SAED: Self-adaptive Error Detection Automation for Leveraging Computational Efficiency of HCI Systems
- PDF / 2,001,493 Bytes
- 19 Pages / 439.37 x 666.142 pts Page_size
- 14 Downloads / 180 Views
SAED: Self‑adaptive Error Detection Automation for Leveraging Computational Efficiency of HCI Systems Sakthidasan Krishnan1 · S. Vaithyasubramanian2 · M. Maragatharajan3
© Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract The human–computer interaction (HCI) system is one of the state-of-art consolidations of intellectual psychology and computer automation technology in the recent era. An organized HCI focuses on designing intelligent and competent processing systems for interaction through human–reciprocation. Processing efficiency and computational precision of intelligent systems unambiguously rely on user interfaces. The improper access to user interfaces results in error-prone responses and hence the computation increases in account of better accuracy. In this manuscript, the self-adaptive error detection (SAED) automation method is introduced for leveraging the computation precision of HCI systems. SAED harmonizes a bi-linear learning process based on Bayes classification subsided by a cumulative distribution function (CDF). CDF defines the maximum error unleashing probability of the inputs to recognize certain computations. Bayes classification regresses the decisive computation as a reference to classify inputs by detaining errors to provide more relevant suggestions as a part of automation. SAED results in non-trivial input processing to enhance the choice of HCI integrated into intelligent computing systems. This method focuses on improving the prediction of inputs by reducing error, computation time, and memory overloading. The errors and memory overloading due to improper and partially classified inputs and convergence are thwarted using this method. The specular conduct of SAED is gauged using experimental modeling and error detection rate, predicted inputs, and distribution function metrics are analyzed. The proposed method is found to achieve 13.61% less completion time, 5.63% less error, and 19.29% less memory consumption, respectively. Keywords Cumulative density function · Bayes classification · Human–computer interaction · Intelligent computing systems · User experience precision
1 Introduction In the recent era of communication, digital information is exchanged between humans and processing systems. Human knowledge, requirement, and queries are transformed into digital form using computer-aided interfaces. Human–computer interaction (HCI) system * Sakthidasan Krishnan [email protected] Extended author information available on the last page of the article
13
Vol.:(0123456789)
S. Krishnan et al.
is designed for users to exchange such information. The machine decodes the high-end control language from end-userfor understanding and processing. The processing systems engage precise data and principles for handling user information [1]. HCI systems are designed with sensing hardware units and graphical user interfaces (GUI) for detecting human interaction. HCI detects input in the form of touch, gestures, voice, and motiondetection and decodes them into m
Data Loading...
