检索结果-内蒙古大学图书馆

Variable Length Multi-Objective Whale Optimization for Trust Aware Data Gathering in Wireless Sensor Network

IEEE Access 2025年 13卷 32100-32121页

作者： Saad, Mohammed Ayad Jaafar, Rosmina Chellappan, Kalaivani Faculty of Engineering and Built Environment Department of Electrical Electronics and System Engineering Selangor Bangi43600 Malaysia Al-Kitab University Department of Medical Instrumentations Technique Engineering Kirkuk36001 Iraq Universitas Airlangga Biomedical Engineering Study Program Faculty of Science and Technology Surabaya60115 Indonesia

Efficient data collection in wireless sensor networks (WSNs) is crucial. While traditional approaches rely on stationary data sinks, the use of mobile sinks, like unmanned aerial vehicles (UAVs), has shown promise in enhancing data-gathering capabilities. However, existing methods often overlook the importance of trust, leaving the network susceptible to malicious or faulty nodes. To address this issue, we propose a novel trust-aware data-gathering algorithm, Variable Length Multi-Objective Whale Optimization Data Gathering (VLMOWO-DG). Our algorithm simultaneously optimizes energy consumption, delay, and trust while employing mobile sinks to collect data from sensor nodes. By considering trust as a key performance metric, we improve data reliability and security. The VLMOWO-DG algorithm introduces flexibility through variable-length solution representation and application-oriented operators, allowing for efficient exploration of the solution space. Simulation results demonstrate that our proposed algorithm significantly outperforms established benchmarks, NSGA-II and NSGA-III, in terms of domination and hypervolume. This leads to a remarkable improvement of 200% in data gathering performance. © 2015 The Authors.

关键词： Data collection

来源：评论

学校读者我要写书评

暂无评论

A Novel Convolutional-Transformer Neural Network Architecture for Diagnosis of Pneumothorax 28

A Novel Convolutional-Transformer Neural Network Architectur...

引用

28th International computer Conference, computer Society of Iran, CSICC 2023

作者： Sanati, Amir Dashtestani, Mansoureh A. Rostami, Habib Azad, Saeed Talatian Persian Gulf University Faculty of Intelligent System Engineering and Data Science Computer Engineering Department Bushehr Iran

ISBN: (纸本)9798350338195

Pneumothorax is a life-threatening and urgent chest disease than can be detected using Chest X-Ray (CXR) image. CXR images are low resolution and diagnosis of pneumothorax based on them is error prone. Deep learning-based computer aided diagnosis systems can improve diagnosis performance of pneumothorax. Convolutional Neural Networks (CNNs) are default networks in deep learning-based medical image process. However, CNNs fail to capture long range features. On the other side, Transformer are proposed to exploit long range feature, but they cannot capture local features. In this paper, we propose a general method with a convolution and a transformer module which can classify CXR images to diagnose pneumothorax by extracting local features, global features and global features attended by local ones using a novel architecture. Results show that the proposed method outperforms base architectures and the other previous works. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Disruptive Instances in Cloud Environment 16

Performance Analysis of Disruptive Instances in Cloud Enviro...

引用

16th International Conference on COMmunication systems and NETworkS, COMSNETS 2024

作者： Nandy, Pranab Saha, Rounak Satpathy, Anurag Chakraborty, Sandip Addya, Sourav Kanti National Institute of Technology Karnataka Cloud and Smart System Services Lab Department of Computer Science and Engineering Surathkal India Missouri University of Science and Technology Cloud and Smart System Services Lab Department of Computer Science and Engineering United States Indian Institute of Technology Kharagpur Cloud and Smart System Services Lab Department of Computer Science and Engineering India

ISBN: (纸本)9798350383119

Virtualization enables the service providers (SPs) to logically partition the resources into virtual machines (VM) instances. Real-world SPs such as Amazon, Google, Microsoft Azure, IBM, and Oracle provide different flavors of VM instances, such as on-demand, reserved, and low-cost or spot, depending on the type of application hosted. The on-demand instances are short-term and typically incur a higher cost than reserved instances that are provisioned for a longer duration at a discounted rate. Low-cost or spot instances are cost-effective compared to on-demand but are reclaimable by the SPs. The SPs often claim that the on-demand and spot instances achieve similar performance, but it is far from that. This paper studies the performance of spot instances via rigorous experimentation over commercial SPs such as Amazon AWS and Microsoft Azure. Real-world evaluations affirm that spot instances perform poorly compared to their on-demand counterpart concerning memory, CPU, disk read, and write operations. We identify such instances as disruptive and name them so because it does not fulfill the performance, durability, and flexibility expectations like an on-demand instance having the same configuration. We also perform hypothesis testing over the experimental data obtained to corroborate our claim further. © 2024 IEEE.

关键词： Cloud Computing Disruptive Instance On-demand Spot Instance

来源：评论

学校读者我要写书评

暂无评论

Predictive Modeling of Child Identity Risk using Machine and Deep Learning: A systematic Literature Review 2

Predictive Modeling of Child Identity Risk using Machine and...

引用

2nd International Conference on Advances in Computation, Communication and Information Technology, ICAICCIT 2024

作者： Dighe, Akshada Garg, Bindu Department of Computer Engineering BVDUCOE Pune India Department of Computer Science and Business System BVDUCOE Pune India

ISBN: (纸本)9798331541217

Intellectual disability (ID), a developmental condition often stemming from prenatal or postnatal factors, exerts a profound influence on individuals' lives and necessitates timely intervention. Conventional screening methods are resource-intensive and demand specialized medical expertise. This study introduces a novel, non-invasive approach to ID screening by meticulously analyzing facial features and vocal characteristics extracted from interview *** the extraction of facial measurements and speech patterns, we devised a Craniofacial Variability Index (CVI) to assess the likelihood of ID. Furthermore, advanced machine learning techniques were strategically employed to augment the predictive accuracy of this index. Our empirical findings unequivocally demonstrate promising results, with an accuracy rate reaching up to 80% when synergizing CVI scores and phonetic features. This research underscores the potential of a non-invasive, AI-powered screening instrument for ID, offering a more accessible and efficient alternative to prevailing practices. Future investigations will concentrate on refining the model and validating its efficacy across diverse populations. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of 3D Rendering Method on Web-Based Augmented Reality Application Using WebGL and OpenGL Shading Language 23

Performance Analysis of 3D Rendering Method on Web-Based Aug...

引用

8th International Conference on Sustainable Information engineering and Technology, SIET 2023

作者： Hamzaturrazak, Multohadi Jonemaro, Eriq Muhammad Adams Pinandito, Aryo Informatics Engineering Department Universitas Brawijaya Faculty of Computer Science Indonesia Information System Department Universitas Brawijaya Faculty of Computer Science Indonesia

ISBN: (纸本)9798400708503

In recent years, web programming has increased to the extent where it is capable of rendering 3D objects on the web. Its rendering performance varied depending on where it ran and what library was used to render the objects. This study aims to investigate the rendering performance of several 3D renderer libraries that render 3D objects in an augmented reality application. WebGL is one of the APIs that uses the Javascript programming language to render 3D objects in web applications. To create augmented reality on the web, a JavaScript library called *** is needed, which allows developers to create augmented reality on the web without the need to use additional plugins. *** supports various types of augmented reality, i.e., bookmarks, images, and location-based types. It also allows developers to incorporate visual and audio effects into augmented reality. This study aims to investigate the rendering performance of WebGL raw shaders and GLSL shaders in an HTML-based augmented reality application. The results suggested that both WebGL and GLSL could render low-poly and medium-poly 3D objects well. However, according to the test, WebGL performance drops significantly when rendering high-polygon 3D objects. Nonetheless, the GLSL library could render the same high-poly 3D objects at a similar level with native library rendering performance. Thus, suggest GLSL shaders as the recommended library to render 3D objects on the web. © 2023 ACM.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Design and development of political rider competitive swarm optimiser enabled deep learning model for air quality detection

引用

International Journal of Intelligent systems Technologies and Applications 2024年第1期22卷 77-104页

作者： Patil, Deepika Dadasaheb Thanuja, T.C. Melinamath, Bhuvaneshwari C. Department of Computer Science and Engineering Vishveshvaraya Technological University Belgavi India Sanjay Ghodawat University Kolhapur India Department of VLSI and Embedded System Visvesvaraya Technological University Belagavi India Department of Computer Science and Engineering BMSIT&M College Bangalore India

The air quality prediction process is a more significant one for air pollution prevention and management because air pollution becomes crueller. The precise identification of air quality has become a more significant concern for controlling air pollution. Recently, the weight of particulate matter (PM) on the human physical condition has become an important research area. In this paper, the political rider competitive swarm optimiser (PRCSO)-based deep recurrent neural network (DRNN) algorithm is devised for air quality and carbon monoxide prediction. The missing value imputation scheme is employed to perform pre-processing. Moreover, technical indicators and location information are extracted for the prediction process. The DRNN is employed for prediction, which is trained by the PRCSO and the training process is performed based on every location independently. The PRCSO-based DRNN outperforms existing techniques in terms of mean square error (MSE) of 0.0313, and mean absolute percentage error (MAPE) of 3.08%. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Carbon monoxide

来源：评论

学校读者我要写书评

暂无评论

Improving Information Delivery Effectiveness and Efficiency Using WebVR Technology 23

Improving Information Delivery Effectiveness and Efficiency ...

引用

8th International Conference on Sustainable Information engineering and Technology, SIET 2023

作者： Pratama, Ardiyan Nur Akbar, Muhammad Aminul Pinandito, Aryo Informatics Engineering Department Universitas Brawijaya Faculty of Computer Science Indonesia Information System Department Universitas Brawijaya Faculty of Computer Science Indonesia

ISBN: (纸本)9798400708503

In this digital era, attracting new students from outside the region to enter a college or university is difficult. This problem can be solved with good marketing and information dissemination techniques. Information is a type of data that has been processed and organized so that it has relevant meaning for the recipient. Useful information can be used to help make decisions, gain new knowledge, or solve problems. One medium for providing information is by using videos that can be uploaded to YouTube for dissemination. However, problems arise when the information depends on the point of view of the video content creator, who may not provide enough information sought by users in their videos. Virtual reality (VR) technology can be pursued as one of the solutions to overcome the lack of detail and control in videos for users to get the expected information. One of the technologies in VR that allows people to explore a three-dimensional virtual world on a web platform is the 360° WebVR technology. Since users have full control over what can be seen using WebVR, it is expected that this technology can assist users in getting deeper and detailed information related to their needs. This study aims to determine the effectiveness and efficiency of using YouTube videos and WebVR in distributing information and delivering detailed information to users. The results show that WebVR technology has the potential to provide greater control over more detailed information to users who use it, in contrast to traditional two-dimensional video playback technology. © 2023 ACM.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Efficiency of Navigation systems: Dijkstra Algorithm Optimization Through Integration of Douglas-Peucker Line Simplification Technique 23

Enhancing the Efficiency of Navigation Systems: Dijkstra Alg...

引用

8th International Conference on Sustainable Information engineering and Technology, SIET 2023

作者： Haq, Muhammad Yasir Anshari Sianturi, Riswan Septriayadi Pinandito, Aryo Informatics Engineering Department Universitas Brawijaya Faculty of Computer Science Indonesia Information System Department Universitas Brawijaya Faculty of Computer Science Indonesia

ISBN: (纸本)9798400708503

Smartphones have grown popular in the current digital era among people. Map-based applications are one of many that are used daily by people to acquire information about specific locations. Google Maps and Waze are two popular examples of map-based applications for travel and navigation, as they provide detailed information while the user navigates from one point to another. One of the most commonly used algorithms in map-based applications is the Dijkstra algorithm. Although the Dijkstra algorithm can determine the shortest route between two points, there is an issue when the selected route involves a large number of data points that need to be processed. The more data points involved, the longer it takes to do a route calculation in the Dijkstra algorithm. This can lead to a degradation in system performance, especially on smartphones with limited resources. To address this issue, the Douglas-Peucker algorithm is proposed as a solution to reduce the number of points involved in the calculation using the line simplification technique. Line simplification means reducing unnecessary points that are considered unimportant. This study suggested that integrating the Douglas-Peucker line simplification technique before Dijkstra could improve the system performance more than the system without integrating line simplification in terms of reducing both memory usage and the time required to compute the solution. © 2023 ACM.

关键词： Navigation systems

来源：评论

学校读者我要写书评

暂无评论

Vision Transformer for Audio-Based Depression Detection on Multi-Lingual Audio Data 24

Vision Transformer for Audio-Based Depression Detection on M...

引用

7th International Conference on Digital Medicine and Image Processing, DMIP 2024

作者： Pratiwi, Monica Sanjaya, Samuel Ady Department of Computer Engineering Faculty of Engineering and Informatics Universitas Multimedia Nusantara Tangerang Indonesia Department of Information System Faculty of Engineering and Informatics Universitas Multimedia Nusantara Tangerang Indonesia

ISBN: (纸本)9798400709586

Depression has the potential to impact death rates, particularly when it comes to death by suicide. Inadequate diagnosis may result in a delay or unsuitable therapy, which can worsen symptoms of depression. Unaddressed or insufficiently addressed depression can result in deteriorating mental well-being, which includes a higher risk of experiencing suicidal ideation and engaging in self-destructive actions. Voice analysis can be employed to distinguish between individuals with depression and those without depression. However, the research that has been conducted on voice recognition to distinguish between depressed and non-depressed individuals keeps focusing on the use of a single dataset source as input for the classification model that is being developed. This work utilizes the Vision Transformer model and various pre-trained transformers, such as DeiT (Data-Efficient Image Transformer) and Swin Transformer, to detect depression based on voice. The objective was to create a more generic model not restricted to a specific language. Integrating Mel-spectrogram characteristics with a vision transformer-based model can enhance the efficacy of voice recognition models when dealing with multi-language data. The result shows 21% higher accuracy than the previous study that also implemented a cross-dataset test. Copyright © 2024 held by the owner/author(s). Publication rights licensed to ACM.

关键词： Spectrographs

来源：评论

学校读者我要写书评

暂无评论

MV-DUO: multi-variate discrete unified optimization for psychological vital assessments

引用

Neural Computing and Applications 2024年第31期36卷 19777-19793页

作者： Pethuraj, Mohamed Shakeel Burhanuddin, M.A. Dzakiyullah, Nur Rachman Department of Information System Faculty of Computer and Engineering Universitas Alma Ata Yogyakarta Indonesia Faculty of Information and Communication Technology Universiti Teknikal Malaysia Melaka Durian Tunggal Melaka Malaysia

Psychological vital assessments are required for monitoring health conditions and observing body reactions toward diseases and medications. Wearable sensors play a vital role in sensing body vitals and presenting them as signals for computer-based analysis. The problem relies on the signal decoding due to its input stream that turns out to be discrete/ continuous. Therefore for addressing the above specific issue, this article introduces MV-DUO (Multi-Variate Discrete Unified Optimization) method. This method addresses the above problem from a multi-variate perspective by sensing differential signals across healthy and unhealthy conditions. The healthy and unhealthy conditions are trained using neural learning by augmenting/ ceasing external vital data. The unification is performed using single-point artificial ecosystem-based optimization for identifying discrete sequences collaborated with continuous signals. The single-point reference is grouped based on the maximum continuity fitness observed under various sensing intervals. In this process, the non-grouped sequences are identified as unhealthy or discrete for which additional detection training and classification are required. Considerably the changes between successive sensing intervals are used for variations detection from unified high-fitness groups. Those grouped instances are used for training new vital changes observed at distinct intervals. This improves detection accuracy under controlled errors. For the varying sensing intervals, the proposed method achieves 14.13% high accuracy, 8.29% high grouping rate, 10.77% less error, and 10.07% less detection time. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： computer aided analysis

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：