Table of Contents (Volume #10, Issue #1)

         Cover Page (Volume #10, Issue #1)

         Editorial (Volume #10, Issue #1)

Paper #1

Urban Public Art as the Renewable Energy Hub: Integrating Aesthetics and Functional Design to Create Sustainable Cities

Yuxia Fu

Abstract: To address the conflict between aesthetic expression and functional efficiency faced by renewable energy facilities in urban spaces, this study proposes a public art installation design framework that integrates interdisciplinary technologies. A multi-source data fusion module integrates geographic context and regional cultural symbols to jointly guide the parametric optimization of device morphology and the layout of energy harvesting components. Complementing this, an improved MPPT (Maximum Power Point Tracking) algorithm enhanced by a Kalman filter-based dynamic allocation strategy ensures robust power extraction under the complex irradiance fluctuations induced by the artistic form. Meanwhile, a parametric aesthetic generation algorithm based on genetic algorithm morphological optimization and CycleGAN (Cycle-Consistent Generative Adversarial Network) texture fusion is developed to achieve the dual goals of urban public art as a renewable energy hub. Structural strength verification and interactive experience design ensure safety and public engagement, respectively. Experimental results demonstrate that the proposed scheme achieves a power generation efficiency of 93.4% of the theoretical value under sunny conditions, with a high public satisfaction rate of 85%. A measured annual internal rate of return of 10.6% verifies its environmental and economic benefits. This research provides an innovative paradigm for the synergy between aesthetics and functionality for sustainable urban development.

Keywords: Aesthetic-Functional Synergy; Functional Design; Parametric Generation; Renewable Energy Hub; Urban Public Art.

Download Full Text

Paper #2

Enhancing Intrusion Detection System Performance Using a Modified Grey Wolf Optimizer

Abdullah Al Mosuli, Mosleh Abualhaj, Ahmad Abu-Shareha, Mohamed Yousif and Mohammad Daoud

Abstract: Cybersecurity is one of the main worries of organizations, businesses, and even individuals. The problems facing cybersecurity are increasing on daily basis as a result of the increased reliance on electronic services and technologies and the associated increase in the number of cyberattacks. The prevention of cyberattacks has become a serious challenge due to the vast increase in cybersecurity threats. Intrusion Detection System (IDS) acts as one of the first line of defence against cyberattacks, protecting computer networks and users data. However, the efficiency and effectiveness of IDS can be challenged by the enormous data monitored by the IDS, and the irrelevant features in the data. This study presents a Machine Learning (ML) model for intrusion detection and aims to enhance the model by employing the proposed Modified-Grey Wolf Optimizer (GWO) for feature selection. A new mutation function and an effective initialization method are introduced to the GWO, enhancing its exploration of the solution space and reducing convergence time. The proposed modified-GWO is then applied to the NSL-KDD dataset for feature selection, identifying the most relevant features for intrusion detection. The ML model will be tested using various ML classifiers. These classifiers are XGBoost, RF, HGB, and MNB. The proposed model achieved remarkable results with the XGBoost classifier reaching an accuracy of 99.52%, a precision of 99.47%, and a recall of 99.46%.

Keywords: Feature Selection; Grey Wolf Optimizer; Machine Learning; NSL-KDD Dataset.

Download Full Text

Paper #3

Explainable AI-Assisted Parkinson s Disease Diagnosis Using Machine Learning and Deep Neural Networks

Ferdaus Ibne Aziz, Daniel Ojeda Rosales, Becky Firomssa Gudeta and Jia Uddin

Abstract: Timely and specific interventions can substantially help in managing the disease, provided that the PD is diagnosed at an early stage. This paper compares machine learning (ML) and deep learning (DL) methods of PD detection with the help of vocal characteristics of a canonical sample (197 samples with 22 voice attributes pre-extracted). To reduce the issue of class imbalance, the Synthetic Minority Over-Sampling Technique (SMOTE) was used on the training data, which enhanced the strength of the models. The classical Machine Learning (ML) classifiers, such as Logistic Regression, Support Vector Machine, Random Forest, Extra Trees, Decision Tree, AdaBoost, and K-Nearest Neighbors (KNN) were evaluated, and KNN produced the best accuracy of 85% as well as competitive accuracy, recall, F1 score, and AUC ROC. In the case of deep learning, 1D CNN, 2D CNN, and LSTM were used, and 2D CNN and LSTM performed better than 1D CNN, with test accuracy of 89.7% and 84.6%, respectively, indicating their capability to learn both time-based and spatial patterns in data. Interpretability was added through Local Interpretable Model Agnostic Explanations (LIME) to ML models that point to Spread2, Recurrence Period Density Entropy, and MDVP-related frequency measures as significant vocal biomarkers. Although the framework has constraints relating to data volume and single modality, it offers a reproducible, interpretable baseline of PD detection and highlights the possibilities of explainable AI and neural networks as an assistant clinical decision-making tool. In the future, larger, multi-modal datasets are needed to offer better generalizability.

Keywords: Parkinson s Disease Diagnosis; Tabular Data; Machine Learning; Deep Neural Network.

Download Full Text

Paper #4

Review and Utilisation of AI in Signal Processing

Johan Note, Maaruf Ali and Lek Pepkolaj

Abstract: Numerous challenges persist within Signal Processing (SP) in communication systems, i.e. maintaining system stability, complexity of multi-dimensional SP and filtering. Many resources are required to cope with these growing problems. The application of AI offers promising solutions. AI is already being applied to solve engineering, medical and scientific problems, including utilisation in SP and Digital Signal Processing (DSP). The research methodology began with common supervised AI algorithms in SP: Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNNs). Regular unsupervised AI learning algorithms investigated included: Sparse Auto-encoder, Deep Auto-encoder, Convolutional Auto-encoder and the De-noising Auto-encoder. Their benefits were ascertained for their utilisation in an intelligent, scalable and secure communication system. The paper also provides over 100 references. The conclusion is that using specifically identified AI algorithms will make communication systems more scalable, thus mitigating overloading, instability and premature breaking point failure. AI use will also eventually make communication systems less expensive, more agile and far more intelligent - essential for Cognitive Radio and SDR (Software Defined Radio). The communication channels will become more reliable with AI SP and aid in its increased robustness in noise, quality and error recovery, compared with using traditional SP. These benefits will cause a shift toward using new methods in SP such as the Advantage Actor Critic and Trust Region Policy Gradient Algorithms. Two different datasets comprising the MNIST (Modified National Institute of Standards and Technology) database consisting of 70,000 28 28 pixels greyscale images of handwritten integers and the CIFAR-10 (Canadian Institute for Advanced Research) database containing 60,000 32 32 pixels small colour images were utilised. These were then processed using the aforementioned algorithms to test their accuracy. Because of 6G radio channel data scarcity for training purposes, image datasets were used to check the feasibility of the effectiveness of AI in SP in general radio communications, due to their two-dimensional nature. The result showed that all seven AI models performed well: 80% - 99.77% (accuracies). The CCN-Autoencoder gave the best result overall using both datasets: 94.5%-99.77% (accuracies). Future work will use real radio communication channel data and other AI algorithms.

Keywords: AI; Artificial Neural Networks; Convolutional Neural Networks; Denoising Auto-encoder; Signal Processing; Sparse Auto-encoder.

Download Full Text

Paper #5

Enhancing Agricultural Sustainability: An IoT-Based RNN-LSTM Model for Precision Sub-Surface Moisture Monitoring and Irrigation Optimisation

Shamala Maniam, Erfan Memar, Tee Yei Kheng, Nisha Kumari, Hin Yong Wong and Mukter Zaman

Abstract: Water directly influences plant growth and vitality and is a critical resource in precision agriculture (PA). Soluble fertilisers are transported to plant roots through irrigation, making precise water management essential for optimising crop productivity and minimising resource wastage. Inadequate or excessive irrigation disrupts nutrient distribution, increases operational costs, and negatively affects crop yield. Accurate monitoring of sub-surface soil moisture, particularly at root depth, is therefore vital for effective irrigation control. This study addresses key limitations in existing PA systems by developing an automated Internet of Things (IoT)-based real-time soil moisture monitoring and irrigation framework integrated with a recurrent neural network (RNN) employing long short-term memory (LSTM) for moisture prediction. Customised sub-surface soil moisture probes equipped with five sensors at different depths were deployed at a real plantation site. The probes utilised time domain reflectometer (TDR) technology to capture high-resolution moisture measurements. Sensor data were transmitted to the cloud using an ESP32-based low-range communication module, forming a wireless sensor network (WSN) across the designated study area. A continuous six-month dataset was collected and analysed to train and validate the proposed RNN-LSTM model. The model demonstrated strong predictive capability, achieving an accuracy of 95 ± 2%, a mean absolute error (MAE) of 0.6362, a root mean square error (RMSE) of 1.1544, and an R² value of 0.3331. These results confirm the model’s effectiveness in capturing sub-surface soil moisture dynamics under real field conditions. Overall, the proposed IoT-enabled predictive irrigation system provides a scalable and data-driven solution for improving irrigation efficiency.

Keywords: Internet of Things; Precision Agriculture; Real-time Monitoring; Recurrent Neural Network.

Download Full Text