{"title":"Grammar Inference Based on Passive Learning and Genetic Algorithm","authors":"P. Grachev","doi":"10.1145/3310986.3311033","DOIUrl":"https://doi.org/10.1145/3310986.3311033","url":null,"abstract":"The mathematical model of a deterministic finite automaton has a wide potential of application, for instance, in control systems. Some of that systems are not trivial and can be defined only in terms of formal language theory. In this paper, we propose a new model for grammar inference, i.e. synthesizing of a deterministic finite automaton by a list of positive and negative examples. We present the results of testing developed model on formal grammars of various complexity.","PeriodicalId":252781,"journal":{"name":"Proceedings of the 3rd International Conference on Machine Learning and Soft Computing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115351753","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":"21st Century Learning Skills Predictive Model Using PART Algorithm","authors":"Betchie E. Aguinaldo","doi":"10.1145/3310986.3310992","DOIUrl":"https://doi.org/10.1145/3310986.3310992","url":null,"abstract":"The skillset of a graduate is the key to success to perform successfully in their chosen career path, thus, academic institution continuously develops strategic ways to develop and prepare the 21st century Learning skills of the student before they completed the higher education studies. This paper presents the 21st Century Learning Predictive Model in Programming Logic Formulation using PART classifier algorithm. It also aims to determine the significant attributes in the development of dataset for predictive model and generate a predictive model for 21st Century Learning Skills using PART classifier algorithm. Six (6) standardized questionnaire of 21st Century Learning Skills of one hundred eight (180) students were coded and used as a dataset of the study. The result of the customized assessment exam in programming logic formulation was used as response attributes of the datasets. As a result of the study, five (5) rules were generated using PART classifier algorithm. Among the 21st Century Learning skills, Communication is the strongest predicting attributes of successful performance of students in programming logic formulation.","PeriodicalId":252781,"journal":{"name":"Proceedings of the 3rd International Conference on Machine Learning and Soft Computing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129584627","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":"An Improvement of Fuzzy Logic Based Clustering Combined for Mobile Sink Algorithm","authors":"Phan Thi The, N. Thang, Tran Cong Hung","doi":"10.1145/3310986.3311018","DOIUrl":"https://doi.org/10.1145/3310986.3311018","url":null,"abstract":"In recent years, the Wireless Sensor Network has attracted more and more researchers for their great potential benefits such as security and environmental monitoring, following and evaluating in agriculture. Many routing protocols are designed for energy resources optimization. However, networks with one fixed sink often suffer from a hot spots problem since nodes near sinks take more energy to forward data during the transmission process. The use of fuzzy logic based clustering combined with mobile sink has been proved to be an effective way to enhance network performance features such as energy efficiency, network lifetime. This paper contributes the improvement of network lifetime by considering the fuzzy logic approach which is used to elect the cluster head based on three descriptors: residual energy, local distance and distance to sink. Simulation result presents that our improvement for fuzzy logic based clustering combined with mobile sink algorithm extends the performance of wireless sensor network and better than some other algorithms.","PeriodicalId":252781,"journal":{"name":"Proceedings of the 3rd International Conference on Machine Learning and Soft Computing","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114393272","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":"TRRS: Temporal Recurrent Recommender System based on Time-sync Comments","authors":"Hao Ren, Dong Wang","doi":"10.1145/3310986.3311022","DOIUrl":"https://doi.org/10.1145/3310986.3311022","url":null,"abstract":"Recent years has witnessed great emerge of online video websites, including the exploded number of videos and users. As a result, there appears a lot of personlized recommender systems. However there remain some challenging problems to tackle such as cold start problem, which scientists have made use of all kinds of sideinformation, e.g. gender, age or comments, to release. Currently a new type of video comments, called TSCs (TSC), plays a more and more important role in video watching activity. In this paper we utilize TSC to recommend videos for users. We developed a deep nueral network model called Temporal Recurrent Recommder System (TRRS) which combine multi-layers neural network to extract feature for users and videos. The first layer convert TSC to embeddings, then RNN layer analyze each comment from user or video, and fianlly the merge layer combine all output from prior layer and produce the feature. We use the feature from the network for users and videos to make personlized recommendation.","PeriodicalId":252781,"journal":{"name":"Proceedings of the 3rd International Conference on Machine Learning and Soft Computing","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114549822","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}
Zaman Wahid, A. Z. Satter, Abdullah Al Imran, T. Bhuiyan
{"title":"Predicting Absenteeism at Work Using Tree-Based Learners","authors":"Zaman Wahid, A. Z. Satter, Abdullah Al Imran, T. Bhuiyan","doi":"10.1145/3310986.3310994","DOIUrl":"https://doi.org/10.1145/3310986.3310994","url":null,"abstract":"Absenteeism at workplace acts as a crucial role in demonstrating the productive and profitable capacity of a company. Thus the knowledge of absenteeism of employees' becomes the foundation for an organization in its multiple dimensions. Because the proper determination of employees' profile allows the identification of excesses of occurrences of certain morbidities. The early absenteeism research primarily focused on predicting the characteristics and the categories of diseases of employees that make them perform higher absenteeism at workplace. However, predicting the absenteeism time of employees using different machine learning classifiers is able to give the researches a new dimension in line with the intention of revealing the underlying causes and patterns of absenteeism. In this paper, we have applied 4 prominent machine learning algorithms namely Decision Tree, Gradient Boosted Tree, Random Forest, and Tree Ensemble on the absenteeism dataset of a courier company in Brazil in order to predict the absenteeism time of employees at work as well as the best classifier. Based on the 7 evaluation metrics such as True Positive, True Negative, False Positive, False Negative, Sensitivity, Specificity, and Accuracy we found that Gradient Boosted Tree produced the best result with an accuracy rate of 82% whereas Tree Ensemble performed the lowest with the accuracy rate of 79%.","PeriodicalId":252781,"journal":{"name":"Proceedings of the 3rd International Conference on Machine Learning and Soft Computing","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116880708","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":"The Role of Attention Mechanism and Multi-Feature in Image Captioning","authors":"Tien Dang, A. Oh, In Seop Na, Soohyung Kim","doi":"10.1145/3310986.3311002","DOIUrl":"https://doi.org/10.1145/3310986.3311002","url":null,"abstract":"Up to now, caption generation is still a hard problem in artificial intelligence where a textual description must be generated for a given image. This problem combines both computer vision and natural language processing. Generally, the CNN - RNN is a popular architecture in image captioning. Currently, there are many variants of this architecture, where the attention mechanism is an important discovery. Recently, deep learning methods have achieved state-of-the-art results for this problem. In this paper, we present a model that generates natural language descriptions of given images. Our approach uses the pre-trained deep neural network models to extract visual features and then applies an LSTM to generate captions. We use BLEU scores to evaluate our model performance on Flickr8k and Flickr30k dataset. In addition, we carried out a comparison between the approaches without attention mechanism and attention-based mechanism.","PeriodicalId":252781,"journal":{"name":"Proceedings of the 3rd International Conference on Machine Learning and Soft Computing","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129509698","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":"Diagnosis of Common Diseases Using Type-2 Fuzzy System","authors":"B. Erin, R. Abiyev","doi":"10.1145/3310986.3311028","DOIUrl":"https://doi.org/10.1145/3310986.3311028","url":null,"abstract":"High level of expertise is required for human disease diagnosis which is a complicated and difficult process. Each disease is characterised with the set of observable sign and symptoms. Based on these symptoms to understand patient health problems and to make a diagnosis of these diseases with their clear definition is difficult. The diagnosis of the disease is based on knowledge of doctor physicians. Fuzzy logic is one of the best approaches to design knowledge-based system for diagnosis of the diseases. In this paper, the design of a type-2 fuzzy system is performed for diagnosis of the common diseases using proper values of the inputs. The input symptoms and output diseases are defined for construction of the fuzzy rule base. The relationships are presented using type-2 IF-Then rules. Based on the fuzzy rules the design of type-2 fuzzy inference system is performed. The designed system will help the physician to diagnose common diseases such as common cold and flu.","PeriodicalId":252781,"journal":{"name":"Proceedings of the 3rd International Conference on Machine Learning and Soft Computing","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130679472","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}
Larry B. de Guzman, Ariel M. Sison, Ruji P. Medina
{"title":"Implementation of Enhanced MD5 Algorithm using SSL to Ensure Data Integrity","authors":"Larry B. de Guzman, Ariel M. Sison, Ruji P. Medina","doi":"10.1145/3310986.3311027","DOIUrl":"https://doi.org/10.1145/3310986.3311027","url":null,"abstract":"Data integrity is the main concern of this paper. An application was developed to implement the Enhanced MD5 Algorithm in Secured Socket Layer (SSL). Furthermore, this application secures the integrity of data sent and received via communication link using SSL. This paper also analyzed the time and space complexity of the Enhanced MD5 Algorithm. The time complexity obtained was 27+7n+2n^2+n log n and space complexity were O (n^2). During uploading and downloading processes, the developed application generated the same hashes for the same files. This means that if an SSL uses a strong standard-based encryption algorithm, data are protected. Using a strong encryption algorithm, data security is assured amidst attacker's interception during transmission.","PeriodicalId":252781,"journal":{"name":"Proceedings of the 3rd International Conference on Machine Learning and Soft Computing","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133067230","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}
Hafiz Muhammad Zubair Hasan, Hammad Khan, Talha Asif, S. Hashmi, Muhammad Rafi
{"title":"Towards a transfer learning approach to food recommendations through food images","authors":"Hafiz Muhammad Zubair Hasan, Hammad Khan, Talha Asif, S. Hashmi, Muhammad Rafi","doi":"10.1145/3310986.3310990","DOIUrl":"https://doi.org/10.1145/3310986.3310990","url":null,"abstract":"User generated text/multimedia content are increasingly shared in online businesses systems and their effective use in user modelling and recommendation strategies is consequently growing too. In restaurant businesses the food menu along with images are a common practice and users also shared the food images they ordered and feel good about. Yelp data set challenge in their round 9 and onward introduced such rich images data for their competition. In this paper, we motivated from this rich images data of food for semantically incorporating image-specific features to the star-rating and recommendation process. We first applied a transfer learning approach with pre-trained CNNs (Convolution Neural Networks) which were used to label the Yelps food images of the restaurants using the Food101 data-set. We defined star-rating for restaurants by capturing a correlation between restaurant images and users shared images. Our proposed strategy works on discovering hidden aspects of food images and labels to be used in recommendation strategy. We performed an extensive set of experiments by creating a baseline using standard rating provided in the Yelp data-set. The proposed approach produced better Root Mean Square Error (RMSE), which is a clear indication of high-quality recommendation strategy","PeriodicalId":252781,"journal":{"name":"Proceedings of the 3rd International Conference on Machine Learning and Soft Computing","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123069402","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}
Shaoming Qiu, Jiahao Li, Bo Chen, Ping Wang, Xiu-e Gao
{"title":"An improved prediction method for diabetes based on a feature-based least angle regression algorithm","authors":"Shaoming Qiu, Jiahao Li, Bo Chen, Ping Wang, Xiu-e Gao","doi":"10.1145/3310986.3311024","DOIUrl":"https://doi.org/10.1145/3310986.3311024","url":null,"abstract":"Existing diabetes prediction algorithms have a number of shortcomings, most notably low accuracy and poor generalizability. In this paper, we propose a method based on feature weights to improve diabetes prediction that combines the advantages of traditional least angle regression (LARS) algorithms and principal component analysis (PCA) algorithms.First of all, a principal component analysis algorithm is used to obtain the characteristic independent variables found in typical diabetes prediction regression models. Each of these variables is assigned its own characteristics. After this, the original variable correlation is multiplied by the weight of the variable obtained using principal component analysis to obtain a new degree of correlation. This new correlation is used to optimize the forward direction and variable selection of a least angle regression solution before calculating the regression coefficients for the new model. An experiment using the Pima Indians Diabetes dataset provided by the University of California was performed to validate the proposed algorithm. The experimental results show that the algorithm improved the approximation speed for the dependent variables and the accuracy of the regression coefficients. It was also able to select the key characteristic variables for diabetes prediction whilst simplifying the standard diabetes prediction model. Thus, it may help with the provision of more accurate diabetes prevention and treatment measures in the future.","PeriodicalId":252781,"journal":{"name":"Proceedings of the 3rd International Conference on Machine Learning and Soft Computing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128427540","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}