silent addresses this by allowing users to communicate silently, without producing audible speech, using acoustic sensing integrated into directional speakers. We leverage FMCW signals as audio carriers, simultaneously playing audio and sensing the user's silent speech. To handle the challenge of multiple users interacting simultaneously, we propose time-shifted FMCW signals and blind source separation algorithms, which help isolate and accurately recognize the speech features of each user. We also present a deep-learning model for real-time silent speech recognition. M2Silent achieves Word Error Rate (WER) of and Sequence Error Rate (SER) of in multi-user silent speech recognition while maintaining high audio quality, offering a novel solution for privacy-preserving, multi-user silent interactions in shared spaces. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Blind source separation

来源：评论

学校读者我要写书评

暂无评论

UMUX and UMUX-Lite as Usability Assessment for Smart Door Lock Systems

UMUX and UMUX-Lite as Usability Assessment for Smart Door Lo...

引用

Information Technology and Computing (ICITCOM), International Conference on

作者： Indra Hermawan Rizki Elisa Nalawati Prihatin Oktivasari Ratna Widya Iswara Informatics and Computer Engineering Department Politeknik Negeri Jakarta Depok Indonesia

Smart Door Lock System is used to protect priceless and prevent unwanted access to a room. A usability evaluation is required to raise the system's usability level because it will help to decide how acceptable the system is. UMUX, UMUX-Lite, and SUS comparative ratings are used to gauge the usability level. The System Usability Score (SUS) has more questions than the UMUX and UMUX-Lite approaches. The general degree of acceptance of this system was deemed to be acceptable during the system's evaluation period. With an average UMUX score of 68,1, which is in the marginal category, the UMUX-LITe score is 77.3, which is categorized as acceptable, and the SUS comparison score is 73.0, which is categorized as acceptable.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Approach to Optimal Power Allocation in MIMO-NOMA: Integrating DGNN and Tyrannosaurus Optimization 4

A Hybrid Approach to Optimal Power Allocation in MIMO-NOMA: ...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Agrawal, Anurag Vijay Anuradha, A. Patil, Kranti D. Patil, Vilaskumar Karthikumar, K. Tallapragada, S. V. V. Satyanarayana Bhagwant Institute of Technology Department of Electronics and Communication Engineering Uttar Pradesh Muzaffarnagar251315 India Sri Aditya Degree College Department of Computer Science Andhra Pradesh Bhimavaram534202 India Trinity Academy of Engineering Ghrcem Department of E & Tc Maharashtra Pune411048 India Sharnbasva University Faculty of Engineering and Technology Department of Electronics and Communication Engineering Karnataka Kalaburagi585103 India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Electrical and Electronic Engineering Avadi Tamil Nadu Chennai600062 India School of Engineering Mohan Babu University Department of Electronics and Communication Engineering Andhra Pradesh Tirupati517102 India

ISBN: (纸本)9798331540364

One of the primary technologies necessary for the upcoming sixth generation of communication networks (6G) is massive multi-input multi-output, or MIMO. However, enormous MIMO presents a challenge in reducing energy use and the sum rate demand due to the power use of the several radio frequencies (RF) links in 6G technology. Therefore, this research presented a novel Deformable Graph Neural Network (DGNN) with Tyrannosaurus optimization for the optimal power distribution that maximized the sum rate and energy efficiency of the MIMO NOMA system. The adaptive mechanism of DGNN enables more accurate and efficient power allocation decisions. The integrated Tyrannosaurus optimization ensures the model converging on optimal power allocation strategies that maximize both sum rate and energy efficiency. The efficiency of the recommended model is compared in regarding sum rate and Energy Efficiency (EE) with the some of the recent approaches. The proposed method gained the greater sum rate and EE outperforming all other compared models. © 2024 IEEE.

关键词： Radio links

来源：评论

学校读者我要写书评

暂无评论

Microwave characterization of two Ba_(0.6)Sr_(0.4)TiO_(3) dielectric thin films with out-of-plane and in-plane electrode structures

引用

Journal of Advanced Ceramics 2023年第8期12卷 1521-1532页

作者： Hanchi Ruan Theo Graves Saunders Henry Giddens Hangfeng Zhang Achintha Avin Ihalage Jonas Florentin Kolb Matthew Blunt Sajad Haq Haixue Yan Yang Hao School of Electronic Engineering and Computer Science Queen Mary University of LondonLondon E14NSUK School of Engineering and Materials Science Queen Mary University of LondonLondon E14NSUK Department of Chemistry University College LondonLondon WC1H 0AJUK Advanced Services and Products QinetiQFarnborough GU140LXUK

Ferroelectric(FE)thin films have recently attracted renewed interest in research due to their great potential for designing novel tunable electromagnetic devices such as large intelligent surfaces(LISs).However,the mechanism of how a polar structure in the FE thin films contributes to desired tunable performance,especially within the microwave frequency range,which is the most widely used frequency range of electromagnetics,has not been illustrated *** this paper,we described several straightforward and cost-effective methods to fabricate and characterize Ba_(0.6)Sr_(0.4)TiO_(3)(BST)thin films at microwave *** prepared BST thin films here exhibit homogenous structures and great tunability(h)in a wide frequency and temperature range when the applied field is in the out-of-plane *** high tunability can be attributed to high concentration of polar *** response to the applied direct current(DC)field was directly visualized using a novel non-destructive near-field scanning microwave microscopy(NSMM)*** results have provided some intriguing insights into the application of the FE thin films for future programmable high-frequency devices and systems.

关键词： ferroelectric(FE) microwave tunability polarization thin film

来源：评论

学校读者我要写书评

暂无评论

High-Efficiency and Low Back-Reflection Fully Etched TM Mode Silicon Waveguide Grating Coupler

High-Efficiency and Low Back-Reflection Fully Etched TM Mode...

引用

IEEE International Conference on Group IV Photonics

作者： Xuetong Zhou Ying Xue Fan Ye Ziyao Feng Jianfeng He Xiankai Sun Kei May Lau Hon Ki Tsang Department of Electronic Engineering The Chinese University of Hong Kong Hong Kong SAR China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong China

We propose a novel design for high-performance fully etched TM waveguide grating coupler with minimum feature size above 260 nm. The device has low back reflection and high efficiency.

ISBN: (数字)9798331506186

ISBN: (纸本)9798331506193

We propose a novel design for high-performance fully etched TM waveguide grating coupler with minimum feature size above 260 nm. The device has low back reflection and high efficiency.

关键词： Couplings Photonic integrated circuits Couplers Production Silicon photonics Reflection Gratings Optical waveguides Substrates Standards

来源：评论

学校读者我要写书评

暂无评论

Collaborative filtering recommendation algorithm based on class correlation distance

Recent Advances in Computer Science and Communications

引用

Recent Advances in computer Science and Communications 2021年第3期14卷 887-894页

作者： Zhang, Hanfei Jian, Yumei Zhou, Ping Department of Computer Science Huaiyin Normal University Jiangsu China School of Electronic and Electrical Engineering Shanghai University of Engineering Science Shanghai China

Background: With the proposal of collaborative filtering algorithm, recommendation system has become an important approach for users to filter excessive Internet information. Objective: A class correlation distance collaborative filtering recommendation algorithm is proposed to solve the problems of category judgment and distance metric in the traditional collaborative filtering recommendation algorithm, which is using the advantage of the distance between the same samples and the class related distance. Methods: First, the class correlation distance between the training samples is calculated and stored. Second, the K nearest neighbor samples are selected, the class correlation distance of training samples and the difference ratio between the test samples and training samples are calculated respectively. Finally, according to the difference ratio, we classify the different types of samples. Results: The experimental result shows that the algorithm combined with user rating preference can get lower MAE value, and the recommendation effect is better. Conclusion: With the change of K value, CCDKNN algorithm is obviously better than KNN algorithm and DWKNN algorithm, and the accuracy performance is more stable. The algorithm improves the accuracy of similarity and predictability, which has better performance than the traditional algorithm. © 2021 Bentham Science Publishers.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Clustering the Academician Knowledge Qualification: K-Means for Performance Measurement Analysis 22

Clustering the Academician Knowledge Qualification: K-Means ...

引用

22nd IEEE Student Conference on Research and Development, SCOReD 2024

作者： Yanti, Novi Defit, Sarjon Okfalisa Universitas Islam Negeri Sultan Syarif Kasim Riau Department of Informatics Engineering Faculty of Science and Technology Riau Pekanbaru Indonesia Universitas Putra Indonesia YPTK Padang Department of Information Technology Faculty of Computer Science Sumatera Barat Padang Indonesia

ISBN: (纸本)9798331510077

The assessment of an academic's performance is not solely based on the tangible results achieved. Nonetheless, the formation aspect of the Knowledge Management (KM) process, which arises in the pursuit of outcomes, must be acknowledged. This emphasizes the significance of KM process development for academics in achieving their essential responsibilities including teaching and learning, research and publishing, and community service. Consequently, it is essential to develop a KM model for assessing the accomplishments of academics in higher education. An evaluation of academic performance in higher education was conducted to identify the success factors of knowledge management, by considering five key elements viz, knowledge creation, knowledge acquisition, knowledge storage, knowledge sharing, and knowledge application. Accordingly, sixty-five sub-variables were identified as success model factors for evaluating academic knowledge management performance. A K-Means clustering method was utilized to assess the KM qualifications of academics at an Islamic public institution in Indonesia (University X) as the primary study. Herein, a 5-point Likert scale questionnaire was administered to 500 academics and subsequently categorized into three performance levels such as low, medium, and high performance. As a result, 140 academicians were categorized as low KM performance, 139 were clustered as medium qualification, and 221 academicians were positioned in high performance. Furthermore, a recommendation analysis is presented to elucidate the accomplishments of academic credentials for each cluster and propose corrective actions for enhancement. Therefore, the scholars at University X might enhance their knowledge management practices to get a superior quality university. © 2024 IEEE.

关键词： Knowledge acquisition

来源：评论

学校读者我要写书评

暂无评论

Leveraging Deep Reinforcement Learning for Geolocation-based MIMO Transmission in FD-RAN

Leveraging Deep Reinforcement Learning for Geolocation-based...

引用

2023 IEEE/CIC International Conference on Communications in China, ICCC 2023

作者： Liu, Zongxi Yu, Kai Zhang, Tianqi Liu, Jingbo Chen, Jiacheng Zhou, Haibo Shen, Xuemin Sherman Nanjing University School of Electronic Science and Engineering Nanjing210023 China Peng Cheng Laboratory Department of Mathematics and Theories Shenzhen518000 China Shanghai Jiao Tong University School of Electronic Information and Electrical Engineering Shanghai200240 China University of Waterloo Department of Electrical and Computer Engineering WaterlooN2L 3G1 Canada

ISBN: (纸本)9798350345384

In the fully-decoupled radio access network (FD-RAN), the base stations (BSs) are classified as control BSs, uplink BSs, and downlink BSs for better flexibility of the BS-user equipment (UE) association and elasticity of resource scheduling. However, the high feedback delay brought by the physically decoupling architecture renders conventional feedback-based MIMO transmission ineffective. Considering the strong correlation between user geolocation and the channel propagation environment, especially when a line-of-sight (LOS) path exists, we propose a geolocation-based MIMO transmission scheme that determines the user's precoder and modulation and coding scheme (MCS) without requiring the conventional feedback procedures. To capture the correlation, we utilize deep reinforcement learning (DRL) to perform the task of mapping from geolocation to transmission parameters. Based on the principles of Type I codebook, we further decompose the task into subtasks to reduce the action space. The extensive simulations on realistic ray-tracing channels demonstrate comparable performance to CSI feedback-based methods in 5G under ideal (zero feedback delay) conditions and better performance against 5G (with feedback delay) and DRL without task decomposition. © 2023 IEEE.

关键词： Radio access networks

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：