检索结果-内蒙古大学图书馆

Suicide risk assessment using word-level model with dictionary-based risky posts selection

Multimedia Tools and applications 2024年第7期83卷 21435-21454页

作者： Tsai, Yun Sheng Chen, Arbee L. P. Institute of Information Systems and Applications National Tsing Hua University Hsinchu Taiwan Department of Computer Science and Information Engineering Asia University Taichung Taiwan Department of Computer Science National Tsing Hua University Hsinchu Taiwan

Suicide is a serious issue around the world and is a leading cause of death in US. In the past 20 years, the suicide rate has seen a significant increase of 35%. With the rapid development of information technology, more and more people begin to use social media to share their inner feelings. It enables social media data to be widely used for research on suicide risk assessment. However, not all social media posts are suicide related. Previous research addressed this problem with post-level attention mechanism. However, post-level attention mechanism may not find relevant suicide posts. This problem becomes more serious in the feature-based post embeddings since each post is converted into a single vector to serve as the input of the model, resulting in the loss of word-level information during training. In this paper, we addressed this problem by introducing a novel word-level model including a post-selectin layer as a solution. Firstly, we utilize a suicide keyword dictionary to identify risky posts that may be missed by the post-level attention mechanism. We then convert the words in the risky posts into word embeddings and use self-attention to generate the post embeddings for the risky posts. Finally, we pass the post embeddings to a multilayer perceptron to classify the suicide risk. We also demonstrate that the FScore used in previous studies can be reduced to a function of accuracy, which does not reflect the model performance in predicting imbalanced datasets. Therefore, we additionally adopt macro F1 score as the evaluation function. Experiment results show that our model not only outperforms previous studies in FScore performance, but also achieves macro F1 Score a nearly 4% improvement compared to previous studies. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2023.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Content Based Image Retrieval: A Study of Approaches and Techniques 4

Content Based Image Retrieval: A Study of Approaches and Tec...

引用

4th International Conference on Technological Advancements in Computational sciences, ICTACS 2024

作者： Bano, Mehnaz Matta, Priya Chandel, Shivali Tula's Institute Department of Computer Science and Engineering Dehradun India Tula's Institute Department of Computer Applications Dehradun India

ISBN: (纸本)9798350387490

The Content Based Image Retrieval (CBIR) is basically used to extract images from the collection of images using several image matching and extraction methods. As it is now with the advancement and ongoing consistent technology and negligible cost of the electronic, digital and virtual sensors, a huge collection of image databases is processed by different types of applications. This type of database of images extends the requirement that we should provide effective search methods for the retrieval of images that can fulfill the demands of end-user. The texture, color, or shape of a picture is the most basic feature used to symbolize and index the images. These distinct elements of photographs are retrieved and used as a measure to find image similarities. A search procedure is initiated for relevant images that fulfill the user's information need using a sketch drawing or a query image given by the user that has similar features. The relevance feedback can be used as an optional step to retrieve and enhance the CBIR process. In this paper, after extracting semantic characteristics from photos, an analysis of the content of the images is performed with respect to features connected to the low level. In this paper, an overview of traditional CBIR methods (e.g.: Color histogram-based, texture based and shape based) are discussed. This paper's primary goal is to study the comprehensive details on the various computational techniques used for content-based image retrieval. To further enhance the efficiency of the image retrieval process, their limitations are also addressed. © 2024 IEEE.

关键词： Content based retrieval

来源：评论

学校读者我要写书评

暂无评论

An Effective Hybrid Model of ELM and Enhanced GWO for Estimating Compressive Strength of Metakaolin-Contained Cemented Materials

引用

computer Modeling in engineering & sciences 2024年第5期139卷 1521-1555页

作者： Abidhan Bardhan Raushan Kumar Singh Mohammed Alatiyyah Sulaiman Abdullah Alateyah Department of Civil Engineering National Institute of Technology PatnaPatnaIndia Department of Computer Engineering and Applications GLA UniversityMathuraIndia Department of Computer Science College of Sciences and Humanities-AflajPrince Sattam Bin Abdulaziz UniversityAl-KharjSaudi Arabia Department of Computer Science College of Science and ArtsQassim UniversityUnaizahSaudi Arabia

This research proposes a highly effective soft computing paradigm for estimating the compressive strength(CS)of metakaolin-contained cemented *** proposed approach is a combination of an enhanced grey wolf optimizer(EGWO)and an extreme learning machine(ELM).EGWO is an augmented form of the classic grey wolf optimizer(GWO).Compared to standard GWO,EGWO has a better hunting mechanism and produces an optimal *** EGWO was used to optimize the ELM structure and a hybrid model,ELM-EGWO,was *** train and validate the proposed ELM-EGWO model,a sum of 361 experimental results featuring five influencing factors was *** on sensitivity analysis,three distinct cases of influencing parameters were considered to investigate the effect of influencing factors on predictive *** consequences show that the constructed ELM-EGWO achieved the most accurate precision in both training(RMSE=0.0959)and testing(RMSE=0.0912)*** outcomes of the ELM-EGWO are significantly superior to those of deep neural networks(DNN),k-nearest neighbors(KNN),long short-term memory(LSTM),and other hybrid ELMs constructed with GWO,particle swarm optimization(PSO),harris hawks optimization(HHO),salp swarm algorithm(SSA),marine predators algorithm(MPA),and colony predation algorithm(CPA).The overall results demonstrate that the newly suggested ELM-EGWO has the potential to estimate the CS of metakaolin-contained cemented materials with a high degree of precision and robustness.

关键词： Metakaolin-contained cemented materials compressive strength extreme learning machine grey wolf optimizer swarm intelligence uncertainty analysis artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Efficient and Precise CNN based Machine Leaming Method for Microwave Medical Imaging in Cancer Detection 2

Efficient and Precise CNN based Machine Leaming Method for M...

引用

2nd IEEE International Conference on Integrated Intelligence and Communication Systems, ICIICS 2024

作者： Sunil, B. Sameer, S. Vaseekaran, K.V. Rishi, R. Department of Computer Applications SRM Institute of Science and Technology Ramapuram Chennai India Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai India Department of Computer Science and Engineering Rajalakshmi Engineering College Thandalam Chennai India

ISBN: (纸本)9798331504960

Cancer detection is critical for early diagnosis and treatment, and non-invasive imaging methods like microwave imaging have shown promise in this domain. This research presents a CNN-based machine learning model to improve the speed and accuracy of microwave medical imaging for cancer detection. Leveraging large datasets, advanced preprocessing techniques such as noise removal, normalization, and data augmentation were applied. The proposed model includes a multi-layer CNN architecture, optimized using stochastic gradient descent (SGD) and categorical cross-entropy loss functions. Evaluation metrics, including accuracy, sensitivity, and specificity, were calculated from a confusion matrix. The system achieved 95.6% accuracy, 94% sensitivity, and 96% specificity, outperforming traditional models both in terms of accuracy and computational efficiency. The results suggest that the proposed model is well-suited for real-time clinical applications. Future work will focus on expanding the dataset and integrating multimodal imaging to enhance diagnostic precision. © 2024 IEEE.

关键词： Stochastic models

来源：评论

学校读者我要写书评

暂无评论

Microplastic Identification in Seawater using Generative Adversarial Networks

Microplastic Identification in Seawater using Generative Adv...

引用

2024 International Conference on Advances in Data engineering and Intelligent Computing Systems, ADICS 2024

作者： Rajasekar, M. Geetha, Angelina Hindustan Institute Of Technology And Science Department Of Computer Applications Chennai India Departmnet Of Computer Science And Engineering Hindustan Insitute Of Technology And Science Chennai India

ISBN: (纸本)9798350364828

In recent years, microplastics-plastic particles smaller than five millimeters-have become a significant environmental contaminant. These tiny plastic pieces have been found permeating aquatic ecosystems globally, posing a threat to marine life upon ingestion. However, identification and quantification of microplastics in seawater samples remains an arduous task. The small size and translucent nature of microplastics makes them difficult to distinguish from natural particulates in seawater under a microscope. This has hindered efforts to accurately monitor microplastic pollution levels in the marine environment. Our goal in this study was to use cutting edge deep learning techniques to create an automated image based system for detecting microplastics in seawater. We chose to employ a generative adversarial network (GAN) architecture for its proven capability in generating highly realistic synthetic images. The GAN model was trained on a dataset of microscope images of microplastics and natural particulates extracted from seawater samples. Coastal seawater samples were first filtered to isolate particulates of a size range containing microplastics. Density separation was then used to separate the plastic microparticles from denser natural particulates. We implemented a deep convolutional GAN with a generator network to produce synthetic microplastic images, and a discriminator network to differentiate real from synthetic images. Through iterative adversarial training, the two networks evolved to produce and accurately classify images of microplastics with a high degree of realism. Advanced image processing techniques were used to enhance the training data. After training, the GAN model was evaluated on an annotated testing dataset of images containing real-world microplastics and natural particulates extracted from seawater. Our proposed GAN-based technique achieved a microplastic classification accuracy of 92.5% on the test set, demonstrating its effectiveness. The

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

MAIDS: malicious agent identification-based data security model for cloud environments

引用

Cluster Computing 2024年第5期27卷 6167-6184页

作者： Gupta, Kishu Saxena, Deepika Gupta, Rishabh Singh, Ashutosh Kumar Department of Computer Science and Engineering National Sun Yat-sen University Kaohsiung80424 Taiwan School of Computer Science and Engineering The University of Aizu Aizuwakamatsu965-0006 Japan Department of Computer Science The University of Economics and Human Sciences Warsaw01-043 Poland Department of Computer Applications SRM Institute of Science & ampTechnology Delhi-NCR Campus Modinagar Uttar Pradesh Ghaziabad201204 India Department of Computer Science and Engineering Indian Institute of Information Technology Bhopal Bhopal462003 India

With the vigorous development of cloud computing, most organizations have shifted their data and applications to the cloud environment for storage, computation, and sharing purposes. During storage and data sharing across the participating entities, a malicious agent may gain access to outsourced data from the cloud environment. A malicious agent is an entity that deliberately breaches the data. This information accessed might be misused or revealed to unauthorized parties. Therefore, data protection and prediction of malicious agents have become a demanding task that needs to be addressed appropriately. To deal with this crucial and challenging issue, this paper presents a Malicious Agent Identification-based Data Security (MAIDS) Model which utilizes XGBoost machine learning classification algorithm for securing data allocation and communication among different participating entities in the cloud system. The proposed model explores and computes intended multiple security parameters associated with online data communication or transactions. Correspondingly, a security-focused knowledge database is produced for developing the XGBoost Classifier-based Malicious Agent Prediction (XC-MAP) unit. Unlike the existing approaches, which only identify malicious agents after data leaks, MAIDS proactively identifies malicious agents by examining their eligibility for respective data access. In this way, the model provides a comprehensive solution to safeguard crucial data from both intentional and non-intentional breaches, by granting data to authorized agents only by evaluating the agent’s behavior and predicting the malicious agent before granting data. The performance of the proposed model is thoroughly evaluated by accomplishing extensive experiments, and the results signify that the MAIDS model predicts the malicious agents with high accuracy, precision, recall, and F1-scores up to 95.55%, 95.30%, 95.50%, and 95.20%, respectively. This enormously enhances the system’s sec

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Embedded Deep NN with Convolution NN-ID to Binominal Sentiment Prediction 9

Embedded Deep NN with Convolution NN-ID to Binominal Sentime...

引用

9th International Conference on science, Technology, engineering and Mathematics, ICONSTEM 2024

作者： Gokila, S. Rajeswari, S. Helen, D. Lakshna, A. Hindustan Institute of Technology And Science Department of Computer Applications Chennai India Shrimathi Devkunvar Nanalal Bhatt Vaishnav College For Women Pg Department of Computer Science Chennai India Srm Institute of Science And Technology Department of Computer Applications Chennai Kattankulathur India Jeppiaar Engineering Collge Department of Computer Science Engineering Chennai India

ISBN: (纸本)9798350365092

Objective: The objective is to develop a generalized deep learning system for sentiment analysis in a feedback system. This implies an intention to create a model that can effectively analyze sentiment across different domains or datasets. Methodology: It is proven that the deep learning systems are playing a major role in NLP, but still there is a need of enhancement to make the prediction system a perfect one. The Convolution Neural Network (CNN) could emphasize its ability to capture spatial dependencies in textual data and the Deep Neural Network(DNN) fetches the feature in text with varying semantics. In this context the proposed work Embed the Deep Neural Network with Convolution Neural Network in a three-layered ID architecture(EDNN with CNN-ID.) The model is enhanced in generalizing input-shape, kernel, channel, and filter parameters of the convolution layer. It produces remarkable results in sentimental analysis. The work is experimented with a feedback system from three different domains like Movie Review, Doctor Treatment Review, Product Review. Result: The EDNN with CNN-ID produces accuracy 93%, 91% and 91% for the three datasets © 2024 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Developing an Integrated IoT Cloud Based Predictive Conservation Model for Asset Management in Industry 4.0

引用

Journal of Social Computing 2023年第2期4卷 139-149页

作者： Karnam Shanmugam Kachhti Satyam Thimma Reddy Sreenivasula Reddy the Department of Computer Applications Annamacharya Institute of Technology and SciencesKarakambadiTirupathi 517520India the Department of Computer Science and Engineering Annamacharya Institute of Technology and SciencesKarakambadiTirupathi 517520India

With the advent of Industry 4.0(I4.0),predictive maintenance(PdM)methods have been widely adopted by businesses to deal with the condition of their *** the help of I4.0,digital transformation,information techniques,computerised control,and communication networks,large amounts of data on operational and process conditions can be collected from multiple pieces of equipment and used to make an automated fault detection and diagnosis,all with the goal of reducing unscheduled maintenance,improving component utilisation,and lengthening the lifespan of the *** this paper,we use smart approaches to create a PdM planning *** five key steps of the created approach are as follows:(1)cleaning the data,(2)normalising the data,(3)selecting the best features,(4)making a decision about the prediction network,and(5)producing a *** the outset,PdM-related data undergo data cleaning and normalisation to get everything in order and within some kind of *** next step is to execute optimal feature selection in order to eliminate unnecessary *** research presents the golden search optimization(GSO)algorithm,a powerful population-based optimization technique for efficient feature *** first phase of GSO is to produce a set of possible solutions or objects at *** objects will then interact with one another using a straightforward mathematical model to find the best feasible *** to the wide range over which the prediction values fall,machine learning and deep learning confront challenges in providing reliable *** is why we recommend a multilayer hybrid convolution neural network(MLH-CNN).While conceptually similar to VGGNet,this approach uses fewer parameters while maintaining or improving classification correctness by adjusting the amount of network modules and *** projected perfect is evaluated on two datasets to show that it can accurately predict the future state of components for upkeep prepara

关键词： Industry 4.0 predictive maintenance golden search optimization multilayer hybrid convolution neural network data cleaning

来源：评论

学校读者我要写书评

暂无评论

Application of Generative Graph Models in Biological Network Regeneration: A Selective Review and Qualitative Analysis

Application of Generative Graph Models in Biological Network...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Teji, Binon Roy, Swarup Guzzi, Pietro Hiram Bhandari, Dinabandhu Lab Department of Computer Applications Gangtok India University of Catanzaro School of Computer Science and Biomedical Engineering Italy Heritage Institute of Technology Department of Computer Science and Engineering Kolkata India

ISBN: (纸本)9798350386226

Biological networks are essential for understanding the complex cellular mechanisms of living organisms. Simulating biological networks allows researchers to model and understand complex cellular processes without the need for extensive and costly experiments. The ability to generate synthetic graphs that closely resemble these real-world, complex biological processes is a vital research area. Graph generation in the context of biological networks is particularly significant because it can lead to insights into cellular functions, disease mechanisms, and therapeutic targets. Recent advances in deep learning, particularly in graph generative models, have opened new avenues for applications in the biological domain. These advancements have the potential to revolutionize our understanding of biological systems. However, despite the development of numerous effective graph generation models, there has been limited work assessing the qualitative aspects of the generated graphs within the context of biological networks. Addressing this gap is crucial for ensuring that synthetic graphs are not only structurally accurate but also biologically *** various graph generation models are available, their application to biological network recreation has been limited. In this paper, we focus on graph generation, specifically edge and node-independent models for biological networks. We assess four candidate models across four gene expression networks. Our systematic assessment examines the models' qualitative aspects, including graph structural properties, generation diversity, and computational efficiency. Our findings highlight the strengths and limitations of current models, offering insights to guide the development of more robust graph generation techniques that accurately replicate biological network characteristics. © 2024 IEEE.

关键词： Biotic

来源：评论

学校读者我要写书评

暂无评论

Adaptive Treatment Planning via Multi-class Segmentation of GI Tract Tumours 6th

Adaptive Treatment Planning via Multi-class Segmentation of ...

引用

6th International conference on communication and computational technologies, ICCCT 2024

作者： Jain, Samyak Pal, Aarush Andrew, J. Maheshwari, Saatvik Department of Computer Science and Engineering and Department of Data Science and Computer Applications Manipal Institute of Technology Manipal Academy of Higher Education Karnataka Manipal576104 India

ISBN: (纸本)9789819774258

This study addresses gastrointestinal cancer radiation therapy challenges by implementing advanced deep learning techniques. We focus on automating manual segmentation tasks during treatment planning to enhance efficiency and patient tolerance. Our methodology uses a diverse 3D MRI scan dataset to employ image analysis, Convolutional Neural Networks (CNNs), and Image Segmentation. The primary architectural choices involve the U-Net and InceptionResNetv2 models, contributing to developing a predictive segmentation model. This substantial result underscores the effectiveness of our approach in achieving accurate segmentations in the clinical setting. The overarching objective of our project is to automate the segmentation of the stomach and intestines in MRI scans, thereby streamlining radiation therapy planning for improved efficiency and patient care. In our evaluations, the implemented model demonstrates a commendable dice coefficient of 0.7, as indicated by metrics such as dice loss. Anticipated outcomes encompass reduced treatment times, enhanced patient comfort, and optimised tumour radiation doses while minimising healthy tissue exposure. The successful implementation of this advanced model holds the potential to revolutionise current radiation therapy practices, significantly elevating cancer treatment outcomes. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

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：