Proceeding of the Electrical Engineering Computer Science and Informatics
Not a member yet
649 research outputs found
Sort by
Sentiment Analysis to Measure Celebrity Endorsment’s Effect using Support Vector Machine Algorithm
Get PDFCelebrity endorsement is a phenomenon in which companies advertises their products by using celebrity services, and celebrities take advantage of their popularity to promote a brand or product of the company through social media. In this study, KFC did a celebrity endorsement to make their menu more popular. KFC choose to work with Raditya Dika to promote their latest menu, KFC Salted Egg Chicken. This study will examine whether in such cases there is a change in public sentiment towards the product after the celebrity endorsement. It can be done using text mining and sentiment analysis. There are several algorithms that can be used to perform sentiment analysis, one of them is Support Vector Machine. Support Vector Machine (SVM) was chosen because this method is quite accurate in various studies. SVM also takes into account various features of the document, including features that often do not appear on the document, so it can reduce the loss of information from the data. The data used in this research are taken from YouTube and Twitter comment about KFC Salted Egg Chicken. Several step was done in this sentiment analysis research, that are preprocessing text, feature extraction, classification, and evaluation. The result model is tested and evaluated before and after endorsement by looking at the value of accuracy, precision, recall, and f1-measure. The test result of accuracy, precision, recall, and f-measure before endorsement were 67,83%, 69%, 68%, and 66%. After the endorsement, the test results were 74.06%, 74%, 74%, and 74% respectively. The results of this study indicate that SVM has an accurate measurement in sentiment analysis studies. Moreover, this study found that there was not significant change in public sentiment regarding the product before and after the celebrity endorsement
Smart Traffic Light based on IoT and mBaaS using High Priority Vehicles Method
Get PDFAn increase of the number of vehicles which is not followed by the number of roads can lead to the increase of congestion, especially in big cities. Regulation of law no 22 Year 2009 explains that there are seven types of vehicles prioritized on the road. This research aims to build a Smart Traffic Light as a solution with the goal of making the prioritized vehicle journey smooth when crossing the road with Smart Traffic Light. The proposed system is "Smart Traffic Light on IoT and mBaaS (Mobile Backend As a Service) using High Priority Vehicles Method". The Smart Traffic Light has three important parts, including: (1) Smart Traffic Application; (2) Smart Traffic Controller; and (3) mBaaS. Prioritized vehicle drivers cross the road using the Smart Traffic Application when they are in an emergency situation. Smart Traffic Application and Smart Traffic Controller communicate using mBaaS. Smart Traffic Application has a vehicle track search facility as well as identification of traffic light location. A few meters before crossing, Smart Traffic Application will send the location to mBaaS and continue to be read by Smart Traffic Controller using internet. If it meets the criteria of High Priority Vehicle, then Traffic Light will be changed to green in the same path. The results show that when testing the data rate from Smart Traffic Application to Smart Traffic Controller, it takes no later than 8.15 seconds and 1.2 seconds (the fastest) with the average data transmission time of 3.39 seconds. Smart Traffic Light is able to identify the direction of the vehicle before passing through the Smart Traffic Application
The Kinematics and Dynamics Motion Analysis of a Spherical Robot
Get PDFMobile robot application has reach more aspect of life in industry and domestic. One of the mobile robot types is a spherical robot whose components are shielded inside a rigid cell. The spherical robot is an interesting type of robot that combined the concept of a mobile robot and inverted pendulum for inner mechanism. This combination adds to more complex controllerdesignthantheothertypeofmobilerobots.Asidefrom these challenges, the application of a spherical robot is extensive, from being a simple toy, to become an industrial surveillance robot. This paper discusses the mathematical analysis of the kinematics and dynamics motion analysis of a spherical robot. The analysis combines mobile robot and pendulum modeling as the robot motion generated by a pendulum mechanism. This paper is expected to give a complete discussion of the kinematics and dynamics motion analysis of a spherical robot
Marine Vessel Telemetry Data Processing Using Machine Learning
Get PDFIn Indonesia, one of the causes of the high cost of fuel in the shipping industry is theft and misuse of fuel. This happened because ship management center unable to monitor all the activities of the ship when the ship sailing in the middle of the ocean. Lately, ship monitoring through the latest technology are being carried out, one of which is the Machine to Machine (M2M) based Vessel Monitoring System (VMS) technology. The development of VMS and telemetry technology has enabled monitoring of engines and fuel consumption of ships in real time. The problem with this VMS system is that there is still a dependency on the analysis of experts who need a long time to analyze various parameters of existing telemetry data, which lead to inaccuracy and delay in anomaly detection. This study conducted a statistical analysis of telemetry data, especially in ship movement and machine activities, and then designed the fuel consumption regularity classification system with the Naive Bayes and Logistics Regression. Naive Bayes method was chosen because it can produce maximum accuracy with little training data, and Logistics Regression was chosen for its simplicity and excellent results in prediction of numerical and discrete data. The results of this study indicate that telemetry data from the VMS system can be used to detect irregularities in Fuel consumption. Tested with selected data, Naive Bayes classification accuracy in irregularities detection is up to 92% while logistic regression is up to 96%
A Third Order based Additional Regularization in Intrinsic Space of the Manifold
Get PDFSecond order graph Laplacian regularization has the limitation that the solution remains biased towards a constant which restricts its extrapolationcapability. The lack of extrapolation results in poor generalization. An additional penalty factor is needed on the function to avoid its over-fitting on seen unlabeled training instances. The third order derivative based technique identifies the sharp variations in the function and accurately penalizes them to avoid overfitting. The resultant function leads to a more accurate and generic model that exploits the twist and curvature variations on the manifold. Extensive experiments on synthetic and real-world data set clearly shows thatthe additional regularization increases accuracy and generic nature of model
Hybrid Improved Differential Evolution and Splinebased Jaya for Photovoltaic MPPT Technique
Get PDFSome Soft Computing algorithms to solve themaximum power point tracking (MPPT) method problem ofthe photovoltaic system under partially shaded conditions willstop tracking Global Maxima and produce reference voltage orthe best duty-cycle if the difference between the worst and thebest candidate solution is smaller than the specified threshold.A large threshold value will produce fast converging, but theaccuracy value will be low, and vice versa, then thedetermination of the threshold value will be very dilemma.Therefore, this study proposed a combination of ImprovedDifferential Evolution (IDE) and Jaya optimization based onpredictive curves using cubic spline interpolation to determinethe best particles after the IDE reaches convergent criteria, sothat with a large threshold value it will still get high accuracyand high convergent speed. Furthermore, the algorithmproposed in this study is known as Improved DifferentialEvolution and Jaya Based Spline (IDESJaya). The proposedalgorithm is compared with conventional P&O, Jaya based onSpline, and IDE. Simulation results show that the IDESJayatechnique is faster converging, provides a better overalltracking efficiency and higher accuracy
Optimization Info Rate Using APSK Modulation Scheme for Delivery GSM ABIS over Satellite Communications
Get PDFMobile operators move quickly from 2G GSM networks in urban areas to remote rural areas, which are 2G networks by offering voice connectivity. As a result, more and more technology is optimizing cellular operators that reduce and perform bandwidth efficiency that will be implemented. The optimization solution for this cellular operator produces voice communication on GSM, in a cost-effective application for satellites. This paper discusses and applies to creating GSM links via satellite communication. The ABIS interface on GSM, which is defined between the Base Transceiver Station (BTS) of GSM remote cells and the Base Station Controller (BSC), is considered here to be transferred via GSM communication with the Modulation and Coding scheme 16 APSK 5/6. The MODCOD scheme determines the efficiency of what MHz is needed to send one Mbps. The efficiency value achieved by allocating, bandwidth (MHz) generated by 1.0 Mhz is an efficiency of 3.222 [bit / baud]. And Info Data Rate is generated from the value (Mbps) of 3,175. The highest traffic intensity with the value of Traffic Volume (Hours) = 3.5, Traffic Intensity (Erlang) 0.145833333. While the lowest traffic intensity with the value of Traffic Volume (Hour) = 2.6, traffic intensity = 0.108333333 (Erlang). The value obtained on Traffic Volume and Traffic Intensity is 0.1%. Service levels are very good at grade of service, because of the small possibility of access fail. Calculation of the availability of link network availability links, using ACM 16APSK LDPC 5/6 techniques that can increase up to 100%
Fuzzy Logic Implementation For Incubator Prototype With Temperature And Humidity Control
Get PDFPremature infant and young baby born with lowbody weight has potential to be in high risk and criticalcondition to survive. Medical equipment functioned as uterineis required, so the infant will have the similar condition as inthe womb of its mother. There is a need to control surroundingtemperature, humidity, oxygen supply, sound and light level tosupport the development of the infant's weight. Infants withlow weight have possibility to feel cold and have body heat loss.The use of additional supporting equipment such as incubatoris absolutely necessary and vital to create a stable surroundingenvironment for infant to keep the body temperature in rangeof normal and relatively constant value. In this paper, thefuzzy logic is implemented as the role of controller for anincubator equipped with temperature and humidity sensor.The propossed incubator prototype was tested in DR. SardjitoHospital, Yogyakarta Indonesia. The experiments showedprospected results to get a stable temperature and humiditywhich are suitable for premature baby
Analysis and Development of Information Security Framework for Distributed E-Procurement System
Get PDFThis paper proposes an information security framework for distributed E-Procurement system in Indonesia. E-Procurement in Indonesia has been implemented since 2008, and has provided many benefits. However, there are also information security issues in the use of IT. Developing an information security program is needed to overcome the issues. We compare and analyze the LPSE and ISO 27001 Standards to develop framework. The results show there are some gaps between LPSE Standard and ISO 27001. By implementing the proposed framework, LPSE as a provider of distributed EProcurement system can be easier to implement the LPSE and ISO 27001 Standards simultaneously as an obligation to comply with government regulation
Anomaly Detection and Data Recovery on Mini Batch Distillation Column based Cyber Physical System
Get PDFThe development of industrial revolution 4.0 in industrial sector opened a cyber gap for outsiders to pose a threat to the system. Industrial control systems initially designed to meet SRA (Safety, Reliability, and Availability) priorities are now beginning to be pressed to consider security aspects related to the magnitude of the impact that can be caused due to external attacks. In making a safe Cyber Physical System (CPS) based automation, risk assessment will be used to determine the level risk of threat. Mini distillation column batch based CPS will be implemented as the approach of CPS in industrial sector. Anomaly detection based data-driven model and data recovery method is proposed to lower the impact of attack on this system