检索结果-内蒙古大学图书馆

Parallel Residual Stacked Bidirectional Long Short-Term Memory Network Optimized with chameleon swarm optimization algorithm for Time-Series Sensor Data

引用

IETE JOURNAL OF RESEARCH 2025年

作者： Shanmuganathan, V. Suresh, A. SRM Inst Sci & Technol Sch Comp Dept Networking & Commun Kattankulathur 603203 Tamil Nadu India

Internet of Things (IoT) allows the linking of disparate devices via wireless and mobile communication technology. The accuracy and integrity of data often determine IoT service quality. An acquired data, however, will be abnormal due to the harsh surroundings or device flaws. As a result, an efficient means of identifying anomalies is critical for ensuring excellent service. This article discusses Parallel Residual Stacked Bidirectional Long Short-Term Memory Network optimized with chameleon swarm optimization algorithm for Time-Series Sensor Data (PRSBi LSTM-CSOA-AD-TSSD) is proposed for anomaly identification for Time Sequence Sensor Data. Initially, the time sequence sensor data are acquired from the Yahoo Webs cope S5 dataset. Then the data are preprocessed using Sparsity Aware Robust Normalized Subb and Adaptive Filtering technique. Then the pre-processed data are given to the proposed PRSBiLSTM Network to detect the anomalous Time-Series Sensor Data. This PRSBiLSTM Network classifies the preprocessed Time-Series Sensor Data into normal and anomaly. Then the PRSBiLSTM Network is optimized using the chameleon swarm optimization algorithm (CSOA) which precisely classifies the anomalistic of the Time-Series Sensor Data. The proposed algorithm is implemented in Python and performance metrics, such as F1-score, precision, sensitivity, specificity, Error rate, accuracy, ROC, and computational time are analyzed to identify the performance of the proposed PRSBiLSTM-CSOA-AD-TSSD approach. The proposed approach provides 22.41%, 25.51%, and 21.65% higher accuracy, 24.56%, 23.36%, and 25.98% lower error rate, 22.59%, 22.29%, and 25.67% lower computational time analyzed with existing methods, such as LSTM-AD-TSSD, Unsupervised TCN-AE-based TCN-ADTSSD, and CNN-AD-TSSD.

关键词： Anomaly detection chameleon swarm optimization algorithm Sparsity Aware Robust Normalized Subb and Adaptive Filtering and time-series sensor data

来源：评论

学校读者我要写书评

暂无评论

Graph CNN-ResNet-CSOA Transfer Learning Architype for an Enhanced Skin Cancer Detection and Classification Scheme in Medical Image Processing

引用

INTERNATIONAL JOURNAL ON ARTIFICIAL INTELLIGENCE TOOLS 2024年第2期33卷

作者： Balaji, G. N. Mary, S. A. Sahaaya Arul Mantravadi, Nagesh Shajin, Francis H. Vellore Inst Technol Sch Comp Sci & Engn Vellore Tamil Nadu India Koneru Lakshmaiah Educ Fdn Vaddeswaram 522302 Andhra Prades India Xpertmindz Innovat Solut Pvt Ltd Res & Dev Kuzhithurai Tamil Nadu India

Skin cancer is a perilous kind of cancer caused by damaged DNA and it leads to death. This damaged DNA causes uncontrolled proliferation of cells. Even though, the image analysis of lesions is highly difficult due to light reflections from skin surface, fluctuations at color lighting, variety of lesions' forms and sizes in skin cancer. Because of these issues, automatic recognition of skin cancer accurateness is decreased. Therefore, a Graph Convolutional Neural Network (GCNN) by ResNet 152 Transfer Learning Architype optimized with chameleon swarm optimization algorithm (GCNN-ResNet 152 TL-CSOA) is proposed at this manuscript for enhancing skin cancer detection with classification in medical image processing. Initially, the input images are taken from International Skin Imaging Collaboration (ISIC) of dermoscopic skin cancer imagery data set. Afterward, the input images are pre-processed utilizing trilateral filter method for removing noise. The pre-processed output is supplied to the process of feature extraction. Here, image features, like morphologic, gray scale statistic and Haralick texture features are extracted by Gray-Level Co-Occurrence Matrix window adaptive approach (GLCM-WAA) technique. After that, the GCNN-ResNet 152 TL classifies the skin cancer images into Actinic Keratosis, Basal Cell Carcinoma, Malignant Melanoma and Squamous Cell Carcinoma. Additionally, GCNN-ResNet 152 TL weight parameters is tuned by chameleon swarm optimization algorithm (CSOA). The simulation process is executed at Python tool. From simulation, the proposed approach attains 23.34%, 12.03%, 21.42% improved accuracy and 18.23%, 21.23%, 14.56% higher sensitivity compared with existing approaches.

关键词： Convolutional neural network chameleon swarm optimization algorithm gray-level co-occurrence matrix ResNet 152 TL skin cancer

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：