International Journal on Robotics, Automation and Sciences

Development of AI-Enabled Contactless Visitor Access Monitoring System

Whei Chung Yuen, Gin Chong Lee, Hock Kheng Sim — Sat, 30 Sep 2023 00:00:00 +0800

Abstract - This research focuses on developing an AI-enabled Contactless Visitors Access Monitoring System. The monitoring system integrated a facial recognition system with a real-time database. Visitors registered themselves through an online registration form. This research developed and compared two different facial recognition systems. The first facial recognition system integrated the dlib model with the face recognition library, while the second integrated the FaceNet model with the Haar Cascade Classifier. Twenty facial images were collected. The researcher found out that the facial recognition system with FaceNet has higher accuracy of 82% while the has 76% of accuracy. The value of EER obtained for FaceNet is at 51% with an allowed threshold of 0.52. This research found that the accuracy of the facial recognition system could be affected by different conditions, such as the visitors’ facial features, the distance between the camera and the face, and the illumination condition of the test environment. The number of images does not affect the speed and the accuracy of the facial recognition system in this research due to the small number of images.

(Manuscript received: 26 June 2023 | Accepted: 1st September 2023 | Published: 30 September 2023)

RFID and Facemask Detector Attendance Monitoring System

Yih Haw Wong, Gin Chong Lee, Hock Kheng Sim — Sat, 30 Sep 2023 00:00:00 +0800

The article emphasizes the significance of attendance monitoring for safety during the COVID-19 pandemic and proposes an RFID-based solution coupled with face mask detection systems to address attendance challenges. The project aims to create a contactless monitoring system that ensures face mask compliance and provides real-time attendance data for data-driven decision-making. The article also covers various technology-related topics, including the historical usage of face masks, the development of attendance systems using biometric identification and electronic methods, and facial recognition technology's applications in surveillance and finance. It introduces XAMPP, a user-friendly web application development and testing tool, and presents an overview of the IC7408 chip used in digital electronics. The study's key findings show that increasing sample size and optimizing epochs and batch size improve face mask detection accuracy, while RFID scanner distance affects scanning delay and accuracy. The research provides valuable insights into the performance of the proposed attendance monitoring system.

(Manuscript received: 23 June 2023 | Accepted: 10 August 2023 | Published: 30 September 2023)

Cuffless Non-invasive Blood Pressure Measurement Using CNN-LSTM Model: A Correlation Study

Jie Shan Vanessa Leong, Kok Beng Gan — Sat, 30 Sep 2023 00:00:00 +0800

Cardiovascular disease is a major concern for people all around the world and still remains as the main cause of death worldwide. Blood pressure has been identified as the most important risk factor. Having the ability to acquire continuous monitoring on this biological parameter plays a significant role in reducing the risk of getting cardiac disease. Many studies conducted utilize two biosignals and features manually extracted from signals as input to the model. However, these methods increase the computational complexity in the pre-processing stage as it involves signal synchronization, and the model performance is highly dependent on the selection of features. The main objective of this study is to build a hybrid convolutional neural network combined with Long-Short Term Memory (CNN-LSTM) model to estimate blood pressure from PPG signals, which eliminates the need for manual feature extraction. Correlation study is performed to evaluate the performance of the model, and it gives a direct visualization of the model’s performance in percentage. This research compared the correlation performance between MIMIC-II dataset, UKM dataset, and PPG-BP dataset using the CNN-LSTM model to estimate blood pressure from PPG signals. The results show that the UKM dataset performs the best, having the highest overall correlation at 0.53 for systolic blood pressure, and 0.29 for diastolic blood pressure. The model trained with this dataset is suitable to estimate systolic blood pressure ranging from 141 to 150mmHg, and diastolic blood pressure ranging 81 to 90 mmHg. In conclusion, among the three datasets, UKM dataset is the most suitable dataset to be used as the input of the CNN-LSTM model to perform cuffless blood pressure measurement with PPG signals.

(Manuscript received: 16 March 2023 | Accepted: 27 July 2023 | Published: 30 September 2023)

Implementation Of The Best-Worst Method For Supplier Selection Of Products Transportation Service In A Pharmaceutical Company

Henrikus Banu Alyodya, Johan Krisnanto Runtuk, Poh Kiat Ng — Sat, 30 Sep 2023 00:00:00 +0800

Supplier selection is an important aspect that must be carried out properly to ensure that the company's supply chain can run well. PT. XZ is a pharmaceutical company that regularly require product transportation service from a dedicated supplier. Currently the supplier selection process in the company is a general process that can be applied for any supplier selection case yet does not have an adjustable criteria and weight to accommodate different evaluation standard for different case. The company prefer to simplify the selection process by neglecting the criteria selection and weight calculation. Numerous studies in the field of multi-criteria decision-making (MCDM) have delved into methods to enhance the supplier selection process and minimize errors. This research aims to assess supplier selection, identify relevant criteria, and incorporate the best-worst method to optimize the choice of the most suitable supplier for product transportation services. The best-worst method (BWM) is employed to assign weights to criteria by utilizing user preference ratings, resulting in a refined and accurate criterion weighting process. With the determined criteria, the alternatives are evaluated by individual assessment form. The evaluation score is normalized and multiplied by the weight with the respect of the specific criteria to find the final weighted score. The result is one of the logistic company’s scores is higher than the other alternatives which indicates that alternative is the best to be chosen.

(Manuscript received: 7 July 2023 | Accepted: 28 August 2023 | Published: 30 September 2023)

Prostate Cancer Classification Based on Histopathological Images

Nalson Mark Loorutu, Haniza Yazid , Khairul Shakir Ab Rahman — Sat, 30 Sep 2023 00:00:00 +0800

Prostate cancer is a significant health concern, ranking as the third most common cancer in Malaysian men, with increasing incidence in Asia. The importance of automating the prostate cancer classification process lies in its potential to significantly improve diagnostic accuracy, reduce subjectivity, and enhance overall efficiency compared to the manual approach. The objective of this thesis is two-fold: firstly, to effectively enhance and segment crucial features in the images to aid in the classification process, and secondly, to implement a binary classification task that indicates the presence or absence of malignant tissue on histopathology images. The study compares the performance of two image enhancement approaches, stain normalization with adaptive histogram equalization (AHE) and sharpening, and stain normalization with traditional histogram equalization (HE) and sharpening. Additionally, three machine learning models, namely SVM, DenseNet121, and InceptionResNetV2, are implemented and evaluated for prostate cancer binary classification. The findings reveal that AHE contributes to better contrast enhancement and image quality preservation. Moreover, the InceptionResNetV2 model demonstrates superior performance in terms of accuracy (97.25%), sensitivity (97.5%), specificity (97.5%), and area under the curve (AUC) (97.5%).

(Manuscript received: 1st August 2023 | Accepted: 21st August 2023 | Published: 30 September 2023)

Neighbourly Edge Irregularity on Interval-valued Pythagorean Neutrosophic Graph

Mullai Murugappan, Govindan Vetrivel, Grienggrai Rajchakit, G. Madhan Kumar — Sat, 30 Sep 2023 00:00:00 +0800

Interval-Valued Pythagorean Neutrosophic Graph (IVPNG) comprises independent and dependent membership elements of interval entries. This paperdemonstrates some kinds of irregular properties on IVPNG like neighbourly irregular, neighbourly totally irregular, strongly irregular, strongly totally irregular, highly irregular,and highly totally irregular. On certain conditions, neighbourly edge irregular and neighbourly edge totally irregular IVPNG satisfy these irregular properties and vice versa.

(Manuscript received: 13 July 2023 | Accepted: 10 August 2023 | Published: 30 September 2023)

Mental Health Problems Prediction Using Machine Learning Techniques

Jia-Pao Cheng, Su-Cheng Haw — Sat, 30 Sep 2023 00:00:00 +0800

Mental health problems encompass a range of conditions that can impact an individual's emotions and behaviors. The conventional methods of mental illness prediction often suffer from the issue of either over-detection or under-detection and the time-consuming manual review process of patients' data during screening sessions. Therefore, this research aims to utilize machine learning techniques to predict mental health problems, complementing the traditional clinical screening and diagnosis process. The proposed models in this project: Logistic Regression, K-Nearest Neighbors, and Random Forest leverage relevant factors from the dataset concerning mental health survey published by Open Source Mental Disorders in 2014 to predict mental health problems. Feature selection and hyperparameter fine-tuning are employed to identify the factors contributing to mental health problems and enhance the performance of the models. The evaluation of these models is measured using accuracy, recall, precision, F1 score, and AUROC. Experimental evaluation results indicated that the Random Forest model utilizing hyperparameters derived from the RandomizedSearchCV method outperforms during model selection using cross-validation. When predicting test set data, it exhibits a good generalization with an accuracy of 83.23%, recall of 89.87%, precision of 78.02%, F1 score of 83.53%, and AUROC of 83.57%.

(Manuscript received: 13 July 2023 | Accepted: 2nd August 2023 | Published: 30 September 2023)

Review on Accessibility of Scissors for the Left-handed and Ambidextrous, and People with Fine Motor Difficulties in the Digital Era

Wai Ti Chan — Sat, 30 Sep 2023 00:00:00 +0800

There had been efforts to provide single-handed tools for small-scale and one-time work, from the industrial to the modern age. This is notable in the case of scissors. The modern era provides more options to produce scissors that fit the individual. This is made possible through 3D printing and rapid prototyping. However, accommodating the exact personal preferences of users remains a persistent problem, especially for the left-handed and ambidextrous, or those who have problems with fine motor skills. The other alternative in the digital era is coaching and instructions that are available through digital platforms for the purpose of helping people practice fine motor skills in the use of scissors. However, like other tutoring methods, their outcomes depend on the individual ability of the learners.

(Manuscript received: 23 June 2023 | Accepted: 10 August 2023 | Published: 30 September 2023)

MATHEMATICAL MODELLING ON THE TRANSMISSION DYNAMICS OF ZIKA VIRUS

Mullai Murugappan, G.Madhan Kumar, Grienggrai Rajchakit, Govindan Vetrivel — Sat, 30 Sep 2023 00:00:00 +0800

Zika virus is a mosquito-borne virus that is commonly transmitted by mosquitoes of the Aedes genus. The transmission dynamics of the Zika virus in males, females, and children are comparatively studied. The study aims to analyze and find the population that affects more due to Zika transmission. This paper deals with the non-linear Mathematical model of the dynamics of Zika virus transmission. The reproductive ratio of the model is calculated to analyze the spread of the Zika virus. The equilibrium and the stability of the model are found and analyzed analytically. Numerical simulation is carried out to support the analytical results and to estimate the most affecting population in different equilibria.

(Manuscript received: 23 June 2023 | Accepted: 14 August 2023 | Published: 30 September 2023)

Smart Manufacturing with Smart Technologies – A Review

chockalingam Palanisamy — Sat, 30 Sep 2023 00:00:00 +0800

The application of smart technologies like the Internet of Things (IoT), Cloud Computing (CC), Cyber Physical Systems (CPS), Big Data (BD), and Artificial Intelligence (AI) in production is known as "smart manufacturing" (SM). This article examines how SM changed as a result of the advancement of these technologies. This review summarises the development of each technology before explaining how SM made these technologies possible. The final topic is the future improvements for Industry 4.0. With the purpose of elucidating next-generation smart manufacturing, this review will make an effort to respond to these questions, i.e., present date of resources in manufacturing and the difficulties associated with using smart technology in manufacturing.

(Manuscript received: 1st November 2022 | Accepted: 27 July 2023 | Published: 30 September 2023)

TRANSMISSION DYNAMICS OF SMOKING - A MATHEMATICAL MODEL

Mullai Murugappan, G. Madhan Kumar, Grienggrai Rajchakit, Govindan Vetrivel — Sat, 30 Sep 2023 00:00:00 +0800

Smoking is a disastrous habit that exposes smokers at a greater chance of cardiovascular and blood vessel ailments.Also, it can cause many diseases like cancer, asthma,strokes etc., to smokers. It plays a major role in one of the economic issues of a country. This articledeals with the transmissiondynamics of smoking addiction of population in a country. To analyse thesmoking addiction among adolescents population, a nonlinear mathematical model is developed here.In this model, the four compartments viz., Susceptible male, Susceptible female, Chain Smokers andSmokers but not chain smokers are considered to study the transmission dynamics of smoking addiction.The deterministic model for smoking addiction is formulated to exhibit the smokers free equilibriumandsmokers equilibrium. Also, the reproductive number of the model is calculated to analyze the spread ofsmoking habit. The local stability of these equilibrium points is also analyzed analytically and numerically.

(Manuscript received: 28 June 2023 | Accepted: 10 August 2023 | Published: 30 September 2023)

Voice Controlled Home Automation System Design

Thangavel Bhuvaneswari, Venugopal Chitra, Goh Chee Cheng — Sat, 30 Sep 2023 00:00:00 +0800

The primary objective of this home automation study is to facilitate the implementation of a voice-controlled capabilities, primarily designed to assist individuals with disabilities or seniors. The system presented in this research enables wireless control of various household devices, such as lights, fans, and any electrical appliances through a dedicated mobile application. This voice-controlled home automation system leverages an android smartphone and a microcontroller using an android application to manage household appliances. The system can be accessed by user name and password. This system is designed with three main control interfaces such as Bluetooth connectivity, voice recognition, and manual control switching. The google cloud speech API which can convert spoken words into text is utilized for voice recognition. This generated text is then transmitted to the designated slave device, facilitating home automation through Bluetooth communication. Additionally, the system provides a manual control switch for user convenience. To control high-voltage appliances safely, an enhanced microcontroller is employed, incorporating a relay circuit for ON/OFF functionality. The developed prototype, encompassing both hardware and software components, has undergone comprehensive testing, validating its security features and compatibility with various home appliances. This innovative home automation system not only offers enhanced convenience but also prioritizes security, providing an attractive alternative to commercial solutions.

(Manuscript received: 31st July 2023 | Accepted: 1st September 2023 | Published: 30 September 2023)

The Application of Augmented Reality Platform for Chemistry Learning

Wei Xiang Lim, Chean Khim Toa, Kok Swee Sim — Sat, 30 Sep 2023 00:00:00 +0800

In this project, a new learning platform was developed. This project uses the technology of Augmented Reality (AR) to develop a graphic animation platform for learning purposes. By applying virtual objects with animations for learning, it helps to engage users and increase their learning efficiency. Besides, the AR platform combines hardware (i.e.s smartphone, headset, and target marker) and software (i.e., Unity, Vuforia, and C#) for the operation. The AR application allow the interaction of the virtual objects by grabbing target marker toward each other or touching the virtual button in real environment. This can increase the immersion and interaction of the user when learning chemistry. In additional, the “Chemical Learn” experiments was designed to study the effectiveness of the AR platform compared to traditional platform as well as to conduct user satisfaction surveys. The overall results showed that the AR learning platform can improved learning efficiency of users in chemistry compared to traditional learning methods. Moreover, users who participate in the survey are generally satisfied with the AR. It is believed that with the rising trend of technology, it is only a matter of time before people become familiar with the AR platform.

(Submitted: 1 December 2021 | Accepted: 24 April 2022 | Published: 30 September 2023)