International Journal of Complexity in Applied Science and Technology (4 papers in press)

Regular Issues

• Deep Learning in Waste Management: a Brief Survey  
  by Suman Kunwar, Abayomi Alade 
  Abstract: The rapid growth of the global population is causing a significant increase in waste production, leading to serious environmental and public health challenges. To address these issues, waste management systems are incorporating advanced technologies. Machine learning and computer vision are used to predict waste patterns, optimise collection schedules, and improve sorting accuracy. Deep learning automates the sorting process, provides predictive analytics, and enhances recycling rates. Robotics, combined with AI and computer vision, improves sorting efficiency, while the Internet of Things (IoT) monitors waste levels and optimizes collection routes. Despite these benefits, challenges such as data scarcity, high computational demands, and the need for substantial infrastructure investments must be addressed. This research explores the integration of advanced technologies into waste management and evaluates their effectiveness using waste datasets. It highlights the potential to tackle environmental challenges and lay the groundwork for more intelligent waste management solutions.
  Keywords: Deep Learning; Waste Management; Waste Classification Benchmarks; Waste Datasets Benchmarks; Waste Detection Benchmarks.
  DOI: 10.1504/IJCAST.2024.10068247
   
  
• A Comparative Study of Machine Learning Models for Hate Speech and Stereotype Detection in Italian Texts  
  by Vincenzo Sammartino 
  Abstract: This study presents a comparative analysis of various machine learning models for hate speech and stereotype detection in Italian texts. The research utilizes datasets from the HaSpeeDe task proposed by EVALITA in 2020. Multiple text representation techniques are evaluated, including nonlexical linguistic information, Bag ofWords, n-grams (characters,words, and Part-of-Speech tags), Word Embeddings, and a Neural Language Model (BERT). The study compares the performance of these models in different metrics such as accuracy, precision, recall, and F1-score. The results indicate that character n-grams and the Neural Language Model (BERT) generally outperform other techniques, with BERT achieving the highest accuracy (76%) for the detection of hate speech and character n-grams performing the best for the detection of stereotypes (72% accuracy). The research highlights the challenges in detecting stereotypes compared to hate speech and emphasises the importance of context in classification tasks.
  Keywords: Hate speech detection; Stereotype classification; Natural Language Processing; Machine learning; Italian text analysis.
  DOI: 10.1504/IJCAST.2024.10068248
   
  
• A Hybrid LSTM-SNN Approach for Robust Multimodal Zero-Shot Learning  
  by Yuejia Li, Zhe Yang, Haonan Zheng, Xiang Zhang 
  Abstract: Zero-Shot Learning (ZSL) has gained significant attention for its ability to identify previously unseen classes by leveraging features extracted from known classes, thus minimizing the need for extensive training data. However, existing ZSL methods often fall short in accurately capturing temporal information in multimodal datasets, particularly in audio and video contexts, leading to suboptimal recognition performance. To address this challenge, we propose TempSimNet, a novel framework that combines Long Short-Term Memory (LSTM) networks with Spiking Neural Networks (SNN). LSTM excels at extracting long-term temporal dependencies, while SNN processes these features with high temporal precision through spike-based encoding. The integration of these two networks in TempSimNet enables effective temporal feature extraction and dynamic processing, enhancing the model’s ability to recognize unseen classes in multimodal datasets. Experimental results demonstrate that TempSimNet achieves state-of-the-art performance across multiple benchmark datasets, significantly outperforming traditional ZSL approaches, particularly in generalized ZSL tasks.
  Keywords: Zero-Shot Learning; Multimodal Learning; Long Short-Term Memory; Spiking Neural Networks; Audiovisual Data; Dynamic Processing.
  DOI: 10.1504/IJCAST.2024.10068249
   
  
• Comprehensive Faults Analysis on the Direct Current Side of Photovoltaic Systems using Logistic Model Tree Algorithm  
  by Bogac Oguz Togay, Coskun Firat 
  Abstract: Fault detection in photovoltaic systems is crucial for maintaining efficiency and longevity. This paper proposes the Logistic Model Tree algorithm for analyzing current-voltage curves to detect line-to-line, shading, degradation, and open circuit faults on the direct current side of photovoltaic systems. A 2x2 PV system was simulated in MATLAB Simulink to generate an imbalanced fault dataset, which was then divided into training and testing sets. K-means under sampling addressed the class imbalance issue. Logistic Model Tree and other popular machine learning algorithms were trained using 5-fold cross-validation with grid-search. Performance evaluation on the testing dataset used Matthew's Correlation Coefficient, Cohen's Kappa, and Macro F-1 scores. Results show Logistic Model Tree outperforming other algorithms with the highest Matthew's Correlation Coefficient, Kappa, and F-1 scores, establishing it as the most effective machine learning algorithm for photovoltaic fault detection.
  Keywords: Machine Learning; Photovoltaic systems; Logistic Model Tree algorithm; PV Systems; Direct Current side failures.
  DOI: 10.1504/IJCAST.2024.10068250