检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Rowel Atienza Electrical and Electronics Engineering Institute and AI Graduate Program University of the Philippines

State of the art (SOTA) neural text to speech (TTS) models can generate natural-sounding synthetic voices. These models are characterized by large memory footprints and substantial number of operations due to the long-standing focus on speech quality with cloud inference in mind. Neural TTS models are generally not designed to perform standalone speech syntheses on resource-constrained and no Internet access edge devices. In this work, an efficient neural TTS called EfficientSpeech that synthesizes speech on an ARM CPU in real-time is proposed. EfficientSpeech uses a shallow non-autoregressive pyramid-structure transformer forming a U-Network. EfficientSpeech has 266k parameters and consumes 90 MFLOPS only or about 1% of the size and amount of computation in modern compact models such as Mixer-TTS. EfficientSpeech achieves an average mel generation real-time factor of 104.3 on an RPi4. Human evaluation shows only a slight degradation in audio quality as compared to FastSpeech2.

关键词： Performance evaluation Degradation Computational modeling Signal processing Transformers Real-time systems Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Classification of Human Tactile Perception Using Vibration Data 23

Classification of Human Tactile Perception Using Vibration D...

引用

23rd International Conference on Cyberworlds, CW 2024

作者： Lee, Hyung-Tak Bak, Keungyonh Chun, Sungwoo Hwang, Han-Jeong Korea University Dept. Electronics and Information Engineering Sejong Korea Republic of Korea University Interdisciplinary Graduate Program for Artificial Intelligence Smart Convergence Technology Sejong Korea Republic of

ISBN: (纸本)9798331527174

To enhance the sense of reality in the VR environment, it is essential to incorporate not only visual and hearing but also tactile feedback. Previous studies related to tactile sensation have only focused on object classification to identify the object in contact with the tactile sensor. When people encounter a new object, they can use tactile perception information, such as roughness, to understand the object's attributes and functions. Therefore, for tactile research to be applicable in real-life scenarios, tactile perception classification is essential not only for classifying an object but also for recognizing its attributes and functions. This study aims to investigate the possibility of predicting roughness, one of the important human tactile perceptions, using deep learning models. We created 63 tactile samples, measured the vibration data of each sample using an acceleration sensor, and investigated how humans perceive the roughness of the tactile samples with five different levels. Object classification was performed using five deep learning models, among which the Shallow ConvNet achieved the highest performance, confirming its suitability as the most appropriate model for analyzing vibration data. Using the Shallow ConvNet, we attained a high accuracy of 98.6 ±5.6% for the identification of five levels of roughness, demonstrating that different levels of tactile perception information can be discriminated with high performance. © 2024 IEEE.

关键词： Deep learning Human tactile perception Roughness Vibration data Virtual reality

来源：评论

学校读者我要写书评

暂无评论

HyperFed: Free-riding Resistant Federated Learning with Performance-based Reputation Mechanism and Adaptive Aggregation using Hypernetworks 10

HyperFed: Free-riding Resistant Federated Learning with Perf...

引用

10th International Conference on Dependable Systems and Their Applications, DSA 2023

作者： Nuannimnoi, Sirapop Delizy, Florian Huang, Ching-Yao National Yang-Ming Chiao Tung University Eecs International Graduate Program Hsinchu Taiwan National Yang-Ming Chiao Tung University Department of Electronics Engineering Hsinchu Taiwan

ISBN: (纸本)9798350304770

Traditional machine learning solutions rely on Cloud based services, which could potentially lead to major problems including security, privacy data leakage, unacceptable latency, and excessive operating expenses. Federated Learning techniques (FL) were introduced to tackle these challenges by allowing distributed edge nodes/servers to collaboratively train AI models without sharing raw training data. However, some of the nodes may intentionally or unintentionally upload virtual (fake) models to the main server. This behavior is called "Free-riding", and it could potentially have a negative effect on the overall performance of the FL system. In this paper, we propose a new adaptive contribution-based aggregation technique using hypernetworks, namely "HyperFed", and evaluate it on two important aspects: resistance against free-riders' fake contributions, and average convergence speed of global model on local datasets. Our simulation results on Federated EMNIST dataset display promising performance in comparison to FedAvg and AdaFed aggregation techniques. © 2023 IEEE.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Silica nanochannel device for pH sensing based on surface charge density changes

Silica nanochannel device for pH sensing based on surface ch...

引用

2010 10th IEEE Conference on Nanotechnology, NANO 2010

作者： Lee, Sang Young Yoon, Sang Youl Lee, Kyeong-Hwan Yang, Sung Department of Nanobio Material and Electronics School of Information and Mechatronics GIST Korea Republic of Graduate- Program of Medical System Engineering Biomedical Micro/Nano Device Laboratory GIST Korea Republic of

ISBN: (纸本)9781424470334

This paper demonstrates a novel micro/nano fluidic device for continuous pH sensing of small fluid volumes. The working principle of the device is based on the change of the surface charge density within the silica nano channels with respect to the pH levels of the electrolyte. In order to measure pH levels of various solutions, AC potential is applied along the silica nanochannels which have 50 nm depth, 2 μm width, and 30 μm length. The running current along the nanofluidic channels is directly measured with respect to pH levels. It was found that the running current is inversely proportional to pH levels regardless of ion concentrations. ©2010 IEEE.

关键词： Electrolytes

来源：评论

学校读者我要写书评

暂无评论

Prototype development of VR based personal zone defense practice equipment 4

Prototype development of VR based personal zone defense prac...

引用

4th IEEE Global Conference on Life Sciences and Technologies, LifeTech 2022

作者： Honma, Hiroki Iida, Yoshiaki Okumura, Yasuyuki Fujii, Katsuyuki Umehira, Masahiro Nanzan University Graduate Program of Mechatronics Graduate School of Science and Engineering Nagoya Japan Nanzan University Physical Education Center Nagoya Japan Nanzan University Faculty of Science and Engineering Department of Mechatronics Nagoya Japan Nanzan University Faculty of Science and Engineering Department of Electronics and Communication Technology Nagoya Japan

ISBN: (纸本)9781665419048

In a basketball game, players must act appropriately according to the position and movement of the player. This needs to be learned through team practice. Therefore, if we can build an environment that allows even one person to practice as a team, the efficiency of practice can be greatly improved. It is effective to use virtual reality (VR) technology to realize team practice alone. This paper proposes a VR-based basketball team practice learning system that provides VR environments similar to the actual team practice environments by arranging players in a virtual space. Focusing on zone defense practice, which is said to be difficult to learn even in team practice, we propose a practice system for orthodox 3-2 zone tactics. In addition, because the distance between the player and the surrounding VR player is important for this system, this paper presents the evaluation result of the 3D virtualization accuracy measured by the experiment. © 2022 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Evaluation of 3D Virtualization Accuracy for VR-Based Personal Basketball Team-Practice System 10

Evaluation of 3D Virtualization Accuracy for VR-Based Person...

引用

10th IEEE Global Conference on Consumer electronics, GCCE 2021

作者： Honma, Hiroki Iida, Yoshiaki Okumura, Yasuyuki Fujii, Katsuyuki Umehira, Masahiro Nanzan University Graduate Program of Mechatronics Graduate School of Science And Engineering Nagoya Japan Nanzan University Physical Education Center Nagoya Japan Nanzan University Faculty of Science And Engineering Department of Mechatronics Nagoya Japan Department of Electronics And Communication Technology Faculty of Science And Engineering Nanzan University Nagoya Japan

ISBN: (纸本)9781665436762

In basketball game, players need to learn how to take a next appropriate action by judging various situations with surrounding players through team practice. Such decision-making capabilities in individual practice with virtual reality (VR) technologies can significantly improve the efficiency of team practice. This paper proposes a VR-based basketball team practice learning system which provides VR environments similar to the actual team practice environments by arranging players in a virtual space Proto-type application for smartphones has been developed for 3D virtualization accuracy evaluation where the smartphone is used for team practice to sense the distance between the player and surrounding VR players This paper describes the evaluation results of 3D virtualization accuracy measured by the experiments. © 2021 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Deep-Hand: A Deep Inference Vision Approach of Recognizing a Hand Sign Language using American Alphabet 2

Deep-Hand: A Deep Inference Vision Approach of Recognizing a...

引用

2nd IEEE International Conference on Computational Intelligence and Knowledge Economy, ICCIKE 2021

作者： Alon, Helcy D. Ligayo, Michael Angelo D. Melegrito, Mark P. Franco Cunanan, Christopher Uy Ii, Edgar E. Technological Institute of the Philippines Graduate Program Manila Philippines Quezon City University Department of Electronics Engineering Quezon City Philippines Technological University of the Philippines Department of Electronics and Communications Engineering Manila Philippines Polytechnic University of the Philippines Department of Computer Engineering Philippines Bohol Island State University College of Engineering and Architecture Tagbilaran Philippines

ISBN: (纸本)9781665429214

Sign-Language is to help people with hearing or speaking disabilities who are not able to communicate well with other people. Communicating with deaf people is a challenge for some speakers and people who do not know sign language. What the study proposed is to help people with such disabilities using the American Sign-Language with the corresponding hand gesture. Deaf individuals will be able to communicate or interact with other people conveniently. The study proposed hand gesture or hand sign language detection trained by using the YOLOv3 algorithm that aims to detect hand gestures or hand sign language that can recognize its equivalent letter alphabet. The study tools such as LabelImg for annotating the data set, categorizing each image of hand gestures based on their equivalent letter alphabet. In this study, Model 18 with 95.1804% training accuracy, 90.8242% validation accuracy, and mAP of 0.8275 is used for the final testing. As video with different hand gestures is presented, the results of every hand gesture detected range over 90%. © 2021 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Quality Improvements in the Electrical Design of Typical DC-DC Electronic Power Converter for High-Voltage Applications 8

Quality Improvements in the Electrical Design of Typical DC-...

引用

8th International Conference on engineering and Emerging Technologies, ICEET 2022

作者： Recto, King Harold A. Escoto, Miguel T. Hernandez, Noel B. Ateneo de Manila University Department of Electronics Computer and Communications Engineering Quezon City Philippines Electrical and Electronics Engineering Institute University of the Philippines Diliman Quezon City Philippines Centro Escolar University Post-doctoral Program in Quality Management of the Graduate School Manila Philippines

ISBN: (纸本)9781665491068

The green transition has brought about a worldwide-shift to the use of renewables as alternative energy sources. Because of this, high voltage DC has been a field of interest in power electronics due to its capability in efficiently transmitting power to reach remote areas. Typical DC-DC electronic power converter design has the capability of boosting voltage level to a certain extent but not enough for high-voltage applications. Using the DMAIC Approach of the Six Sigma, quality improvements in the design was proposed to stabilize operating frequency, bring up the output voltage from 100 VDC to 4,000 VDC and provide at least 10% margin of error in the apparent power measured at the output side to offset inherent losses in the electrical design. These proposed quality improvements were sustained by designing a control circuit that would ensure the attainment of the parameters set in the Define Phase of the DMAIC Approach. The result of the study is a practical 12 VDC to 4,000 VDC boost converter design that has incorporated all the proposed quality improvements. © 2022 IEEE.

关键词： Six sigma

来源：评论

学校读者我要写书评

暂无评论

Wafer Map Defect Analysis Based on EfficientNetV2 using Grad-CAM

引用

Transactions of the Korean Institute of Electrical Engineers 2023年第4期72卷 553-558页

作者： Lee, Han-Sung Cho, Hyun-Chong Dept. of Electronics Engineering and Interdisciplinary Graduate Graduate Program for BIT Medical Convergence Kangwon National University Korea Republic of

In semiconductors, various defect patterns appear on the wafer map due to problems in the design and manufacturing process. Analysis of generated defect patterns will reduce the rate of defects and enable the production of high-quality semiconductors. Considering the number of semiconductors produced, performing defect analysis by human resources is inefficient. Recently, as hardware performance has improved, high-performance deep learning models have been designed. These models show high performance in image classification and have advantages in terms of processing speed. Therefore, this paper used EfficientNetV2 designed to achieve maximum efficiency with few parameters for semiconductor failure analysis. Identifying the location of defects is a critical element of defect analysis, not just classifying defect patterns. Therefore, in this study, we used Grad-CAM to identify the classification of defect patterns and their approximate location. Wafer map dataset is difficult to collect as data includes defects in manufacturing companies' processes. To train EfficientNetV2, we used the WM-811K dataset, a publicly available dataset on Kaggle. This dataset has an imbalance in the number of data between classes. We increased the data using Flip and Rotate to address the dataset's imbalances, ultimately improving the classification performance. The test results showed an accuracy of 0.944 and an F1-score of 0.929. Copyright © The Korean Institute of Electrical Engineers.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

Low Routing Complexity Multiframe Pipelined LDPC Decoder Based on a Novel Pseudo Marginalized Min-Sum Algorithm for High Throughput Applications

引用

IEEE Transactions on Very Large Scale Integration (VLSI) Systems 2023年第1期31卷 29-42页

作者： Davila, HenryLopez Wu, Tsung-Han Jou, Shyh-Jye Jerry Chen, Sau-Gee Tsai, Pei-Yun National Chiao Tung University Eecs International Graduate Program Hsinchu30010 Taiwan National Yang Ming Chiao Tung University Institute of Electronics Hsinchu30010 Taiwan National Central University Electrical Engineering Department Taoyuan32001 Taiwan

This article presents a high throughput and low routing complexity multiframe pipelined low-density parity check (LDPC) decoder design based on a novel pseudo marginalized min-sum (PMMS) message passing approach. The proposed PMMS approach reduces the required number of interconnections in the routing network allowing the design to be implemented with reduced hardware complexity, low power consumption and high throughput capability while supporting multiple coding rates with short and long codewords as defined in many application standards. Implementation results for IEEE802.11ad/ay standards show that the proposed design satisfies a target bit error rate (BER) requirement of 3× 10-7 with 64 quadrature amp mod (QAM) targeting high throughput applications. Furthermore, the proposed design is able to achieve a throughput of 62 and 101.8 Gb/s with two pipelining stages under 28-nm CMOS and 16-nm FinFET CMOS process, respectively. As compared to the existing NMS algorithm, the proposed design based on the PMMS approach reduces the number of wires in the routing network by 45.5%, and the wirelength of the overall decoder by 17%. The area and power consumption are also reduced by 9.4% and 12%, respectively, as compared to the conventional normalized min-sum (NMS) algorithm. © 1993-2012 IEEE.

关键词： Message passing

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：