IAES International Journal of Artificial Intelligence (IJ-AI)
Not a member yet
1769 research outputs found
Sort by
Enhancing plagiarism detection using data pre-processing and machine learning approach
Get PDFModern technology and the internet have enhanced academic information accessibility, but this has led to a rising global concern about plagiarism. Researchers are actively exploring machine learning as a promising solution for detection. This study underscores the importance of robust data preprocessing for optimal machine learning algorithm performance. Using a dataset of 67 research papers, big five factors (OCEAN), and plagiarism rates, the study employed machine learning to detect plagiarism. The training process involved exposing algorithms to an 80% training subset, followed by evaluating their performance on the remaining 20% in the testing phase, assessing generalization capabilities. For the random forest regressor, bagging regressor, gradient boosting regressor, XGB regressor, and AdaBoost regressor, corresponding root mean squared error (RMSE) are 9.48, 10.66, 11.79, 12.53, and 12.79, respectively. This research contributes novel insights to existing literature by introducing a plagiarism detection model that innovatively integrates outlier detection, normalization, missing value imputation, and feature selection. The unique aspect lies in the effective combination of feature selection and missing value imputation, surpassing previous benchmarks and optimizing precision and efficiency. The approach is metaphorically likened to assembling puzzle pieces, highlighting the distinctive methodology employed in enhancing the performance of the plagiarism detection model using data preprocessing
Deep neural network for maximizing output power estimation of dual-axis solar tracker
Get PDFThe abundance of solar energy sources has encouraged many researchers to maximize solar photovoltaic (PV) output power using dual-axis solar tracking. However, environmental conditions, time of day, and the angle of movement of the solar tracker can affect the resulting power output. This study aims to predict the power output of dual-axis solar tracking in order to maintain the powerโs stability and quality. Deep neural networks (DNN) with variations of 5 and 6 hidden layers have been proposed. The dataset used in this study was obtained from observation results and then divided into 80% training data and 20% testing data. A series of algorithms are used to recognize relationship patterns between input and hidden layers, between hidden layers, as well as hidden layers and output. Statistical results show that DNN with a variation of 6 hidden layers is better at estimating solar tracking power output with a mean absolute percentage error (MAPE) value of 12.328%, mean square error (MSE) of 0.332, and mean absolute error (MAE) of 0.425. This study can be used as a reference in utilizing artificial intelligence to predict the output power of solar panels as a renewable energy source
A hybrid model for handling the imbalanced multiclass classification problem
Get PDFData in many application domains is imbalanced. In machine learning, addressing imbalanced data is crucial to prevent bias towards the dominant class label and ensure that prediction models can learn and predict the minority class proficiently. This paper proposes a hybrid imbalanced classification model (HICD) to address the multiclass imbalanced data problem. The primary idea is to combine effective methods to construct a classification model that can handle multiclass imbalanced data effectively. Four methods are employed: an oversampling method to balance the data, a decomposition method to convert the multiclass problem into a set of binary problems, ensemble classification to integrate base classifiers to improve prediction, and a boosting method to encourage the classifier to pay more attention to misclassified samples. To evaluate the proposed model, seventeen imbalanced datasets from various application domains, featuring different numbers of classes, instances, features, and imbalance ratios, are assessed. The experimental results and statistical significance tests demonstrate that the proposed hybrid model significantly outperforms the standard one-vs-one (OVO) approach and the OVO combined with oversampling technique (SMOTE), both considered state-of-the-art for addressing imbalanced multiclass datasets, in terms of F1-score
Insights from the vision-mission statements of Philippine and other ASEAN universities: a K-means clustering analysis
Get PDFThis study analyzed the vision and mission statements (VMS) of 117 Philippine state universities and colleges (SUCs) and compared them with 330 other ASEAN universities to identify thematic trends and institutional priorities. Using web scraping and K-means clustering, the study identified thematic clusters in VMS. Thematic trends through word frequency and collocation analyses provided further insights and a comparative analysis examined differences between Philippine SUCs and other ASEAN universities. Philippine SUCsโ vision statements formed three clusters: global competitiveness, premier recognition, and regional leadership in science and technology. Mission statements clustered into: mandated functions, global innovation, and advancement in the sciences. Philippine SUCs emphasized institutional prestige, workforce development, and sustainability while other ASEAN universities focus more on knowledge creation, student empowerment, and internationalization. Philippine SUCs aligned their VMS with national development and global ranking metrics and prioritizes institutional recognition and economic contributions more than the other ASEAN universities. Future studies should expand to more private institutions and international comparisons to assess broader higher education trends
A novel method for examining promoters using statistical analysis and artificial intelligence learning
Get PDFAccurately classifying promoters has become a significant focus in bioinformatics research. Although numerous studies have attempted to address this challenge, the performance of existing methods still leaves room for improvement this study, statistical feature analysis has been applied to the features that have been developed in our previous work. This approach extracted additional informative features from basic sequence characteristics and then used them together with the original and newly engineered features. Utilizing statistical feature analysis enhanced key patterns, which lead to an improvement in the accuracy of the promoter classification. Results demonstrated that our proposed method outperforms other models that use only basic features. The value of the area under the curve (AUC) of 0.83958 achieved when using the combined feature set confirmed the effectiveness of our approach. Furthermore, the AUC value reached 1 when these optimized features were used with naive Bayes (NB) classifier, referring to the strength of incorporating statistical analysis into feature design
Inverse-Mel scale spectrograms for high-frequency feature extraction and audio anomaly detection in industrial machines
Get PDFUnlike humans, the energies in industrial machine sounds (IMS) vary across a wide range of frequencies. Mel scales, which are developed for the perception of human audio, fail to capture the complete information present in IMS. To improve performance, we propose using an inverse-Mel scale, along with the concatenation and combination of Mel and inverse-Mel scale based spectrograms, as feature vectors for audio anomaly detection (AAD) in industrial machines. Adaptation in the Librosa Python package and the DCASE 2022 Challenge Task 2 baseline system is pursued for the construction of inverse-Mel scale spectrograms. Experiments are conducted using the malfunctioning industrial machine investigation and inspection for domain generalization (MIMII DG) datasets. Systems based on the inverse-Mel scale achieve a maximum improvement of up to 37% in the bearing machine and an average improvement of up to 9% in the area under the curve (AUC) score across all machines in the MIMII DG datasets. The proposed features also enhance DG, overcoming the effects of environmental and operational domain shifts caused by variations in recording setup, load, background noise, and operational patterns. Challenge official evaluator assessed the proposed system against the evaluation datasets, ranking it three positions higher than the baseline system
Laurent series intelligent multidimensional object optimization classification for crop disease detection
Get PDFRice crop disease detection and its diagnosis methods are vitally important for the agriculture field to be sustainable. Traditional methods suffer from paddy yield, complex issues, and crop diseases, leading to inefficiencies in the agriculture domain. Our research provides space for a novel approach, combining the Laurent series with an intelligent multidimensional object optimization (LIMO) classification framework based on generative adversarial networks (GANs) to recognize various types of crop diseases in agricultural fields. Through our proposed research work, IoT nodes sense the values of the field crop, and gathered information is shared with processing units through base station communication. Multi-objective and cognitive learning routing (MOCLEAR) protocol supports choosing the optimal path for data transmission improvement. Then, for image segmentation, GAN combined with cognitive residual convolution network (CRCNet) is modified to segment values from input images. After receiving segment input images, perform feature extraction and classification using significant attributes. The proposed Laurent series with IMO is newly formulated by integrating the Laurent series with Intelligent IMO algorithms. Through extensive experimentation and analysis, the proposed LIMO-based GAN network provides effective and improved performance metrics with overall accuracy, sensitivity, and specificity values at 91.5%, 92.6%, and 92.41%, respectively.
Comparative analysis of gender classification methods using convolutional neural networks
Get PDFGender classification has become an important application in the fields of system automation and artificial intelligence, having important implications across various fields. The main challenge in this classification task is the variation in illumination that affects the quality of facial images. This study presents a method for identifying genders with Convolutional Neural Networks (CNNs). To address this issue, various preprocessing methods are applied, including Self Quotient Image (SQI), Histogram Equalization, Locally Tuned Inverse Sine Nonlinear (LTISN), Gamma Intensity Correction (GIC), and Difference of Gaussian (DoG), to stabilize the effects of illumination variations before the images are processed by the CNN. The CNN architecture used consists of 5 convolutional blocks and 2 fully connected blocks, which have proven effective in image recognition. The results of the study show that the model trained with the DoG method achieved an accuracy of 91.07%, making it the best preprocessing technique compared to other methods such as SQI and HE, which achieved accuracies of 90.39% and 88.76%, respectively. These findings demonstrate that the application of SQI in CNN can improve the accuracy of gender classification on facial images, providing better performance than previous methods. These findings are expected to serve as a foundation for further developments in facial image classification and its applications in various fields
Unpacking the drivers of artificial intelligence regulation: driving forces and critical controls in artificial intelligence governance
Get PDFThe burgeoning field of artificial intelligence (AI) necessitates a nuanced approach to governance that integrates technological advancement, ethical considerations, and regulatory oversight. As various AI governance frameworks emerge, a fragmented landscape hinders effective implementation. This article examines the driving forces behind AI regulation and the essential control mechanisms that underpin these frameworks. We analyze market-driven, state-driven, and rights-driven regulatory approaches, focusing on their underlying motivations. Furthermore, critical regulatory controls such as data governance, risk management, and human oversight are highlighted to demonstrate their roles in establishing effective governance structures. Additionally, the importance of international cooperation and stakeholder collaboration in addressing the challenges posed by rapid technological change is emphasized. By providing insights into the strengths, weaknesses, and potential synergies of different governance models, this study contributes to the development of equitable and effective AI regulatory frameworks that encourage innovation while safeguarding societal interests. Ultimately, the findings aim to inform policymakers, industry leaders, and civil society organizations in their efforts to foster a future where AI is utilized responsibly and equitably for the betterment of humanity
Backpropagation neural networks for solving gas flow equations in porous media
Get PDFThis study proposes a backpropagation neural network (BPNN) as an alternative solver for nonlinear equations in gas flow simulation through porous media. Conventional solvers like the Newton-Raphson (N-R) method are accurate but may become inefficient for large-scale or heterogeneous systems. We develop a feedforward BPNN architecture with adaptive learning rates to solve discretized residual equations from the one-dimensional gas flow model. The methodology includes finite difference discretization and mapping the nonlinear algebraic system into a four-layer neural network. The BPNN solver is validated against the Newton method across various grid sizes and heterogeneous permeability-porosity distributions. Results show that BPNN achieves high accuracy, with maximum absolute errors (MAE) of only 0.241 psi in the homogeneous model and 0.0418 psi in the heterogeneous model. While the BPNN requires more iterations and longer computation time, especially for finer grids, it exhibits the ability to learn pressure patterns and improve efficiency over time. This approach demonstrates that BPNN can serve as a viable nonlinear solver in reservoir simulation, offering flexibility in handling nonlinearities while maintaining accuracy