Nineteenth International Conference On Computer Applications (ICCA 2021)https://onlineresource.ucsy.edu.mm/handle/123456789/26042024-03-28T12:58:00Z2024-03-28T12:58:00ZLocation Tracking of Accident Detection on Expressway for Informing Nearest Rescue ServiceAung, Nay WinThein, Thin Lai Laihttps://onlineresource.ucsy.edu.mm/handle/123456789/27412022-07-05T05:50:22Z2021-02-25T00:00:00ZLocation Tracking of Accident Detection on Expressway for Informing Nearest Rescue Service
Aung, Nay Win; Thein, Thin Lai Lai
In order to reduce the risks related to the expressway vehicle accidents, it is considered that the timely hazard information and the prompt rescue operations are the vital elements to save the victims and users of the expressway. In addition, the modern technologies such as video surveillance, alarm units, high-technology sensors assist to detect the victim's latest position and send the fast notification to the rescue services. In this paper, to detect the victims of automobile accidents, the Motion Sensing Method assists to evaluate the values received from the sensors of accident detection system to categorize the level of accident such as minor, major and critical while the Difference Angle Method supports to indicate the accurate angle direction of the vehicle based on the GPS values. To enhance the accuracy of data analyzation, the Modern Positioning Method is opted to track the victims constantly by using the signals, which are transmitted from the victims' smartphones to the base stations such as available mobile networks. Moreover, the Object Detection in Fence Algorithm assists the victims to receive the medical support from the rescue services within a short period of time. This system is aimed to be a user-friendly system; thus, the prescribed algorithm and methods are dedicated to apply with built-in technology sensors. Therefore, the location tracking and accident detection system can easily identify the precise accident place by using Geofence technologies and GPS, connecting with the mobile network.
2021-02-25T00:00:00ZText Extraction and Recognition System for Myanmar Warning Signboard ImagesZaw, Kyi PyarWar, Nuhttps://onlineresource.ucsy.edu.mm/handle/123456789/27402022-07-05T04:45:23Z2021-02-25T00:00:00ZText Extraction and Recognition System for Myanmar Warning Signboard Images
Zaw, Kyi Pyar; War, Nu
Text extraction and character recognition are the computer vision tasks which became important after smart phones with good camera. Character recognition from scene text images is still challenging area, because the camera captured text images have various background noise and the text also varies in shape, font, color. In this research, a camera captured based text extraction and character recognition system is developed for Myanmar warning text images. One major challenge of this research is that Myanmar OCR system has been greatly under-researched on the camera captured images. This research therefore considers these challenges of Myanmar OCR system and proposes a new algorithm for segmentation and recognition of Myanmar script. In the character segmentation, zone-based character segmentation is performed using position and size of connected component objects. Combination of features with chain code, pixel density, a new shape-based features of boundary-centroid distance and centroid-boundary distance, are explored and exploited in recognition process. This system uses K-Nearest Neighbors (KNN) classifiers to recognize the segmented characters. From the experiment, this system achieves satisfied results 93.9% segmentation accuracy and 92.77% classification accuracy.
2021-02-25T00:00:00ZNoun-Noun Metaphor Identification in Myanmar LanguageOo, Sheinn ThawtarThida, Ayehttps://onlineresource.ucsy.edu.mm/handle/123456789/27392022-07-05T04:45:22Z2021-02-25T00:00:00ZNoun-Noun Metaphor Identification in Myanmar Language
Oo, Sheinn Thawtar; Thida, Aye
Figurative languages can be found in all areas of human activities, literary, discourse and conversation. Metaphor, which is one of the figurative languages, becomes a problem in natural language processing (NLP). In Myanmar language, there is a gap for specific work of metaphor in NLP research field. This paper presents about the identification of noun-noun metaphor by using Myanmar WordNet (MMWN) and additional resources, such as wordnet2sql, bilingual dictionary and compound noun corpus. In this work, step by step processing of noun-noun metaphor identification are explained in details. Sentences are used for the experiments and categorized in five domains. Semantic relations in the WordNets are used for metaphor identification (MI) and compound noun corpus is used to identified the literal usage. The experimental results of noun pairs extraction and metaphor identification are described in this paper. The precisions are 57% in News, 76% in Novels, 79% in Articles, 81% in Formal and 76% in Conversational sentences. The issues found in metaphor identification and overall discussion about these issues are also presented in this paper.
2021-02-25T00:00:00ZBroadcast Monitoring System using MFCC-based Audio FingerprintingHtun, Myo ThetOo, Twe Tahttps://onlineresource.ucsy.edu.mm/handle/123456789/27382022-07-05T04:45:21Z2021-02-25T00:00:00ZBroadcast Monitoring System using MFCC-based Audio Fingerprinting
Htun, Myo Thet; Oo, Twe Ta
An efficient broadcast monitoring system is really needed in Myanmar music industry to solve the issues of copyright infringements and illegal benefit-sharing between artists and broadcasting stations. In this paper, a broadcast monitoring system is proposed for Myanmar FM radio stations by utilizing Mel Frequency Cepstral Coefficient (MFCC) based audio fingerprinting. The proposed system is easy to implement and achieves the correct and speedy music identification even for noisy and distorted broadcast audio streams. In this system, we deploy an audio fingerprint database of 4,379 songs and broadcast audio streams of 3 local FM channels of Myanmar to evaluate the performance of the proposed system. Experimental results show that the system achieves reliable performance.
2021-02-25T00:00:00Z