IJITEE (International Journal of Information Technology and Electrical Engineering)
Not a member yet
95 research outputs found
Sort by
Development of Bot Detection Applications on Twitter Social Media Using Machine Learning with a Random Forest Classifier Algorithm
No full textA Twitter bot is a Twitter account programmed to automatically do social activities by sending tweets through a scheduling program. Some bots intend to disseminate useful information such as earthquake and weather information. However, not a few bots have a negative influence, such as broadcasting false news, spam, or become a follower to increase an account's popularity. It can change public sentiments about an issue, decrease user confidence, or even change the social order. Therefore, an application is needed to distinguish between a bot and non-bot accounts. Based on these problems, this paper develops bot detection systems using machine learning for multiclass classification. These classes include human classes, informative, spammers, and fake followers. The model training used guided methods based on labeled training data. First, a dataset of 2,333 accounts was pre-processed to obtain 28 feature sets for classification. This feature set came from analysis of user profiles, temporal analysis, and analysis of tweets with numeric values. Afterward, the data was partitioned, normalized with scaling, and a random forest classifier algorithm was implemented on the data. After that, the features were reselected into 17 feature sets to obtain the highest accuracy achieved by the model. In the evaluation stage, bot detection models generated an accuracy of 96.79%, 97% precision, 96% recall, and an f-1 score of 96%. Therefore, the detection model was classified as having high accuracy. The bot detection model that had been completed was then implemented on the website and deployed to the cloud. In the end, this machine learning-based web application could be accessed and used by the public to detect Twitter bots
Improving Phoneme to Viseme Mapping for Indonesian Language
Full text linkThe lip synchronization technology of animation can run automatically through the phoneme-to-viseme map. Since the complexity of facial muscles causes the shape of the mouth to vary greatly, phoneme-to-viseme mapping always has challenging problems. One of them is the allophone vowel problem. The resemblance makes many researchers clustering them into one class. This paper discusses the certainty of allophone vowels as a variable of the phoneme-to-viseme map. Vowel allophones pre-processing as a proposed method is carried out through formant frequency feature extraction methods and then compared by t-test to find out the significance of the difference. The results of pre-processing are then used to reference the initial data when building phoneme-to-viseme maps. This research was conducted on maps and allophones of the Indonesian language. Maps that have been built are then compared with other maps using the HMM method in the value of word correctness and accuracy. The results show that viseme mapping preceded by allophonic pre-processing makes map performance more accurate when compared to other maps
A High-Frequency Surface Wave Radar Simulation Using FMCW Technique for Ship Detection
Full text linkIndonesia is an archipelagic country with a vast sea area. This vast sea area becomes a challenge in conducting regional surveillance to maintain maritime conditions. The use of buoys and satellites still has shortcomings in carrying out surveillance despite its excellent surveillance capabilities. A high-frequency radar technology with 3-30 MHz frequency and surface wave propagation are very suitable because it has a radar range that can cross the horizon or commonly refer to as Over the Horizon (OTH). The Frequency Modulated Continuous Wave (FMCW) technique on this radar obtains distance and velocity information by a continuously transmitted frequency modulation. The use of radar in Indonesia for marine surveillance is still infrequent. Therefore, it is relatively difficult to conduct testing and obtain data. In addition, the direct examination requires extended time, so a simulation program is needed. This paper discusses the design of a High-Frequency Surface Wave Radar (HFSWR) simulation program using FMCW modulation technique. The simulation program detected two objects based on time delays due to the distance and velocity of the object with a maximum range of 350 km. It displayed the results in an informative manner. The object detection was based on the results of the Fast Fourier Transform (FFT) from the mixed signals. The mixed signal is a combination of transmitted signal and reflected signal in which there are time delay components due to the object. The simulation program had been tested with input values of distance and velocity that vary, both for one object and two objects, in the radial direction. It generated output that was close to the input value with a level of accuracy of ± 2 km
LQR Tuning Using AIS for Frequency Oscillation Damping
Full text linkCommonly, primary control, i.e. governor, in the generation unit had been employed to stabilize the change of frequency due to the change of electrical load during system operation. But, the drawback of the primary control was it could not return the frequency to its nominal value when the disturbance was occurred. Thus, the aim of the primary control was only stabilizing the frequency to reach its new value after there were load changes. Therefore, the LQR control is employed as a supplementary control called Load Frequency Control (LFC) to restore and keep the frequency on its nominal value after load changes occurred on the power system grid. However, since the LQR control parameters were commonly adjusted based on classical or Trial-Error Method (TEM), it was incapable of obtaining good dynamic performance for a wide range of operating conditions and various load change scenarios. To overcome this problem, this paper proposed an Artificial Immune System (AIS) via clonal selection to automatically adjust the weighting matrices, Q and R, of LQR related to various system operating conditions changes. The efficacy of the proposed control scheme was tested on a two-area power system network. The obtained simulation results have shown that the proposed method could reduce the settling time and the overshoot of frequency oscillation, which is better than conventional LQR optimal control and without LQR optimal control
Characterization of Electromagnetic Wave Absorbers with Broadside SRR Method on C-Band
Full text linkElectromagnetic wave absorber is a material that can reduce the energy available in electromagnetic waves. Electromagnetic wave absorber can be used to reduce interference in wireless communication devices so as not to quickly suffer damage, as a layer in the room free of reflection and to reduce radar cross section of an object detected in radar tracking applications. In this paper, a discussion about the use of the broadside form using the Split Ring Resonator (SRR) method as an absorber of electromagnetic waves and its characteristics in C-Band. Broadside shape is obtained from the initial form of a square which is developed into a square resonator and then given a gap at the end of the resonator. The results show that the SRR broadside form can be used as an absorbent of electromagnetic waves on the C-Band, precisely the frequency of 6.41 GHz with absorption rates reaching 99.99% and bandwidth of 0.077 GHz with dimensions of 7 mm. From the experimental results, it can also be seen that the change in the gap length variable in the SRR broadside shape is the most influential in changing the resonant frequency value and the amount of bandwidth produced
Design of Web-Based Cashier and Spare Part Warehouse Application Display (Case Study at Surya Motor Shop)
Full text linkA cashier and spare parts warehouse application is an information system facilitating financial reporting and items inventory systems. This has become a necessity in almost all fields of large and small-scale businesses in every country. The information system that belongs to Surya Motor Shop does not have a display that can facilitate users in operating the company's financial and transaction systems in accordance with company needs. This information system uses Bootstrap with HTML, CSS, and Javascript programming languages. In this paper, an interactive display was developed, so as to be able to accommodate web users' responses, by developing a prototype using Bootstrap at the Surya Motor Shop. This was carried out to digitize the transaction system, making it easier to report the items inventory and financial reporting of the company. The prototype development was developed using the The Elements of User Experience method, a user-centered design process. After developing the prototype, a test was carried out to determine the quality of the user experience. The test employed the User Experience Questionnaire (UEQ) method. UEQ testing shown that the prototype interface developed had a positive level of user experience. Compared with the benchmarks set by UEQ, the test results were above the mean benchmark, except for the pull factor which was still below the benchmark average
LNA Prototype at 54 MHz to 88 MHz Using Discrete Components
Full text linkThis paper presents a design and prototyping of a Low-Noise Amplifier (LNA) for Wireless Regional Area Network (WRAN) operating in TV broadcast bands between 54 MHz – 88 MHz. The LNA design was then implemented by using discrete components. Components values was obtained by utilized DC analysis according to specifications which follows the Institute of Electrical and Electronics Engineering (IEEE) 802.22 standard on WRAN technical specifications. Simulation with 88 MHz produced S11 = -5.72 dB, S12 = -41.57 dB, S21 = 15.07 dB, S22 = -4.76 dB, Noise Figure (NF) = 3.9 dB, Input Third Order Intercept Point (IIP3) = 2.21 dBm, and power consumption of 45.39 mW. Experiments results on 88 MHz showed S11 = -6.13 dB and S21 = 0.74 dB
Applying Integrating Testing of Microservices in Airline Ticketing System
Full text linkMicroservices have been applied on several major systems including airlines. The characteristics of microservices which are independent and also interconnected need to be tested. The testing is done to preserve the system’s sequential stage processes, especially the online ticket reservation. Four features which are the search, booking, payment, and booking info feature are tested. This research performed three stages of testing on the microservices, those are unit testing, integrity testing, and end-to-end testing. Unit testing was conducted to test every function on every nodule, integrity testing was done to test interconnection between microservices, and end-to-end testing was to test the final results obtained after the unit test and integrity test were carried out. The three stages of testing must be done sequentially. The system on the airline provides the valid or correct response. Three stages of testing can be applied on other airlines by obtaining a legal API and can be accessed publicly
Design and Comparative Study Among Antennas of GCS for Telemetry Communication System of UAV
Full text linkRecently, Unmanned Aerial Vehicle (UAV) becomes a popular and interesting technology for researchers and academics because it has high potential to be implemented in various fields. The UAV operation is managed by a Ground Control Station (GCS) on which requires a communication system to send control signals and acquire data collected by sensors on UAV. The longer the UAV's flying distance needs a higher transmission power budget that can be achieved by increasing transmitter power, increasing receiver sensitivity, or increasing antenna gain. However, the design of communications systems on a flying platform is limited by the following constraints. The transmitter, receiver, and antenna must be compact, lightweight, and energy-efficient to save battery on the vehicle. Although the antenna does not directly influence the energy consumption from the battery, an increase in antenna gain usually requires an increase of the antenna dimension that causes higher weight and or reduces the aerodynamics. Therefore, the most efficient way to increase the link budget is by modifying the antenna on the GCS. This paper describes the analysis of antennas commonly used in GCSs for UAV communication links, namely the Yagi-Uda, bi-quad, and double bi-quad antennas. The antenna is designed to work at a frequency of 433.5 MHz following the transceiver device used. The antenna designs are numerically simulated then fabricated for evaluating their performance. The testing is done on the following issues, i.e. the antenna's basic parameters measurement, the ground-to-ground transmission test, and the ground to air transmission test. The test results show that the double bi-quad gives better performance than the other two other testing antennas
Design of Quadrotor UAV and Internet-of-Things Based Air Pollution Monitoring Systems
Full text linkAir pollution is one of problems causing global warming that is currently taking a place. Several air quality monitoring devices usually located at the city center are only limited to display data at one point. Therefore, a mobile device to monitor air quality is needed so as to enable the monitoring in several points. This paper aims to design an air quality monitoring system based on quadrotor Unmanned Aerial Vehicle (UAV) and Internet-of-Things (IoT) technology. The sensor system is designed to detect CO, CO2, air quality, and temperature variables. This sensor systems was then integrated with quadrotor in order to make the monitoring process can be carried out at various points. Quadrotor was designed using Ardupilot Mega (APM) 2.6 as the flight controler. Measurement data from system sensor was transmitted wirelessly using internet network via Wi-Fi module. Based on the test results, the sensor system was able to detect concentration of several test gas and was linear to the output voltage. Quadrotor orientation parameters at takeoff produced transient responses in less than 1 second. The air pollution sensor parameter data could also be displayed every 10 seconds on the ThingSpeak and ThingView interfaces, and could be mapped based on the data retrieval coordinates