4 research outputs found
Face Recognition Performance Improvement Using Derivative of Accumulated Absolute Difference Based on Probabilistic Histogram
No full textAbstractIn the paper we propose a face verifying algorithm for face recognition that can identify two face mismatch pairs in cases of incorrect decisions. The computational approach taken in this system is performed by the derivative of accumulated absolute difference between two faces unseen before. Unlike the traditional multi-dimensional distance measurement, the proposed algorithm also considers an increasing trend of accumulated absolute difference in respect to the Gaussian components. A Gaussian mixture model of bag-of-feature from training faces is also widely applicable to several biometric systems. Evaluation of the proposed algorithm is done on unconstrained environments using Labeled Face in the Wild (LFW) datasets. Experiments show that the proposed algorithm outperforms all conventional face recognition algorithms with advantage of about 4.92% over direct-bag-of-features and 18.05% over principal component analysis-based and is also appropriate for identification task of the face recognition systems. Furthermore, some particular advantages of our approach are that it can be applied to other verification systems
IKDSIFT: An Improved Keypoint Detection Algorithm Based-on SIFT Approach for Non-uniform Illumination
No full textAbstractIn this paper, we propose an improved keypoint detection algorithm of object-based recognition for non-uniform illumination, called IKDSIFT, which is implemented using the SIFT approach, morphological operations, Top-Hat filtering and various techniques in pre-processing procedures. The number of keypoint rate of data sets was compared. Data sets consist of three hundred 150x150 images and thirty 851x566 images with different uniform and non-uniform illumination. The experimental results show that the number of keypoint detection is reciprocal to peak selection thresholds. The best algorithm is the proposed IKDSIFT, followed by the SIFT. The ASIFT performs the worst. Additionally, the SIFT and ASIFT can detect some peak selection thresholds while the IKDSIFT can detect all ranges of the peak and obtains the best result comparing to other ones. Hence, the proposed algorithm looks promising to be used for recognizing under non-uniform illumination
Sentiment and Data Analysis of Mental Health Hotline in Thailand Based on Social Media by Machine Learning
No full textIntroduction
The Thai Mental Health Hotline has been utilized to help people with their mental health issues, bridging the gap in mental health access. However, no previous article has identified its drawbacks. Thus, this evidence on social media response might reflect real world feedback and show substantial impediments to providing mental health care via telepsychiatry in Thailand.
Objective
Our research aims to describe and analyze feedback on social media about receiving mental health services from the Thai Mental Health Hotline by using sentiment analysis, machine learning, visualization of data, and text analytics.
Method
Thai Mental Health Hotline comments were gathered manually from Facebook and Pantip, and automatically from Twitter by using related keywords. Data preparation and sentimental analysis were applied to interpret all comments by using WangchanBERTa, the latest and largest Thai language NLP model. Exploratory Data Analysis was performed through Python and Excel to clean and investigate trends of feedback by time. The negative opinion was focused to identify causes of adverse outcomes. The overall data was visualized to discuss and conclude the outcome.
Result
From 555 comments gathered from 2013-2020, 52.40% of the comments are neutral, followed by negative at 35.05%, and positive at 12.55%. The number of comments from social media were low from 2013 - 2019, and then rose extremely to climax (213 comments) during 2020. Focused on the complaints, most of them are about absent response issues (79.47% out of all negative response), service quality (13.16% out of all negative response) and others.
Conclusion
The peak of comment in 2020 may be influenced by Covid-19. Moreover, aside from neutral reactions, data suggest that there are more negative than positive responses. To deal with negative feedback, including absent response and poor service quality, more psychologists should be provided, and more expenditure should be spent on training consultants.
 
Model Predictive Control with Laguerre Functions for a Buoyancy-Driven Airship
No full textAbstractThe high altitude platform such as a buoyancy-driven airship has been receiving much attraction recently. However, to control the airship is challenging because of its complicated model. This paper applies model predictive control with Laguerre functions to the airship. The simulation results are given in this paper and show satisfaction regarding the proposed control method
