International Journal on Robotics, Automation and Sciences

Some Insights on Pythagorean Neutrosophic Graphs

Mullai Murugappan — 2025-07-30

Pythagorean neutrosophic graphs (PNeuGr) are a specialized extension of the neutrosophic graphical idea, where the total sum range of memberships is adjusted by squaring each membership. This article is furnished to enhance the handling of uncertain events in a complex environment. The discussion encloses the irregular properties of the PNeuGr and its practical implications

Manuscript received:9 Apr 2025 | Revised: 28 May 2025 | Accepted: 19 Jun 2025 | Published: 30 Jul 2025

Fuzzy Frontiers in Rift Valley Fever Virus Control: Exploring the Dynamics of Transmission and Treatment

Sangavi Meyyappan — 2025-07-30

Rift Valley Fever (RVF) is a mosquito-borne zoonotic viral disease that poses significant health threats to both human and animal populations across Africa and parts of the Middle East. Traditional epidemiological models often assume precise parameter values, which may not accurately reflect the inherent uncertainty in real-world disease transmission. To address this, we propose a novel stochastic and fuzzy logic-based Susceptible-Infected-Susceptible (SIS) model to analyze the spread of RVF under uncertain conditions. The model incorporates fuzziness in transmission and recovery rates using fuzzy set theory. Equilibrium points are analytically derived, and stability analysis is performed to explore the long-term dynamics of the disease. We compute and compare the fuzzy expectation of infected individuals with the classical expectation to assess the effect of parameter uncertainty. The basic reproduction number is calculated for both strictly increasing and strictly decreasing transmission functions, and their impacts on transcritical and backward bifurcations are thoroughly investigated. Furthermore, we incorporate optimal control strategies, including vaccination and vector control, within the fuzzy framework and evaluate how uncertainty influences their effectiveness. Numerical simulations validate the analytical results and illustrate the temporal progression of the disease. Our findings emphasize that integrating fuzzy logic with stochastic modeling provides a more realistic and robust approach to understanding and controlling RVF than conventional deterministic models, offering valuable insights for public health intervention planning under uncertainty.

Manuscript received:8 Apr 2025 | Revised: 2 Jun 2025 | Accepted: 19 Jun 2025 | Published: 30 Jul 2025

First Zagreb Index and its Characteristics on Neutrosophic Graph

Vetrivel Govindan — 2025-07-30

Topological indices mark an irreplaceable place for applications in crisp and fuzzy graphs. These indices are extended to the neutrosophic graphical idea to rectify the imprecise values or information acquired before, since the uncertain cases are organized and allocated as a separate membership called "indeterminacy". We apply and explore the First zagreb index and its properties on the neutrosophic graphical system in the line of Wiener and Forgotten indices. This fills the gap between fuzzy and its graphical extensions on indices discussion, thereby extends the applicable areas. Also, an improvised and unique application is portrayed to observe the importance of First zagreb index in the neutrosophic theme of graphs. This contributes to the real life in a greater way than the fuzzy idea.

Manuscript received:8 Apr 2025 | Revised: 31 May 2025 | Accepted: 19 Jun 2025 | Published: 30 Jul 2025

Numerical Integration Approach for Nonlinear Differential Equation in Growth Modelling

Hui Shan Tai — 2025-07-30

The nonlinear ordinary differential equation (ODE) is a common mathematical model for real-world problems. However, its analytical solution is hard to find and may not exist due to the nonlinear and complex structures. Thus, an approximate method is usually employed in mathematical modelling to obtain its solution. This study applies numerical integration techniques, namely Gaussian quadrature and Simpson’s rule methods, to solve nonlinear ODE, which is a hyperbolic growth model. We first discuss the ODE model and then substitute its exact solution model into the ODE model to obtain the model’s numerical solution using numerical integration approaches. Next, we aim to predict the solution of the nonlinear growth model by proposing two linear models and integrating them iteratively. We introduce a least square optimization problem and derive a set of first-order necessary conditions for estimating the model parameter optimally. A gradient descent method is employed to iterate and update the solution of the linear model. The numerical integration techniques are efficient, while the proposed method has proved to be an alternative approach to handling nonlinear ODEs, especially for a nonlinear growth model, since the optimal linear model solution satisfactorily approximates the growth model solution with a small mean square error value.

Manuscript received:3 Apr 2025 | Revised: 15 May 2025 | Accepted: 22 May 2025 | Published: 30 Jul 2025

A Comprehensive Review on Machine Learning-Based Job Recommendation Systems

Rui Ern Yap — 2025-07-30

A dynamic, constantly shifting labor market creates enormous job postings, overwhelming candidates and making it difficult for businesses to find quality candidates. It is also hard for job seekers to find suitable jobs. Addressing these issues, machine learning-driven job recommender systems have recently become an essential tool using predictive models to improve the match between jobs and candidates. A hybrid design that combines collaborative filtering with content-based filtering and adds contextual information like geographic location, industry trends, and user behavioural data can enhance the accuracy and relevance of recommendations. This paper reviews and critically analyzes contemporary job recommender system techniques. The focus is on hybrid recommendation models and the integration of algorithmic approaches, indicating their strengths and weaknesses. This review also looks into the evaluation metrics like precision, recall, normalized discounted cumulative gain (NDCG), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE). To provide an overall perspective of the various approaches employed and the performance trade-offs inherent therein, this paper hopes to shed some light on the optimization of job recommendation systems for better effectiveness and user satisfaction.

Manuscript received:19 Mar 2025 | Revised: 29 Apr 2025 | Accepted: 10 May 2025 | Published: 30 Jul 2025

Optimizing Reviewer Assignment with Recommender Systems: Models, Related Work, and Evaluation

Ye Xin Lim — 2025-07-30

Peer reviewer assignment to academic articles is important in ensuring the quality and originality of academic publications. Traditional methods of selecting reviewers are generally plagued by inefficiency, reviewer burnout, and inconsistency between the subject of the manuscript and the reviewer area of expertise. In attempting to avoid such drawbacks, recommender systems have been explored as a means of solving the reviewer assignment problem. This article reviews the recommender system techniques in detail by reviewing their application in peer reviewer selection. Additionally, related works shall be examined for how different methods work, their strength and limitations, the dataset used by them, and evaluation metrics used in measuring system performance.

Manuscript received:11 Mar 2025 | Revised: 30 Apr 2025 | Accepted: 13 May 2025 | Published: 30 Jul 2025

Artificial Intelligence-Based Facial Expression Recognition for Identifying Customer satisfaction on Products

Samreen Ihsan — 2025-07-30

Facial Expression Recognition (FER) for Identifying Customer Satisfaction on Products is one of the most powerful and challenging research tasks in social communication. Artificial intelligence (AI)-based emotion recognition harnesses the collective strength of machine learning, deep learning, and computer vision to decipher the subtleties of human emotions. By intricately analyzing facial expression, including the nuanced movements of the mouth, eyes, and eyebrows. Recent innovations have driven notable progress in face detection and recognition that enhance performance and reliability. This study focuses on leveraging AI-based facial expression recognition to identify customer satisfaction with products. The objective of this research is to develop a robust and accurate facial expression recognition system capable of analyzing customer emotions and determining their satisfaction levels based on their facial expressions. The proposed study used a hybrid convolutional neural network (CNN) and deep neural networks (DNN) model to extract meaningful features from facial images and classify them into different emotional states. The trained model is to be evaluated using a separate test dataset to measure its performance in accurately recognizing customer emotions and assessing satisfaction levels. The evaluation metrics include accuracy, precision, recall, and F1-score. The proposed experiment achieved excellent result with a real-time image-based dataset.

Manuscript received:7 Mar 2025 | Revised: 22 May 2025 | Accepted: 11 Jun 2025 | Published: 30 Jul 2025

EEG-Based Emotion Recognition Using CNN-LSTM: Dynamic Segmentation and Feature Fusion

Nazia Tabraiz — 2025-07-30

This study examines current developments and persistent difficulties in identifying emotions from EEG data, particularly when it comes to real-time systems. The need for precise, quick-response models has increased as interest in emotion-aware applications—from adaptive human-computer interfaces to mental health tools—increases. Although deep learning methods such as CNNs and LSTMs have demonstrated remarkable accuracy (up to 98%), a number of practical issues still need to be addressed, especially in the areas of delay minimization and data preprocessing. In order to improve recognition speed and reliability, the research presents real-time prioritization techniques and dynamic segmentation procedures. It also examines the wider socioeconomic and ethical implications of EEG-based systems and highlights important avenues for further study, such as multimodal feature fusion and dataset diversification.

Manuscript received:1 Mar 2025 | Revised: 23 Apr 2025 | Accepted: 8 May 2025 | Published: 30 Jul 2025

DRD-Net: Diabetic Retinopathy Diagnosis Using A Hybrid Convolutional Neural Network

Muhammad Hassaan Ashraf — 2025-07-30

Diabetic Retinopathy (DR) has become a leading cause of blindness among diabetic patients. Accurate and timely diagnosis of DR is critical to slowing disease progression. This research proposes a Hybrid Convolutional Neural Network (CNN)-based model, named Diabetic Retinopathy Detection Network (DRD-Net). The proposed DRD-Net designed to enhance diagnostic accuracy by addressing key challenges such as gradient vanishing and lesion scale variability in fundus images. Contrast-Limited Adaptive Histogram Equalization (CLAHE) was used to enhance contrast and highlight lesions in fundus images. To increase the diversity of training samples, the proposed framework employs geometric data augmentation techniques. DRD-Net incorporates the Swish activation function along with densely connected blocks to mitigate gradient vanishing and enhancing feature propagation within the network. Additionally, the model integrates two Inception blocks to facilitate multiscale feature extraction, which is essential for detecting small Regions of Interest (RoI) in fundus images. Experimental results demonstrate that DRD-Net achieves a precision of 84.4%, recall of 84.5%, F1-score of 84.1%, and accuracy of 85.1%, outperforming several state-of-the-art models on the IDRiD dataset. These results highlight DRD-Net’s potential as an effective solution for automated DR diagnosis, contributing to more efficient and accurate DR screening.

Manuscript received:1 Mar 2025 | Revised: 23 Apr 2025 | Accepted: 5 May 2025 | Published: 30 Jul 2025

Improved Lyapunov Functional for Stability Analysis in Delay-Differential Systems

Krissana Antharat — 2025-07-30

This paper explores the stability of differential systems influenced by time delays, with a specific focus on situations where these delays change over time. Such systems often present analytical challenges due to the unpredictable nature of the delays. To tackle this, we introduce a new form of Lyapunov–Krasovskii functional, which leads to a refined condition for stability that depends directly on the characteristics of the delay. This condition is formulated using Linear Matrix Inequalities (LMIs), which offer a practical way to assess stability while maintaining a solid theoretical foundation. By modeling the effects of time-varying delays more accurately, the method contributes both to a deeper understanding of how such delays affect system behavior and to more reliable tools for analyzing systems where delays are a built-in feature that cannot be ignored.

Manuscript received:23 Feb 2025 | Revised: 16 Apr 2025 | Accepted: 29 Apr 2025 | Published: 30 Jul 2025

Chaos Synchronization of the Lu System Using Single-Variable Feedback

Grienggrai Rajchakit — 2025-07-30

This paper explores a simple yet effective way to synchronize the chaotic Lü system using just one variable from the master system. Rather than relying on full-state observation or advanced nonlinear control, the method uses a straightforward linear feedback approach and takes advantage of the inherent stability in cascade-connected systems to achieve synchronization. One of the main strengths of this approach is its efficiency. By transmitting only a single state variable, it keeps communication demands low—something that’s especially helpful in real-time applications or when resources are limited. Another benefit is that the method doesn’t depend on knowing the bounds of the master system’s trajectories in advance, which makes it more flexible for systems that are unpredictable or constantly changing. The controller itself is also relatively simple to put into practice, avoiding the complexity often seen in other synchronization methods. The approach is backed by solid theoretical analysis, and simulation results using MATLAB show that it works well in practice. Overall, this method offers a lightweight and practical solution for chaos synchronization—ideal for situations where minimal data and easy implementation are key.

Manuscript received:16 Feb 2025 | Revised: 16 Apr 2025 | Accepted: 1 May 2025 | Published: 30 Jul 2025

Design of a Smart Surveillance Robot Using HUSKYLENS AI Vision Sensor

Sin Ting Lim — 2025-07-30

This study aims to enhance security by implementing a smart surveillance robot using existing facial recognition technology. The developed robot is equipped with the HUSKYLENS AI vision sensor camera and an ESP32 CAM module to provide a real-time video feed to a connected computer via Wi-Fi. The results demonstrate the successful integration of facial recognition technology into the surveillance robot's functionality. The robot exhibits an acceptable ability to identify and track intruders, underscoring its potential for enhancing security applications. The robot features a height of 12 cm, a width spanning 11.5 cm, a length measuring 19 cm, and a weight totalling 1.3 kg. Operating on a basic configuration of two main wheels, the robot forms a two-wheeled system with three degrees of freedom (DOF). The developed robot demonstrates an ability to identify and track intruders with a tested accuracy of 77.5%, precision of 80%, specificity of 79%, and sensitivity of 76.1%. The compact and low-profile design enables it to operate discreetly in diverse environments, making it particularly well-suited for scenarios where inconspicuous surveillance is needed.

Manuscript received:27 Feb 2025 | Revised: 29 Apr 2025 | Accepted: 7 May 2025 | Published: 30 Jul 2025

Design for Additive Manufacturing Optimized Vertical Lunchbox

Chockalingam Palanisamy — 2025-07-30

The vertical lunchbox (VL) project, propose an innovative and functional solution for movement. Traditional lunchboxes often fail to meet the diverse needs of today’s consumers, including the desire for convenience, portability, and meal freshness. This project uses the advantages of additive manufacturing to create a lunchbox that not only offers practicality and usability but also incorporates distinctive features tailored to present lifestyles. The design process employs a concept of Design for Additive Manufacturing (DfAM) and Design for Manufacturing and Assembly (DfMA) principles. These concepts enable the development of required features and at the same time reducing assembly time and improve the functionality. Important features of the vertical lunchbox include customizable compartments that can accommodate ice packs, the lid that can be used as a handphone holder, and removable containers for easy cleaning. These features are catering to the needs of busy professionals and students. Parametric modeling and topological optimization helped to ensure that the lunchbox design is appealing and at the same time lightweight and strong. The adoption of 3D printing technology enabled faster production processes with required dimensional accuracy. Test results indicate that the vertical lunchbox meets most of the user requirements. The important features such as a secured locking and snap-fit lid design ensured the reliable transport containers for carrying food. In Addition, the project proved that additive manufacturing can be used for time to market approach of the product development. Finally, the vertical lunchbox project demonstrates how advanced manufacturing techniques can transform traditional product design to meet modern consumer needs.

Manuscript received:18 Feb 2025 | Revised: 12 Apr 2025 | Accepted: 29 Apr 2025 | Published: 30 Jul 2025