ECTI Transactions on Computer and Information Technology (ECTI-CIT)

Development Cyber Risk Assessment for Intrusion Detection Using Enhanced Random Forest

Aomduan Jeamaon — 2024-09-14

In cybersecurity, the lack of statistical data on cyber-attacks presents a significant challenge from an insurance perspective, hindering the accurate calculation of insurance premiums, furthermore assessing cybersecurity risk exposure and identifying high-risk threat categories. Effective intrusion detection systems (IDS) are paramount in addressing these issues. This research introduces a sophisticated cyber risk assessment model utilizing the Random Forest classification algorithm, tailored explicitly for IDS, and leverages the comprehensive CIC-IDS 2017 dataset. The central objective was to engineer robust models capable of classifying a broad array of cyber threats, focusing on classification accuracy. The model achieved an accurate average classification rate of 96.94% through systematic experimentation and hyperparameter tuning.
This study found that 'n_estimators' values of 10 to 300 did not affect cyberattack performance. It was also shown that Bagging and bootstrapping improve model stability by mitigating variance and improving accuracy without many trees. Model performance was high, with an average F1-Score of 97.86%. Cyber-attack statistics are scarce, and from an insurance perspective, the lack of statistical data on cyber-attacks hinders the calculation of insurance premiums. Risk assessment allows for informed self-insurance or risk transfer processes ensuring that policies align with risk management strategies and premium calculations.

An Exponential Map-based Whale Optimization Algorithm (Exp-WOA) for Optimization

Vaibhav Godbole — 2024-09-14

This research work offers three variations of the Whale Optimization Algorithm (WOA) based on exponential chaotic maps, namely Logistic-Exponential-Logistic WOA (LEL-WOA), Logistic-Exponential-Sinusoidal WOA (LES-WOA), and Logistic-Exponential-Tent WOA (LET-WOA). The WOA with an exponential chaos-based mechanism is developed in this study to overcome the poor rate of convergence of the WOA and to prevent getting caught in local optimal solutions while dealing with the challenges. An exponential chaotic mechanism was employed in this research to initialize the agents and control the parameters of the exploration and exploitation phases of WOA. The proposed methodologies (Exp-WOA) are evaluated using twenty-three widely recognized test functions. The results demonstrate that the given solutions can enhance the performance of WOA by achieving optimal (minimum) values. The findings also indicate that LEL-WOA and LES-WOA exhibit faster convergence than WOA.

Wiener Filter with Convolutional Neural Network for Noise Removal in API-Based AI Models

Joel Ryan A. de Guzman — 2024-09-14

This research aims to develop a robust Application Program Interface (API)-Based Artificial Intelligence (AI) system for effective noise removal from audio signals, enhancing speech quality and intelligibility in noisy environments to be fed into different AI models to assess the applicant interview. The proposed methodology combines sophisticated signal processing techniques and noise reduction algorithms with AI models trained on clean voice data and noise patterns. To achieve this goal, we leverage two key components: the Wiener filter and a Convolutional Neural Network (CNN). The Wiener filter serves as the foundational noise reduction technique, exploiting statistical properties of the signal and the noise to suppress unwanted noise components effectively. Concurrently, CNN is integrated to classify the clean and noisy audio. In this research, the best optimizers selected, including Adam, SGD, RMSprop, Adagrad, and Adadelta are evaluated to identify the most suitable classification. The optimizers evaluated through cross-validation and hold-out validation in the same batch size (25) and epoch (25) were used. The study demonstrates that the Adam optimizer yields the best results. The epoch was optimized to 35, 75, 105, and 125 and epoch of 105 was selected with accuracy of 99.52%, Recall of 100%, F1-Score of 99.50%, and ROC_AUC of 99.99% for cross-validation while Accuracy of 98.79%, Recall of 99.21%, F1-Score of 98.81%, and ROC_AUC of 99.54% for hold-out validation, significantly improving AI model performance. Lastly, we ensured the batch size parameter was suitable for our model by tuning it with different settings (25, 50, 75, and 125) using the optimized optimizer and epoch. The batch size of 25 yielded the best accuracy. The modeled CNN also included kernel regularization L2 to avoid overfitting.

IoT malware detection and Mitigation in AMQP simulated Environment

Ajeet Kumar Sharma — 2024-09-21

Internet of Things(IoT) devices are increasing rapidly and providing an infrastructure to connect and share information. Attackers are targeting the IoT network and sending malicious Trac to IoT devices. Devices share large volumes of data, so malware is a security issue. IoT devices work in resource-constrained environments, and malware changes the trac pattern. Due to that, it is a challenging situation to detect malware. An optimized ensemble learning-based approach is applied to detect the malware by analyzing the behavior. Training models employ the NF-BoT-IoT dataset to understand benign and attack trac patterns. Multiple machine learning algorithms were evaluated on a given dataset, and observed that optimized ensemble learning performs best with an outstanding accuracy of 0.9915 and a precision of 0.9937. Another phase of the model mitigates malware by blocking attack IPs of Trac agged as malicious by the detection phase. The model's performance is evaluated in a simulated environment of advanced message queuing protocol(AMQP) using RabbitMQ broker. Future research directions will assist in further research work in enhancing the security of IoT infrastructure.

Development of Exporting Fresh Fruits Ontology for Improving the Knowledge-Based System on the Domain of Export Process in Thailand

Thanisorn Tangarommun — 2024-09-28

Thailand's exports are crucial to the country's economic income, with agricultural products among the most important. Import-export firms mainly manage the export process because agriculturists hesitate to deal with complex procedures. Based on the complex procedures and lack of knowledge about the export process, new entrepreneurs and agriculturists often struggle to export their products directly. Therefore, a simplied system is needed for those seeking information on export procedures. To address this, the Exporting Fresh Fruits Ontology was developed to en- hance the knowledge-based system for managing fresh fruit exports. This system involves three main steps: reviewing export processes and documents, generating ontology for the fresh fruit export domain, and developing the knowledge-based system. The Hozo Ontology Editor is the system's backbone, built using the Ontology-based Application Management (OAM) framework. The Exporting Fresh Fruits Ontology comprises 12 main classes, sub-classes, and attributes, capturing knowledge of the export process. It includes mappings between relational database entities and the ontology, capturing semantic information, and validating mapping consistency to eliminate errors. The results show that the Exporting Fresh Fruits Ontology performs well, achieving an average F-measure value of 0.98.

Removal of Fix Magnitude Impulsive Noise (FMIN) Through Innovative Recursive MDBUTMF Procedure

Vorapoj Patanavijit — 2024-09-28

This article proposes an innovative recursive modied decision based unsymmetrical trimmed median filter (RMDBUTMF) procedure for noisy overriding of digital photographs, which are eminently contaminated by FMIN. The proposed procedure reinstates the noisy photographical basis (which has magnitude at 0 or 255) by trimmed median magnitude (or the mean magnitude of all the free-noise photographical basis) in the computational photographical basis region under the recursive framework. The proposed procedure is experimented on distinctive digital photographs (Lena, Girl, Pepper and F16) on broad noise density and the proposed procedure reveals superior noisy-overridden photographs than the Mean Filter (MF), Median Filter (SMF), Adaptive Median Filter (AMF), Weight Median Filter (WMF), MDBUTMF in both Peak Signal-to-Noise Ratio (PSNR) and photographical quality.

BCS-Based Encoding Schemes for Monoview and Multiview Visual Configurations in WVSN Data Gathering: A Survey

G. L. Priya — 2024-09-21

Wireless Visual Sensor Network (WVSN) has become a valuable tool in addressing the evolving needs of modern monitoring systems. Encoding in WVSNs is a multifaceted process that involves compressing visual data, optimizing energy consumption, ensuring error resilience, and adapting to various network and application requirements. The associated lightweight encoders and the demand for less storage space make block compressive sensing (BCS) techniques suitable for WVSN applications where energy, bandwidth, and storage resources are limited. Based on the number of visual perspectives or camera angles available within a network for data capture, there are two primary congurations: monoview and multiview. This paper provides a comprehensive survey of dierent BCS-based encoding schemes used for data-gathering in both monoview and multiview scenarios within WVSNs. A comparative study of these algorithms based on compression level, computational complexity, relative gain in encoder energy, and reconstruction quality is performed. A BCS-based joint encoding scheme for multiview conguration that ensures a relatively high compression level is also proposed in this paper.

Multi-granularity self-attention mechanisms for few-shot Learning

Wang Jing — 2024-10-05

Few-shot learning aims to classify novel data categories with limited labeled samples. Although metric-based meta-learning has shown better generalization ability as a few-shot classification method, it still faces challenges in handling data noise and maintaining inter-sample distance stability. To address these issues, our study proposes an innovative few-shot learning approach to enhance image features' global and local semantic representation. Initially, our method employs a multiscale residual module to facilitate extracting multi-granularity features within images. Subsequently, it optimizes the fusion of local and global features using the self- attention mechanism inherent in the Transformer module. Additionally, a weighted metric module is integrated to improve the model's resilience against noise interference. Empirical evaluations on CIFAR-FS and MiniImageNet few-shot datasets using 5-way 1-shot and 5-way 5-shot scenarios demonstrate the effectiveness of our approach in capturing multi-level and multi-granularity image representations. Compared to other methods, our method improves accuracy by 2.63% and 1.27% for 5-shot scenes on these two datasets. The experimental results validate the efficacy of our model in significantly enhancing few-shot image classification performance.

Comparative Study on Stock Movement Prediction Using Hybrid Deep Learning Model

Neny Sulistianingsih — 2024-10-05

Applying machine learning techniques in stock market prediction has evolved significantly, with deep learning methodologies gaining prominence. Conventional algorithms such as Linear Regression and Neural Networks initially dominated but struggled to capture complex temporal dependencies in financial data. Recent research has explored deep learning architectures like LSTM and CNN and hybrids such as CNN-LSTM and LSTM-CNN, showcasing promising results. However, there's a gap in research comparing these models across different datasets, particularly in predicting stock movements. This study addresses this gap by conducting a comparative analysis of deep learning and hybrid models for stock movement prediction in the Indonesian banking sector. The evaluation based on RMSE and MAE reveals that the LSTM-CNN hybrid consistently outperforms other models, showcasing its versatility and accuracy across different data characteristics. Then, exploration through hyperparameter tuning demonstrates the criticality of parameter selection in optimizing model performance. These findings contribute to advancing predictive modeling in financial markets, offering valuable insights for investors, analysts, and policymakers. Further research in hyperparameter tuning and model optimization holds promise for enhancing accuracy and reliability in stock price prediction.

A Neural Architecture Search CNN for Alzheimer’s Disease Classification

Nicodemus Songose Awarayi — 2024-10-12

The evolution of automated machine learning (AutoML) is gradually reengineering the design of deep learning architectures for various imaging tasks. AutoML effectively develops model architectures and tunes hyperparameters through neural architecture search (NAS). Deep learning model architecture design is generally considered a tedious and time-consuming task that requires mastery skills to develop robust and better-performing models for imaging tasks. Again, the model's hyperparameters must be well-tuned to ensure optimal performances, which can be tedious and time-consuming if the hyperparameters are manually selected; using existing hyperparameter optimization algorithms can be expensive regarding resources. This study addresses these challenges in developing an optimal convolutional neural network (CNN) for classifying Alzheimer's (AD). The study, therefore, adopted a NAS approach to generate a CNN model architecture using a customized search space comprising only CNN patterns implemented with a NAS framework. The search was done for ten (10) trials, yielding a CNN architecture with an accuracy of 95.85% and a loss of 0.22. Training the model with a 10-fold cross-validation approach using a 0.0009 learning rate for 150 epochs improved the model's performance. The model recorded 97.17% accuracy, 97.21% precision, 97.14% recall, and a 0.99 area under the curve (AUC) in classifying AD as one of AD, mild cognitive impairment (MCI), and normal control (NC). The model obtained 98.06%, 98.66%, and 98.62% accuracy on binary classes of AD/NC, AD/MCI, and NC/MCI, respectively. The model generally showed robustness and better performance than existing CNN architectures.

A Period Prediction System for Sinhala Epigraphical Scripts using Ensemble CNNs and Attention Modules

Pabasara Surasinghe — 2024-10-12

Identifying the period of epigraphical scripts is crucial for archaeologists and others to determine the age of inscriptions. Since different sets and shapes of letters were used in different eras, identifying the period of an epigraphical script also aids in recognizing these scripts. An ideal period prediction system should detect the era of an epigraphical script in real time with high accuracy. The objective of this study is to develop an automated system to predict the period of Sri Lankan Sinhala epigraphical scripts. In the first stage, a dataset of Sinhala epigraphical letter images was created using 7,012 samples from estampage pictures of Sri Lankan inscriptions, addressing the absence of a proper dataset. The proposed approach is more efficient than previous models as it can detect the period of individual letters as well as the period of raw, whole estampage images. Moreover, the approach incorporates a mechanism to detect the period of letters from inscriptions written between two consecutive eras. An ensemble CNN model with attention modules is utilized to identify the eras of epigraphical scripts. Experimental results show that the proposed system achieves an average classification accuracy of 93.88% in identifying the era of individual letters. The system can automatically determine the era of an inscription by analyzing its estampage image within thirty seconds.

A Hybrid Prediction Model for Short-Term Load Forecasting in Power Systems

Zuriani Mustaffa — 2024-10-12

Short-term load forecasting (STLF) plays a vital role in effective power system management by assisting power dispatch centers in developing generation plans and ensuring smooth system operation. This study introduces a novel hybrid prediction model called iSSA-LSSVM to tackle the STLF challenge. By integrating the Salp Swarm Algorithm (SSA) with Least Squares Support Vector Machines (LSSVM), the iSSA-LSSVM model significantly improves LSSVM's prediction accuracy. One of the key contributions is the model's ability to autonomously ne-tune LSSVM hyperparameters, eliminating the need for manual adjustments and optimizing performance. Modifying the SSA within iSSA-LSSVM enhances the original algorithm's exploration and exploitation capabilities, ensuring better search efficiency and precision. Using a dataset with four independent variables as input and electrical power output as the target variable, the model demonstrates superior predictive performance. Comparative analysis with three other models shows that iSSA-LSSVM achieves a lower Mean Square Error (MSE) and faster convergence. This improvement in accuracy and efficiency enhances STLF, allowing power dispatch centers to develop more precise generation plans and ensure more reliable power system operation.

Brain Tumor Detection through Image Fusion Using Cross Guided Filter and Convolutional Neural Network

Srikanth M.V. — 2024-10-19

This Data fusion has become a significant issue in diagnostic imaging, particularly in medical applications like radiation and guided image surgery. Medical image fusion aims to enhance the precision of tumor diagnosis, by preserving the salient information and characteristics of the original images in the fused image. It has been shown that guided filters are capable of maintaining edges well. In this paper, we propose a novel cross-guided filter-based fusion approach for multimodal medical images utilizing convolutional neural networks. The cross-guided filter is used in the proposed algorithm to extract the detailed features from the source images. Convolutional neural networks are used to generate the feature weights of source images derived from the detail layers. The weighted average rule is used to merge the source images based on these weights. We used thirty distinct types of medical images from diverse sources to compare the effectiveness of the proposed strategy to that of existing methods, both numerically and visually. The experimental findings demonstrated that, in terms of both objective evaluation and qualitative image quality, the suggested system performs better than other standard methods already in use. The quantitative results show that compared to existing methods under consideration for comparison, the proposed algorithm improves mutual information by 25%, image entropy by 9.5%, spatial frequency by 21%, standard deviation by 18.1%, structural similarity index by 30%, and edge strength of the fused image by 39%.

Codepickle: Portable Python Grid Computing

Ekasit Tangmunchittham — 2024-10-19

We present Codepickle, a groundbreaking solution designed to overcome Python version constraints and enhance portability, especially within distributed Python grids and volunteer computing environments. Unlike existing serialization libraries such as Cloudpickle and Dill, which rely on Python bytecode and are prone to version conflicts, Codepickle offers a robust alternative. Our methodology includes innovative adjustments for function serialization and shared variable management. Experimental results reveal challenges like code sourcing and nonlocal variable handling. Performance benchmarks highlight Codepickle's significant advantages over Cloudpickle, including better portability and reduced message sizes. Notably, Codepickle achieves message sizes that are 84% of those produced by Cloudpickle especially for small code segments, with comparable execution performance. Proposed enhancements target critical issues such as lambda functions and cross-version compatibility. This comprehensive study not only demonstrates Codepickle's transformative potential but also underscores the ongoing quest for advanced serialization techniques in Python's distributed computing landscape.

Articial Intelligence - Driven Prediction of Health Issues in Infants - A Review

M. Ramya — 2024-10-26

Advances in technology and data availability have helped in improving the quality of care and in predicting health issues in infants. Currently, Information and Communication technology aids in reaching the essentiality and the applications of infant health to a greater extent. Over a few decades, researchers have dived into sensing and the prediction of Artificial Intelligence (AI) for infant health. Since these healthcare systems deal with large amounts of data, significant development is seen in several computing platforms. AI, including both machine learning (ML) and deep learning (DL), plays a crucial role in the medical industry in the prediction and classification of various infant diseases. The prediction of diseases in infants using extubation readiness and their utility ranges is still lacking. Thus, the present study aims to present a complete review of the adaption of ML and DL approaches to infant health prediction. The current review paper provides a complete overview of the research predicting infant health issues. Effectual comparisons are made among the AI approaches performing infant disease prediction. Furthermore, the paper identifies the research gaps and the future direction of the research in the present domain. A comprehensive form of analysis of the current landscapes involved in predicting infant health issues using AI is presented.