Malaysian Journal of Computer Science

ENHANCING BRIX VALUE PREDICTION IN STRAWBERRIES USING MACHINE LEARNING: A FUSION OF PHYSIOCHEMICAL AND COLOR-BASED FEATURES FOR IMPROVED SWEETNESS ASSESSMENT

Ameetha Junaina T. K — 2024-04-30

This study contributes to the ongoing wave of artificial intelligence integration by applying machine learning techniques to automate the assessment of strawberry quality. This research focuses on determining if the sweetness of strawberries can be predicted using a combination of physiochemical variables, their interaction parameters, and color-based features extracted from image data. This research used a 150-sample collection of strawberry images and physiochemical characteristics such as salinity, specific gravity, pH, and Brix. Normalized raw and derived feature variables and selected dataset transformations were done. We then split the dataset into mutual exclusivity training and test sets. Exponential Gaussian Process Regression (GPR) suited well due to low validation errors. This best model predicted Brix values for the remaining test samples. The Mean Absolute Percentage Error(MAPE) showed 98.783% forecast accuracy (Acc). We also examined the model's coefficient of determination (R²) values, which were 0.78 and 0.9739 for training and testing, respectively. The Mean Square Error (MSE) and Mean Absolute Error (MAE) obtained after training were 0.32994 and 0.0453, and testing was 0.35286 and 0.0663. Using input characteristics with high Acc and low error rates, deep learning models like Recurrent Neural Network (RNN) and its derivatives were constructed. Using physiochemical and visual data, machine learning and deep learning models successfully predict strawberry sweetness. This prediction accuracy shows the complex link between internal components and Brix readings, enabling high-quality strawberry production.

USAGE OF PARTICLE SWARM OPTIMIZATION IN DIGITAL IMAGES SELECTION FOR MONKEYPOX VIRUS PREDICTION AND DIAGNOSIS

Akshaya Kumar Mandal — 2024-04-30

Identifying skin diseases by using digital images of skin that are also automated, efficient, and accurate is critical for biomedical image analysis. Many researchers have developed numerous machine-learning techniques for the prediction and diagnosis of various diseases that help clinicians identify infections early and provide crucial data for virus management. In this work, we use the inherent attributes of Particle Swarm Optimization (PSO), such as exploration and exploitation, to identify images for monkeypox virus prediction and diagnosis. Alongside, monkeypox, chickenpox, smallpox, cowpox, measles, tomato flu, and normal skin images were all considered in this study for monkeypox virus prediction and diagnosis. We collect photos from the International Skin Imaging Collaboration (ISIC) for analysis and experimentation purposes. Finally, we compare the proposed model Particle Swarm Optimization- Monkeypox Virus (PSOMPX) for monkeypox virus identification with four distinct pre-trained deep learning models (e.g., VGG16, ResNet50, InceptionV3, and Ensemble). Then we use four performance evaluation metrics—accuracy, precision, recall, and F1 score—to evaluate the model and analyze the outcomes of experiments. The experimental results obtained through the PSOMPX model significantly outperform other models due to its numerous traits.

ENHANCING IIOT SECURITY WITH MACHINE LEARNING AND DEEP LEARNING FOR INTRUSION DETECTION

Omer Fawzi Awad — 2024-04-30

The rapid growth of the Internet of Things (IoT) and digital industrial devices has significantly impacted various aspects of life, underscoring the importance of the Industrial Internet of Things (IIoT). Given its importance in industrial contexts that affect human life, the IIoT represents a key subset of the broader IoT landscape. Due to the proliferation of sensors in smart devices, which are viewed as points of contact, as the gathering of data and information regarding the IIoT systems and devices operating on the IoT, there is an urgent requirement for developing effective security methods to counter such threats as well as protecting IIoT systems. In this study, we develop and evaluate a well-optimized intrusion detection system (IDS) based on deep learning (DL) and machine learning (ML) techniques to enhance IIoT security. Leveraging the Edge-IIoTset dataset, specifically designed for IIoT cybersecurity evaluations, we focus on detecting and mitigating 14 distinct attack types targeting IIoT and IoT protocols. These attacks are categorized into five threat groups: information collection, malware, DDoS, man-in-the-middle attacks, and injection attacks. We conducted experiments using machine learning algorithms (k-nearest neighbors, decision tree) and a neural network on the KNIME platform, achieving a remarkable 100% accuracy with the decision tree model. This high accuracy demonstrates the effectiveness of our approach in protecting industrial IoT networks.

PERFORMANCE EVALUATION OF MULTILABEL EMOTION CLASSIFICATION USING DATA AUGMENTATION TECHNIQUES

Zahra Ahanin — 2024-04-30

One of the challenges of emotion classification is the existence of low annotated datasets, that makes the task more complex. Certain existing datasets often suffer from imbalanced data for the emotion classes. Several data augmentation approaches can help to overcome the challenges regarding imbalanced datasets. However, the existing data augmentation techniques in emotion classification lack consideration for the contextual nuances of emotions and this area is still relatively underexplored. In this work, we study the impact of data augmentation on classification performance of three machine learning models including Logistic Regression, BiLSTM and BERT and compare frequently used methods to address the issue. Specifically, we assessed Easy Data Augmentation (EDA) and contextual Embedding-based data augmentation (BERT) on two datasets. Based on the experimental results, we combined two BERT-based augmentation techniques including insert and substitute, to generate data for minority emotion classes. Furthermore, we proposed a data augmentation method using ChatGPT. Compared to the baseline models, incorporating the BERT augmentation techniques with BERT model resulted in improvements of +4.34% and +5.56% in Macro F1 score on the SemEval-2018 and GoEmotions datasets, respectively. Moreover, the proposed augmentation technique utilizing ChatGPT yielded improvements of +3.55% and +4.83% on the same datasets.

SIMILARITY-BASED ROUGH SET APPROACH IN INCOMPLETE INFORMATION SYSTEM USING POSSIBLE EQUIVALENT VALUE-SET

Asma’ Mustafa — 2024-04-30

Data analytics generally helps businesses or entities to make better and efficient decision making. But in the face of growing volume of data or information, it becomes challenging to achieve these goals. One of which is on classification of information with high accuracy. Furthermore, when the information is incomplete, definitely it is more challenging in order to classify the information with high accuracy. Although incomplete information is well discussed using rough set theory for data classification, such as based on tolerance and similarity relations, there are still issues on accuracy to evaluate data classification. The main objective of this paper is to introduce a new similarity approach with semantically justified based on possible equivalent value-set related to incomplete information systems. It is based on a classification of three semantics types of incomplete information i.e., “any value”, “maybe value” and “not applicable value” for modelling similarity. Subsequently, the similarity precision between objects in incomplete information systems is considered. The comparative studies and simulation results between the proposed approach in terms of accuracy on synthetic data, four well-known classification datasets and one real marine dataset are presented. The proposed approach improves the accuracy up to two orders of magnitude and, thus verifying its data classification accuracy.