检索结果-内蒙古大学图书馆

7th International Conference on computer Science and Computational Intelligence, CSCI 2022

作者： Ramadhan, M. Vickya Muchtar, Kahlil Nurdin, Yudha Oktiana, Maulisa Fitria, Maya Maulina, Novi Elwirehardja, Gregorius Natanael Pardamean, Bens Department of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh23111 Indonesia Universitas Syiah Kuala Banda Aceh23111 Indonesia Microbiology Department School of Medicine Universitas Syiah Kuala Banda Aceh23111 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program-Master of Computer Science Program Bina Nusantara University Jakarta 11480 Indonesia

The spread of Corona Virus Disease 19 (COVID-19) in Indonesia is still relatively high and has not shown a significant decrease. One of the main reasons is due to the lack of supervision on the implementation of health protocols such as wearing masks in daily activities. Recently, state-of-The-Art algorithms were introduced to automate face mask detection. To be more specific, the researchers developed various kinds of architectures for the detection of masks based on computer vision methods. This paper aims to evaluate well-known architectures, namely the ResNet50, VGG11, InceptionV3, EfficientNetB4, and YOLO (You Only Look Once) to recommend the best approach in this specific field. By using the MaskedFace-Net dataset, the experimental results showed that the EfficientNetB4 architecture has better accuracy at 95.77% compared to the YOLOv4 architecture of 93.40%, InceptionV3 of 87.30%, YOLOv3 of 86.35%, ResNet50 of 84.41%, VGG11 of 84.38%, and YOLOv2 of 78.75%, respectively. It should be noted that particularly for YOLO, the model was trained using a collection of MaskedFace-Net images that had been pre-processed and labelled for the task. The model was initially able to train faster with pre-Trained weights from the COCO dataset thanks to transfer learning, resulting in a robust set of features expected for face mask detection and classification. © 2022 Elsevier B.V.. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

FDAM: Filter-Dedicated Approximate Multiplier Design for Real-Time CNN Acceleration

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年

作者： Nguyen, Kihwan Kim Xuan Truong Jeon, Dongsuk Lee, Hyuk-Jae Korea Republic of program Department of Electrical Engineering Seoul08826 Korea Republic of Inter-University Semiconductor Research Center Seoul National University Graduate School of Convergence Science and Technology Research Institute for Convergence Science Seoul08826 Korea Republic of Department of Electrical and Computer Engineering Seoul08826 Korea Republic of

Video super-resolution (VSR) is widely used in various high-definition applications, such as HDTVs and smartphones, requiring a dedicated upscaling technique for realtime full-HD generation. To reduce on-chip buffers for largesize output feature maps, a streaming VSR accelerator may employ an output stationary dataflow, leading to a large energy consumption caused by frequent filter switching. To mitigate this, we introduce a new filter-dedicated multiplier design for realtime VSR acceleration. We replace costly multipliers with adders, shifters, and multiplexers (MUXes), referred to as unified multiple constant multiplications (UMCM). The conventional UMCM, however, may incur considerable area/power overhead due to the unified topology constraint among different filter sets. To address this problem, we propose a new approximated MCM (AMCM) problem to relax the constraint and an approximate compatible graph synthesis (A-CGS) framework to efficiently solve AMCM by jointly searching for approximated filters and constructing a unified graph. Additionally, we suggest a lightweight finetuning method by freezing approximated filters and only finetuning biases, which can recover the original model’s accuracy within a few epochs. Experimental results with synthetic data demonstrate that AMCM reduces the area by up to 49.8%, 44.8%, and 40.3% when considering constant sets of 2, 4, and 8, respectively. Our designs with SR application achieve up to a 73.3% reduction in energy consumption. Experiments with the Set5 and Set14 datasets show that our model with bias correction achieves similar restoration performance compared to the eightbit models. © 1982-2012 IEEE.

关键词： Acceleration

来源：评论

学校读者我要写书评

暂无评论

The Impact of Hot Carrier Injection-Induced Device Degradation for Lower-Power FinFETs

引用

Journal of Electronic Materials 2023年第2期52卷 1391-1399页

作者： Chen, Yu-Lin Yeh, Wen-Kuan Hsu, Heng-Tung Chen, Ke-Horng Lien, Der-Hsien Lin, Wen-Chin Yu, Tien-Han Chiu, Yu-Sheng Godwinraj, D. Godfrey, D. Wu, Chien-Hung International College of Semiconductor Technology National Yang Ming Chiao Tung University Hsinchu Taiwan Graduate Degree Program of College of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan Institute of Electronics National Yang Ming Chiao Tung University Hsinchu Taiwan Institute of Microelectronics National Cheng Kung University Tainan Taiwan Department of ECE Amal Jyothi College of Engineering Kerala Kottayam India Department of Optoelectronics and Materials Engineering Chung Hua University Hsinchu Taiwan Department of Electronics and Communication Engineering Dayananda Sagar University Bengaluru India National Applied Research Laboratories Hsinchu Taiwan

The impact of hot carrier injection (HCI) on the performance of standard and low-VT FinFETs are investigated and benchmarked with each other. For this investigation, these FinFETs were fabricated with various gate lengths (L) from 16 to 36 nm. HCI-induced transconductance degradation in standard devices for gate length variations of 36 nm down to 16 nm was 75%, while it was 35% for low-VT devices. Similarly, the degradation of threshold voltage in standard devices for gate length variations of 36 nm down to 16 nm was 39%, while it was 36% for low-VT device. In this work, as the device is subject to HCI, we found that: (1) short-channel devices cause severe degradation on the threshold voltage and transconductance (gm) compared to long-channel devices, owing to the higher electric field for short-channel devices at the gate edge, (2) standard devices exhibit a more stable threshold voltage than that of low-VT power devices, since the TiN barrier layer prevents Al atom diffusion into the HfO2 layer, and (3) the transconductance efficiency of standard devices is better than that of low-VT power devices. Further, the lower-VT devices show lower transconductance degradation than standard devices. However, the transconductance degradation of the long-channel standard and low-VT devices are the same. Compared to short-channel low-VT devices, extended-channel standard devices are more immune to the HCI effect. © 2022, The Minerals, Metals & Materials Society.

关键词： Threshold voltage

来源：评论

学校读者我要写书评

暂无评论

Demonstration of a polarization-agnostic geometric phase in nonlocal metasurfaces

Demonstration of a polarization-agnostic geometric phase in ...

引用

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Overvig, Adam C. Kasahara, Y. Alu, Andrea Photonics Initiative Advanced Science Research Center City University of New York New YorkNY10031 United States Department of Electrical and Computer Engineering The University of Texas at Austin AustinTX78712 United States Physics Program Graduate Center of the City University of New York New YorkNY10016 United States

We theoretically propose and experimentally demonstrate nonlocal metasurfaces rationally designed using symmetry-breaking principles to manipulate the optical wavefront with a geometric phase selective to custom ellip...

ISBN: (纸本)9781957171258

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cancer Prediction Using Clinical and Genomic Data Fusion: A Systematic Review

Cancer Prediction Using Clinical and Genomic Data Fusion: A ...

引用

International Conference on Cybernetics and Intelligent System (ICORIS)

作者： Kelvin Julian Kuncahyo Setyo Nugroho Rudi Nirwantono Bens Pardamean Computer Science Department BINUS Graduate Program - Master of Computer Science Bina Nusantara University Jakarta Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta Indonesia Biotechnology Department Faculty of Engineering Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331539603

ISBN: (纸本)9798331539610

This systematic review provides a comprehensive overview of the methods used to integrate genomic and clinical data in cancer prediction. The review includes 19 studies across various cancers, including breast, colorectal, melanoma, lung, pancreatic, and thyroid. The studies employed different methods to combine genomic and clinical data, including weighted polygenic risk scores, genetic and non-genetic risk scores, and different machine learning algorithms. The results show significant improvements in model prediction performance accuracy across multiple studies. The review highlights the potential benefits of integrating genetic and phenotypic information to improve disease risk prediction models and inform personalized healthcare strategies.

关键词： Accuracy Machine learning algorithms Genomics Data integration Medical services Predictive models Data models Bioinformatics Cancer Systematic literature review

来源：评论

学校读者我要写书评

暂无评论

Cardiovascular Disease Analysis Using Correlational Analysis and Association Rules Mining for In-depth Analysis to Identify Predominant Variables

Cardiovascular Disease Analysis Using Correlational Analysis...

引用

computer Science, Information Technology and engineering (ICCoSITE), International Conference on

作者： Boby Siswanto Haryono Soeparno Nesti F. Sianipar Widodo Budiharto Computer Science Department BINUS Graduate Program- Computer Science Bina Nusantara University Jakarta Indonesia Food Technology Department Engineering Faculty Bina Nusantara University Jakarta Indonesia Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

Cardiovascular disease is one of the dangerous non-communicable disorders or diseases that has become one of the causes of death worldwide. Various studies have been conducted to prevent cardiovascular disease in the world. This study analyzed cardiovascular disease medical record data from the Kaggle public dataset by implementing correlational analysis combined with association rule mining to identify variables that are the predominant cause of cardiovascular disease. Correlational analysis can analyze the interrelationships between variables in a dataset, but not in depth. Association rule mining can identify the interrelationships of variables in the form of frequent item sets, which can be calculated for their support and confidence values. The result of this study is a combination of correlation analysis with association rule mining that can identify predominant variables to cause cardiovascular disease. Found that the variable gender=woman, height=short (<165 cm), and age=middle (45-60 years) are more likely to be affected by cardiovascular disease. The variable gender=woman with height=short indicates a 76.07% probability of developing cardiovascular disease.

关键词： computer science Correlation Itemsets Cardiovascular diseases Data mining Information technology

来源：评论

学校读者我要写书评

暂无评论

Analysis of the Effect of Capacitors on the Voltage Generated by a 3-Phase Induction Generator

Analysis of the Effect of Capacitors on the Voltage Generate...

引用

2022 International Conference on Electrical engineering and Informatics, ICELTICs 2022

作者： Syukri, Mahdi Syuhada, Ahmad Tarmizi Suriadi Ramadhani, Satika Marwan Affan, Muzailin Yanis, Muhammad Universitas Syiah Kuala Doctoral Program School of Engineering Post Graduate Program Banda Aceh23111 Indonesia Universitas Syiah Kuala Dept. of Mechanical and Industrial Engineering Banda Aceh Indonesia Universitas Syiah Kuala Dept. of Electrical and Computer Engineering Banda Aceh Indonesia Universitas Syiah Kuala Dept. of Geophisic Engineering Banda Aceh Indonesia Universitas Syiah Kuala Dept. of Informatics Fmipa Banda Aceh Indonesia

ISBN: (数字)9781665487665

ISBN: (纸本)9781665487665

Induction motors can be operated as induction generators when additional capacitors are added to the stator terminals. Capacitors connected to induction generators can generate voltage and can provide reactive power. The advantage of induction generators can be used in small-scale plants such as micro-hydro power plants. However, the weakness of induction generators are weak voltage regulation and dependence on capacitors to generate voltage. This study conducted a test to see how the effect of capacitor capacity on the voltage generated by a induction generator when serving multiple incandescent lamp loads. The capacitor used is connected with a wye connection because the Wye connection can generate a higher voltage than the Delta connection circuit. This research has been successfully carried out with variations in capacitor values, namely 45 F, 60 F, and 75 F and variations in lamp load values, namely 5W, 15W, 25W, 40W and 60W. Based on the results of the study, the induction generators uses a 45 F capacitor with a load of 5 W, the terminal voltage for line to line is 374 V. However, when using a 75 F capacitor with a 60W load, the terminal voltage for line to line is 239 V. The terminals voltage of the induction generators can also be kept at a constant 380 V by providing varying capacitor values even though it serves varying loads. © 2022 IEEE.

关键词： Asynchronous generators

来源：评论

学校读者我要写书评

暂无评论

Traffic-Aware Beacon Interval for Position-Based Protocols in VANETs

Traffic-Aware Beacon Interval for Position-Based Protocols i...

引用

IEEE Latin-American Conference on Communications, LATINCOM

作者： Alvaro T. Amaya Alexandre A. P. Pohl Mauro S. Fonseca Ricardo Lüders Graduate Program in Electrical and Computer Engineering (CPGEI) Universidade Tecnológica Federal do Paraná (UTFPR) Curitiba Brazil

Position-based protocols in vehicular ad-hoc networks (VANETs) depend on the transmission of periodic beacon messages to keep the nodes informed about the current position of their neighbors. However, an excessive load of beacons can drastically deteriorate the network performance. This work presents a novel adaptive vehicular traffic-aware strategy to compute the beacon interval in a position-based protocol. The strategy relies on three mobility factors: vehicular density, the mean difference of speed among neighbors, and the spatial distribution of neighbors. Its effectiveness is proven through extensive simulations in an urban mobility scenario using the packet delivery ratio, the average end-to-end delay, overhead, and processing time as the performance metrics. The results show that our approach maintains a high delivery ratio and low End-To-End delay, overhead, and processing time regardless of the density of the surrounding vehicular traffic. The results also show that our method uses the available beacon interval range more efficiently than another traffic-aware approach.

关键词： Measurement Adaptation models Graphical models Computational modeling Collaboration Routing protocols Delays

来源：评论

学校读者我要写书评

暂无评论

Code-mixed sentiment analysis of Indonesian language and Javanese language using Lexicon based approach 2

Code-mixed sentiment analysis of Indonesian language and Jav...

引用

2nd Annual Conference of Science and Technology, ANCOSET 2020

作者： Tho, C. Heryadi, Y. Lukas, L. Wibowo, A. Department of Computer Science Binus Graduate Program Bina Nusantara University Jakarta Indonesia Cognitive Engineering Research Group Faculty of Engineering Universitas Katolik Indonesia Atma Jaya Jakarta Indonesia

Nowadays mixing one language with another language either in spoken or written communication has become a common practice for bilingual speakers in daily conversation as well as in social media. Lexicon based approach is one of the approaches in extracting the sentiment analysis. This study is aimed to compare two lexicon models which are SentiNetWord and VADER in extracting the polarity of the code-mixed sentences in Indonesian language and Javanese language. 3,963 tweets were gathered from two accounts that provide code-mixed tweets. Pre-processing such as removing duplicates, translating to English, filter special characters, transform lower case and filter stop words were conducted on the tweets. Positive and negative word score from lexicon model was then calculated using simple mathematic formula in order to classify the polarity. By comparing with the manual labelling, the result showed that SentiNetWord perform better than VADER in negative sentiments. However, both of the lexicon model did not perform well in neutral and positive sentiments. On overall performance, VADER showed better performance than SentiNetWord. This study showed that the reason for the misclassified was that most of Indonesian language and Javanese language consist of words that were considered as positive in both Lexicon model. © Published under licence by IOP Publishing Ltd.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Advances and Challenges in Multi-Domain Task-Oriented Dialogue Policy Optimization

引用

APSIPA Transactions on Signal and Information Processing 2023年第1期12卷

作者： Rohmatillah, Mahdin Chien, Jen-Tzung EECS International Graduate Program National Yang Ming Chiao Tung University Taiwan Institute of Electrical and Computer Engineering National Yang Ming Chiao Tung University Taiwan

Developing a successful dialogue policy for a multi-domain task-oriented dialogue (MDTD) system is a challenging task. Basically, a desirable dialogue policy acts as the decision-making agent who understands the user's intention to provide suitable responses within a short conversation. Furthermore, offering the precise answers to satisfy the user requirements makes the task even more challenging. This paper surveys recent advances in multi-domain task-oriented dialogue policy optimization and summarizes a number of solutions to policy learning. In particular, the case study on the task of travel assistance using the MDTD dataset based on MultiWOZ containing seven different domains is investigated. The dialogue policy optimization methods, categorized into dialogue act level and word level, are systematically presented. Moreover, this paper addresses a number of challenges and difficulties including the user simulator design and the dialogue policy evaluation which need to be resolved to further enhance the robustness and effectiveness in multi-domain dialogue policy representation. © 2023 M. Rohmatillah and J.-T. Chien.

关键词： Reinforcement 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：