{"title":"Fill-a-Pix Puzzle as a SAT Problem","authors":"Aye Myat, Khine Khine Htwe, N. Funabiki","doi":"10.1109/AITC.2019.8920898","DOIUrl":"https://doi.org/10.1109/AITC.2019.8920898","url":null,"abstract":"Fill-a-Pix Puzzle is a Picture Logic Puzzle that has not been solved as a SAT Problem as well as there is no SAT Conjunctive Normal Form (CNF) Encoding Method to solve this puzzle yet. There are several practical SAT problems in various fields such as Artificial Intelligence (AI), Automatic Theorem Proving, Circuit Design, etc. Fill-a-Pix puzzle is also one of the SAT problems. This research proposes the SAT CNF Encoding Method to solve Fill-a-Pix Puzzle as a SAT Problem using SAT Solvers. The proposed SAT CNF Encoding Method will be executed on different standard SAT solvers – MiniSAT, CryptoMiniSAT and RSAT. The evaluation is presented regarding the CPU Execution Times of each solver for executing the proposed SAT CNF Encoding, the Number of Variables and Clauses produced by the proposed SAT CNF Encoding as well as the Comparison of Fill-a-Pix Puzzle with the other Similar Puzzles such as Sudoku and Slitherlink based on the Number of Variables and Clauses produced by the proposed SAT CNF Encoding when executing Puzzle Sizes above 50 × 50.","PeriodicalId":388642,"journal":{"name":"2019 International Conference on Advanced Information Technologies (ICAIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127057224","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Evaluation of TCP and UDP Traffic over Software-Defined Networking","authors":"May Thae Naing, Thiri Thitsar Khaing, A. Maw","doi":"10.1109/AITC.2019.8921086","DOIUrl":"https://doi.org/10.1109/AITC.2019.8921086","url":null,"abstract":"In Software-Defined Networking (SDN), the decoupling of control and data planes brings advantages in terms of logically centralized control and application programming. This paper presents an analysis of the SDN traffic flow based on the transmission control protocol (TCP) and the user datagram protocol (UDP) generated from source host to the destination host over SDN infrastructure. For system evaluation, the Mininet Emulator is used to build the SDN infrastructure, the Network Performance Measurement Tool (iPerf) to generate the traffic according to the specified command-line options, and the Wireshark packet analyzer analyzes the protocol especially TCP and UDP. The analysis shows throughput and packet loss in three network topologies: single, linear, and custom tree topology. According to the evaluation results, the throughput of TCP falls off dramatically during the retransmission sequence. In the evaluation of UDP traffic, the single topology can handle the packet loss, the linear topology can take place 10 ~ 30 % packet loss and the custom tree topology can only occur a negligible amount of packet loss in two testing environments.","PeriodicalId":388642,"journal":{"name":"2019 International Conference on Advanced Information Technologies (ICAIT)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129584731","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Melanoma Classification on Dermoscopy Skin Images using Bag Tree Ensemble Classifier","authors":"N. Lynn, Nu War","doi":"10.1109/AITC.2019.8920908","DOIUrl":"https://doi.org/10.1109/AITC.2019.8920908","url":null,"abstract":"Melanoma classification on dermoscopy skin images is a demanding work as a result of the low contrast of the lesion images, the intra-structural variants of melanomas, the much visually likeliness level of whether melanoma or non-melanoma lesions, and the covering of hair and ruler marker artifacts. In this study, the malignant melanoma skin cancer classification system is proposed with the aid of correctly classify melanoma skin cancer. The system involves three main steps: segmentation, feature extraction and classification. Ahead of the segmentation process, the preprocessing skin lesion images is processed for getting rid of the covered hair artifacts. In the segmentation step, the input preprocessed lesion image is segmented by using the proposed texture filter-based segmentation method. Then, the extraction of features with the underlying ABCD (Asymmetry, Border, Color, Differential Texture) dermatology rules using shape, edge, colored and textural features are computed from the segmented region. Lastly, the extracted features are classified to identify if the skin image is malignant melanoma or non-melanoma with the use of bag tree ensemble classifier. The system performance is evaluated with the use of the benchmarking datasets: PH2 dataset, ISBI2016 dataset and ISIC2017 dataset. According to the experimental results, the proposed design allows for both reliable classification of real world dermoscopy images and feasible operation time with today’s standard PC computing platforms. To address the class imbalance in the dataset and to yield the improved classification performance, the experiments are also analyzed not only on original imbalanced dataset but also on balancing datasets: undersampled and oversampled datasets. The system works well and provides both high sensitivity and specificity according to the experimental results on the oversampled dataset with bag tree ensemble classifier to leading to statistically better performance compared to original imbalanced dataset.","PeriodicalId":388642,"journal":{"name":"2019 International Conference on Advanced Information Technologies (ICAIT)","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126759081","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"C2Ont: An OWL Ontology Learning Approach from Apache Cassandra","authors":"N. Soe, Tin Tin Yee, Ei Chaw Htoon","doi":"10.1109/AITC.2019.8921025","DOIUrl":"https://doi.org/10.1109/AITC.2019.8921025","url":null,"abstract":"Big Data is a massive volume of both unstructured and structured data. It is crucial to efficiently represent big data as knowledge for data management. Ontologies provide knowledge as a formal description of a domain of interest. Therefore, the ontology learning approach is proposed for Apache Cassandra. It is composed of six mapping rules and converts OWL ontology from data in Cassandra by applying these mapping rules. NorthWind dataset is applied for demonstrating how to learn ontology from data in Cassandra. The evaluation result indicates that our approach can learn ontology in covering terminologically the modeled domain since the adequacy of extracted ontology is greater than 15%.","PeriodicalId":388642,"journal":{"name":"2019 International Conference on Advanced Information Technologies (ICAIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114557350","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Thazin Nwe, Tin Tin Yee, Ei Chaw Htoon, Junya Nakamura
{"title":"A Consistent Replica Selection Approach for Distributed Key-Value Storage System","authors":"Thazin Nwe, Tin Tin Yee, Ei Chaw Htoon, Junya Nakamura","doi":"10.1109/AITC.2019.8921008","DOIUrl":"https://doi.org/10.1109/AITC.2019.8921008","url":null,"abstract":"When the amount of data is increasing, most of the distributed key-value storage systems use the quorum based consistent replica selection algorithms for fault-tolerance and load balancing. These algorithms allow higher consistency because the quorum requires a majority of replicas to execute the request. The fewer failure nodes the system has, the higher the consistency. On the other hand, it has a high latency of a read/write request due to the static consistency level for a quorum. Higher read/write consistency level dramatically increases the read/write latency and is not suitable for accessing the updated version of the data and massive workload. We propose a consistent replica selection approach with dynamically changing the consistency level. The system distributes data in a distributed hash table for the write request. And the system searches the nearest replica with an existing consistent hashing algorithm instead of random selection and predicts the staleness rate with the Probability of Bounded Staleness (PBS) to select the consistent replicas for the read request. The experimental result shows that the proposed system reduces the staleness rate and the number of replicas by varying consistency level.","PeriodicalId":388642,"journal":{"name":"2019 International Conference on Advanced Information Technologies (ICAIT)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132640541","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Kyi Pyar Hlaing, Nyein Thwet Thwet Aung, Swe Zin Hlaing, K. Ochimizu
{"title":"Analysis of accident severity factor in Road Accident of Yangon using FRAM and Classification Technique","authors":"Kyi Pyar Hlaing, Nyein Thwet Thwet Aung, Swe Zin Hlaing, K. Ochimizu","doi":"10.1109/AITC.2019.8921119","DOIUrl":"https://doi.org/10.1109/AITC.2019.8921119","url":null,"abstract":"Road accidents are unpredictable and undetermined occurrence. Analysis of road accidents needs to understand the factor causing road accident severity. Careful analysis of road accident record is important to find out leading indicator factor for road accident. This paper introduces the analysis of severity factor using Functional Resonance Analysis Method (FRAM) that can be used an accident analysis method providing a new concept for people to analyze accidents. It also applies Naïve Bayes (NB) Algorithm is one of the classification techniques and based on probability models that incorporate strong independence assumptions. In this paper, firstly, FRAM shows the model of analysis of road accident. Secondly NB algorithm applies to calculate the probability of severity level attribute. Finally, this paper shows some experiment of the real dataset of road accident in Yangon by applying the actual scenario. The result shows that the performance variability from the function of the model such as accident time, causes of accident reason and type of vehicle are important factor to lead the level of road accident severity.","PeriodicalId":388642,"journal":{"name":"2019 International Conference on Advanced Information Technologies (ICAIT)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123175791","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Foreground Objects Segmentation in Videos with Improved Codebook Model","authors":"S. Aung, Nu War","doi":"10.1109/AITC.2019.8921193","DOIUrl":"https://doi.org/10.1109/AITC.2019.8921193","url":null,"abstract":"Extraction of foreground objects in real-time is a significant topic for applications in computer vision. Most of the proposed techniques use background subtraction technique to detect moving or static foreground objects in the scene. Despite ongoing lots of research, the domain has not reached mature status and needs more advanced and improved solutions. In this proposed system, background subtraction is done by improved codebook model-based method to get segmented foreground objects. In background modeling, the L*a*b* color space is used instead of RGB color space. This method has been tested with standard datasets and the accuracy of segmentation results are also evaluated. The experimental results demonstrate that the proposed method perform well under difference background subtraction challenges such as dynamic background, shadow, illumination changes and bad weather.","PeriodicalId":388642,"journal":{"name":"2019 International Conference on Advanced Information Technologies (ICAIT)","volume":"03 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127200766","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Optimized Resource Allocation Model in Cloud Computing System","authors":"Thura Win., Tin Tin Yee, Ei Chaw Htoon","doi":"10.1109/AITC.2019.8920852","DOIUrl":"https://doi.org/10.1109/AITC.2019.8920852","url":null,"abstract":"The resource allocation in the cloud system is the major role to determine the performances, resource utilization and total overall power consumption of the cloud data center. The optimal allocation of the virtual machines is one of the resource optimization problems in cloud due to the resource contention and starvation. This paper proposes the important parameters consideration proved with linear programming to be applied for limitation of resource allocation conditions in cloud and to identify the resource minimized allocation model at first. Then, the optimal resource allocation model (ORAM) based on modification of cost matrix in Hungarian algorithm is proposed as a solution and experimental evaluation is carried out for the proposed model. According to the performance evaluation, the proposed model outperforms both the conventional binding policy and existing Hungarian based allocation model HABBP in term of the optimal execution time.","PeriodicalId":388642,"journal":{"name":"2019 International Conference on Advanced Information Technologies (ICAIT)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129100249","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"University Classroom Attendance System Using FaceNet and Support Vector Machine","authors":"Thida Nyein, Aung Nway Oo","doi":"10.1109/AITC.2019.8921316","DOIUrl":"https://doi.org/10.1109/AITC.2019.8921316","url":null,"abstract":"Nowadays, face recognition system becomes popular in research area. Face recognition is also used in many application areas such as attendance management system, people tracking system, and access control system. For multi-face recognition, it has still many challenges for detection and recognition because it is not easy to detect multiple faces from one frame and it is also difficult to recognize the faces with poor resolution. Therefore, the main objective of this paper is to get a better accuracy for multi-face recognition by using the combination of FaceNet and Support Vector Machine (SVM). In this proposed system, FaceNet is used for feature extraction by embedding 128 dimensions per face and SVM is used to classify the given training data with the extracted feature of FaceNet. University Classroom Attendance System is applied by the proposed multi-face recognition. The Experimental result show that the proposed approach is good enough for multi-face recognition with an accuracy of 99.6%. It is better than VGG16 model on the same data-set.","PeriodicalId":388642,"journal":{"name":"2019 International Conference on Advanced Information Technologies (ICAIT)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125479482","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Edge based Crime Assistance System with Cloud Computing","authors":"Khin Myint Myat Thu, N. Thein","doi":"10.1109/AITC.2019.8920883","DOIUrl":"https://doi.org/10.1109/AITC.2019.8920883","url":null,"abstract":"Nowadays, the level of crime is increasing more and more in every corner of the world. With the rising rate of criminal activities, the identification process of the person who committed crime takes a lot of time. Most of the crime reporting systems currently are reported personally. In order to create a fast and reliable crime reporting system, the face identification in crime assistance system between edge and cloud computing is proposed. The processing power of ubiquitous devices (e.g. smartphones, sensors, and actuators) are very powerful today. They allow capturing the image of the criminal anywhere at any time. They also have the capability of detecting faces from captured image. Therefore, the face detection process using Haar face detection and face identifier generation process using Local Binary Pattern (LBP) from the captured image can take place on the edge devices. Face identifier matching is proceeded on the cloud. The paper proposed the edge-based face identification system and represents the analysis result of face detection time, matching time and total processing time of the proposed system with the increasing number of test image data set. The results show the effective usage of edge devices and improve the efficiency of face identification.","PeriodicalId":388642,"journal":{"name":"2019 International Conference on Advanced Information Technologies (ICAIT)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123521933","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}