Pub Date : 2024-01-10DOI: 10.1080/00051144.2023.2296793
Prabhakar K, K. V
{"title":"An evolutionary approach for depression detection from Twitter big data using a novel deep learning model with attention based feature learning mechanism","authors":"Prabhakar K, K. V","doi":"10.1080/00051144.2023.2296793","DOIUrl":"https://doi.org/10.1080/00051144.2023.2296793","url":null,"abstract":"","PeriodicalId":503352,"journal":{"name":"Automatika","volume":"2 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139440255","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-10DOI: 10.1080/00051144.2023.2296790
S. Lakshmi, C. Maheswaran
{"title":"Effective deep learning based grade prediction system using gated recurrent unit (GRU) with feature optimization using analysis of variance (ANOVA)","authors":"S. Lakshmi, C. Maheswaran","doi":"10.1080/00051144.2023.2296790","DOIUrl":"https://doi.org/10.1080/00051144.2023.2296790","url":null,"abstract":"","PeriodicalId":503352,"journal":{"name":"Automatika","volume":"1 7","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139440262","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-02DOI: 10.1080/00051144.2023.2295141
Shirly Sudhakaran, R. Maheswari, V. Kanchana Devi
RFID (radio frequency identification) is a progressively adopted technology in today’s automated world. Wireless technologies have enabled contactless payments, tracking, identifying, and many more features in a system that can be introduced to build a smart environment. This work overviews the usage of the IoT (Internet of Things) platform for tracking passengers and enabling online payments through wireless sensors and RFID technology in Chennai Suburban Railways. The tracking system consists of an RFID reader that can locate and track passive as well as mobile objects attached with passive RFID tags. The proposed system incorporates the installation of RFID readers at every entrance and exit of the railway station, and every passenger carries their own RFID tags. This not only enables online payments for passengers but also helps the government in tracking the crowd for demand monitoring. The new methodology creates a digital workspace and enforces lawful safety regulations both for the administration and the consumers. A prototype of the proposed system is implemented in real-time to understand the workings of the system. Data collection is done through RFID tags that act as transit cards and an analysis for consumer demand is done using the DBSCAN (Density-Based Spatial Clustering of Application with Noise) algorithm with a Randomized KD-tree for the analysis of spatial and temporal patterns. A new algorithm, the iDBSCAN (improved Density-Based Spatial Clustering of Application with Noise) algorithm is proposed for faster performance on the datasets.
RFID（射频识别）是当今自动化世界逐步采用的一项技术。无线技术实现了非接触式支付、跟踪、识别等多种功能，可用于构建智能环境。本作品概述了钦奈市郊铁路使用物联网（IoT）平台追踪乘客，并通过无线传感器和 RFID 技术实现在线支付的情况。追踪系统由一个 RFID 阅读器组成，该阅读器可定位和追踪附有无源 RFID 标签的无源物体和移动物体。建议的系统包括在火车站的每个出入口安装 RFID 阅读器，每个乘客都携带自己的 RFID 标签。这不仅可以实现乘客在线支付，还能帮助政府追踪人群，进行需求监测。新方法为行政部门和消费者创建了一个数字化工作空间，并执行合法的安全规定。为了解该系统的工作原理，我们实时实施了拟议系统的原型。数据收集通过作为交通卡的 RFID 标签完成，消费者需求分析则使用 DBSCAN（基于密度的带噪声应用空间聚类）算法和随机 KD 树来分析空间和时间模式。为了在数据集上获得更快的性能，我们提出了一种新的算法，即 iDBSCAN（改进的基于密度的带噪声应用空间聚类算法）。
{"title":"An improvised analysis of smart data for IoT-based railway system using RFID","authors":"Shirly Sudhakaran, R. Maheswari, V. Kanchana Devi","doi":"10.1080/00051144.2023.2295141","DOIUrl":"https://doi.org/10.1080/00051144.2023.2295141","url":null,"abstract":"RFID (radio frequency identification) is a progressively adopted technology in today’s automated world. Wireless technologies have enabled contactless payments, tracking, identifying, and many more features in a system that can be introduced to build a smart environment. This work overviews the usage of the IoT (Internet of Things) platform for tracking passengers and enabling online payments through wireless sensors and RFID technology in Chennai Suburban Railways. The tracking system consists of an RFID reader that can locate and track passive as well as mobile objects attached with passive RFID tags. The proposed system incorporates the installation of RFID readers at every entrance and exit of the railway station, and every passenger carries their own RFID tags. This not only enables online payments for passengers but also helps the government in tracking the crowd for demand monitoring. The new methodology creates a digital workspace and enforces lawful safety regulations both for the administration and the consumers. A prototype of the proposed system is implemented in real-time to understand the workings of the system. Data collection is done through RFID tags that act as transit cards and an analysis for consumer demand is done using the DBSCAN (Density-Based Spatial Clustering of Application with Noise) algorithm with a Randomized KD-tree for the analysis of spatial and temporal patterns. A new algorithm, the iDBSCAN (improved Density-Based Spatial Clustering of Application with Noise) algorithm is proposed for faster performance on the datasets.","PeriodicalId":503352,"journal":{"name":"Automatika","volume":"138 41","pages":"361 - 372"},"PeriodicalIF":0.0,"publicationDate":"2024-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139453069","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-02DOI: 10.1080/00051144.2023.2293274
M. Shimja, K. Kartheeban
The diagnosis of lung disease is a challenging process that frequently combines clinical information, such as patient symptoms, medical history and test findings, with medical imaging, like X-rays or CT scans. The classification of lung diseases is very important in healthcare since it helps with diagnosis and treatment of many different lung diseases. A precise classification of lung conditions can aid doctors in choosing the best course of action and enhancing patient outcomes. Additionally, accurate classification can aid in evaluating the effectiveness of therapies, forecasting results and tracking the development of diseases. It is extremely important to accurately classify lung conditions. A comparison of a novel model for lung disease classification from chest CT and CXR images was presented in this paper. A modified VGG-16 model was used as the classification model. To improve the performance, a fine-tuning mechanism was added to the proposed model. The effectiveness of the suggested method is analyzed and compared on two distinct datasets in terms of performance metrics. The experimental outcomes showed that the suggested model performs better on the CXR image dataset.
{"title":"A comparative study of lung disease classification using fine-tuned CXR and chest CT images","authors":"M. Shimja, K. Kartheeban","doi":"10.1080/00051144.2023.2293274","DOIUrl":"https://doi.org/10.1080/00051144.2023.2293274","url":null,"abstract":"The diagnosis of lung disease is a challenging process that frequently combines clinical information, such as patient symptoms, medical history and test findings, with medical imaging, like X-rays or CT scans. The classification of lung diseases is very important in healthcare since it helps with diagnosis and treatment of many different lung diseases. A precise classification of lung conditions can aid doctors in choosing the best course of action and enhancing patient outcomes. Additionally, accurate classification can aid in evaluating the effectiveness of therapies, forecasting results and tracking the development of diseases. It is extremely important to accurately classify lung conditions. A comparison of a novel model for lung disease classification from chest CT and CXR images was presented in this paper. A modified VGG-16 model was used as the classification model. To improve the performance, a fine-tuning mechanism was added to the proposed model. The effectiveness of the suggested method is analyzed and compared on two distinct datasets in terms of performance metrics. The experimental outcomes showed that the suggested model performs better on the CXR image dataset.","PeriodicalId":503352,"journal":{"name":"Automatika","volume":"132 11","pages":"312 - 322"},"PeriodicalIF":0.0,"publicationDate":"2024-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139453313","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-02DOI: 10.1080/00051144.2023.2295143
Maniveena C, R. Kalaiselvi
One of the most popular technological frameworks of the year is without a certain Internet of Things (IoT). It permeates numerous industries and has a profound impact on people's lives in all spheres. The “Internet of everything” age is by the IoT technology's rapid development, but it also alters the function of terminal equipment at the network's edge. The name “Internet of Things” has evolved as a result enabling things to be intelligent and competent in talking with verified devices (IoT). Between smart devices, social IoT (IoT) devices interact and adopt social networking concepts. It takes a secure connection between the smart gadgets to enable sociability. To determine whether the suggested strategy is practical it is applied to a convolutional neural network (CNN)-based language similarity analysis model in the context. The model created using the encounter training method is more accurate than the original CNN.
{"title":"A security and privacy preserving approach based on social IoT evolving encoding using convolutional neural network","authors":"Maniveena C, R. Kalaiselvi","doi":"10.1080/00051144.2023.2295143","DOIUrl":"https://doi.org/10.1080/00051144.2023.2295143","url":null,"abstract":"One of the most popular technological frameworks of the year is without a certain Internet of Things (IoT). It permeates numerous industries and has a profound impact on people's lives in all spheres. The “Internet of everything” age is by the IoT technology's rapid development, but it also alters the function of terminal equipment at the network's edge. The name “Internet of Things” has evolved as a result enabling things to be intelligent and competent in talking with verified devices (IoT). Between smart devices, social IoT (IoT) devices interact and adopt social networking concepts. It takes a secure connection between the smart gadgets to enable sociability. To determine whether the suggested strategy is practical it is applied to a convolutional neural network (CNN)-based language similarity analysis model in the context. The model created using the encounter training method is more accurate than the original CNN.","PeriodicalId":503352,"journal":{"name":"Automatika","volume":"132 14","pages":"323 - 332"},"PeriodicalIF":0.0,"publicationDate":"2024-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139453310","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-02DOI: 10.1080/00051144.2023.2296798
Satheeswari Damodaran, Leninisha Shanmugam, N. M. J. Swaroopan
Ensuring the optimal efficiency of electrical networks requires vigilant surveillance and preventive maintenance. While traditional methods, such as human patrols and helicopter inspections, have been longstanding practices for grid control by electrical power distribution companies, the emergence of Unmanned Aerial Vehicles (UAV) technology offers a more efficient and technologically advanced alternative. The proposed comprehensive pipeline integrates various elements, including preprocessing techniques, deep learning (DL) models, classification algorithms (CA), and the Hough transform, to effectively detect powerlines in intricate aerial images characterized by complex backgrounds. The pipeline begins with Canny edge detection, progresses through morphological reconstruction using Otsu thresholding, and concludes with the development of the RsurgeNet model. This versatile model performs binary classification and feature extraction for power line identification. The Hough transform is employed to extract semantic powerlines from intricate backgrounds. Comparative assessments against three existing architectures and classification algorithms highlight the superior performance of RsurgeNet. Experimental results on the VL-IR dataset, encompassing both visible light (VL) and infrared light (IR) images validate the effectiveness of the proposed approach. RsurgeNet demonstrates reduced computational requirements, achieving heightened accuracy and precision. This contribution significantly enhances the field of electrical network maintenance and surveillance, providing an efficient and precise solution for power line detection.
{"title":"Overhead power line detection from aerial images using segmentation approaches","authors":"Satheeswari Damodaran, Leninisha Shanmugam, N. M. J. Swaroopan","doi":"10.1080/00051144.2023.2296798","DOIUrl":"https://doi.org/10.1080/00051144.2023.2296798","url":null,"abstract":"Ensuring the optimal efficiency of electrical networks requires vigilant surveillance and preventive maintenance. While traditional methods, such as human patrols and helicopter inspections, have been longstanding practices for grid control by electrical power distribution companies, the emergence of Unmanned Aerial Vehicles (UAV) technology offers a more efficient and technologically advanced alternative. The proposed comprehensive pipeline integrates various elements, including preprocessing techniques, deep learning (DL) models, classification algorithms (CA), and the Hough transform, to effectively detect powerlines in intricate aerial images characterized by complex backgrounds. The pipeline begins with Canny edge detection, progresses through morphological reconstruction using Otsu thresholding, and concludes with the development of the RsurgeNet model. This versatile model performs binary classification and feature extraction for power line identification. The Hough transform is employed to extract semantic powerlines from intricate backgrounds. Comparative assessments against three existing architectures and classification algorithms highlight the superior performance of RsurgeNet. Experimental results on the VL-IR dataset, encompassing both visible light (VL) and infrared light (IR) images validate the effectiveness of the proposed approach. RsurgeNet demonstrates reduced computational requirements, achieving heightened accuracy and precision. This contribution significantly enhances the field of electrical network maintenance and surveillance, providing an efficient and precise solution for power line detection.","PeriodicalId":503352,"journal":{"name":"Automatika","volume":"18 11","pages":"261 - 288"},"PeriodicalIF":0.0,"publicationDate":"2024-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139452095","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-02DOI: 10.1080/00051144.2023.2293280
Arathi Chandran, V. Mary, Amala Bai
Breast cancer remains a pervasive global health concern, necessitating continuous efforts to attain effectiveness of recurrence prediction schemes. This work focuses on breast cancer recurrence prediction using two advanced architectures such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), integrated with feature selection techniques utilizing Logistic Regression (LR) and Analysis of Variance (ANOVA). The well-known Wisconsin cancer registry dataset, which contains vital diagnostic data from breast mass fine-needle aspiration biopsies, was employed in this study. The mean values of accuracy, precision, recall and F1-score for the proposed LR-CNN-LSTM model were calculated as 98.24%, 99.14%, 98.30% and 98.14% respectively. The mean values of accuracy, precision, recall and F1-score for the proposed ANOVA-GRU model were calculated as 96.49%, 97.04%, 96.67% and 96.67% respectively. The comparison with traditional methods showcases the superiority of our proposed approach. Moreover, the insights gained from feature selection contribute to a deeper understanding of the critical factors influencing breast cancer recurrence. The combination of LSTM and GRU models with feature selection methods not only enhances prediction accuracy but also provides valuable insights for medical practitioners. This research holds the potential to aid in early diagnosis and personalized treatment strategies.
乳腺癌仍然是全球普遍关注的健康问题，因此需要不断努力实现有效的复发预测方案。这项工作的重点是利用长短期记忆（LSTM）和门控复发单元（GRU）等两种先进架构，结合利用逻辑回归（LR）和方差分析（ANOVA）的特征选择技术，进行乳腺癌复发预测。本研究采用了著名的威斯康星癌症登记数据集，该数据集包含乳腺肿块细针穿刺活检的重要诊断数据。经计算，所提出的 LR-CNN-LSTM 模型的准确率、精确率、召回率和 F1 分数的平均值分别为 98.24%、99.14%、98.30% 和 98.14%。经计算，拟议的 ANOVA-GRU 模型的准确率、精确率、召回率和 F1 分数的平均值分别为 96.49%、97.04%、96.67% 和 96.67%。与传统方法相比，我们提出的方法更胜一筹。此外，从特征选择中获得的洞察力有助于深入了解影响乳腺癌复发的关键因素。将 LSTM 和 GRU 模型与特征选择方法相结合，不仅能提高预测准确率，还能为医疗从业人员提供有价值的见解。这项研究有望为早期诊断和个性化治疗策略提供帮助。
{"title":"Breast cancer recurrence prediction with deep neural network and feature optimization","authors":"Arathi Chandran, V. Mary, Amala Bai","doi":"10.1080/00051144.2023.2293280","DOIUrl":"https://doi.org/10.1080/00051144.2023.2293280","url":null,"abstract":"Breast cancer remains a pervasive global health concern, necessitating continuous efforts to attain effectiveness of recurrence prediction schemes. This work focuses on breast cancer recurrence prediction using two advanced architectures such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), integrated with feature selection techniques utilizing Logistic Regression (LR) and Analysis of Variance (ANOVA). The well-known Wisconsin cancer registry dataset, which contains vital diagnostic data from breast mass fine-needle aspiration biopsies, was employed in this study. The mean values of accuracy, precision, recall and F1-score for the proposed LR-CNN-LSTM model were calculated as 98.24%, 99.14%, 98.30% and 98.14% respectively. The mean values of accuracy, precision, recall and F1-score for the proposed ANOVA-GRU model were calculated as 96.49%, 97.04%, 96.67% and 96.67% respectively. The comparison with traditional methods showcases the superiority of our proposed approach. Moreover, the insights gained from feature selection contribute to a deeper understanding of the critical factors influencing breast cancer recurrence. The combination of LSTM and GRU models with feature selection methods not only enhances prediction accuracy but also provides valuable insights for medical practitioners. This research holds the potential to aid in early diagnosis and personalized treatment strategies.","PeriodicalId":503352,"journal":{"name":"Automatika","volume":"11 6","pages":"343 - 360"},"PeriodicalIF":0.0,"publicationDate":"2024-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139452302","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-02DOI: 10.1080/00051144.2023.2301240
K. Selvakumar, S. Lokesh
Cloud computing is a technology that holds great promise and has potential to revolutionize the healthcare sector. Many security and privacy issues are brought up by the cloud’s centralization of data for both patients and healthcare professionals. There is a need for maintaining secrecy in communication in exchanging medical data between the sender and the receiver, which can be done by cryptography. This article presents a cryptographic algorithm (encryption and decryption) to have a secure communication of digital health care confidential data using DNA cryptography and Huffman coding. The interesting property is the cipher size obtained from our algorithm is equal to the size of the cipher obtained from the character set of given data. Security analysis is provided to show the security of data when stored and transmitted to the cloud. The cryptographic requirements, key space analysis, key and plain text sensitivity, sensitive score analysis, sensitivity and specificity, optimal threshold, randomness analysis, uniqueness of implementation, entropies of binary bits, DNA bases, DNA bases with Huffman code, Huffman encoded binary bits and cloud service provider’s risk are analyzed. The method proposed is compared with other cryptographic methods and results that it is more secure and stronger than other methods.
云计算是一项前景广阔的技术，有可能给医疗保健行业带来革命性的变化。云计算对患者和医疗保健专业人员的数据集中管理带来了许多安全和隐私问题。发送方和接收方在交换医疗数据时需要保持通信秘密，这可以通过加密技术来实现。本文介绍了一种加密算法（加密和解密），利用 DNA 密码学和哈夫曼编码实现数字医疗保密数据的安全通信。有趣的特性是，从我们的算法中得到的密码大小等于从给定数据的字符集中得到的密码大小。安全分析表明了数据在存储和传输到云端时的安全性。分析了密码学要求、密钥空间分析、密钥和明文敏感性、敏感性得分分析、敏感性和特异性、最佳阈值、随机性分析、实现的唯一性、二进制位的熵，DNA 碱基，带有哈夫曼编码的 DNA 碱基，哈夫曼编码的二进制位和云服务提供商的风险。将所提出的方法与其他加密方法进行了比较，结果表明它比其他方法更安全、更强大。
{"title":"A cryptographic method to have a secure communication of health care digital data into the cloud","authors":"K. Selvakumar, S. Lokesh","doi":"10.1080/00051144.2023.2301240","DOIUrl":"https://doi.org/10.1080/00051144.2023.2301240","url":null,"abstract":"Cloud computing is a technology that holds great promise and has potential to revolutionize the healthcare sector. Many security and privacy issues are brought up by the cloud’s centralization of data for both patients and healthcare professionals. There is a need for maintaining secrecy in communication in exchanging medical data between the sender and the receiver, which can be done by cryptography. This article presents a cryptographic algorithm (encryption and decryption) to have a secure communication of digital health care confidential data using DNA cryptography and Huffman coding. The interesting property is the cipher size obtained from our algorithm is equal to the size of the cipher obtained from the character set of given data. Security analysis is provided to show the security of data when stored and transmitted to the cloud. The cryptographic requirements, key space analysis, key and plain text sensitivity, sensitive score analysis, sensitivity and specificity, optimal threshold, randomness analysis, uniqueness of implementation, entropies of binary bits, DNA bases, DNA bases with Huffman code, Huffman encoded binary bits and cloud service provider’s risk are analyzed. The method proposed is compared with other cryptographic methods and results that it is more secure and stronger than other methods.","PeriodicalId":503352,"journal":{"name":"Automatika","volume":"141 35","pages":"373 - 386"},"PeriodicalIF":0.0,"publicationDate":"2024-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139453068","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-02DOI: 10.1080/00051144.2023.2298099
Lina Jin, Shuanghe Yu, Guoyou Shi, Xiaohong Wang
Based on a line-of-sight (LOS) guidance law for a curve parametrized path, a finite-time backstepping control is proposed for the kinematic path-following of an underactuated autonomous surface vehicle (ASV). Finite-time observer is utilized to estimate the unknown external disturbances accurately. The first-order Levant differentiator is introduced into the finite-time filter technique, such that the output of filter can not only approximate the derivative of the virtual control, but also avoid the singularity problem of real heading control. The integral terminal sliding mode is employed to improve the tracking performance and converging rate in the surging velocity control. By virtue of Lyapunov function, all the signals in the closed-loop system can be guaranteed uniformly ultimate boundedness, and accurate path-following task can be fulfilled in finite time. The simulation results and comparative analysis validate the effectiveness and robustness of the proposed control approach.
{"title":"Finite-time kinematic path-following control of underactuated ASV with disturbance observer","authors":"Lina Jin, Shuanghe Yu, Guoyou Shi, Xiaohong Wang","doi":"10.1080/00051144.2023.2298099","DOIUrl":"https://doi.org/10.1080/00051144.2023.2298099","url":null,"abstract":"Based on a line-of-sight (LOS) guidance law for a curve parametrized path, a finite-time backstepping control is proposed for the kinematic path-following of an underactuated autonomous surface vehicle (ASV). Finite-time observer is utilized to estimate the unknown external disturbances accurately. The first-order Levant differentiator is introduced into the finite-time filter technique, such that the output of filter can not only approximate the derivative of the virtual control, but also avoid the singularity problem of real heading control. The integral terminal sliding mode is employed to improve the tracking performance and converging rate in the surging velocity control. By virtue of Lyapunov function, all the signals in the closed-loop system can be guaranteed uniformly ultimate boundedness, and accurate path-following task can be fulfilled in finite time. The simulation results and comparative analysis validate the effectiveness and robustness of the proposed control approach.","PeriodicalId":503352,"journal":{"name":"Automatika","volume":"33 10","pages":"303 - 311"},"PeriodicalIF":0.0,"publicationDate":"2024-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139452448","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-02DOI: 10.1080/00051144.2024.2301888
Yoji Yamato
Systems using graphical processing units (GPUs) and field-programmable gate arrays (FPGAs) have increased due to their advantages over central processing units (CPUs). However, such systems require the understanding of hardware-specific technical specifications such as Hardware Description Language (HDL) and compute unified device architecture (CUDA), which is a high hurdle. Based on this background, we previously proposed environment-adaptive software that enables automatic conversion, configuration and high-performance operation of existing code according to the hardware to be placed. As an element of this concept, we also proposed a method of automatically offloading loop statements of application source code for CPUs to GPUs and FPGAs. In this paper, we propose a method for offloading a function block, which is a larger unit, instead of individual loop statements in an application to achieve higher speed by automatically offloading to GPUs and FPGAs. We implemented the proposed method and evaluated it using current applications offloading to GPUs and FPGAs.
{"title":"Study and evaluation of automatic offloading for function blocks of applications","authors":"Yoji Yamato","doi":"10.1080/00051144.2024.2301888","DOIUrl":"https://doi.org/10.1080/00051144.2024.2301888","url":null,"abstract":"Systems using graphical processing units (GPUs) and field-programmable gate arrays (FPGAs) have increased due to their advantages over central processing units (CPUs). However, such systems require the understanding of hardware-specific technical specifications such as Hardware Description Language (HDL) and compute unified device architecture (CUDA), which is a high hurdle. Based on this background, we previously proposed environment-adaptive software that enables automatic conversion, configuration and high-performance operation of existing code according to the hardware to be placed. As an element of this concept, we also proposed a method of automatically offloading loop statements of application source code for CPUs to GPUs and FPGAs. In this paper, we propose a method for offloading a function block, which is a larger unit, instead of individual loop statements in an application to achieve higher speed by automatically offloading to GPUs and FPGAs. We implemented the proposed method and evaluated it using current applications offloading to GPUs and FPGAs.","PeriodicalId":503352,"journal":{"name":"Automatika","volume":"83 12","pages":"387 - 400"},"PeriodicalIF":0.0,"publicationDate":"2024-01-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139452475","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：