检索结果-内蒙古大学图书馆

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

The Smart Analysis of Performing Scalable Inference for Big Data Analytics

The Smart Analysis of Performing Scalable Inference for Big ...

引用

International Conference on Power Energy, Environment and Intelligent Control (PEEIC)

作者： Vishakha D Bhandarkar Aruna Sri Rongali Mohamed Dawood Shamout Prof. Sachin Pund Gigih Forda Nama Shrishailappa Patil Applied Mathematics and Humanities Yeshwantrao Chavan College of Engineering India Graduate Doctoral Information Technology/Graduate (Information Technology Emphasis/Information Technology Ph.D.) University of The Cumberlands US Department of Management College of Business Administration University of Sharjah Sharjah United Arab Emirates Department of Industrial Engineering Shri Ramdeobaba College of Engineering and Management Nagpur Maharashtra India Department of Informatics Doctoral Program of Environtmental Science University of Lampung Bandar Lampung Computer engineering Vishwakarma Institute of Technology Pune

This paper examines the reproducibility of massive information analytics under particular factors. The paper proposes the “performing Scalable Inference” technique to cope with scalability troubles and to exploit current big statistics platforms for efficient computing and statistics garage of the statistics. In particular, the paper describes how to perform leak-free, parallelizable visible analytics over massive datasets using present extensive records analytics frameworks such as Apache Flink. This method presents an automated manner to execute analytics that preserves reproducibility and the ability to make adjustments without re-running the entire technique. The paper also demonstrates how these analytics may help several real-world use instances, explore affected person cohorts for studies, and develop stratified patient cohorts for hospital therapy. In the end, the paper observes how the proposed method may be exercised within the real world. Actively scalable inference for massive information analytics is pivotal in optimizing decision-making and allocation of assets. Typically, such inferences are made based on information accumulated from numerous sources, databases, unstructured data, and different digital sources. So one can ensure scalability, a complete cloud-primarily based platform has to be hired. This solution will permit the ***, deploying the essential records series and evaluation algorithms are prime here. It could permit the platform to recognize the styles inside the statistics and discover any ability correlations or traits. Additionally, predictive analytics and system mastering strategies may be incorporated to provide insights into the results of the information. In the long run, by leveraging those techniques, the platform can draw efficient inferences and appropriately compare situations in an agile and green way..

关键词：

来源：评论

学校读者我要写书评

暂无评论

It's about time: Feeding competition costs of sociality are affected more by temporal characteristics than spatial distribution

引用

Ecology and Evolution 2024年第4期14卷 e11209页

作者： Ekanayake-Weber, Marcy Mathew, Namita Cunha, Deanna Payen, Nathanael Grimm, Volker Koenig, Andreas Department of Anthropology Stony Brook University Stony Brook NY United States Interdepartmental Doctoral Program in Anthropological Sciences Stony Brook University Stony Brook NY United States Department of Computer Science Stony Brook University Stony Brook NY United States Department of Ecological Modeling Helmholtz Centre for Environmental Research – UFZ Leipzig Germany Graduate Program in Ecology and Evolution Stony Brook University Stony Brook NY United States

For most herbivorous animals, group-living appears to incur a high cost by intensifying feeding competition. These costs raise the question of how gregariousness (i.e., the tendency to aggregate) could have evolved to such an extent in taxa such as anthropoid primates and ungulates. When attempting to test the potential benefits and costs, previous foraging models demonstrated that group-living might be beneficial by lowering variance in intake, but that it reduces overall foraging success. However, these models did not fully account for the fact that gregariousness has multiple experiences and can vary in relation to ecological variables and foraging competition. Here, we present an agent-based model for testing how ecological variables impact the costs and benefits of gregariousness. In our simulations, primate-like agents forage on a variable resource landscape while maintaining spatial cohesion with conspecifics to varying degrees. The agents' energy intake rate, daily distance traveled, and variance in energy intake were recorded. Using Morris Elementary Effects sensitivity analysis, we tested the sensitivity of 10 model parameters, of which 2 controlled gregarious behavior and 8 controlled food resources, including multiple aspects of temporal and spatial heterogeneity. We found that, while gregariousness generally increased feeding competition, the costs of gregariousness were much lower when resources were less variable over time (i.e., when calorie extraction was slow and resource renewal was frequent). We also found that maintaining proximity to other agents resulted in lower variance in energy intake when resources were more variable over time. Thus, it appears that the costs and benefits of gregariousness are strongly influenced by the temporal characteristics of food resources, giving insight into the pressures that shaped the evolution of sociality and group living, including in our own lineage. © 2024 The Authors. Ecology and Evolution published by Jo

关键词： agent-based model foraging group living resource availability resource distribution resource quality

来源：评论

学校读者我要写书评

暂无评论

Hand-Woven Fabric Motif Recognition Methods: A Systematic Literature Review

Hand-Woven Fabric Motif Recognition Methods: A Systematic Li...

引用

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

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

ISBN: (纸本)9781665427340

Knowledge of hand-woven motif recognition is only owned by the older generation, which has not been passed down to the younger generation. Moreover, computer technology can be used to support the recognition of traditional woven fabric motifs. The aim of this research is to conduct a literature review on hand-woven fabric motif recognition, with an emphasis on performance accuracy, techniques, and datasets utilized. This research included three distinct stages of systematic literature review (SLR): planning, execution, and reporting of findings. We found several datasets between 924,845 data and the number of classes between 3–25 class. Based on research result, we obtained several methods for hand-woven fabric motif recognition focused on performance examination. We recommended image pre-processing method, including Adaptive Filtering Denoising, Adaptive Wiener Filtering, Histogram Equalization, Gradient Pyramid (GP) Decomposition. Moreover, we suggested five feature extraction methods, including Radon Transform, Wavelet Transform, Locally Rotation Invariance Measure (LBP-ROR), Transform Invariant Low-Rank Textures (TILT) and Histogram of Oriented Gradients (HOG). For learning method, we recommend Fuzzy C-Mean (FCM), Convolutional neural network (CNN), Deep Neural Network (DNN), MobileNets, Inception-v3 and ResNet-50.

关键词： Wavelet transforms Histograms Wiener filters Systematics Bibliographies Neural networks Fabrics

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：