Guest Editors
Prof. Nagaraj Balakrishnan, Rathinam Group of Institutions, India
Prof. Danilo Pelusi, University of Teramo, Italy
Prof. Yong Deng, University of Electronic Science and Technology of China, China
Prof. V Thanikaiselvan, VIT University, India
Summary
Data science systems are used in extracting knowledge and information that gives insight to the core of structured and unstructured data (which is collected in massive quantity). It uses scientific methods and algorithms to analyze and provide deep insights into the data. The rapid growth of fields such as industry, business, and medical, requires more such insights for further development; in fact, the situation created by COVID-19 pandemic needs the most. The data science needs to be involved with techniques such as data mining, big data, and machine learning to get such in-depth knowledge into the fields as mentioned above. In this research, the optimal usage strategy of learning algorithms, along with the clustering methodologies, is addressed for unsupervised data classification applications.
On the other hand, the requirement towards the need for efficient Signal Processing to achieve the targeted goal is high. However, the high-performance system always needs interaction with its environment through real-time signal processing. The exchange of information between the systems enables a better learning methodology that results in responsible governance. The developed a fully automated system in the field of signal processing would help identify abnormalities and rectify them accurately. The accuracy of the computer-aided systems is highly superior to the manual observations; hence, the physicians significantly prefer automated systems. During the previous decade, soft computing has emerged as potential candidates for solving complex and intricate global optimization problems, which are otherwise difficult to solve by traditional methods. In the present scenario, Signal signal processing, Industrial optimization, Control system applications, and power system application fields have challenging deeds that are to be unraveled by researchers. ANN algorithms are capable of scientifically learn and understand the situation with the iterative learning process organized with the help of previously generated/ collected data. On the other hand, the data mining algorithm is a field of study in machine learning which follows the unsupervised learning methodology (Deep Embedded Clustering).
Day by day, the processing of signals with in-depth features has become nearly impractical for several reasons. The technology for processing the signal has many challenges and hurdles that need proper optimization through intelligence. This special issue seeks to bring forward the research opportunities that focus on enhancing the behavior and nature of the deep learning methods with the kind of the clustering algorithm. So, that intelligent automation based unsupervised learning methodology can be implemented in signal processing applications.
Keywords
• Intelligent signal computing based on Deep Embedded clustering
• An evolutionary approach to Process the signals and its application
• Architectures for Real-time sensing and intelligent processing
• Auto-Encoders, Restricted Boltzmann Machines for signal classification
• Real-time Signal processing based on DEC
• Parallel and distributed algorithm design and implementation in signal sensing
• Analytics for multi-dimension data
• Intelligent computing on signal for data analysis
• Real-time remote sensing signals, such as hyperspectral signal classification, content-based signal indexing, and retrieval, monitoring of natural.
Login
Register
Submit a Paper
Propose a Special lssue