·         Table of Contents (Volume #8, Issue #3)

·         Cover Page (Volume #8, Issue #3)

·         Editorial (Volume #8, Issue #3)

Paper #1

Adaptive Meta-heuristic Framework for Real-time Dynamic Obstacle Avoidance in Redundant Robot Manipulators

Sheik Masthan Shahul Abdul Rahim, Kanagaraj Ganesan and Mohammed Shafi Kundiladi

Abstract: Robotic manipulator faces a challenge in navigating dynamic environments while ensuring collision-free trajectories, especially for redundant manipulators. Inverse kinematics involves finding joint angles to reach a specific point in 3D space. The shift from classical analytical and numerical methods to optimization heuristic algorithms is driven by the increasing complexity of robotic systems and the demand for more versatile and adaptive solutions. Meta-heuristic algorithms offer a transformative approach by framing the inverse kinematics problem as an optimization challenge, providing a flexible and robust means to navigate complex solution spaces. Metaheuristic algorithms, known for their ability to explore high-dimensional search spaces and avoid local optima, offer robust solutions for these challenges. They enhance computational efficiency, enabling real-time decision-making and obstacle avoidance, making them ideal for complex robotic applications. These characteristics of the metaheuristic algorithms can used in developing an integrated framework that offers complete solution to robot manipulators. This research article presents a generalized framework leveraging meta-heuristic algorithms to address dynamic obstacle avoidance in redundant manipulators. The framework uses meta-heuristic algorithms as the inverse kinematics solver, 3D trajectory planner, and obstacle avoidance mechanism, encompassing both static and dynamic obstacles. The proposed framework is generalized and gives the user to select the type of robot manipulator, with any number of links with any custom trajectory within the workspace of the robot manipulator. Also, any metaheuristic algorithm can be used in the proposed framework. The proposed framework is implemented in MATLAB’s app designer for simulation with six different meta-heuristic algorithms. The effectiveness of the framework was evaluated in terms of its capability to generate 3d path, its ability to follow generated trajectory, while seamlessly adapting to dynamically changing environments. Through simulation, the framework showcased robust performance in navigating workspaces with moving obstacles, ensuring collision-free motion for redundant manipulators.

Keywords: Adaptive Trajectory Tracking; Collision-free Trajectory Follower; Dynamic Obstacle Avoidance; Hybrid Meta-heuristic Algorithm; Inverse Kinematics Solver; Real-time Obstacle Avoidance; Redundant Robot Manipulator.

Download Full Text

Paper #2

Air Pollution Monitoring Using IoT and Machine Learning in the Perspective of Bangladesh

Md Monirul Islam, Shalah Uddin Perbhez Shakil, Nasim Mahmud Nayan, Mohammod Abul Kashem and Jia Uddin

Abstract: Air pollution is a big concern in developing countries due to its negative effects on both human well-being and the environment. Collecting real-time values of air quality is challenging using traditional methods. Because they have limited coverage and may not accurately reflect pollution levels in a specific location. However, Advances in Internet of Things (IoT) technology and Machine Learning (ML) algorithms, can play a vital role in collecting and analyzing large amounts of air quality data, resulting in a more complete and exact knowledge of pollution levels. Throughout this work, based on several air pollutants including sulfur dioxide (SO2), ozone (O3), nitrogen dioxide (NO2), particulate matter (PM) 2.5, particulate matter (PM) 10 and carbon monoxide (CO) across a large urban region, we establish an IoT-based framework to collect real-time data. After collecting the real-time values, we applied two types of machine learning algorithms named regression and classification models including linear regression, decision trees (DT), random forest (RF), K-Nearest Neighbours (KNN), Naive Bayes (NB), and gradient boosting (GB), to analyze the gathered data and estimate pollution levels into good, satisfactory, moderate, poor and very poor. Among the machine learning models, RF outperforms the result. This work and the dataset will be helpful for researchers, environmental practitioners and agencies.

Keywords: Air pollutant monitoring; AQI prediction; IoT; Machine Learning; Real-time values.

Download Full Text

Paper #3

Enhancing Depressive Post Detection in Bangla: A Comparative Study of TF-IDF, BERT and FastText Embeddings

Saad Ahmed Sazan, Mahdi H. Miraz and A B M Muntasir Rahman

Abstract: Due to massive adoption of social media, detection of users’ depression through social media analytics bears significant importance, particularly for underrepresented languages, such as Bangla. This study introduces a well-grounded approach to identify depressive social media posts in Bangla, by employing advanced natural language processing techniques. The dataset used in this work, annotated by domain experts, includes both depressive and non-depressive posts, ensuring high-quality data for model training and evaluation. To address the prevalent issue of class imbalance, we utilised random oversampling for the minority class, thereby enhancing the model's ability to accurately detect depressive posts. We explored various numerical representation techniques, including Term Frequency – Inverse Document Frequency (TF-IDF), Bidirectional Encoder Representations from Transformers (BERT) embedding and FastText embedding, by integrating them with a deep learning-based Convolutional Neural Network-Bidirectional Long Short-Term Memory (CNN-BiLSTM) model. The results obtained through extensive experimentation, indicate that the BERT approach performed better the others, achieving a F1-score of 84%. This indicates that BERT, in combination with the CNN-BiLSTM architecture, effectively recognises the nuances of Bangla texts relevant to depressive contents. Comparative analysis with the existing state-of-the-art methods demonstrates that our approach with BERT embedding performs better than others in terms of evaluation metrics and the reliability of dataset annotations. Our research significantly contributes to the development of reliable tools for detecting depressive posts in the Bangla language. By highlighting the efficacy of different embedding techniques and deep learning models, this study paves the way for improved mental health monitoring through social media platforms.

Keywords: BERT; Bi-LSTM; CNN; Depression; FastText; Post Detection; TF-IDF; Text Classification.

Download Full Text

Paper #4

Optimization of Road Detection using Semantic Segmentation and Deep Learning in Self-Driving Cars

Mohammed Sameeh Hammoud and Sergey Lupin

Abstract: Robust and accurate road detection is an essential part of Automatic Driver Assistance Systems (ADAS). Self-driving Cars have the capability to revolutionize the way we travel, making transportation safer, more effective and more available to all. With the ability to navigate roads without human intervention, self-driving cars can reduce the number of accidents caused by human error, eliminate the demand for drivers to be behind the wheel and make it easier for people who can’t drive, such as the elderly or disabled people to get around. In addition, self-driving cars can enhance traffic flow by reducing congestion and optimizing routes, eventually saving time and reducing emissions. As technology continues to advance, self-driving cars are poised to transform the transportation industry and change the way we think about mobility. In this work, a convolutional neural network-based deep learning to achieve road detection based on image segmentation to be applied in self-driving cars. In addition to our proposed network, multiple experiments were conducted to investigate the impact of different deep-earning architectures on performance. A public dataset called the KITTI road dataset is used to train and validate the model. The images were down-sampled from 1224x370 to 256x256. We compared our model’s performance with the performance of popular deep learning architectures such as Unet and LinkNet A transfer learning technique is used while training the models based on network weights trained on the famous dataset ImageNet, including popular architectures such as ResNet, VGG, SeresNet and EfficientNet. The results show that our model achieves an F1-score of 0.9909, outperforming Unet and LinkNet architectures. In the second place, the best results were obtained based on Unet and ResNet50 with an F1-score of 0.9904.

Keywords: Advanced Driver Assistance Systems; Computer vision; Deep Learning; Image segmentation; Mobile Robots; Navigation; Road Detection; Self-Driving Cars.

Download Full Text

Paper #5

Secure Autonomous Vehicle Localization Framework using GMCC and FSCH-KMC under GPS-Denied Locations

Mohammed Shafi Kundiladi, Sheik Masthan Shahul Abdul Rahim and Mohammed Shahal Rishad

Abstract: For safe and efficient navigation, self-driving cars rely on determining their position through a system called Autonomous Vehicle Localization (AVL). Traditional self-driving cars face challenges related to security and speed in finding their location. To address these problems, this article presents a more secure way, called the Secured Localization (SL), to locate the vehicle, even when signals are weak. First, vehicles are registered and logged in. If Global Positioning System (GPS) signals are available, they are processed securely utilizing Gini-Montgomery Curve Cryptography (GMCC); If GPS signals are not available, then the car uses nearby signal points to find its location. SL data and sensed data from the sensors, including Light Detection and Ranging (LIDAR), Radio Detection and Ranging (RADAR), and Camera are given to On Board Unit (OBU). Then, the vehicle’s position is matched with a pre-stored map for accurate navigation. Finally, various methods such as Fisher Score Chi-Hell Square based K Means Clustering (FSCH-KMC), Cosine Gramian-Kalman Filter (CG-KF), and Hadoop Distributed File System (HDFS) are applied to prioritize and refine the vehicle’s location for better navigation. The proposed framework is simulated and the results show an accuracy of 98%, precision of 98%, and recall of 99%, with improvements in security and faster location finding compared to previous systems.

Keywords: Cosine Gramian-Kalman Filter (CG-KF); Fisher Score Chi-Hell Square based K Means Clustering (FSCH-KMC); Gini-Montgomery Curve Cryptography (GMCC); Global Positioning System (GPS); Secured Localization (SL).

Download Full Text