检索结果-内蒙古大学图书馆

5th International Conference on Information and Communications Technology, ICOIACT 2022

作者： Widianto, Mochammad Haldi Heryadi, Yaya Lukas Suparta, Wayan Wibowo, Antoni Bina Nusantara University Computer Science Department Binus Graduate Program - Doctor of Computer Science Jakarta11480 Indonesia Faculty of Engineering Jakarta12930 Indonesia Institut Teknologi Nasional Yogyakarta Faculty of Industrial Technology Departement of Electrical Engineering Yogyakarta55281 Indonesia

ISBN: (数字)9781665451406

ISBN: (纸本)9781665451406

Recently, cooking oil has been widely discussed on social media. Many people ask how to analyze this phenomenon, one of which is using a sentiment analysis application on Twitter that performs a scientific analysis of the tweets of this media user. This study aims to test the performance of the sentiment analysis algorithm utilizing the Bidirectional Encoder Representations from Transformers (BERT) algorithm from Twitter, which is used to classify the types of tweets processed in 2000 tweets. The study shows the results of the confusion matrix, accuracy, and precision. The study obtained a fairly good accuracy and precision performance of 84%, which occurred at a learning rate of 1e-6 and epoch 5. The author also discusses the factors that affect the performance of BERT, such as;pre-processing, data quantity, and data variation. © 2022 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

NCU-IISR/AS-GIS: Using BERTScore and Snippet Score to Improve the Performance of Pretrained Language Model in BioASQ 10b Phase B

NCU-IISR/AS-GIS: Using BERTScore and Snippet Score to Improv...

引用

2022 Conference and Labs of the Evaluation Forum, CLEF 2022

作者： Ting, Hao-Hsuan Zhang, Yu Han, Jen-Chieh Tsai, Richard Tzong-Han Interdisciplinary Program of Electrical Engineering and Computer Science National Central University Taiwan Department of Computer Science and Information Engineering National Central University Taiwan IoX Center National Taiwan University Taiwan Research Center for Humanities and Social Sciences Academia Sinica Taiwan

This paper presents our system for the BioASQ10b Phase B task. For ideal answers, we used the fine-tuned BioBERT model on the MNLI dataset to construct sentence embeddings and combined it with BERTScore to select sentences from the provided Snippets as answers. For the exact answers, we also used the BioBERT model and used the snippet scores generated from the ideal answer selection model to predict the exact answers for factoid and list questions. The exact answers of our fifth test batch ranked second place. In addition, the ideal answers we submitted achieved first place in the ROUGE score in all test batches from batch second to fifth. © 2022 Copyright for this paper by its authors.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Hyperbolic Diffusion Procrustes Analysis for Intrinsic Representation of Hierarchical Data Sets

Hyperbolic Diffusion Procrustes Analysis for Intrinsic Repre...

引用

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

作者： Ya-Wei Eileen Lin Yuval Kluger Ronen Talmon Viterbi Faculty of Electrical and Computer Engineering Technion Interdepartmental Program in Computational Biology and Bioinformatics Yale University Applied Math Program Yale University Department of Pathology School of Medicine Yale University

In this paper, we present Hyperbolic Diffusion Procrustes Analysis (HDPA), a new method for informative representation of hierarchical datasets based on hyperbolic geometry, diffusion geometry, and Procrustes analysis. Our method jointly embeds multiple datasets in a product manifold of hyperbolic spaces, where the data's hidden common hierarchical structure is provably recovered. In addition, our method generates an intrinsic embedding that accommodates the joint representation of multiple datasets with different features, acquired by different equipment, at different sites, or under different environmental conditions. Experimental results demonstrate the efficacy of HDPA on three biomedical datasets comprising heterogeneous gene expression and mass cytometry data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automatic 2D Material Detection in Optical Images using Deep Learning Based computer Vision 4

Automatic 2D Material Detection in Optical Images using Deep...

引用

AI and Optical Data Sciences IV 2023

作者： Ramezani, Fereshteh Parvez, Sheikh Fix, J. Pierce Battaglin, Arthur Whyte, Seamus Borys, Nicholas J. Whitaker, Bradley Electrical and Computer Engineering Department Montana State University Bozeman United States Department of Physics Montana State University Bozeman United States Materials Science Program Montana State University Bozeman United States Optical Technology Center Montana State University Bozeman United States

ISBN: (纸本)9781510659810

computer vision algorithms can quickly analyze numerous images and identify useful information with high accuracy. Recently, computer vision has been used to identify 2D materials in microscope images. 2D materials have important fundamental properties allowing for their use in many potential applications, including many in quantum information science and engineering. In order to use these materials for research and product development, single-layer 2D crystallites must be prepared through an exfoliation procedure and then identified using reflected light optical microscopy. Performing these searches manually is a time-consuming and tedious task. Deploying deep learning-based computer vision algorithms for 2D material search can automate the flake detection task with minimal need for human intervention. In this work, we have implemented a new deep learning pipeline to classify crystallites of 2D materials based on coarse thickness classifications in reflected-light optical micrographs. We have used DetectorRS as the object detector and trained it on 177 images containing hexagonal boron nitride (hBN) flakes of varying thickness. The trained model achieved a high detection accuracy for the rare category of thin flakes ( © 2023 SPIE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Assessing Distributed Energy Resource Hosting Capacity Under Different Grid-Tie Inverter Control Strategies

Assessing Distributed Energy Resource Hosting Capacity Under...

引用

Workshop on Communication Networks and Power Systems (WCNPS)

作者： Brenda L. M. Santos Luciano S. Barros Daniel Barbosa Fernando A. Moreira Graduate Program in Electrical Engineering Federal University of Bahia Salvador Brazil Computer Systems Department Federal University of Paraíba João Pessoa Brazil Department of Electrical and Computer Engineering Federal University of Bahia Salvador Brazil

Despite the potential benefits that the integration of distributed energy resources (DERs) can bring to the system, it may cause problems related to power quality constraints, such $as$ reverse power flow in substation and overvoltages. An effective approach to address these problems involves the adoption of reactive and active power control in grid-tie inverters associated with DER. Therefore, this paper assesses the impacts of grid-tie inverter control modes, including both Volt-Var and Volt-Watt strategies, on the DER hosting capacity. In order to improve the overall system operation, modifications in the Volt-Var and Volt-Watt curves were proposed. It is noteworthy that these control strategies can have adverse effects on certain distribution system performance indicators, such $as$ voltage deviation and power losses; for this reason, these indicators are also evaluated in this study. A stochastic approach was adopted to deal with the uncertainties associated with DERs and loads. Finally, from tests conducted in the IEEE 33-bus test system, it was concluded that the proper adjustment of the Volt-Var and Volt-Watt control curves significantly influences DER hosting capacity, $as$ well $as$ voltage deviation and power losses.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Model for Pauses in the Synthesized Speech of Mathematical Expressions in MathML 14

A Dynamic Model for Pauses in the Synthesized Speech of Math...

引用

14th International Conference on Education Technology and computers, ICETC 2022

作者： Souza, Adriana Freitas, Diamantino Bahia Federal Institute of Education Science and Technology Porto Seguro Bahia Brazil Doctoral Program in Digital Media Faculty of Engineering Faculty of Engineering of University of Porto Porto Portugal Department of Electrical and Computer Engineering Faculty of Engineering of University of Porto Porto Portugal

ISBN: (纸本)9781450397766

Voice synthesizers still present several challenges in the speech of mathematical content, as spoken mathematics has quite peculiar rules. In the synthesized speech, pauses help blind and visually impaired students identify the limits of mathematical operators and subexpressions. However, most studies on pauses define them uniformly or use simple punctuation marks to force the synthesizer to introduce pauses in certain parts of the expression. Speech is a dynamic process and pauses in expressions also need to be dynamic to make the synthetic speech of expressions more natural, as this can help in memorizing this type of content. This work proposed a dynamic model of pauses for mathematical expressions. Collected math expressions spoken by teachers were used to create the model. These expressions were useful for identifying patterns and creating a linear regression model. Blind and visually impaired students evaluated the model. Some improvements were observed when we compared the synthesized mathematical expressions with the model and Audiomath, the parameter tool used in this study. © 2022 ACM.

关键词： Dynamic models

来源：评论

学校读者我要写书评

暂无评论

Modular Self-Lock Origami: design, modeling, and simulation to improve the performance of a rotational joint

arXiv

引用

arXiv 2023年

作者： Zare, Samira Spaeth, Alex Suresh, Sandya Teodorescu, Mircea Department of Electrical and Computer Engineering University of California Santa Cruz United States SIP program University of California Santa Cruz United States Department of Computer Science and Engineering United States

Origami structures have been widely explored in robotics due to their many potential advantages. Origami robots can be very compact, as well as cheap and efficient to produce. In particular, they can be constructed in a flat format using modern manufacturing techniques. Rotational motion is essential for robotics, and a variety of origami rotational joints have been proposed in the literature. However, few of these are even approximately flat-foldable. One potential enabler of flat origami rotational joints is the inclusion of lightweight pneumatic pouches which actuate the origami’s folds;however, pouch actuators only enable a relatively small amount of rotational displacement. The previously proposed Four-Vertex Origami is a flat-foldable structure which provides an angular multiplier for a pouch actuator, but suffers from a degenerate state. This paper presents a novel rigid origami, the Self-Lock Origami, which eliminates this degeneracy by slightly relaxing the assumption of flat-foldability. This joint is analysed in terms of a trade-off between the angular multiplier and the mechanical advantage. Furthermore, the Self-Lock Origami is a modular joint which can be connected to similar or different joints to produce complex movements for various applications;three different manipulator designs are introduced as a proof of concept. Copyright © 2023, The Authors. All rights reserved.

关键词： Manipulators

来源：评论

学校读者我要写书评

暂无评论

Seafloor Imaging Maps by Incorporating Side Scan Sonar Technology on Hybrid Autonomous Underwater Glider

Seafloor Imaging Maps by Incorporating Side Scan Sonar Techn...

引用

International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)

作者： Ardian Budi Kusuma Atmaja Egi Muhammad Idris Hidayat Bambang Riyanto Trilaksono Simon Siregar Natsir Habibullah School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia Department Computer Engineering Faculty of Applied Science Doctoral Program of Electrical Engineering Institut Teknologi Bandung Telkom University

This research aims to construct a two-dimensional image to represent an underwater geometry map with a Side Scan Sonar (SSS) mounted on a Hybrid Autonomous Underwater Glider (HAUG). Building the underwater map has two stages of the process. The first stage is preprocessing which includes Time-varying gains (TVG), slant range correction, and ground range correction. The second is HAUG navigation, the movement of HAUG orientation to the angle and distance of SSS readings and plotting the geometry of the grid map. With these two stages, a two-dimensional grid map will be formed. Meanwhile, the 3D plot utilizes slant range and ground range correction to obtain the surface height of the bottom of the pool. From the experiments conducted to conduct mapping in the pool, two-dimensional and three-dimensional visual forms of the pool floor and pool walls were produced. The results of the estimated measurement of the width of the pool obtained 14.05 meters and the height of the pool 3.199 meters with an SSS beam angle of 58 degrees.

关键词：

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

Outage Performance Analysis of Terahertz Band Drone-to-Ground Communications

Outage Performance Analysis of Terahertz Band Drone-to-Groun...

引用

Communications and Networking (BalkanCom), International Balkan Conference on

作者： Akhtar Saeed Ozgur Gurbuz Fatih Alagoz Department of Electrical Engineering DHA Suffa University Karachi Pakistan Electronics Engineering Program Sabanci University Istanbul Turkiye Department of Computer Engineering Bogazici University Istanbul Turkiye

Recent studies have shown the potential of em-ploying the Terahertz (THz) band for 6G non-terrestrial communications including drones. This paper assesses the outage performance of the THz band Drone-to-Ground (D2G) vertical communications up to 100 m altitude at four practically feasible THz transmission windows (TWs): f 1 = 0.140 THz; [0.110-0.170] THz, f 2 = 0.300 THz; [0.275-0325] THz, f 3 = 0.850 THz; [0.790-0.910] THz, and f 4 = 0.935 THz; [0.930-03940] THz. We consider vertical D2G communication, where realistic THz-based absorption gains of the four THz TWs at the drone altitudes are obtained via the International Telecommunications Union (ITU) model using the Standard Weather Profile. Additionally, multipath (MP) fading and beam misalignment (BM) fading are incorporated into the overall channel gain for assessing the outage performance. Numerical results reveal that under severe BM fading and Rayleigh fading, THz band D2G communication employing 60 dBi total antenna gains at $f_{1},\ f_{2},\ f_{3}$, and f 4 can be reliably established up to the drone altitudes: 76.9 m, 59.2m, 34.4 m, and 43.2 m, and up to 85.1 m, 60.3m, 36.9m, 45.5m under the severe BM fading and the presence of a strong Line-of-Sight component, truly showcasing the achievable altitude and range limits for the THz band D2G communications among 6G non-terrestrial cognitive networks.

关键词：

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：