IAES International Journal of Artificial Intelligence (IJ-AI)
Not a member yet
1769 research outputs found
Sort by
Comparison of feature extraction and auto-preprocessing for chili pepper (Capsicum Frutescens) quality classification using machine learning
Get PDFThe low-cost camera for machine vision, such as a webcam, still has a problem with resolution noise. Therefore, it is important to learn strategies to reduce noise from low-cost camera images so that they can be widely used for grading machines in the future. This paper aims to compare three feature extraction methods with auto-preprocessing to classify chili pepper (Capsicum Frutescens) quality using a machine learning algorithm. Three extraction methods were used, including the color feature, oriented FAST and rotated BRIEF (ORB), and the combination color feature and ORB. A total of 525 image data for quality chili pepper were collected using the webcam. The auto-preprocessing strategy to classify chili peppers can improve the performance of machine-learning algorithms for all data generated by the feature extractor. The performance of the chili paper quality classification model with auto-preprocessing of the variable color feature can improve the performance of machine learning algorithms by up to 64.21%. The performance improvement of the classification model using the ORB feature variable and the auto-preprocessing of up to 4.41%. The performance improvement of the classification model using machine learning algorithms is 11.27% when using the combination color feature and ORB feature and auto-preprocessing
Sectoral electricity micro-spatial load forecasting based on partitional clustering technique
Get PDFLoad demand forecasting is crucial in energy supply planning due to economic progress and territorial expansion, where land utilization transforms dynamically. An accurate sectoral load prediction can preclude the loss of beneficial opportunities arising from excessive load demand or excessive investment at a low-growth juncture. However, the particular area in this sectoral approach is still relatively large, rendering it incapable of precisely projecting load at minor points (micro-spatial). This study has proposed a micro-spatial load prediction strategy that categorizes identified areas into smaller grids or districts. This procedure includes clustering similar sites together for improved accuracy. K-Means is one of the partitional clustering approaches, a clustering algorithm utilizing object-based centroid-based partitioning approaches. The algorithm determines a cluster's centroid or centre as the average point for the cluster. This technique is advantageous as it can process extensive data efficiently and is appropriate for circular data. This technique can divide the data into multiple partitions, ensuring that each object belongs to precisely one cluster. Subsequently, mathematical modelling is used to predict the load of each cluster, which can then be utilized to more accurately evaluate the positions and sizes of prospective substations, transmission, and distribution facilities
Novel computational intelligence-based model for effective traffic management in intelligent transportation system
Get PDFThe evolution of intelligent transportation system (ITS) is essentially meant for upgrading the driving experience with more safety and accessibility of various analytical information from its extensive network. However, a significant gap is observed that doesn't cater up the complete demands of ITS. It has been also noted that computational intelligence (CI) based approach is slowly gaining pace in solving the transport related problems in ITS as compared to its other counterpart existing methodologies like artificial intelligence. The proposed manuscript introduces a novel computational framework towards assisting in relaying routing and navigational services using CI-based approach. A design of novel navigational controller unit is presented for global ITS scenario towards yielding an optimal decision of routing. The CI-based approach is implemented by integrating fuzzy process with evolutionary searching, learning and probability theory in most simplified form. The study also introduces a novel concept of relaying decision as feedback from navigational controller unit to specific vehicular node discretely unlike existing traffic controller system with an agenda to offer faster and effective clearance of queued vehicular nodes from target area. The study outcome shows higher consistency in its relay with better performance from existing study model in ITS
Defending against label-flipping attacks in federated learning systems using uniform manifold approximation and projection
Get PDFThe user experience can be greatly improved by using learning models that have been trained using data from mobile devices and other internet of things (IoT) devices. Numerous efforts have been made to implement federated learning (FL) algorithms in order to facilitate the success of machine learning models. Researchers have been working on various privacy-preserving methodologies, such as deep neural networks (DNN), support vector machines (SVM), logistic regression, and gradient boosted decision trees, to support a wider range of machine learning models. The capacity for computing and storage has increased over time, emphasizing the growing significance of data mining in engineering. Artificial intelligence and machine learning have recently achieved remarkable progress. We carried out research on data poisoning attacks in the FL system and proposed defence technique using uniform manifold approximation and projection (UMAP). We compare the efficiency by using UMAP, principal component analysis (PCA), Kernel principal component analysis (KPCA) and k-mean clustering algorithm. We make clear in the paper that UMAP performs better than PCA, KPCA and k-mean, and gives excellent performance in detection and mitigating against data-poisoning attacks.
A new efficient decoder of linear block codes based on ensemble learning methods
Get PDFError-correcting codes are used to partially or completely correct errors as much as possible, while ensuring high transmission speeds. Several machine learning models such as logistic regression and decision tree have been applied to correct transmission errors. Among the most powerful machine learning techniques are aggregation methods which have yielded to excellent results in many areas of research. It is this excellence that has prompted us to consider their application for the hard decoding problem. In this sense, we have successfully designed, tested and validated our proposed EL-BoostDec decoder (hard decision decoder based on ensemble learning-boosting technique) which is based on computing of the syndrome of the received word and on using ensemble learning techniques to find the corresponding corrigible error. The obtained results with EL-BoostDec are very encouraging in terms of the binary error rate (BER) that it offers. Practically EL-BoostDec has succeed to correct 100% of errors that have weights less than or equal to the correction capability of studied codes. The comparison of EL-BoostDec with many competitors proves its power. A study of parameters which impact on EL-BoostDec performances has been established to obtain a good BER with minimum run time complexity
Hybrid model for extractive single document summarization: utilizing BERTopic and BERT model
Get PDFExtractive text summarization has been a popular research area for many years. The goal of this task is to generate a compact and coherent summary of a given document, preserving the most important information. However, current extractive summarization methods still face several challenges such as semantic drift, repetition, redundancy, and lack of coherence. A novel approach is presented in this paper to improve the performance of an extractive summarization model based on bidirectional encoder representations from transformers (BERT) by incorporating topic modeling using the BERTopic model. Our method first utilizes BERTopic to identify the dominant topics in a document and then employs a BERT-based deep neural network to extract the most salient sentences related to those topics. Our experiments on the cable news network (CNN)/daily mail dataset demonstrate that our proposed method outperforms state-of-the-art BERT-based extractive summarization models in terms of recall-oriented understudy for gisting evaluation (ROUGE) scores, which resulted in an increase of 32.53% of ROUGE-1, 47.55% of ROUGE-2, and 16.63% of ROUGE-L when compared to baseline BERT-based extractive summarization models. This paper contributes to the field of extractive text summarization, highlights the potential of topic modeling in improving summarization results, and provides a new direction for future research
Autonomous radar interference detection and mitigation using neural network and signal decomposition
Get PDFAutonomous radar interference is a challenging problem in autonomous vehicle systems. Interference signals can decrease the signal-to-interference-noise ratio (SINR), and this condition decreases the performance detection of autonomous radar. This paper exploits a neural network and signal decomposition to detect and mitigate radar interference in autonomous vehicle applications. A neural network (NN) with four inputs, one hidden layer, and one output is trained with various signal-to-noise (SNR), interference radar bandwidth, and sweep time of autonomous radar. Four inputs of NN represent SNR, mean, total harmonic distortion (THD), and root means square (RMS) of the received radar signal. Variational mode decomposition (VMD) and zeroing based on a constant false alarm rate (CFAR-Z) are used to mitigate radar interference. VMD algorithm is applied to decompose interference signals into multi-frequency sub-band. As a result, the proposed neural network can detect radar interference, and NN-VMD-CFAR-Z can increase SINR up to 2dB higher than the NN-CFAR-Z algorithm
An improved convolutional recurrent neural network for stock price forecasting
Get PDFStock price forecasting is a challenging area of research, particularly due to the complexity and unpredictability of financial markets. The accuracy of prediction models is influenced by various factors, including nonlinearity, seasonality, and economic shocks. Deep learning has demonstrated better forecasts of stock prices than traditional approaches. This study, therefore, proposed a new approach to improve forecasting system based on an end-to-end convolutional recurrent neural network (CRNN) with attention mechanism. Our approach first investigates local stock price features using 1D convolutional neural network, and then employs a bidirectional long short-term memory (Bi-LSTM) network for forecasting. This model stands out by effectively utilizing contextual data and representing the temporal character of data. The Bi-LSTM is helpful for understanding the history and future contextual information since it uncovers both past and future contexts of stock data. Furthermore, integrating attention mechanism within the CRNN represents a significant improvement. This allows our model to handle long input sequences more effectively and capture the inherent stochasticity in stock prices, which is often missed by traditional models. The effectiveness of our approach is investigated using data on 10 stock indexes from Yahoo Finance. The results show that our method outperforms ARIMA, LSTM, and conventional methods.
Thai COVID-19 patient clustering for monitoring and prevention: data mining techniques
Get PDFThis research aims to optimize emerging infectious disease monitoring techniques in Thailand, which will be extremely valuable to the government, doctors, police, and others involved in understanding the seriousness of the spread of novel coronavirus to improve government policies, decisions, medical facilities, treatment. The data mining techniques included cluster analysis using K-means clustering. The infection data were obtained from the open data of the digital government development agency, Thailand. The dataset consisted of 1,893,941 cumulative cases from January 2020 to October 2021 of the outbreak. The results from clustering consisted of 8 groups. Clustering results determined the three largest, three medium-sized, and the two most minor numbers of infected people, respectively. These clusters represent their activities, namely touching an infected person and checking themselves. The components of emerging diseases in Thailand are closely related to waves, gender, age, nationality, career, behavioral risk, and region. The province of onset was mainly in Bangkok and its vicinity or central Thailand, as well as industrial areas. Adult workers aged 19 to 27 years and 43 to 54 years or over were seeds of new infection sources
Enhancing accessibility and discoverability of digital archive images through automated image recognition tool
Get PDFThis research paper presents a comprehensive evaluation of the effectiveness of Imagga and Google cloud vision application programming interface (API) as image recognition tools for generating metadata in digital archive images. The assessment encompasses a diverse range of archive images, including those without text, images with text, and both color and black-and-white images. Through the use of evaluation metrics such as cosine similarity, word overlap similarity, recall, precision, and F1 score, the performance of these tools is quantitatively measured. The findings highlight the strong individual performance of both Imagga and Google cloud vision API, with the combined metadata outputs achieving significantly higher scores across all metrics. This emphasizes the potential benefits of employing a combined approach, leveraging the strengths of multiple tools to enhance the reliability and robustness of the metadata extraction process. The findings contribute to the advancement of metadata management in digital archives and underscore the importance of utilizing multiple tools for improved performance in image metadata generation