检索结果-内蒙古大学图书馆

9th EAI International Conference on Advancement of Science and Technology, ICAST 2021

作者： Abebaw, Zeleke Rauber, Andreas Atnafu, Solomon IT Doctoral Program Addis Ababa University Addis Ababa Ethiopia Institute of Information Systems Engineering Technical University of Vienna Vienna Austria Department of Computer Science Addis Ababa University Addis Ababa Ethiopia

ISBN: (纸本)9783030937089

As online social media content continues to grow, so does the spread of hate speech. Hate speech has devastating consequences unless it is detected and monitored early. Recently, deep neural network-based hate speech detection models, particularly conventional single-channel Convolutional Neural Network (CNN), have achieved remarkable performance. However, the effectiveness of the models depends on the type of language they are trained on and the training data size. We argue that the effectiveness of the models could further be enhanced if we use multi-channel CNN models even for under-resourced languages that have limited training data size. This is because the single-channel CNN might fail to consider the potential effect of multiple channels to generate better features, which is not well investigated for hate speech detection. Therefore, in this work, we explore the use of multi-channel CNN to extract better features from different channels in an end-to-end manner on top of a word2vec embedding layer. Tested on a new small-scale Amharic hate speech dataset containing 2000 annotated social media comments, the experimental results show that the proposed multi-channel CNN model outperforms the single-channel CNN models but underperform from the baseline Support Vector Machine (SVM) with an average F-score of 81.3%, 78.2%, and 92.5% respectively. The finding of the study implies that the proposed MC-CNN model can be used as an alternative solution for hate speech detection using a deep learning approach when dataset scarcity is an issue. © 2022, ICST Institute for Computer Sciences, Social Informatics and Telecommunications engineering.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

TAST-Trademark Application Assistant

TAST-Trademark Application Assistant

引用

IEEE International Conference on Image Processing

作者： P.W.H. Kwan K. Toraichi K. Kameyama F. Kawazoe K. Nakamura Doctoral Program Graduate School of Engineering University of Tsukuba Japan Institute of Information Sciences and Electronics University of Tsukuba Japan Doctoral Program Graduate School of Systems and Information Engineering University of Tsukuba Japan

In this paper, a Trademark Application Assistant (TAST) that aims to speed up the process of a successful trademark application is proposed. The core of TAST is a similarity-based image retrieval system that makes use of relaxation matching on extracted contour segments. A novelty of this research lies in the processing architecture introduced for adapting the highly effective but computation expensive relaxation matching algorithm to real-time image retrieval. Preliminary results illustrating the quality of matching and the scalability of the processing architecture in terms of response time are included. The proposed architecture is not limited to using relaxation matching based servers, but is also applicable to other types of matching server as well.

关键词： Trademarks Image retrieval Computer architecture Scalability Delay Character recognition Image databases Hardware Gray-scale systems engineering and theory

来源：评论

学校读者我要写书评

暂无评论

Advanced semisoft handoff method of cellular IP access networks

Advanced semisoft handoff method of cellular IP access netwo...

引用

International Conference on Advanced information Networking and Applications (AINA)

作者： Joungwoong Lee S. Kimura Y. Ebihara Doctoral Program in Systems and Information Engineering University of Tsukuba Japan Institute of Information Sciences and Electronics University of Tsukuba Japan

Mobile IP is the current standard for supporting global mobility, however the performance degrades to support micro mobility. Cellular IP could be a good solution to accommodate efficiently hundreds of, thousands of mobile hosts that perform fast and frequent handoff in a small local area network. In semisoft handoff of cellular IP, a mobile host sends a semisoft packet to the new base station before performing actual handoff to guarantee that the routing cache mapping associated with the new base station is created before actual handoff takes place. But packet loss and handoff delay are still occurred by this model. We propose an advanced semisoft handoff method with no packet loss but with additional small packet delay just before or after handoff. In this method, the cross-over node calculates the time for the last message to be delivered to the mobile host via the old base station just before handoff based on four typical network models. On receiving that packet, the mobile host performs handoff to the new base station. Our simulation experiment results show that the proposed semisoft handoff method actually outperforms the traditional semisoft handoff method in both handoff packet loss and handoff delay. We study the performance of the advanced semisoft handoff method with the network models.

关键词： Cellular networks Base stations Routing Degradation Local area networks Protocols Analytical models systems engineering and theory Added delay IP networks

来源：评论

学校读者我要写书评

暂无评论

A model of context-dependent association using selective desensitization of nonmonotonic neural elements

引用

systems and Computers in Japan 2005年第7期36卷 73-83页

作者： Morita, Masahiko Matsuzawa, Kouhei Morokami, Shigemitsu Institute of Engineering Mechanics and Systems University of Tsukuba Tsukuba 305-8573 Japan Doctoral Program in Systems and Information Engineering University of Tsukuba Tsukuba 305-8573 Japan

In neural networks based on a distributed information representation, when different patterns are to be recalled from the same input by association depending on the context, the usual method is to concatenate the pattern representing the context with the input pattern. However, there is a serious problem in this approach, and strong constraints are imposed on the number of inputs and the number of context patterns. This paper tries to apply a different method of contextual modification to nonmonotonic neural networks in order to construct a context-dependent associative model that can solve the longstanding problem. In the proposed model, the number of associations that can be learned increases almost in proportion to the number of elements, regardless of the numbers of the input and context patterns. In addition, the state transitions among attractors can be controlled flexibly by switching the context, which enables the model to simulate the behavior of any finite automaton without inducing an explosive increase in the number of elements or the training time. The model also has a high generalization power ability based on fully distributed representations and has potential for overcoming the limitations of conventional symbol processing. © 2005 Wiley Periodicals, Inc.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Prediction of Consumer Purchase Intention on Green Product

Prediction of Consumer Purchase Intention on Green Product

引用

2021 International Seminar on Application for Technology of information and Communication, iSemantic 2021

作者： Hariyadi, Guruh Taufan Purwanto Isnanto, R Rizal Wibowo, Adi Warsito, Budi Universitas Diponegoro Doctoral Program of Information Systems Semarang Indonesia Universitas Diponegoro Faculty of Engineering Department of Chemical Engineering Semarang Indonesia Universitas Diponegoro Faculty of Engineerig Department of Computer Engineering Semarang Indonesia Universitas Diponegoro Faculty of Science and Mathematics Departement of Informatics Semarang Indonesia

ISBN: (纸本)9781665428040

Education to the public on green products has been widely carried out. Consumers who buy green products can be profiled by segmenting green consumers. In green marketing, consumer education on sustainable consumption is increasingly needed in recent years due to the problem of environmental pollution which poses a serious threat to the world population. Concern for the environment is an important topic in most countries, and individuals also study environmental issues. Individuals or groups of individuals who are 'ecologically aware' are also referred to as 'green consumers.' Such consumers are considered to have more concern for the environment. This study examined the predictions on the effect of the Green Perceived Value variables consisting of functional, conditional, and social values on the purchase intention of green consumers. It also tested the comparisons with other classification models. The models used in this research were Random Forest, Decision Tree, and Neural Network.. © 2021 IEEE.

关键词： Consumer behavior

来源：评论

学校读者我要写书评

暂无评论

Influence of cognitively distracting activity on driver’s eye movement during preparation of changing lanes

Influence of cognitively distracting activity on driver’s e...

引用

SICE Annual Conference

作者： Huiping Zhou Makoto Itoh Toshiyuki Inagaki Doctoral Program in Risk Engineering Graduate School of Systems and Information Engineering University of Tsukuba Tsukuba Japan Department of Risk Engineering Faculty of Systems and Information Engineering University of Tsukuba Tsukuba Japan

ISBN: (纸本)9784907764302

This paper investigates driverpsilas behavior of checking a traffic situation by analyzing driverpsilas eye movement when the driver is cognitively distracted during preparation of changing lanes. We made an experiment with a motion-based driving simulator under conditions of several types of secondary tasks. Collected data resulted in lower detection rates of intent of changing lanes, less checking behaviors and longer time length of checking behavior. These facts clarified that there are discrepancies between secondary tasks and no secondary one. It showed an influence of cognitively distracting activity on driverpsilas behavior.

关键词： Eye movement Distraction Driver behavior Intent inference Changing lanes Eye Movements Driver Behavior distractability Lanes Drivers detection rate (DR) activity driver circuits

来源：评论

学校读者我要写书评

暂无评论

Power assist control for leg with HAL-3 based on virtual torque and impedance adjustment

Power assist control for leg with HAL-3 based on virtual tor...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： S. Lee Y. Sankai Doctoral Program of System and Information Engineering University of Tsukuba Japan Institute of Systems and Engineering Mechanics University of Tsukuba Ibaraki Japan

This paper describes a method of power assist control for lower body based on neuromuscular signal, s-EMG (surface ElectroMyogram/Myoelectricity), and impedance adjustment around knee joint with the assist system, HAL (Hybrid Assistive Leg) -3 we have developed. Virtual Torque calculated by s-EMG enabled the HAL-3 to be operated as to intention of the experimental subject put on HAL, and assist the motion of lower body by predicting the moment around joints. Besides, the operator was able to swing the leg lighter by reducing the inertia and viscous friction around joint of the subject and HAL-3. In order to verify the proposed method, experiments for simple motion was performed with impedance values found by parameter identification with RLS (Recursive Least Square) method. The evaluation of assisted motion was done by Assist Efficiency (AE) calculated from s-EMG in nearly proportion to the operator's muscle force. The results showed the response of operational signal into actuator with impedance adjustment was improved dramatically, and the amplitudes of s-EMG were reduced significantly, then we could confirm the availability of impedance adjustment.

关键词： Torque control Leg Surface impedance Control systems Neuromuscular Knee Friction Parameter estimation Resonance light scattering Least squares methods

来源：评论

学校读者我要写书评

暂无评论

Study on the quench behaviour of molten fuel material jetted into coolant

Nihon Kikai Gakkai Ronbunshu, B Hen/Transactions of the Japa...

引用

Nihon Kikai Gakkai Ronbunshu, B Hen/Transactions of the Japan Society of Mechanical Engineers, Part B 2005年第703期71卷 947-953页

作者： Abe, Yutaka Kizu, Tetsuya Nariai, Hideki Chitose, Keiko Koyama, Kazuya Doctoral Program in Engineering Mechanics and Energy Graduate School of Systems and Information Engineering 1-1-1 Tennodai Tsukuba-shi Ibaraki 305-8573 Japan

In a core disruptive accident (CDA) of a Fast Breeder Reactor, the post accident heat removal (PAHR) is crucial for the accident mitigation. The molten core material should be solidified in the sodium coolant in the reactor vessel. In the present experiment, molten material is injected into water to experimentally obtain fragments and the visualized information of the fragmentation. The distributed particle behaviour of the molten material jet is observed with high-speed video camera. The distributions of the fragmented droplet diameter from the molten material jet are evaluated by correcting the solidified particles. The experimental results of the mean fragmented droplet diameter are compared with the existing theories. Consequently, the fragmented droplet diameter is close to the value estimated based on the Kelvin-Helmholtz instability. Once the particle diameter of the fragmented molten,material could be known from a hydrodynamic model, it becomes possible to estimate the mass ratio of the molten particle to the total injected mass by combining an appropriate heat transfer model The mass ratio of the molten fragment to total mass of the melted mixed oxide fuel in sodium coolant estimated in the present study is very small. The result means that most of the molten mixed oxide fuel material injected into the sodium coolant can be cooled down under the solidified temperature, if the amount of the coolant is sufficient.

关键词： Breeder reactors

来源：评论

学校读者我要写书评

暂无评论

引用

7th International Conference of Computer and Informatics engineering, IC2IE 2024

作者： Wandy, Wandy Adi, Kusworo Ayu, Media Anugerah Diponegoro University Doctoral Program of Information Systems School of Postgraduate Studies Semarang Indonesia Diponegoro University Faculty of Science and Mathematics Department of Physics Semarang Indonesia Sampoerna University Faculty of Engineering and Technology Department of Computer Science South Jakarta Indonesia

ISBN: (纸本)9798331505530

Full-marathon and Half-marathon distances are categorized as road running. Full-marathon running is becoming increasingly popular, and Half-marathon is increasing worldwide in both sexes and all age groups. Some aspects might relate to Full-marathon and Half-marathon running performance during training and races. Technology also plays an essential role in supporting runners and running races. Technology like artificial intelligence (AI) now supports the running athlete, not only predicting performance and results. It can also be used later to help the coach generate training programs for the athlete. This research aimed to find many aspects of marathons and performance and analyze them to see if artificial intelligence could later support them. It used secondary data and a systematic literature review proposed by Kitchenham. Out of the 58 articles, 21 of them (36.21%) received a score of 1 from Q1. Additionally, 19 articles (32.76%) received a score of 1 from both Q2 and Q3. Among the 58 articles, 9 (15.52%) received a total score of 3, with all three Q1, Q2, and Q3 scores being 1. This indicates that artificial intelligence will likely support the content of these nine articles. Several factors were also discovered to be connected to marathons and athletic performance. These findings suggested that additional investigation into marathons and performance, later backed by artificial intelligence, remained pertinent and essential. © 2024 IEEE.

关键词： artificial intelligence aspects marathon performance

来源：评论

学校读者我要写书评

暂无评论

Air Particulate Matters Auto-Rule-Based Labeling to Support Long-Distance Run Environment Data Classification 13

Air Particulate Matters Auto-Rule-Based Labeling to Support ...

引用

13th IEEE Symposium on Computer Applications and Industrial Electronics, ISCAIE 2023

ISBN: (纸本)9798350347319

Sports Science is an interdisciplinary and multidisciplinary science that strives to increase athletic performance and endurance. Sport Science recognizes and prevents injuries. Sensors and statistics formalize Sports Science. Runners need coaches and teams to support them before, during, and after the run race. Coaches generate running training plans to boost performance. Running race performances may be impacted by air pollution exposure while training, so coaches should consider limiting air pollution exposure when training. One of the external factors is Particulate Matter (PM2.5 and PM10). Sensors connecting to the Internet can record external factors and produce csv data. The foundation of supervised machine learning is the labeling process. Labeling a set of data is one of the laborious and time-consuming phases in every machine-learning application because it requires verifying the accuracy of the labels and making any necessary revisions. This research aimed to find a solution to automatically label numerous air particulate matter raw data using a rule based on parameters to reduce manual work, human errors and faster processes. This labeled data will later be used for supervised machine learning classification to support the coach in generating training programs for the runners in a Sports information System. Based on Indonesia Air Quality index rule-based approach, labeled text data in csv has been generated and tested with PM2.5 and PM10 parameters in three scenarios with a 100% success rate. It was possible to automate the labeling process, and it explained how automation results in fast and accurate results. © 2023 IEEE.

关键词： Classification (of information)

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：