Tipajin Thaipisutikul

Bio: Tipajin Thaipisutikul is an academic researcher from National Central University. The author has contributed to research in topics: Computer science & Artificial intelligence. The author has an hindex of 3, co-authored 14 publications receiving 20 citations. Previous affiliations of Tipajin Thaipisutikul include Mahidol University.

A collaborative filtering recommendation system with dynamic time decay

Abstract: The collaborative filtering (CF) technique has been widely utilized in recommendation systems due to the precise prediction of users' interests. Most prior CF methods adapted overall ratings to make predictions by collecting preference information from other users. However, in real applications, people’s preferences usually vary with time; the traditional CF could not properly reveal the change in users’ interests. In this paper, we propose a novel CF-based recommendation, dynamic decay collaborative filtering (DDCF), which captures the preference variations of users and includes the concept of dynamic time decay. We extend the idea of human brain memory to specify the level of a user’s interests (i.e., instantaneous, short-term, or long-term). According to different interest levels, DDCF dynamically tunes the decay function based on users’ behaviors. The experimental results show that DDCF with the integration of the dynamic decay concept performs better than traditional CF. In addition, we conduct experiments on real-world datasets to demonstrate the practicability of the proposed DDCF.

A Learning-Based POI Recommendation With Spatiotemporal Context Awareness.

Abstract: Due to the great advances in mobility techniques, an increasing number of point-of-interest (POI)-related services have emerged, which could help users to navigate or predict POIs that may be interesting. Obviously, predicting POIs is a challenging task, mainly because of the complicated sequential transition regularities, and the heterogeneity and sparsity of the collected trajectory data. Most prior studies on successive POI recommendation mainly focused on modeling the correlation among POIs based on users' check-in data. However, given a user's check-in sequence, generally, the relationship between two consecutive POIs is usually both time and distance subtle. In this article, we propose a novel POI recommendation system to capture and learn the complicated sequential transitions by incorporating time and distance irregularity. In addition, we propose a feasible way to dynamically weight the decay values into the model learning process. The learned awareness weights offer an easy-to-interpret way to translate how much each context is emphasized in the prediction process. The performance evaluations are conducted on real mobility datasets to demonstrate the effectiveness and practicability of the POI recommendations. The experimental results show that the proposed methods significantly outperform the state-of-the-art models in all metrics.

DAViS: A unified solution for data collection, analyzation, and visualization in real-time stock market prediction

Abstract: The explosion of online information with the recent advent of digital technology in information processing, information storing, information sharing, natural language processing, and text mining techniques has enabled stock investors to uncover market movement and volatility from heterogeneous content. For example, a typical stock market investor reads the news, explores market sentiment, and analyzes technical details in order to make a sound decision prior to purchasing or selling a particular company’s stock. However, capturing a dynamic stock market trend is challenging owing to high fluctuation and the non-stationary nature of the stock market. Although existing studies have attempted to enhance stock prediction, few have provided a complete decision-support system for investors to retrieve real-time data from multiple sources and extract insightful information for sound decision-making. To address the above challenge, we propose a unified solution for data collection, analysis, and visualization in real-time stock market prediction to retrieve and process relevant financial data from news articles, social media, and company technical information. We aim to provide not only useful information for stock investors but also meaningful visualization that enables investors to effectively interpret storyline events affecting stock prices. Specifically, we utilize an ensemble stacking of diversified machine-learning-based estimators and innovative contextual feature engineering to predict the next day’s stock prices. Experiment results show that our proposed stock forecasting method outperforms a traditional baseline with an average mean absolute percentage error of 0.93. Our findings confirm that leveraging an ensemble scheme of machine learning methods with contextual information improves stock prediction performance. Finally, our study could be further extended to a wide variety of innovative financial applications that seek to incorporate external insight from contextual information such as large-scale online news articles and social media data.

Automated Classification of Criminal and Violent Activities in Thailand from Online News Articles

Abstract: Criminal and violent activities are a universal concern that affects a society's nature of life and economic dynamics. With dramatically increasing crime rates, law enforcement agencies have begun to show attention in utilizing machine learning approaches to analyze crime patterns to protect their communities. However, there are only a few studies that carried out experiments to classify Thai crime news articles into their proper categories. Also, the comparison of various machine learning algorithms toward this task has still been under-investigated. Therefore, in this paper, we aim to develop a framework to automate the classification and visualization of criminal and violent activities from online Thai news articles. Six classifiers are employed to classify crime news articles into one of the five crime categories including Burglary, Drug, Murder, Accident, and Corruption. The results have shown that Support Vector Machine and Logistic Regression approaches outperform other classifiers in terms of Accuracy, Precision, Recall, and F-Measure metrics.

Feature line embedding based on support vector machine for hyperspectral image classification

Abstract: In this paper, a novel feature line embedding (FLE) algorithm based on support vector machine (SVM), referred to as SVMFLE, is proposed for dimension reduction (DR) and for improving the performance of the generative adversarial network (GAN) in hyperspectral image (HSI) classification. The GAN has successfully shown high discriminative capability in many applications. However, owing to the traditional linear-based principal component analysis (PCA) the pre-processing step in the GAN cannot effectively obtain nonlinear information; to overcome this problem, feature line embedding based on support vector machine (SVMFLE) was proposed. The proposed SVMFLE DR scheme is implemented through two stages. In the first scatter matrix calculation stage, FLE within-class scatter matrix, FLE between-scatter matrix, and support vector-based FLE between-class scatter matrix are obtained. Then in the second weight determination stage, the training sample dispersion indices versus the weight of SVM-based FLE between-class matrix are calculated to determine the best weight between-scatter matrices and obtain the final transformation matrix. Since the reduced feature space obtained by the SVMFLE scheme is much more representative and discriminative than that obtained using conventional schemes, the performance of the GAN in HSI classification is higher. The effectiveness of the proposed SVMFLE scheme with GAN or nearest neighbor (NN) classifiers was evaluated by comparing them with state-of-the-art methods and using three benchmark datasets. According to the experimental results, the performance of the proposed SVMFLE scheme with GAN or NN classifiers was higher than that of the state-of-the-art schemes in three performance indices. Accuracies of 96.3%, 89.2%, and 87.0% were obtained for the Salinas, Pavia University, and Indian Pines Site datasets, respectively. Similarly, this scheme with the NN classifier also achieves 89.8%, 86.0%, and 76.2% accuracy rates for these three datasets.

Spectral–Spatial Feature Tokenization Transformer for Hyperspectral Image Classification

Abstract: In hyperspectral image (HSI) classification, each pixel sample is assigned to a land-cover category. In the recent past, convolutional neural network (CNN)-based HSI classification methods have greatly improved performance due to their superior ability to represent features. However, these methods have limited ability to obtain deep semantic features, and as the layer’s number increases, computational costs rise significantly. The transformer framework can represent high-level semantic features well. In this article, a spectral–spatial feature tokenization transformer (SSFTT) method is proposed to capture spectral–spatial features and high-level semantic features. First, a spectral–spatial feature extraction module is built to extract low-level features. This module is composed of a 3-D convolution layer and a 2-D convolution layer, which are used to extract the shallow spectral and spatial features. Second, a Gaussian weighted feature tokenizer is introduced for features transformation. Third, the transformed features are input into the transformer encoder module for feature representation and learning. Finally, a linear layer is used to identify the first learnable token to obtain the sample label. Using three standard datasets, experimental analysis confirms that the computation time is less than other deep learning methods and the performance of the classification outperforms several current state-of-the-art methods. The code of this work is available at https://github.com/zgr6010/HSI_SSFTT for the sake of reproducibility.

Cost-aware job scheduling for cloud instances using deep reinforcement learning

Abstract: As the services provided by cloud vendors are providing better performance, achieving auto-scaling, load-balancing, and optimized performance along with low infrastructure maintenance, more and more companies migrate their services to the cloud. Since the cloud workload is dynamic and complex, scheduling the jobs submitted by users in an effective way is proving to be a challenging task. Although a lot of advanced job scheduling approaches have been proposed in the past years, almost all of them are designed to handle batch jobs rather than real-time workloads, such as that user requests are submitted at any time with any amount of numbers. In this work, we have proposed a Deep Reinforcement Learning (DRL) based job scheduler that dispatches the jobs in real time to tackle this problem. Specifically, we focus on scheduling user requests in such a way as to provide the quality of service (QoS) to the end-user along with a significant reduction of the cost spent on the execution of jobs on the virtual instances. We have implemented our method by Deep Q-learning Network (DQN) model, and our experimental results demonstrate that our approach can significantly outperform the commonly used real-time scheduling algorithms.

Exploring an Efficient POI Recommendation Model Based on User Characteristics and Spatial-Temporal Factors

Abstract: The advent of mobile scenario-based consumption popularizes and gradually maturates the application of point of interest (POI) recommendation services based on geographical location. However, the insufficient fusion of heterogeneous data in the current POI recommendation services leads to poor recommendation quality. In this paper, we propose a novel hybrid POI recommendation model (NHRM) based on user characteristics and spatial-temporal factors to enhance the recommendation effect. The proposed model contains three sub-models. The first model considers user preferences, forgetting characteristics, user influence, and trajectories. The second model studies the impact of the correlation between the locations of POIs and calculates the check-in probability of POI with the two-dimensional kernel density estimation method. The third model analyzes the influence of category of POI. Consequently, the above results were combined and top-K POIs were recommended to target users. The experimental results on Yelp and Meituan data sets showed that the recommendation performance of our method is superior to some other methods, and the problems of cold-start and data sparsity are alleviated to a certain extent.

JAGAN: A Framework for Complex Land Cover Classification Using Gaofen-5 AHSI Images

Abstract: Owing to their powerful feature extraction capabilities, deep learning-based methods have achieved significant progress in hyperspectral remote sensing classification. However, several issues still exist in these methods, including a lack of hyperspectral datasets for specific complicated scenarios and the need to improve the classification accuracy of land cover with limited samples. Thus, to highlight and distinguish effective features, we propose a hyperspectral classification framework based on a joint channel-space attention mechanism and generative adversarial network (JAGAN). To relearn feature-based weights, a higher priority was assigned to important features, which was developed by integrating a two-joint channel-space attention model to obtain the most valuable feature via the attention weight map. Additionally, two classifiers were designed in JAGAN: sigmoid was used to determine whether the input data were real or fake samples produced by the generator, while Softmax was adopted as a land cover classifier to yield the prediction type labels of the input samples. To test the classification performance of the JAGAN model, we used a self-constructed complex land cover dataset based on GaoFen-5 AHSI images, which consists of mixed landscapes of mining and agricultural areas from the urban-rural fringe. Compared with other methods, the proposed model achieved the highest overall classification accuracy of 86.09%, the highest kappa amount of 79.41%, the highest F1 score of 85.86%, and the highest average accuracy of 82.30%, indicating the JAGAN can effectively improve the classification accuracy for limited samples in complex regional environments using GF-5 AHSI images.