Phankokkruad, Manop
Loading...
Preferred name
Phankokkruad, Manop
Main Affiliation
Email
manop.ph@kmitl.ac.th
28 results
Now showing 1 - 10 of 28
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Classification of file duplication by hierarchical clustering based on similarity relations(2018-06-21)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 yourconsent settings
Item type:Publication, Comparative study of text-to-speech synthesis techniques for mobile linguistic translation process(2014-03-30) - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Identification, counting, and sizing of dispersed phase droplet of scanning electron microscopy micrograph using digital image processing(2012-12-01); Wacharawichanant, SiriratThe identification of dispersed phase droplet in scanning electron microscopy (SEM) image is the heart of the process polymer blends, especially for the development of the polymeric materials and improvement of the polymer properties. Manual identification is the hard work and inaccurate method. To solve this problem, a digital image processing (DIP) method based on Hough transform is proposed for automatically identifies the dispersed phase droplet in SEM images. By combining the characteristics of SEM images and the DIP method, this method performed hierarchical Hough transform on the circular droplet to detect the object boundary in the SEM images. The DIP method has been experimented on variety of SEM images and very promising results have been achieved given more accuracy. Experimental results show that the proposed method with high adaptability is more accurate and rapidly than the traditional method. © 2012 IEEE. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, An application of convolutional neural network-long short-term memory model for service demand forecasting(2019-07-01); Wacharawichanant, SiriratThe medical services are very important requirement for being healthy human. In order to ensure the availability of resources for the medicine needed, the most hospital makes an service demand estimation by forecasting a number of patients to provide the sufficient medical services. Therefore, the accurately forecast a number of patients would be valuable knowledge for managing. This work proposed the CNN-LSTM model, which was a combination of CNN and LSTM, to forecast the number of patients who used hospital services. The CNN model was used to interpret, and extract the features from the input data. Then, it was provided this information to the LSTM model for interpreting and making a forecast. The CNN-LSTM models were applied to forecast on the two datasets. The results indicated that CNN-LSTM model made reliable forecasting. This work measured the model performnace by calculating RMSE and MAE value. The result showed RMSE and MAE of the models were very low in all experiments. Forecasting the number of patients can help the hospital to estimate the service demand, make a better policy for managing the medical resources on demand, and improve the efficiency of medical services for the future. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, An improvement of recommender system to find appropriate candidate for recruitment with colloborative filtering(2015-09-28) - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Analysis of interaction user interface patterns and usability study in computer assisted instruction for Tablet PC(2014-03-30) - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Morphology and Properties of Poly(Lactic Acid) and Ethylene-Methyl Acrylate Copolymer Blends with Organoclay(2017-10-25) - Some of the metrics are blocked by yourconsent settings
Item type:Publication, An evaluation of technical study and performance for real-time face detection using Web Real-Time Communication(2015-08-24); Jaturawat, PhichayaThis paper proposed the technical study of real-time face detection system and also cover a key technology. In order to find the most appropriate factors, techniques, and algorithm by evaluating the performance that included connection speed, and effectiveness of tracking and detecting a human face in various conditions. WebRTC worked perform in any condition of device and platform independence. Furthermore, WebRTC could operate securely on the HTTPS protocol. In the case of the transferring ability of images, it relied on the connection speed; that LAN and WiFi are the most prefer for this best image quality. The results shown that Haar-like feature and CLM have significantly detected the face area over the web browser in almost light conditions. However, Haar-like has the better precision when operated on the low-speed processor. The real-time face detection system could be identified the person who walked through the capture device. In addition, this proposed system could be applied to any scope of the personal identification system. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, A Comparison of Extreme Gradient Boosting and Convolutional Neural Network-Long Short-Term Memory for Service Demand Forecasting(2019-01-01); Wacharawichanant, SiriratThe accurate demand forecasting gives powerful insights on amount of the available resources should be allocated for the operation and can improve the effectiveness of the management to assure the completeness of the services. This work studied to forecast the number of patients, that applied for service demand forecasting. We proposed the comparison between XGBoost model and CNN-LSTM model for service demand forecasting. We created the XGBoost model and configured the optimal parameters by using grid search optimization techniques. In the same way, the CNN-LSTM model was constructed and adjusted the layers in the network structure. Later, the model has configured the optimal parameters obtained from the grid search optimization techniques. Both models were applied to two different datasets for forecasting the number of patients in the future. The results indicated that two models had skillful, and made the reliable forecasting in two datasets. This work evaluated and measured the model performance by calculating RMSE, and sMAPE, which was acceptable in all case study. The CNN-LSTM model gave better efficiency forecasting than XGBoost model. In contrast, XGBoost model operated faster, took a lower performing time, and lower CPU consumption than the CNN-LSTM model. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Convolutional neural network models for deep face recognition on limitation and interfering factors in image dataset(2018-09-14)Face recognition is one of effective method often used for personal identification, the accuracy of the face recognition depends on many factors typically implemented at different places in unconstrained environments. Not only, the amount of images in the dataset are affected to the accuracy of face recognition but also the quality of the images is also an impact. For this reason, this work proposed the convolutional neural networks model to improve the accuracy of the face recognition under an insufficient a number of images in dataset and the images that contains an interfering factors. The challenge of this work is the regulating and configuring of many parameters the network for its best performance and suite for this conditions. The experiment results shown that the CNN model gives encouraging accuracy of the face recognition. Furthermore, this work also compared the accuracy with the different face recognition techniques such as Fisherfaces, Eigenfaces, LBPH, and MLP neural networks. For these result, CNNs were used as an efficient solution for improving the rate of recognition accuracy on this conditions.