检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Aldahdooh, Jehad Tanoli, Ziaurrehman Tang, Jing Research Program in Systems Oncology Faculty of medicine University of Helsinki Finland Doctoral Program in Computer Science University of Helsinki Finland Department of Mathematics and Statistics University of Helsinki

In this research, we present our work participation for the DrugProt task of BioCreative VII challenge. Drug-target interactions (DTIs) are critical for drug discovery and repurposing, which are often manually extracted from the experimental articles. There are >32M biomedical articles on PubMed and manually extracting DTIs from such a huge knowledge base is challenging. To solve this issue, we provide a solution for Track 1, which aims to extract 10 types of interactions between drug and protein entities. We applied an Ensemble Classifier model that combines BioMed-RoBERTa, a state of art language model, with Convolutional Neural Networks (CNN) to extract these relations. Despite the class imbalances in the BioCreative VII DrugProt test corpus, our model achieves a good performance compared to the average of other submissions in the challenge, with the micro F1 score of 55.67% (and 63% on BioCreative VI ChemProt test corpus). The results show the potential of deep learning in extracting various types of DTIs. © 2021, CC BY-NC-SA.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Matching Images on the Face of A Buddha Statue Using the Scale Invariant Feature Transform (SIFT) Method 7

Matching Images on the Face of A Buddha Statue Using the Sca...

引用

7th International Conference on Information Technology, computer, and Electrical Engineering, ICITACEE 2020

作者： Marlinda, Linda Rustad, Supriadi Basuki, Ruri Suko Budiman, Fikri Fatchan, Muhamad Universitas Dian Nuswantoro Doctoral Program of Computer Science Semarang Central Java Indonesia Universitas Pelita Bangsa Informatica Engineering Cikarang West Java Indonesia

ISBN: (纸本)9781728172255

The condition of the statue in Indonesia at this time many are missing, especially the face of the statue. 504 Buddha statues in the Borobudur temple, there are 248 statues which are now in a headless condition. The condition of the lost statue face is due to being stolen, still buried in the area around the temple, or has changed hands to another party. To find the statue's head according to the face, a matching image is needed, one of which uses the sift method. Buddha face statue matching can be done based on the characteristics of hair, eyebrow shape, lips, head shape or attributes found on the head of the statue. The image matching method can describe an image with a specific keypoint using Scale Invariant Feature Transform (SIFT), where each keypoint has a gradient orientation (GO) and gradient magnitude (GM) which are processed into features in the image registration process. The purpose of this study is to match the face images of Buddha statues with different angles. This study aims to match the face image of the original statue with the image of the statue chosen from different angles. The results of this study are that the same image with different angles obtains 90% accuracy. © 2020 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Systematic Literature Review of Knowledge Sharing Practices in Academic Institutions

A Systematic Literature Review of Knowledge Sharing Practice...

引用

International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS)

作者： Mariana Purba Ermatita Ermatita Abdiansah Abdiansah Vina Ayumi Handrie Noprisson Anita Ratnasari Doctoral Program in Engineering Universitas Sriwijaya Palembang Indonesia Faculty of Computer Science Universitas Sriwijaya Palembang Indonesia Faculty of Computer Science Universitas Sriwijaya South Sumatera Indonesia Faculty of Computer Science Universitas Mercu Buana Jakarta Indonesia

ISBN: (纸本)9781665427340

Many knowledge-sharing activities take place in educational institutions, both formally and informally. If this activity is organized with good knowledge management, then this will support a faster knowledge sharing process to get quality and innovative ideas. This paper aims to obtain a summary of existing research, issues, and opportunities for further analysis on knowledge-sharing (KS) practices in academic institutions. The phases of the systematic literature review (SLR) method are described based on Kitchenham (2009) guideline. We found 21 articles, seven articles from IEEE, nine articles from science Direct, and five articles from Springer. The collection of research data on knowledge sharing has been carried out in the United States, Australia, China, Cyprus, United Kingdom, Ghana, Hungary, Indonesia, Iran, Israel, Italy, Jordanian, Malaysia, and Saudi Arabia, with the most research locations being Malaysia (14%) and Saudi Arabia (19%). We also attempted to identify the research topic trend of knowledge sharing research in academic institutions. We found two types of research trends of knowledge sharing research in university, including factor analysis and architecture development. Of the two categories of research trends, 76% discussed factor analysis, and 24% discussed architectural development. We also identified six methods in KS research including Partial Least Square Structure Equation Modeling (PLS-SEM), questionnaire, data triangulation, focus groups discussion, observation and interview. Moreover, the most used method in related research is questionnaire, because it is a relatively inexpensive, fast and efficient way of collecting large amounts of information.

关键词： Systematics Bibliographies Multimedia systems Market research Mathematical models Data models Knowledge management

来源：评论

学校读者我要写书评

暂无评论

Evaluating natural language processing derived linguistic features associated with current suicidal ideation, past attempts, and future suicidal behavior

引用

Journal of Psychiatric Research 2025年 187卷 25-33页

作者： McBride, Lauren Badal, Varsha D. Harvey, Philip D. Pinkham, Amy Aich, Ankit Parde, Natalie Depp, Colin San Diego State University/University of California San Diego Joint Doctoral Program in Clinical Psychology San Diego CA United States Department of Psychiatry University of California San Diego La Jolla CA United States Department of Psychiatry University of Miami Miller School of Medicine Miami FL United States Research Service Bruce W Cater Miami VA Healthcare System Miami FL United States School of Behavioral and Brain Sciences The University of Texas at Dallas Richardson TX United States National Institute on Drug Abuse National Institutes of Health Baltimore MD United States University of Pennsylvania Philadelphia PA United States Department of Computer Science University of Illinois Chicago Chicago IL United States

Background: People with psychosis have a higher suicide risk than the general population. Natural language processing (NLP) has been used to understand communication in psychosis and suicide risk prediction, but not to predict future suicidal behavior in people with psychosis. We utilized NLP-derived linguistic features from a dyadic task among people with psychotic disorders to predict current suicide ideation, past suicide attempts, and future suicidal behavior. Methods: N = 112 adults with psychotic disorders completed the Columbia-Suicide Severity Rating Scale at baseline and one-year follow-up to capture lifetime suicide attempts, current suicidal ideation, and suicidal behavior during the follow-up period. At baseline, participants completed a dyadic role-play task called the Social Skills Performance Assessment. Lexical features, lexical diversity, and sentiment features were extracted from task transcripts. Models for each outcome were generated using a 70 %–30 % train-test split with MLPRegressor. SHapley Additive exPlanations (SHAP) was utilized for feature analysis. Results: A total of 42.9 % of participants had baseline suicidal ideation, 67.9 % had at least one past suicide attempt, and 13.3 % had at least one reported new suicidal behavior at one-year follow-up. The models had strong predictive performance for past attempts (F1 = 0.75) and current ideation (F1 = 0.74–0.79), with future suicide behavior models showing the strongest predictive performance (F1 = 0.86–0.93). The top features varied across suicide ideation, past attempts, and future behavior. Discussion: NLP-derived features from a dyadic task were associated with high predictive accuracy for future suicidal behavior. Pending replication, these findings suggest that NLP-derived linguistic features from dyadic tasks could contribute to understanding suicide risk among people with psychosis. © 2025 Elsevier Ltd

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring Low Rate Dos Attack Detection Methods: A Bibliometric Analysis and Roadmap for Further Research

Exploring Low Rate Dos Attack Detection Methods: A Bibliomet...

引用

International Conference on Data and Software Engineering (ICODSE)

作者： Anteng Widodo Adian Fatchur Rochim Budi Warsito Doctoral Program of Information System School of Postgraduated Studies Diponegoro University Semarang Indonesia Department of Information System Faculty of Engineering Muria Kudus University Kudus Indonesia Department of Computer Engineering Faculty of Engineering Diponegoro University Semarang Indonesia Department of Statistics Faculty of Science and Mathematics Diponegoro University Semarang Indonesia

Low-Rate Denial of Service (LDoS) attacks, an emerging breed of DoS attacks, present a formidable challenge in terms of their detectability. Within the realm of network security, these attacks cast a substantial shadow over the availability and integrity of services. This study seeks to delve into the intricate mechanics of LDoS attacks and explore the landscape of developed detection methodologies. Employing bibliometric analysis, we employ a multifaceted approach to gather research insights pertaining to LDoS attack detection. This approach encompasses the examination of evolving research trends, scrutiny of widely cited scientific publications within the same domain, identification of prolific researchers shaping the field, and a judicious selection of reputable publishers for dependable information acquisition. Furthermore, our study undertakes a meticulous categorization and classification of previously proposed LDoS detection methods documented in well-established scientific literature. This endeavor not only provides a more profound comprehension of the evolutionary trajectory and thematic thrusts within LDoS attack detection research, but it also facilitates the identification of gaps and directions for future exploration. The culmination of these analytical efforts culminates in a comprehensive framework. This contribution manifests through structured categorization, classification, and a forward-looking research roadmap, which collectively serve as valuable tools for both current and aspiring researchers engaged in LDoS attack detection. In summary, this research not only delves into the complexities of LDoS attacks and their mechanisms but also augments the current understanding of detection capabilities. Through its nuanced contributions, this paper extends a helpful guide to the dynamic realm of LDoS attack detection, thus catalyzing advancements and insights for the future.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Blockchain Scalability: Innovative Solutions for Optimized Performance in Decentralized Networks

Enhancing Blockchain Scalability: Innovative Solutions for O...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： Akanksha Srivastav Sheenu Agarwal Arpit Jain Shikha Tayal Shalu Jain Khemraj Sharma Tula’s institute Dehradun U.K. India Department of Electronics and Communication Engineering Uttarakhand Technical University Dehradun U.K. India Department of Computer Science & Engineering Koneru Lakshamaiah Education Foundation Vadessahwaram A.P. India Department of Computer Science & Engineering Tula’s Institute Dehradun Uttarakhand India Maharaja Agrasen Himalayan Garhwal University Pauri Garhwal Uttarakhand Department: Department of Business Administration Doctoral Program in Management Sciences Nanhua University Dalin Chiayi R.O.C

ISBN: (数字)9798350350067

ISBN: (纸本)9798350350074

A substantial number of people are presently making use of decentralised cryptocurrencies that are built on blockchain technology. These crypto currencies have garnered a lot of interest over the course of the last few years and are currently being used by their users. Being the first use of blockchain technology, Bitcoin has been a resounding success, which drives further research and improvement in the sector concerned with blockchain technology. Bitcoin was the first usage of blockchain technology. Bitcoin, on the other hand, is susceptible to significant performance issues due to the fact that it has a high transaction latency and a limited throughput. The operations of the cryptocurrency are considerably impacted as a result of these concerns. As a result of the fact that other cryptocurrencies that rely on proof-of-work also carry over its deficiencies, there has been an increase in the number of concerns about the scalability of blockchain technology. The fact that this is the case makes scaling blockchain technology more challenging. All during the course of this investigation, an effort is made to analyse and classify the various scaling mechanisms that are now being used for blockchains. In addition to this, we are going to look at a variety of various approaches and present a list of possible solutions to the issue of scalability that the blockchain technology is now dealing.

关键词： Hands computers Distributed ledger Scalability Bitcoin Throughput Proof of Work Fabrics Blockchains Informatics

来源：评论

学校读者我要写书评

暂无评论

Integrating Noise Classification and Speech Enhancement Model for Hearing Aids

Integrating Noise Classification and Speech Enhancement Mode...

引用

International SoC Design Conference, ISOCC

作者： Ying-Hsiu Hung Yen-Ching Chang Shin-Chi Lai Wen-Ho Juang Ming-Hwa Sheu Jeng-Dao Lee Dept. Electronics Engineering National Yunlin University of Science and Technology Douliu Taiwan Doctoral Degree Program in Smart Industry Technology Research and Development National Formosa University Huwei Taiwan Dept. Automation Engineering & Smart Machinery and Intelligent Manufacturing Research Center National Formosa University Huwei Taiwan Dept. Computer Science and Information Engineering National Formosa University Huwei Taiwan Dept. Automation Engineering National Formosa University Huwei Taiwan

ISBN: (数字)9798350377088

ISBN: (纸本)9798350377095

As the global population ages, the number of elderly people needing hearing aids is increasing. This paper proposed an architecture designed to enhance speech based on noise conditions. After noise types are identified by a Convolutional Neural Network (CNN) noise classification model, these noise conditions are combined with the noisy speech and input into a conditional Generative Adversarial Network (cGAN) for speech enhancement. The CNN noise classification model achieves an average recognition accuracy of nearly 92%, with a Kappa value as high as 0.88. The cGAN speech enhancement achieves lower error values in the Mel-Cepstral Distortion (MCD) measure. Although some parts of the human voice may be filtered out, the results demonstrate the potential development of the proposed algorithm.

关键词： Accuracy Noise Noise reduction Speech recognition Speech enhancement Hearing aids Classification algorithms Convolutional neural networks Human voice Older adults

来源：评论

学校读者我要写书评

暂无评论

Analysis of the quantum perceptron algorithm for classification of bank marketing data

引用

AIP Conference Proceedings 2023年第1期2714卷

作者： Solikhun Syahril Efendi Muhammad Zarlis Poltak Sihombing Doctoral Program Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia

Quantum computing is a technology that takes advantage of quantum effects, which operates using quantum computing, resulting in increased algorithm speed compared to the speed of algorithms that use classical computing. This study aims to classify bank marketing data in determining the eligibility of customers who are entitled to become depositors with the quantum perceptron algorithm using calculations with 5 variables, namely employment, status, education, home credit, and bank loans. The result of this research is the analysis of bank marketing classification data to determine the eligibility of customers who are entitled to become depositors using the quantum perceptron algorithm with quantum computation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection using Deep Neural Network Algorithm on the Internet of Things

Intrusion Detection using Deep Neural Network Algorithm on t...

引用

IEEE International Conference on Communication, Networks and Satellite (ComNetSat)

作者： Syariful Ikhwan Adi Wibowo Budi Warsito Doctoral Program of Information System School of Postgraduate Studies Diponegoro University Semarang Indonesia D3 Telecommunication Engineering Institut Teknologi Telkom Purwokerto Banyumas Indonesia Computer Science Informatics Department of Science and Mathematics Faculty Diponegoro University Semarang Indonesia Statistics Department of Science and Mathematics Faculty Diponegoro University Semarang Indonesia

ISBN: (数字)9781665460309

ISBN: (纸本)9781665460316

The increasing use of IoT devices on future networks is very helpful for humans in their lives. However, the increase in devices connected to IoT networks also increases the potential for attacks against those networks. Vulnerabilities in Internet of Things (IoT) networks can be exposed at any time. Artificial intelligence can be used to protect the IoT network by being able to detect attacks on the network so that they can be prevented. In this study, network detection was carried out using the Deep Neural Network (DNN) algorithm. The test was carried out using the UNSW Bot-IoT dataset with a comparison of training data of 75% of the overall data. The results obtained show the ability of the algorithm to detect attacks on average with 99.999% accuracy. The validation loss and training loss look very small. In this study, there is a validation loss that still occurs in overfitting, but the difference is very small.

关键词： Deep learning Training Satellites Neural networks Intrusion detection Training data Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Study on Medicinal Plant Leaf Recognition Using Artificial Intelligence

A Study on Medicinal Plant Leaf Recognition Using Artificial...

引用

International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS)

作者： Vina Ayumi Ermatita Ermatita Abdiansah Abdiansah Handrie Noprisson Mariana Purba Marissa Utami Doctoral Program in Engineering Universitas Sriwijaya Palembang Indonesia Faculty of Computer Science Universitas Sriwijaya Palembang Indonesia Faculty of Computer Science Universitas Mercu Buana Jakarta Indonesia Program of Informatics Management Politeknik Anika Palembang Indonesia Faculty of Engineering Muhammadiyah University of Bengkulu Bengkulu Indonesia

ISBN: (纸本)9781665427340

Medicinal plant recognition manually takes a lot of time and money. Moreover, to reduce these resources, some researchers propose to implement artificial intelligence technology. This paper aims are to conduct a systematic literature review of medicinal plant leaf recognition published in the last two years (2019–2020) from IEEE, Springer and science Direct. We obtained 15 studies in the field of medicinal plant leaf recognition using artificial intelligence. The dataset used for medicinal plant leaf recognition is mostly used private dataset, however, there are public dataset named Leaf, Flavia, Swedish dataset. We also found robust method that can be used for medicinal plant leaf recognition is Multichannel Modified Local Gradient Pattern (MCMLGP) and Gray Level Co-Occurrence Matrix (GLCM) as feature extraction; and Convolutional Neural Network (CNN), Multi-Layer Perceptron trained with Backpropagation algorithm (MLP-BP), Support Vector Machine (SVM), and Transfer Learning (VGG19) as classifier.

关键词： Support vector machines Systematics Bibliographies Multimedia systems Transfer learning Backpropagation algorithms Feature extraction

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：