{"title":"Prediction modelling in career management","authors":"Hadary Mallafi, D. H. Widyantoro","doi":"10.1109/CYBERNETICSCOM.2016.7892560","DOIUrl":"https://doi.org/10.1109/CYBERNETICSCOM.2016.7892560","url":null,"abstract":"A question that is often arose on career management is how to choose potential employees to become chief and achieve performance target based on employees' historical data. This research attempts to answer the question and tries to determine what factors can affect an employee to become a chief and capable to achieve performance target. To address the question, this study adopts predictive modelling approach using classification techniques and kl-divergence function. The research proposes some recommendations based on applied algorithm. Additionally, the study shows it is easier to choose a chief based on their historical data compare to predicting which employee can perform well in the future or predicting both potential chief and high performer employees. If organization wants to select potential employees to become chief and predicts them achieving their target, classification techniques should include all employees as the population and avoid to choose only subsets to ensure the confidence of result. Meanwhile, KL-Divergence function generates competencies that affect employee who become a chief and achieve the target. They are achievement orientation, adaptability, analytical thinking, communication and information seeking.","PeriodicalId":424359,"journal":{"name":"2016 International Conference on Computational Intelligence and Cybernetics","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124197641","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}
Indrabayu, Rizki Yusliana Bakti, I. Areni, A. Prayogi
{"title":"Vehicle detection and tracking using Gaussian Mixture Model and Kalman Filter","authors":"Indrabayu, Rizki Yusliana Bakti, I. Areni, A. Prayogi","doi":"10.1109/CYBERNETICSCOM.2016.7892577","DOIUrl":"https://doi.org/10.1109/CYBERNETICSCOM.2016.7892577","url":null,"abstract":"Intelligent Transport System (ITS) is a method used in traffic arrangements to make efficient road transport system. One of the ITS application is the detection and tracking of vehicle objects. In this research, Gaussian Mixture Model (GMM) method was applied for vehicle detection and Kalman Filter method was applied for object tracking. The data used are vehicles video under two different conditions. First condition is light traffic and second condition is heavy traffic. Validation of detection system is conducted using Receiver Operating Characteristic (ROC) analysis. The result of this research shows that the light traffic condition gets 100% for the precision value, 94.44% for sensitivity, 100% for specificity, and 97.22% for accuracy. While the heavy traffic condition gets 75.79% for the precision value, 88.89% for sensitivity, 70.37% for specificity, and 79.63% for accuracy. With avarage consistency of Kalman Filter for object tracking is 100%.","PeriodicalId":424359,"journal":{"name":"2016 International Conference on Computational Intelligence and Cybernetics","volume":"85 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122083899","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}
Rosmawati Ab. Raub, Azmirul Hamzah Nor Hamzah, Mohd Daud Jaafar, Khairul Nizam Bin Baharim
{"title":"Using subscriber usage profile risk score to improve accuracy of telecommunication fraud detection","authors":"Rosmawati Ab. Raub, Azmirul Hamzah Nor Hamzah, Mohd Daud Jaafar, Khairul Nizam Bin Baharim","doi":"10.1109/CYBERNETICSCOM.2016.7892579","DOIUrl":"https://doi.org/10.1109/CYBERNETICSCOM.2016.7892579","url":null,"abstract":"Look for telecommunications fraud in masses of call records is more difficult than finding a needle in a haystack. Even though fraud techniques are constantly evolving and whenever a detection method become know, fraudsters will adapt their strategies and try others. Therefore we propose a novel approach which make use of both threshold rules engine and usage pattern history for fraud detection in telecommunications. Threshold rules engine comprises of set of rules which if compromised would trigger an alarm. The alarm generated would be evaluated further through fraud risk score. The score is generated based on score value generated through subscriber's usage pattern on a formula formulated by domain expert. The alarm is categorized as fraud or vice versa depending on which range the scoring value falls into.","PeriodicalId":424359,"journal":{"name":"2016 International Conference on Computational Intelligence and Cybernetics","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133925872","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}
A. Bustamin, Indrabayu, I. Areni, Novy N. R. A. Mokobombang
{"title":"Speech to text for Indonesian homophone phrase with Mel Frequency Cepstral Coefficient","authors":"A. Bustamin, Indrabayu, I. Areni, Novy N. R. A. Mokobombang","doi":"10.1109/CYBERNETICSCOM.2016.7892562","DOIUrl":"https://doi.org/10.1109/CYBERNETICSCOM.2016.7892562","url":null,"abstract":"In this study, speech to text system for homophone phrases in Indonesian was designed using an extraction method which featured Mel Frequency Cepstral Coefficient (MFCC). Feature extraction results were classified by comparing the two classifiers of Backpropagation Neural Network (BPNN) and K-Nearest Neigbour (KNN). The input data used were the recordings of each of 3 male and female respondents. The recording process was conducted for 5 seconds at a sampling frequency of 16 kHz and at channel mono. Classification results with test data to BPNN showed accuracy rates of 96.67% and 90% respectively for male and female respondents. Moreover, the level of accuracy obtained on KNN amounted to 83.33% for males and 73.33% for females.","PeriodicalId":424359,"journal":{"name":"2016 International Conference on Computational Intelligence and Cybernetics","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116277126","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":"Network-on-chip with guaranteed-bandwidth data communication service","authors":"Faizal Arya Samman","doi":"10.1109/CYBERNETICSCOM.2016.7892571","DOIUrl":"https://doi.org/10.1109/CYBERNETICSCOM.2016.7892571","url":null,"abstract":"A network-on-chip (NoC), having guaranteed-throughput (GT) or guaranteed bandwidth service by using a flexible method to establish a connection-oriented data communication at runtime, is presented in this paper. The GT packets can share communication link with a flexible manner, where flits belonging to the same packet will have the same local identity-tag (ID-tag). The ID-tags of each packet will vary locally along communication links, and are organized with an ID-tag mapping management unit, which is implemented at each output part of the on-chip routers. There is no need for a specific algorithm for finding a conflict-free scheduling as commonly used in the TDM-based methods that use time slots allocation technique. The contention problem is solved with the hardware solution based on the locally organized message identity (ID). This guaranteed bandwidth/throughput service will provide a good interconnect platform for many core processor systems running computer vision and multimedia applications with better performance.","PeriodicalId":424359,"journal":{"name":"2016 International Conference on Computational Intelligence and Cybernetics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129957757","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}
Sitti Wetenriajeng Sidehabi, Indrabayu, S. Tandungan
{"title":"Statistical and Machine Learning approach in forex prediction based on empirical data","authors":"Sitti Wetenriajeng Sidehabi, Indrabayu, S. Tandungan","doi":"10.1109/CYBERNETICSCOM.2016.7892568","DOIUrl":"https://doi.org/10.1109/CYBERNETICSCOM.2016.7892568","url":null,"abstract":"This study proposed a new insight in comparing common methods used in predicting based on data series i.e statistical method and machine learning. The corresponding techniques are use in predicting Forex (Foreign Exchange) rates. The Statistical method used in this paper is Adaptive Spline Threshold Autoregression (ASTAR), while for machine learning, Support Vector Machine (SVM) and hybrid form of Genetic Algorithm-Neural Network (GA-NN) are chosen. The comparison among the three methods accurate rate is measured in root mean squared error (RMSE). It is found that ASTAR and GA-NN method has advantages depend on the period time intervals.","PeriodicalId":424359,"journal":{"name":"2016 International Conference on Computational Intelligence and Cybernetics","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126887184","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":"WayBotDu: A low cost articulated arm platform for education","authors":"S. Adinandra, Akmalazakia F. D. Marsiano","doi":"10.1109/CYBERNETICSCOM.2016.7892573","DOIUrl":"https://doi.org/10.1109/CYBERNETICSCOM.2016.7892573","url":null,"abstract":"The use of robotics in industry has been increasing, especially in the manufacturing systems. Using articulated arms type, robots are used to assemble different components in manufacturing. Flexibility of the robots provides movements that are difficult to tackle by human. As a consequence, early age understanding, knowledge, and education about articulated arm become more important. This paper provides a low cost platform for education and learning. An articulated arm, designed as a Javanese puppet character Semar is built using 4 servo motors and acrylic links. Following a 4R-rotational structure, the forward and inverse kinematics are built using typical Denavit-Hattenberg (DH) convention. A custom user interface made using LabVIEW serves a tool to test, simulate and create experiments with the platform. The user interface, available in executable file for mobility, sending and receiving data with the arm platform via serial communication. All components, electrical and mechanical, are all bought in local shop and cost not more than 200 USD to fulfill the “low cost” concept. The experimental results show that the proposed low cost platform has root-mean-square errors (RMSE) for forward kinematics movements in x, y, and z direction of 1.23 [cm], 1.10 [cm] and 0.71 [cm] respectively. For the inverse kinematics test, the errors are 1.38 [cm], 0.66 [cm], and 0.74 [cm] in x, y, and z respectively.","PeriodicalId":424359,"journal":{"name":"2016 International Conference on Computational Intelligence and Cybernetics","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130426813","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":"Process model extension using heuristics miner: (Case study: Incident management of Volvo IT Belgium)","authors":"B. Hidayat, A. Kurniati, Shaufiah","doi":"10.1109/CYBERNETICSCOM.2016.7892570","DOIUrl":"https://doi.org/10.1109/CYBERNETICSCOM.2016.7892570","url":null,"abstract":"VINST is a system used to record all activities related to the incident and problem management in Volvo IT Belgium. In this VINST system, activities recorded in several attributes, such as serial number, change date and time, status, and any other attributes needed, which is stored in the event log. In these sequenced activities, there are some specific knowledge that is not explicitly described in the event log. To find some of the necessary knowledge, this study extracts knowledge from the event log, by using process mining. Heuristic miner algorithm was implemented in this study, because this algorithm has advantages compared to other methods, such as the ability to calculate the frequency of the process, to handle noise, and to combine the frequency between events and trace in the event log to build a process model. The steps being taken in this study began with the discovery process, followed by conformance checking, and completed with process model extension in enhancement step, which was finding knowledge based on analysing process model and event log. This study was using a specifically designed program to achieve the goals of this study. This study used VINST incident records with 149 cases consisting of 2.771 events. By applying heuristics miner, a process model discovered with precision, recall, and f-measure more than 96%. Knowledge gained from this process model extension were the analysis of time and organizational perspectives in forms of timestamp-impact attribute relation and originator-impact attribute relation.","PeriodicalId":424359,"journal":{"name":"2016 International Conference on Computational Intelligence and Cybernetics","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129955099","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":"A formal model of quorum based k-mutex algorithm using input/output automata","authors":"I. M. Nur, A. Lawi","doi":"10.1109/CYBERNETICSCOM.2016.7892576","DOIUrl":"https://doi.org/10.1109/CYBERNETICSCOM.2016.7892576","url":null,"abstract":"An input/output automata model is a distributed computation model in distributed systems to create a formal model or to prove a distributed algorithm. This research aims to create a formal model of quorum based k-mutual exclusion (k-mutex) algorithm. The formal model of quorum based k-mutex algorithm using input/output automata consists of five components: signature, state, initial state, transition, and task. The constructed model proved by using time line and execution of input/output automata. The result of research shows that the input/output automata model of quorum based k-mutex algorithm solved the problem of k-mutex given.","PeriodicalId":424359,"journal":{"name":"2016 International Conference on Computational Intelligence and Cybernetics","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134256712","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":"Multiclass classification using Least Squares Support Vector Machine","authors":"Nurkamila Jafar, S. Thamrin, A. Lawi","doi":"10.1109/CYBERNETICSCOM.2016.7892558","DOIUrl":"https://doi.org/10.1109/CYBERNETICSCOM.2016.7892558","url":null,"abstract":"In this paper, multiclass classification problem; One Against All and One Against One, with Least Squares Support Vector Machine (LS-SVM) will be used. There are three type of kernels were used in this paper; Radial Basis Function (RBF), polynomial and linear. One Against All method and One Against One method will be compared to see the accuracy of each kernel, and the amount of misclassification using the confusion matrix. This is illustrated by using iris plant species dataset and the preferred method of contraception dataset. The results showed that the method of One Against One is better than the One Against All based on the accuracy for kernels RBF, polynomial, and linear.","PeriodicalId":424359,"journal":{"name":"2016 International Conference on Computational Intelligence and Cybernetics","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127312259","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}