Open Access Original Research Article

Sign Translation Via Natural Language Processing

Shadman A. Khan, Zulfikar Ali Ansari, Riya Singh, Mohit Singh Rawat, Fiza Zafar Khan, Shubham Kumar Yadav

Asian Journal of Research in Computer Science, Page 1-7
DOI: 10.9734/ajrcos/2021/v11i130251

Artificial Intelligence (AI) technologies are new technologies with new complicated features emerging quickly. Technology adoption has been beneficial for many general models. The models help in train the voice user-interface assistance (Alexa, Cortona, Siri). Voice assistants are easy to use, and thus millions of devices incorporate them in households nowadays. The primary purpose of the sign language translator prototype is to reduce interaction barriers between deaf and mute. To overcome this problem, we have proposed a prototype. It is named sign language translator with Sign Recognition Intelligence which takes the user input in sign language and processes it, and returns the output in voice out load to the end-user.

Open Access Original Research Article

An Improved Coronary Heart Disease Predictive System Using Random Forest

Abdulraheem Abdul, Rafiu M. Isiaka, Ronke S. Babatunde, Jumoke F. Ajao

Asian Journal of Research in Computer Science, Page 17-27
DOI: 10.9734/ajrcos/2021/v11i130253

Aims: This work aim is to develop an enhanced predictive system for Coronary Heart Disease (CHD).

Study Design: Synthetic Minority Oversampling Technique and Random Forest.

Methodology: The Framingham heart disease dataset was used, which was collected from a study in Framingham, Massachusetts, the data was cleaned, normalized, rebalanced. Classifiers such as random forest, artificial neural network, naïve bayes, logistic regression, k-nearest neighbor and support vector machine were used for classification.

Results: Random Forest outperformed other classifiers with an accuracy of 98%, a sensitivity of 99% and a precision of 95.8%. Feature selection was employed for better classification, but  no significant improvement was recorded on the performance of the classifier with feature selection. Train test split also performed better that cross validation.

Conclusion: Random Forest is recommended for research in Coronary Heart Disease prediction domain.

Open Access Original Research Article

Design and Construction of Speech Controlled Door

Falohun Adeleye Samuel, Adegbola Oluwole Abiodun, Adedeji Oluyinka Titilayo, Makinde Bukola Oyeladun, Taiwo Olayinka David, Damilare Gbohunmi Aduragbemi

Asian Journal of Research in Computer Science, Page 28-40
DOI: 10.9734/ajrcos/2021/v11i130254

Home security is extremely important, and several methods of security have been improved, such as the usage of alarms, monitoring systems, and the interplay of electronic hardware, software, and other factors. Keys can be misplaced and found by others, putting the guarded structure at risk; keys can also be fabricated or stolen. This project entails creating a voice message-based door access system that can both open the door and identify intruders, trespassers, criminals, or any other type of illegal behaviour. The speech-controlled door was meant to generate a voice message based on the input data and was developed around a microcontroller (ATmega328p). A speech recognition module is used to allow the owner or user entry to the door. To gain access to the door, the owner must first utter the specific speech or key word required to open it. A voice notification is then outputted through the associated speaker if the pronounced word does not match the speech recognized by the microcontroller. To signify that access is refused, a red-light emitting diode will flash. The microprocessor would activate a relay and current will flow through the latch, allowing the door to be unlocked, if the uttered speech matches. A speech recognition module is used to allow the owner or user entry to the door. To gain access to the door, the owner must first utter the specific speech or key word required to open it. A voice notification is then outputted through the associated speaker if the pronounced word does not match the speech recognized by the microcontroller. To signify that access is refused, a red light emitting diode will flash. The microprocessor will activate a relay and current will flow through the latch, allowing the door to be unlocked, if the uttered speech matches.

Open Access Review Article

Application of Artificial Neural Network in Distillation System: A Critical Review of Recent Progress

Chunli Li, Chunyu Wang

Asian Journal of Research in Computer Science, Page 8-16
DOI: 10.9734/ajrcos/2021/v11i130252

Distillation is a unit operation with multiple input parameters and multiple output parameters. It is characterized by multiple variables, coupling between input parameters, and non-linear relationship with output parameters. Therefore, it is very difficult to use traditional methods to control and optimize the distillation column. Artificial Neural Network (ANN) uses the interconnection between a large number of neurons to establish the functional relationship between input and output, thereby achieving the approximation of any non-linear mapping. ANN is used for the control and optimization of distillation tower, with short response time, good dynamic performance, strong robustness, and strong ability to adapt to changes in the control environment. This article will mainly introduce the research progress of ANN and its application in the modeling, control and optimization of distillation towers.

Open Access Review Article

Internet Crimes- it’s Analysis and Prevention Approaches

Mohammad Dawood Babakerkhell, Habibullah Slimanzai

Asian Journal of Research in Computer Science, Page 41-48
DOI: 10.9734/ajrcos/2021/v11i130255

In the present period of computerized handling, high level of online information is looked with digital threats. There are unlimited dangers and difficulties to information existence online.  Cyber-attacks which are considered the emerging and serious threats that are going on each second and investigation of those dangers and threats are exceptionally hard to confine and vanquish them. Cybercrimes have a terrible effect on governmental and non-governmental organizations, educational institutions, financial banks and economic infrastructures. Numerous worldwide societies, policy makers and intelligent agencies are trying to react and control cybercrimes. One of the most serious issue in the online processing is that how to secure and deal with our day by day information against digital misrepresentation and cybercrimes. To comprehend cybercrime and save our digital assets, this paper will analyze about various cybercrimes and addresses the effective prevention and detection ways and methods used for the avoidance, controlling, detection and combatting of those crimes.