检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Yamamoto, Yuya Nam, Juhan Terasawa, Hiroko Doctoral Program in Informatics University of Tsukuba Japan Graduate School of Culture Technology KAIST Korea Republic of

Singing techniques are used for expressive vocal performances by employing temporal fluctuations of the timbre, the pitch, and other components of the voice. Their classification is a challenging task, because of mainly two factors: 1) the fluctuations in singing techniques have a wide variety and are affected by many factors and 2) existing datasets are imbalanced. To deal with these problems, we developed a novel audio feature learning method based on deformable convolution with decoupled training of the feature extractor and the classifier using a class-weighted loss function. The experimental results show the following: 1) the deformable convolution improves the classification results, particularly when it is applied to the last two convolutional layers, and 2) both re-training the classifier and weighting the cross-entropy loss function by a smoothed inverse frequency enhance the classification performance. © 2022, CC BY.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Bibliometric Analysis: Research Trends in Leaf Image Segmentation and Classification

Bibliometric Analysis: Research Trends in Leaf Image Segment...

引用

Artificial Intelligence and Mechatronics Systems (AIMS), International Conference on

作者： Eka Puji Agustini Rahmad Gernowo Kurnianingsih Adi Wibowo Budi Warsito Doctoral Program of Information System School of Postgraduated Studies Diponegoro University Semarang Indonesia Doctoral Program of Information System Diponegoro University Semarang Indonesia Master of Applied Science Program Polytechnic Semarang Indonesia Department of Informatics Faculty of Science and Mathematics Diponegoro University Semarang Indonesia Department of Statistics Faculty of Science and Mathematics Diponegoro Universitty Semarang Indonesia

Exploring various phenomena and issues related to leaf images is paramount, particularly in segmentation and classification of such images. This study employs bibliometric analysis to delve into two overarching themes: the trends in publication and the evolution of publications, along with a keyword-based analysis. The research methodology unfolds in two stages: (1) data collection and (2) analysis. The dataset comprises 1,248 articles sourced from the Scopus database, covering the period from 1988 to 2023. The research findings unveil a noteworthy surge in publication trends, peaking at 231 documents in 2023. An in-depth examination of journal names demonstrates that studies on the segmentation and classification of leaf images are predominantly featured in computer science journals, exemplified by the publication of 589 documents. Furthermore, an analysis of frequently used keywords highlights “Extraction” as the predominant term, employed a total of 364 times. This underscores that the research focus on leaf image segmentation and classification presents ample opportunities for researchers to delve more profoundly into the subject.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LE-DTA: Local Extrema Convolution for Drug Target Affinity Prediction 48

LE-DTA: Local Extrema Convolution for Drug Target Affinity P...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Langore, Tanoj Hsu, Te-Cheng Hsieh, Yi-Hsien Lin, Che Taipei10617 Taiwan Institute of Communications Engineering National Tsing Hua University Hsinchu30013 Taiwan Department of Electrical Engineering Ntu Taipei10617 Taiwan Center for Computational and Systems Biology Center for Biotechnology Ntu Taipei10617 Taiwan Smart Medicine and Health Informatics Program Ntu Taipei10617 Taiwan

ISBN: (纸本)9781728163277

One of the essential parts of drug discovery and design is the prediction of drug-target affinity (DTA). Researchers have proposed computational approaches for predicting DTA to circumvent the more expensive in vivo and in vitro tests. More recent approaches employed deep network architectures to obtain the features from the drug molecules and protein sequences. The drug compounds are represented as graphs and the target protein as a sequence to extract this information. In this work, we develop a new graph-based prediction model, termed LE-DTA, that utilizes local extrema convolutions for effective feature extraction. It focuses on the local and global extrema of graphs for node embedding. We investigated the performances of both the proposed models on three different benchmark datasets. Our proposed model showed improvement in CI by 1.12% and 0.35% and a reduction in MSE by 7.7% and 3.33% on the KIBA and BindingDB datasets, respectively. we also showed that despite using various pooling operations on our proposed model, we achieved an average reduction in MSE by 7% on the KIBA dataset and 3% improvement on the BindingDB dataset. © 2023 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Towards Continual Federated Learning of Monocular Depth for Autonomous Vehicles

Towards Continual Federated Learning of Monocular Depth for ...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Elton F. de S. Soares Carlos Alberto V. Campos Brazil Research Lab IBM Research Rio de Janeiro RJ Brazil Graduate Program in Informatics Federal University of the State of Rio de Janeiro Rio de Janeiro RJ Brazil

ISBN: (数字)9798331517786

ISBN: (纸本)9798331517793

Recent investigations in computer vision for autonomous vehicles have focused on depth estimation from images, owing to its cost-efficiency and adaptability. Monocular depth estimation, using a single camera, is notable for its adaptability compared to binocular techniques that require two fixed cameras. Sophisticated methodologies employ self-supervised deep neural networks, while latest research proposes the use of federated learning to tackle crucial challenges for autonomous driving, such as data privacy, network usage, computation distribution, and connectivity robustness. Nevertheless, continual learning presents an additional challenge for both centralized and federated training, as updating models with novel datasets may induce the forgetting of previously acquired samples, thereby diminishing the model’s versatility. Meanwhile, recent research indicates that experience replay strategies can be used to alleviate forgetting in autonomous driving use cases. We introduce ERFedSCDepth, an innovative approach amalgamating experience replay, federated learning, and deep self-supervision to allow the training of monocular depth estimators with high effectiveness and efficiency. Assessment using KITTI and DDAD datasets shows the efficacy of our approach, achieving enhanced continual learning performance over state-of-the-art baseline at standard depth metrics.

关键词： Continuing education Training Data privacy Vehicular and wireless technologies Federated learning Computational modeling Transportation Cameras Autonomous vehicles Testing

来源：评论

学校读者我要写书评

暂无评论

New Media as a Tools to Improve Creative Thinking: A Systematic Literature Review 7

New Media as a Tools to Improve Creative Thinking: A Systema...

引用

7th International Conference on Information Technology, Information Systems and Electrical Engineering, ICITISEE 2023

作者： Hermawan, Hellik Mahardika, Fajar Darmayanti, Irma Sumantri, R. Bagus Bambang Saputra, Dhanar Intan Surya Aminuddin, Afrig Universitas Amikom Purwokerto Faculty of Computer Science Department of Informatics Jawa Tengah Banyumas Indonesia Institut Teknologi Dan Sains Nahdlatul Computer Technology Study Program Faculty of Science and Technology Ulama Pekalongan Indonesia Universitas Amikom Purwokerto Faculty of Computer Science Department of Information Technology Jawa Tengah Banyumas Indonesia Universitas Harapan Information Systems Study Program Faculty of Science and Technology Bangsa Indonesia Universitas Amikom Yogyakarta Faculty of Computer Science Sleman Indonesia

ISBN: (纸本)9798350382266

This systematic literature review (SLR) study aims to analyze the role of New Media as a Tool to Improve Creative Thinking, with relevant articles from 2018 to 2023 taken from reputable international journals. It uses three research questions (RQ) to explore New Media's relevance in stimulating creativity. The results indicate that interactive platforms such as social media and online collaboration tools positively influence creative thinking skills. Interaction through New Media allows individuals to share ideas, discuss, and be exposed to various points of view, all of which stimulate creative thinking. In addition, New Media also facilitates the creative process of solving problems and generating original ideas. The immersive experiences offered by this technology can enhance the exploration of ideas and increase the ability to think out-of-the-box. While New Media offers great potential to enhance creativity, there are also potential risks, such as false information, media addiction, and privacy concerns. Therefore, awareness of the wise use of New Media needs to be increased, especially in education and everyday life. Overall, this literature review provides in-depth insight into the role of New Media in enhancing creative thinking skills and driving innovation. With the right approach, New Media can be an effective tool in stimulating creative thinking and encouraging the creation of original ideas beneficial for future social and technological developments. © 2023 IEEE.

关键词： Creative Thinking New Media Original Ideas Systematic Literature Review The Effect of Using New Media

来源：评论

学校读者我要写书评

暂无评论

Predicting Potential Fires in Indonesia by Analyzing VIIRS Night Data during 2018 – 2022

Predicting Potential Fires in Indonesia by Analyzing VIIRS N...

引用

International Symposium on Grids and Clouds 2023 in conjunction with HEPiX Spring Workshop, ISGC and HEPiX 2023

作者： Suhardiman, Basuki Hermanto, Benni Rio Directorate of Information Technology Institut Teknologi Bandung Jl Ganesha 10 Bandung Indonesia Master’s Program in Computational Science Faculty of Mathematics and Natural Sciences Institut Teknologi Bandung Jl Ganesha 10 Bandung Indonesia Biomedical Engineering Department School of Electrical Engineering and Informatics Institut Teknologi Bandung Indonesia

Forest fires have been detected to occur in Indonesia since 1998. The forest fires mostly resulted from human activities in order to expand their land, especially oil palm lands. Once a land clearing is carried out, it covers areas of tens to hundreds of thousands of hectares. The peak of the forest fires occurred in 2015 when almost half of the world was affected especially by smoke from the fire. In 2011, VIIRS (Visible Infrared Imaging Radiometer Suite) was launched by NOAA (National Oceanic and Atmospheric Administration). In their collected data, there is data on Indonesia issued daily for areas in the islands of Java, Sumatra, Kalimantan, Sulawesi, and the general areas of Indonesia. The VIIRS night data shows the possibility of some burning at night. We need to identify burnings that potentially become fires, which are potentially producing smoke. It is important to observe areas where large-scale forest fires frequently occur, so the authority could do some prevention beforehand. Using existing data released per day per area, we utilize an ANN (Artificial Neural Network) to identify a potential fire. The processes start with data cleaning and processing, Neural Network creation, and finally ANN training and testing. By using the ANN prediction model with the MinMax Scaler, we choose variables Temperature, Radiant Heat Intensity, and Source Footprint. Simulations are made to show the ranges of these variables that predict the possibility of’flame’ status occurring. We conclude that the ANN method can give more accurate results than the existing classification. © Copyright owned by the author(s) under the terms of the Creative Commons.

关键词： Fires

来源：评论

学校读者我要写书评

暂无评论

Exploring AI Applications in Digital Art Creation of Hanoman Balinese Dance Animation

Exploring AI Applications in Digital Art Creation of Hanoman...

引用

IEEE International Symposium on Consumer Electronics (ISCE)

作者： I Made Marthana Yusa I Gede Adi Sudi Anggara Ngakan Putu Darma Yasa Dwi Novitasari I Nyoman Widhi Adnyana Visual Communication Design Institut Bisnis dan Teknologi Indonesia Denpasar Indonesia Study Program of Informatics Technology Multimedia Design Subject Institut Bisnis dan Teknologi Indonesia Denpasar Indonesia

ISBN: (数字)9798350365191

ISBN: (纸本)9798350365207

This paper examines the integration of Artificial Intelligence (AI) in the digital creation of Balinese dance animations, with a specific focus on the Hanoman dance character as the case study. Hanoman dance as a part of Balinese dance, known for its intricate movements, unique costume and cultural significance, presents a unique challenge for digital artists. AI technologies, such as machine learning and computer vision, offer novel approaches to capturing and animating these complex dance forms. This study examines current AI applications in this domain, assesses their effectiveness, and discusses the potential advancements and limitations. Through the use of rotoscoping and motion capture techniques, this study adeptly examines the intricate movements of the Hanoman dance, an integral part of Balinese dance heritage, employing text-to-animation and AI models for video footage motion capture. The thorough processes of data collection, preprocessing, and model training emphasized in the study highlight the necessity of a meticulous methodology. Furthermore, incorporating expert feedback during the validation and refinement phases ensures that the digital representations are both authentic and expressive. The study concludes that AI technologies can play a crucial role in preserving Balinese dance, offering educational tools and digital archives that uphold the cultural integrity of this traditional art form.

关键词： Training Computer vision Computational modeling Digital representation Machine learning Data collection Animation Motion capture Data models Cultural differences

来源：评论

学校读者我要写书评

暂无评论

IoT: Monitoring Temperature, Water pH, and Automatic Water Drainage Systems for Gurami Cultivation

IoT: Monitoring Temperature, Water pH, and Automatic Water D...

引用

Networking, Electrical Engineering, Computer Science, and Technology (IConNECT), International Conference on

作者： Heni Sulistiani Wijaya Saputra Dedi Darwis Auliya Rahman Isnain Ardy Rimanda Putra Yosi Khairunisa Study Program of Accounting Information System Universitas Teknokrat Indonesia Lampung Indonesia Study Program of Computer Engineering Universitas Teknokrat Indonesia Lampung Indonesia Study Program of Informatics Universitas Teknokrat Indonesia Lampung Indonesia Regional Research and Development Agency Lampung Province (Balitbangda) Lampung Indonesia

Gurami is a native fish from Indonesian waters that is much-loved by Indonesian people for daily food consumption. The gurami inhabits still waters such as swamps, lakes, and ponds. Besides that, carp cannot live in a water content that is too alkaline or acidic, the oxygen content in the water must be stable. Water quality is a very important factor and can affect the survival of cultivated fish. Several parameters must be considered in improving the development of carp, one of which is the temperature and pH of the water and automatic drainage of water. In this paper, we conduct IoT-based research that focuses on controlling water temperature and pH and automatically draining pool water. Water temperature and pH control such as a pH sensor temperature sensor and a water turbidity sensor will later be connected to the ESP 32 microcontroller which already has a wi-fi module. A system that is linked to electrical power and the internet then the sensor will read the water quality including the pH temperature value and water turbidity from inside the fish pond, after getting the data, the data will go to ESP 32. This research can help gurami cultivating farmers to make it easy to control the pH temperature and perform automatic pool water draining. The results of sensor testing with actual data are pretty accurate with the average error value of the ds18b20 sensor being 0.05% while the value of the pH sensor itself is 0.07%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Properties of the mixing layer height retrieved from ceilometer measurements in Slovakia and its relationship to the air pollutant concentrations

引用

Environmental Science and Pollution Research 2023年第54期30卷 115666-115682页

作者： Nguyen, Duy-Hieu Štefánik, Dušan Šedivá, Tereza Lin, Chitsan Ph.D. Program in Maritime Science and Technology College of Maritime National Kaohsiung University of Science and Technology Kaohsiung811213 Taiwan Slovak Hydrometeorological Institute Jeséniova 17 Bratislava833 15 Slovakia Faculty of Mathematics Physics and Informatics Comenius University in Bratislava Mlynská Dolina F1 Bratislava842 48 Slovakia Department of Marine Environmental Engineering National Kaohsiung University of Science and Technology Kaohsiung811213 Taiwan

Mixing layer height (MLH) is an important meteorological parameter for air quality since it significantly affects ground-level pollution in the atmosphere. This study examined the properties of the MLH on diurnal and seasonal timescales over a 3-year period (2020–2022) using high temporal resolution measurements from eight Vaisala CL31 ceilometers situated around Slovakia. Hourly averaged MLH data was retrieved from the BL-View software using merged method. The highest daily maxima for the MLH occurred mostly in summer and spring, while the lowest values occurred predominantly during winter and autumn. The average MLH daily maximum in summer was 2229 m, and just 859 m in winter. During summer, the spatial distribution of the MLH daily maxima was more uniform compared to winter, when the air masses within the individual valleys did not mix well. Correlations between ground-level pollutant concentrations and hourly mean/daily mean MLH were analyzed. The highest correlation, R≈0.6, was found for O3. For PM10, PM2.5, and NOx, the anticorrelations with MLH were found with maximum in winter (R ≈ − 0.3 for hourly data and R ≈ − 0.5 for daily mean data) but no relation in summer. Lastly, the ceilometer MLH was compared to the radiosonde retrieved MLH for various cloud covers. Our analysis is based on an extensive set of empirical data, which can improve the accuracy and effectiveness of meteorological and atmospheric chemistry models. The findings can support air pollution forecasting and warning systems, providing valuable insights for policymakers and researchers. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

FluxProg 2.0 - Extended Version of a Visual Tool for Teaching programming Logic Using Flowcharts with Real and Simulated Robots

FluxProg 2.0 - Extended Version of a Visual Tool for Teachin...

引用

2024 Brazilian Symposium on Robotics (SBR), and 2024 Workshop on Robotics in Education (WRE)

作者： Matheus Biscaya Gutierrez João Alberto Fabro André Cristiano Cordeiro Academic Department of Informatics (DAINF-CT) Federal University of Technology - Paraná (UTFPR) Curitiba PR Brazil Graduate Program on Applied Computing (PPGCA) DAINF-CT - UTFPR Curitiba PR Brazil

ISBN: (数字)9798350391084

ISBN: (纸本)9798350391091

This paper presents a new teaching tool with the goal of facilitating the learning of basic programming concepts among high school students and university freshmen. The tool incorporates a user-friendly visual interface and robotics, expanding on the existing Fluxprog project. New features were implemented, such as variables, logical and mathematical operations, conditional structures, and loops, to motivate students to engage in challenges that promote logical thinking. This paper presents the design, implementation and evaluation of a programming teaching tool using a visual language based on flowcharts, with subsequent data collection through a questionnaire and analysis of preliminary results to evaluate the user's experience while interacting with the tool.

关键词： Visualization Flowcharts Conferences Education Data collection User experience Logic Robots programming profession

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：