KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Search Results

Now showing 1 - 10 of 16

Some of the metrics are blocked by your
consent settings
Classification of Equatorial Ionospheric Irregularities Using Unsupervised Machine Learning Based on Spatiotemporal ROTI Keograms
(2025-01-01)
Mutasov, Gleb
;
Supnithi, Pornchai
;
Budtho, Jirapoom
;
Tongkasem, Napat
;
Nishioka, Michi
Equatorial ionospheric irregularities, particularly those associated with equatorial plasma bubbles (EPB), can significantly disrupt satellite navigation and communication systems. As the demand for reliable Global Navigation Satellite System (GNSS) and communication services grows, the prediction of ionospheric irregularities becomes critical. A key step in the prediction process is to identify distinct spatiotemporal patterns of irregularities, including day-to-day, longitudinal, and seasonal variations. However, with large datasets, manually classification or identification of these irregularities is a complex and challenging task. In this work, we propose unsupervised machine learning techniques to recognize and group irregularity patterns in large, unlabeled Rate of Total Electron Content (TEC) Index (ROTI) keograms. Specifically, two machine learning models: Gaussian Mixture Model and k-means clustering are employed. The ROTI keograms are constructed using GNSS data from two low-latitude receiver stations in Thailand. To reduce redundancy in the keogram images, three feature extraction techniques are applied before the clustering process. A comparative analysis is performed to determine the optimal number of clusters using these models. Based on the results, the optimal combination of feature extraction and clustering technique is determined for the proposed clustering model. The resulting k-means model with contour extractor classifies five distinct patterns of ionospheric irregularity patterns, providing valuable insights for enhancing EPB prediction models and deepening our understanding of ionospheric dynamics. Furthermore, these five irregularity patterns are analyzed in relation to space weather parameters such as the solar radio flux index (F10.7), and the geomagnetic index (Kp). The findings contribute to the development of robust prediction models, improving the reliability of satellite-based communication and navigation systems.
Some of the metrics are blocked by your
consent settings
Clustering Performance Comparison in K-Mean Clustering Variations: A Fraud Detection Study
(2022-12-01)
Chuenjarern, Nattaporn
;
Khonthapagdee, Subhorn
K-means clustering is a common clustering approach that is based on data partitioning. However, the k-means clustering has significant drawbacks, such as it is sensitive to deciding the initial condition. Several ways to improve the algorithm have been offered. To assess the algorithm's efficiency and correctness, the performance comparison should be evaluated. In this paper, several k-means algorithms, including random k-means, global k-means, and fast global k-means, were evaluated for their efficiency when applied to a fraud detection data set. The accuracy of each method and the Davies-Bouldin index was investigated for each algorithm to compare the clustering performance. The findings demonstrated that when a small number of groups was used, random k-means, global k-means, and fast global k-means gave similar clustering, but fast global k-means offered better errors when a big number of groups was used. Furthermore, global k-means took longer to execute than others.
Some of the metrics are blocked by your
consent settings
Thai stock news classification based on price changes and sentiments
(2022-01-01)
Netisopakul, Ponrudee
;
Saewong, Woranun
This research investigates the daily stock news influences toward a company's stock price direction in the Stock Exchange of Thailand. First, machine learning's text classification methods, namely, naïve Bayes, decision tree, random forest, support vector machine, and the three-layer and the five-layer backpropagation neural networks, are applied to predict the stock price directions using stock news collected during the year 2018. Then, the stock news sentiment is incorporated to help improve the prediction accuracy. Last, a meaningful grouping of stock news is carried out to further improve the direction prediction. The testing dataset collected from January to March 2019 stock news are used for model evaluations. The best accuracy obtained from the baseline dataset using stock news only is 78.6%. When dataset is augmented with sentiments and grouped, the best accuracy increases to 90.6%.
Some of the metrics are blocked by your
consent settings
Deterministic Initialization of k-means Clustering by Data Distribution Guide
(2022-01-01)
Sirikayon, Chaloemphon
;
Thammano, Arit
Clustering by the k-means is the most widely used method because of its ease of use. But the disadvantage of the k-means algorithm is that it relies on a random initialization. Therefore, the results obtained from each clustering are not stable depending on the starting point, affecting the results obtained in other applications. This paper, therefore, presents a method for determining the initialization of the k-means algorithm using the Data Distribution Guide (DDG). And use it as an aid in determining the starting point without random. Make the results of clustering always equal. And from the experimental results, We found that the accuracy obtained from clustering using the initialization from this method was good. Compared to the commonly used initialization designation.
Some of the metrics are blocked by your
consent settings
DASSL: Dynamic, AI-assisted, Scalable System for Labelling Used Bottle Images
(2020-09-21)
Daengphruan, Parnmet
;
Sangpetch, Orathai
;
Sangpetch, Akkarit
To ensure sustainable consumption and production, one way is to reduce waste generation by increasing the reuse rate. We have been working with the bottle classification facility to enhance the efficiency and productivity. Many used bottles come in with unimaginable ways of dirty, defective conditions. To manage the sheer volume of used bottles, we create an AI-enabled, bottle classification system. However, it requires many labelled images for training to improve accuracy. Unfortunately, the traditional approach, having human label individual images, is very time consuming. Even worse, it is not effective for our dataset because conditions of used bottles are not well defined and studied. From our experiments, the human experts cannot agree on the same labelling for similar bottle conditions, especially when impurities or defects are not separable objects. For 42%-99% of images in certain subcategories, human experts assign different labels to bottles with similar conditions. With huge inconsistency in data labelling, it deteriorates the accuracy of our classification models. To alleviate this problem, we propose a Dynamic, AI-assisted, Scalable System for Labelling used bottle images, called DASSL. DASSL employs multiple algorithms to extract and/or quantize different features of used bottle images, and cluster the images into groups with the supervision of human. With DASSL, we can achieve labelling consistency and improve scalability by reducing the data labelling time by at least 10x. To enhance agility, we can dynamically adjust DASSL to adapt to changes of cleaning machines' capabilities or bottle demand.
Some of the metrics are blocked by your
consent settings
Aircraft trajectory recognition via statistical analysis clustering for Suvarnabhumi International Airport
(2020-02-01)
Kamsing, Patcharin
;
Torteeka, Peerapong
;
Yooyen, Soemsak
;
Yenpiem, Siriporn
;
Delahaye, Daniel
Since Suvarnabhumi International Airport is considered to be the biggest airport in Thailand, a big travelling-hub of southeast Asia and plays a significant part to the economy of Thailand relying on the tourism industry, an aircraft trajectory recognition is essential to support the high traffic management system from around the world. The first and essential stage of airport capacity enhancement is descriptive-analytic in several sections of the airport, including flight trajectory behaviors in order to plan an improvement procedure in the future. This experiment deploys K-mean and Gaussian Mixture clustering to compare results by using available automatic dependent surveillance-broadcast (ADS-B) dataset provided by the bigdata system from various websites. The test varies the number of clustering from three to ten and measures how similar an object is to its cluster by using the Silhouette score. Gaussian Mixture clustering produces at least three unique flight trajectories when setting the number of clustering equal to four, giving the Silhouette score of 0.43. K-mean clustering with the number of clustering equal to ten gives the highest Silhouette score of 0.45. However, its routes are not clearly recognized when compared with the Gaussian Mixture clustering. Although the overall results are not clearly shown in the pattern, it is enough to describe the trajectory patterns of the aircrafts taking off or landing over Suvarnabhumi International Airport.
Some of the metrics are blocked by your
consent settings
Road Traffic Injury Prevention Using DBSCAN Algorithm
(2020-01-01)
Chantamit-o-pas, Pattanapong
;
Pongpum, Weerakorn
;
Kongsaksri, Krisakorn
Machine learning has been used in innovation research for the last two decades. It is widely applied in decision making such as clustering, analysis, predicting, evaluating prognosis, and recommendation. The car accident often causes death or disability in most countries. Road accident victims usually have poor quality of life because of serious illness, long-term disability, which is a huge burden to their families and some eventually died. The behavior of driving on road is a major risk factor to road traffic. This research develops a mobile application that can notify the driver when there is a risk nearby. It focuses on Thailand and it is applied only to local cases. The dataset comes from Thai Road Safety Collaboration (ThaiRSC), which is a non-governmental organization that records a lot of daily accident cases. It uses the DBSCAN algorithm, a clustering technique, for road traffic injury prevention applied on the ThaiRSC’s dataset that focused on 3 districts of Bangkok, namely Ladkrbang, Pravet, Suan Lung, as well as all province in eastern Thailand. The outcomes of this research are beneficial in warning drivers if they are likely to encounter a road accident.
Some of the metrics are blocked by your
consent settings
An improvement of extreme learning machine using subclass clustering
(2018-07-02)
Watchareeruetai, Ukrit
;
Jiramaneepinit, Boonnithi
Extreme learning machine (ELM) is an extremely fast learning algorithm proposed for a single-hidden-layer feed-forward neural network (SLFN). ELM projects a set of training instances into a random feature space, and then analytically calculates the weight matrix connecting between the hidden layer and the output layer, leading to a very fast learning speed. This paper proposes an improved version of ELM, named clustering-ELM, that assigns a subclass to each training instances and learns for a weight matrix that projects random features into subclass. In the prediction step, the responses from output nodes of the same class are integrated into one using maximum function. Experimental results conducted on various benchmark datasets reveal a promising performance of the proposed clustering-ELM, compared to the standard ELM.
Some of the metrics are blocked by your
consent settings
Classification of file duplication by hierarchical clustering based on similarity relations
(2018-06-21)
Phankokkruad, Manop
This paper have proposed the classification of the duplicate file by measuring the similarity score between the couple of files. This work examined the distance between the pairwise of files by the Smith-Waterman algorithm. In addition, the make use of the Euclidean distance matrix could identify the relativity between the persons who often copies the files each other. Since the regularity of the duplication happens, this work could classify the proximity to the persons, and a group of person who positioned closely together by applying the hierarchical clustering. The result revealed that the Smith-Waterman algorithms could measure the similarity between files effectively. Also, this work could analyze the relativity of the persons, classifies the person who positioned closely together, and the person between nearest related members of the group. Finally, this work represented the amount of time that person duplicated the files.
Some of the metrics are blocked by your
consent settings
Efficient Discovery of Traveling Companion from Evolving Trajectory Data Stream
(2018-06-08)
Puntheeranurak, Sutheera
;
Shein, Thi Thi
;
Imamura, Makoto
Trajectory data stream contain an enormous amount of data about spatial and temporal information of moving objects. Discovering useful pattern from moving objects can convey valuable knowledge to a variety applications such as transportation management, military surveillance, and weather forecasting by analyzing animal movement behaviors. In many real applications, trajectory data keep coming into the database or server for immediate analysis. Most moving objects' pattern discovery approaches analyze the data by re-computing from scratch. Now, existing some group pattern approaches incrementally illuminate this problem. However, there was still high computational time complexity to the efficient and accurate discovery of traveling together moving objects(i.e., traveling companion) from evolving data streams. In this paper, we propose micro-group based clustering algorithm over evolving data stream to reduce computational time complexity. Experiments of this proposed system will conduct on real taxi trajectory data and synthetic data.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results