Journal of Telematics and Informatics
Not a member yet
147 research outputs found
Sort by
Software Defect Prediction Using Synthetic Minority Over-sampling Technique and Extreme Learning Machine
Get PDFSoftware testing is one of the crucial processes in software development life cycle which will influence the software quality. One of the strategies to help testing process is predicting the part or module of software which is prone to defect. Then, the testing process can be more focused to those parts. In this research a classifier model for predicting software defect was built. One of the most important problems in software defect prediction is imbalance data distribution between samples of positive class (prone to defect) and of negative class. Therefore, in this research SMOTE is implemented to handle imbalance data problem and extreme learning machine is implemented as a classification algorithm. As a comparison to SMOTE-ELM, a modification of ELM which directly copes with imbalance problem, weighted-ELM, is also observed. This research used NASA MDP dataset PC1, PC2, PC3 and PC4. The results of experiment using 10-fold cross validation show that directly classification using ELM obtain the worse result compared to SMOTE-ELM and weighted-ELM. When the value of imbalance ratio is not very small, the SMOTE-ELM is better than weighted-ELM. When the value of imbalance ratio is very small, the g-mean of weighted-ELM is higher than the g-mean of SMOTE-ELM, but the accuracy of weighted-ELM is lower than the accuracy of SMOTE-ELM. Therefore, in this software defect prediction case it can be concluded that SMOTE is effective to increase the generalization performance of classifier in minority class as long as the value of imbalance ratio is not very small
MIMO Printed Dipole Antenna for Wimax Network Usage Application
Get PDFStandard wimax have 2 versions : IEEE 802.16-2004 and IEEE 802.16d. this comprehension also supported by Orthogonal Frequency Division ultiplexing on Physical Layer. OFDm provide wireless DSL technology where broadband cable is not available. Wimax 802.16e use Standard OFDMA Technic. It provide the support for nomadic and mobility service also known as WiMAX phone. Wimax is a wireless broadband technology that have an improvement on WI - FI and UMTS. One of the devices that is needed in the technology is the antenna. The technique used is the MIMO technique. MIMO technique uses multiantene or more than one antenna from both the transmitter and receiver sides. The design and realization of the antenna in this paper is used for 5G devices in the future that work at a frequency of 5.4 GHz - 5.6 GHz. Antenna simulation shows that the planned working frequency is between 5.4 GHz to 5.6 GHz, has a Return Loss of -20.007 dB, VSWR ≤ 2, which is 1.2216, 414 MHz bandwidth, gain of 3.898 dB, impedance of 50.00 Ohm, Omnidirectional radiation pattern. From the design and analysis, this antenna can be used as a 5G technology antenna for the future
CONSTRUCT DESIGN DEVELOPMENT OF ROBOTIC HAND ACTUATOR FOR AFTER STROKE PATIENT REHABILITATION
Get PDFThis research is analyzing about construct design development of robotic hand actuator for after stroke patient rehabilitation, implementation for people paralyzed due stroke, the function is to move a paralyzed hand member. It consists of 12 actuators, and for each actuator is driven by DC Motor idependently. This actuator is movements by the other normal hand of stroke patient with symmetrical movements, asymmetry as well some physiotherapy movements that have been programmed. This integration control is carried out using an Arduino Uno microcontroller. The testing of the instrument was carried out by simulating the Simulink test, simulation testing using Proteus and direct testing of the prototype. This research have some diviations, and it happen because of the inertia of tools and equipment. This finding of this research is that robotic hand is quite heavy, and some movements that arise is not according in the program, and the response time is take a long time
The Layer 2 Network Security at SMK Negeri 1 Rantau Alai using DHCP Snooping
Get PDFSMK Negeri 1 Rantau Alai is located at Ogan Ilir Regency, South Sumatera Province. In this Vocational High School (SMK), there are two majors namely Computer and Network Engineering (TKJ) and Software Engineering (RPL). SMK Negeri 1 Rantau Alai already has a computer network that used to communicate all users for file sharing called Local Area Network (LAN). It has been connected to the internet, but does not have a network security system so it`s very vulnerable to hacker intrusion who can do cyber crime. Therefore in this research, researcher built the network security on layer 2 Open System Interconnection (OSI) by utilizing DHCP Snooping technology to avoid cyber crime such as loss of important data from SMK Negeri 1 Rantau Alai database server. To implement DHCP Snooping, researcher need a routerboard Mikrotik device and also a switch that is one of hardware needed on the Data Link Layer. Besides that, Winbox and Putty software are also needed to help in the overall configuration of this research. The results obtained after DHCP snooping configuration done is the ability to recover IP addresse when converted to Fake IP will be able to return to its original IP address and limit the number of users who can access the internet at SMK 1 Rantau Alai Keywords: LAN, DHCP Snooping, Switch, Winbox, Putt
The Decision Support System of the selection of tourist attractions of Bali Island is used Preference method of Organization For Enrichment Evaluation
Get PDFTourism today is very potential to be developed as one source of local revenue by providing information both online and offline and online for the community so that increased regional revenue desired by the government. The number of tourist attractions in Bali to make many tourists from abroad and in the country feel confusion in determining the destination, the most beautiful and easy to reach the place. There are many criteria to be considered, then through this recommender system, tourists can find out what tours they will visit while in Bali. One of the problems of decision making with many criteria and attributes in choosing a tourist attraction is to provide detailed decisions that refer to the weight scale they have. The decision support system gives priority result of tourist attraction suitable for every tourist from abroad and in the country. This research is focused on applying multi-attribute decision making, for decision support system using the preferred method of organization for enrichment evaluation. This research uses the descriptive analytical method to present a summary of survey results made by spreading quizzers to domestic, foreign and foreign tourists, from tourists who want to choose the island of Bali tourism in accordance with cost, security, natural beauty, facilities and infrastructure and location the island of Bal
MONITORING THE USAGE OF MARINE FUEL OIL ABOARD PASSANGER SHIP BASED ON INTERNET OF THINGS
Get PDFMeasurement of the remaining MFO oil in the tank when the ship is sailing makes the crew become more troublesome because it must be reported within a certain period of time, for example every once an hour using a pendulum sensor. The measurement using this pendulum sensor the accuracy and precision of each becomes a deficiency of the value produced because the position of the ship is not taken into account. Another disadvantage of conventional methods is that fraud can occur if the tank capacity is full by manually falsifying measurement data, then MFO can be sold in the middle of the sea to fishermen or smuggled illegally to an outside country. To overcome these problems, the need for special monitoring for the availability of MFO oil in tanks by ship-owners needs to be carried out. In this case the accuracy, precision and the need for data that is always displayed and known by ship-owners is very important for the business management process of the company. For that, a precise, accurate and real-time fuel consumption monitoring tool is needed. As a comparison, manual measurement of appeal sensors was also carried out in order to get a more significant comparison value. There are 4 HC-SR04 ultrasonic sensors needed to get accuracy and precision on the position of the ship such as horizontal, tilted to the right, tilted to the left with a slope of 8 degrees and 16 degrees. The test results have shown that the four HC-SR04 sensors are able to read more accurate than the pendulum sensors in various ship positions. The reading result with HC-SR04 sensor has an error below 5% compared to an error in the pendulum sensor of 7.5%. Then, the mean error on the surface of the tank with the condition of a flat vessel of 2, 08%, on the position of the tilted vessel of 2.17% and the condition of the ship with a bumpy wave of 3.35%. The results of the measurement of the MFO volume in the tank sent through the internet to the monitoring station can be perfectly received so that it becomes accurate and real-time information for the observation of fuel consumption by the company management. Thus the prototype of monitoring the use of MFO fuel on passenger ships can be used to replace conventional measurement models which use pendulum sensors. Keywords: Arduino Uno, Ultrasonic Sensor, Potentiometer Pendulum Sensor, Esp 826
DESIGN OF ZIS MANAGEMENT INFORMATION SYSTEM USING WATERFALL MODEL
Get PDFBasically, the functions of computers are generally used as a medium for storing data and programs in which there are many applications that can facilitate and support a man's work. At the administration of the institution Baitul Maal Pupuk Kujang, data processing about zakat, infaq and sodaqoh (ZIS), reports, and data storage is done manually. Error and inaccuracies of data can be occurring in this case. To help simplify the ZIS management system in that section, program design is the best solution to solve the problems that exist. Data processing is more accurate because of the availability of the form data entry and storage media are centralized in a single database that will make the ZIS management system become more effective and efficient. This aplication program was created with a simple and interactive interface but can process data well and can meet the requirement of the system, so that users can easily use i
Prediction of Elpiji price using artificial neural network
Get PDFElpiji cylinder (Liquefied petroleum gas) are basic life needs of the general public. Unfortunately for customers, unstable elpiji price in retailer. The Indonesian Government plays an important role for the Liquefied petroleum gas industry to give elpiji price stable for end user. This work use artificial neural network and backpropagation for prediction of elpiji price. Total of 1096 records collected from 2015 until 2017 were fed into the neural network models with nine variable for input data. There are inflation, elpiji Allocation, elpiji prices previous, the poor society (the poor, very poor, the near poor), and date (year, month, day). This data were used to evaluate prediction accuracy, and the price prediction results were found to be more accurate than those made by a method using only eight input variable. Root Mean Square Error (RMSE) nine variable 0.030959131, RMSE variable just 0.199884634, and the test result 0.121417236. The presented results were proved that this model can be used with good accuracy for the prediction elpiji price
Sentiment Analysis of Indonesian Figure using Support Vector Machine
Get PDFOn the political year 2018 will be mutually popping reverberated figures for Indonesian presidential candidate 2019. The figures recognition process generally are now using social media, so it would appear the opinions of social media users. Opinions that appeared not only contain positive and negative polarity, but also contain a sentence of subjective and objective. By using a machine learning algorithm, namely Support Vector Machine, made sentiment analysis. The results of the analysis of this sentiment more optimally use the kernel Linear with the F-Measure of Polarity 68%, 68%, 63%, and the F-Measure Subjectivity 73%, 77%, 75% for each figure Anies Baswedan, Joko Widodo, and Prabowo Subianto
COAL DUST CONTROLLER ON INDRAMAYU POWER PLANTS CONVEYOR LANE BASED IOT
Get PDFThe coal is combustion fuel of power plant which is located in Indramayu West Java. Power plant has produce coal dust during combustion process. Moreover, the residu of coal dust has potentially self combustion which damage or could explosived arround the environment. To addressing this situation, detection and controlling combustion dust is needed. To avoid this situation, a prototype devices which able to control combustion dust is proposed. The prototype has comprises of processing signal which controlling by Arduino microcontroller and sensed by MQ2 sensor for flammable gas and MQ135 for CO2 sensor, and Sharp GP2Y1010AU0F for dust sensor.These sensor are detected combustion dust, if the level more than set level then springkle will spray the water. The reading point value of sensors transmitted on to thingspeak IoT could server, which of sensor are consist of methane, gas, CO2, and dust. These value has monitored and able to conduct for controlling the combustion dust. The evaluation shows that the value of sensors are able to delivered as well and the relay as able to activated whenever level of combustion is above