Articles
<![CDATA[Purwarupa Sistem Monitoring Tangki Bahan Bakar Genset pada STO dengan Metode Sensing Akumulasi Kecepatan Fluida (Studi Kasus PT. Telekomunikasi Indonesia) ]]>
<![CDATA[Fahmi Farizal]]>;
<![CDATA[Mochammad Hannats Hanafi Ichsan]]>;
<![CDATA[Gembong Edhi Setyawan]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 4 (2019): April 2019 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (491.914 KB)
<![CDATA[Sentral Telepon Otomatis (STO) is a one of many communication structure belongs to PT. Telekomunikasi Indonesia with purpose to connecting or distributing data from one area to another area. When a STO is down it will be disturbing data distribution to/from another STO. So, PT. Telkom has a secondary power supply is a Genset. Unfortunately, PT. Telkom haven't tank measuring system, that giving a chance for fuel to stealed. On some of this considerations, the author conducted a research using technology to measuring fuel and send the result into database. The author applied a mini-pc with the type of Arduino UNO and feature it with ethernet shield that works for communication mediator data within database and a measuring system. The beginning of system is accumulating liquid per second that through 2 sensors. Result of this proccess, user can obtain result of measuring that can be calibrated so the result have higher accuracy. Accuracy of first sensor is between 92,3% and second sensor is between 95%. Then, result of measuring sent to the database with PHP called-self function and saved in the mySQL.]]>
<![CDATA[Sistem Deteksi Api pada Quadcopter Ar Drone Menggunakan Metode Color Filtering HSV dan YCbCr Color Space ]]>
<![CDATA[Anata Tumonglo]]>;
<![CDATA[Gembong Edhi Setyawan]]>;
<![CDATA[Rizal Maulana]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 5 (2019): Mei 2019 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1129.75 KB)
<![CDATA[Fire events are disasters that occur because of the expansion of the source of the fire that propagates to potentially burned objects. In addition, these events are also often caused by irresponsible human negligence. Therefore risk management is carried out in anticipation of minimizing the impact of losses. One of them is by using a quadcopter to monitor and detect objects. This study was designed to detect hotspot objects in a room through image processing using the ArDrone front camera for sending raw frame data images at UDP port 5555. Image processing is implemented on the ROS platform which is used to connect quadcopter with GCS using OpenCv. This system utilizes the Hue Saturation Value (HSV) Color Filtering and YCbCr Color Space methods. The results of this study are in the form of a system on ArDrone that is capable of detecting hotspot objects. Testing on the system is done by doing detection tests with different distances with reference to the position of the hotspot object, testing the range of HSV value parameters along with YCbCr values in each condition, testing with a certain speed by reference to the position of hotspot objects and testing the system response performance. The results obtained are effective detection distance is 8 meters with an overall percentage of 83.33%, the speed of the appropriate ArDrone quadcopter if detected is with a speed of 1m/s and the system response performance to detect hotspot objects by 0.022 seconds.]]>
<![CDATA[Sistem Deteksi Marka Membujur Garis Utuh dan Putus Menggunakan Metode Thresholding dan Hough Transform Berbasis Raspbery Pi ]]>
<![CDATA[Putra Wijaya]]>;
<![CDATA[Hurriyatul Fitriyah]]>;
<![CDATA[Gembong Edhi Setyawan]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 6 (2019): Juni 2019 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (868.039 KB)
<![CDATA[Road lines with longitudinal line types are road lines that we often encounter on highways, all highways always have this type of marker. Although this marker has the function of dividing the road into two directions and helping motorists drive in place, in fact there are still many traffic accidents caused by not concentrating and are not aware that the driver is in the wrong position. On this basis as an effort to improve driving safety in combination with current computer technology, this study was made a tool that can detect the type of longitudinal road lines with the addition of features to measure the position of the vehicle with markers and provide a warning to driving if the position is in a position danger or violating line markings. Enter from the system in the form of video obtained from the use of a camera mounted on the body of a motorcycle that is parallel to the front wheels of the vehicle. The method used to recognize objects uses a Thereshold blend with Hough Transform so that an image will be produced where longitudinal line can be detected and can be calculated in length with the help of Raspberry Pi 3, then the results of the process will be displayed on the LED lights and sounds from buzzer as output media. From the results of functional testing the tool can detect markers objects and can provide information to users about the distance of vehicles with line markers, as well as sound signals if the driver is in a dangerous condition. In accuracy testing obtained an accuracy of 85% of the video sample with four distance conditions and two type longitudinal road lines conditions. From testing computation time starting from object recognition to processing data takes an average of 1,265 seconds.]]>
<![CDATA[Rancang Bangun Sistem Pembeda Gerakan Berlari dan Berjalan Untuk Atlet Lari Menggunakan MPU6050 dan Metode Klasifikasi K-Nearest Neighbor ]]>
<![CDATA[Agastya Bramanta Sanjaya]]>;
<![CDATA[Dahnial Syauqy]]>;
<![CDATA[Gembong Edhi Setyawan]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 7 (2019): Juli 2019 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (714.727 KB)
<![CDATA[Athletics run is one of sport as archievment. In developing the ability of athletes needs training. Training in athletics running athletes requires at least 2 main components, coaches and athletes. Often the athlete does not do training properly and the trainer does not pay attention to it, this may lead training not getting maximum results. From the problem was create a system that can classify the movement of running, walking and stopping using MPU6050 sensor module with the input are sensor values from gyroscope and accelerometer with method k-nearest neighbor as classification algorithm. This system expected to can help the coaches to monitor the exercise of an athlete by not having to always observe the athlete during exercise and this system is expected can help too coaches conduct training with the number of athletes running more than 1 person in sametime. This system is based on the wearable device used on the athlete's body and sends sensor data to other devices on the trainer. The system has an accuracy rate of 96.7% in distinguishing running, running and silent movements as well as the required compute time of 0.922 seconds.]]>
<![CDATA[Sistem Notifikasi Kondisi Cuaca Untuk Keselamatan Take Off Paralayang Menggunakan Metode Naive Bayes (Studi Kasus: Paralayang Gunung Banyak, Batu) ]]>
<![CDATA[Muhammad Fajaruddin Akbar]]>;
<![CDATA[Dahnial Syauqy]]>;
<![CDATA[Gembong Edhi Setyawan]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 8 (2019): Agustus 2019 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (605.195 KB)
<![CDATA[Paragliding is a free-flying sport using cloth wings (parachutes) that take off and land using legs that use the wind, the wind itself has several types including dynamic lift and thermal lift. The wind in the paragliding take-off area is very important for athletes and tourists who will take off. The lack of information obtained in the take-off paragliding area, especially for most people (tourists) who want to fly, has difficulty getting wind information in the paragliding take-off area. From this problem, this research was conducted to determine the wind conditions in the form of notifications using 3 parameters, namely wind speed, wind direction and the presence of raindrops and then processed using the naive bayes method on the microcontroller that produces safe, alert and hazardous output. The wind speed sensor uses a rotary encoder which has an accuracy rate of 96.4% compared to the existing anemometer, in wind direction reading using a dual axis module which has a degree difference of 7.75 ° and on a rain sensor, the sensor can detect well the presence of raindrops with the results of the whole system compared to the actual situation has an accuracy rate of 85.71%.]]>
<![CDATA[Sistem Tracking Objek Menggunakan Metode Edge Detection pada Quadcopter ]]>
<![CDATA[Dimas Bagus Jatmiko]]>;
<![CDATA[Gembong Edhi Setyawan]]>;
<![CDATA[Hurriyatul Fitriyah]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 8 (2019): Agustus 2019 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1046.315 KB)
<![CDATA[Tracking objects are usually used to determine the position of objects and environmental conditions around the object. Objects that require supervision to be able to run properly require a system to monitor the object. Quadcopter is a type of UAV (Unmanned Aerial Vehicle) that can do several movements (pitch, yaw, roll and gaz). With a camera on a quadcopter, every movement of the object will be known directly through the camera image. So that in this study a system was created to detect and track objects. Applying an image processing system based on image processing using the shape detection method. Then displays the detection results in the frame image which is divided into 9 grids and tracks the object in the form of forward, backward, upward, downward, turn right and turn left. System will be tested based on tracking accuracy of objects. From the testing of object tracking accuracy obtained an average success of 76,6%, failure of 23,4% caused by uncertain lighting in the room and objects with shapes resembling objects that are tracking.]]>
<![CDATA[Sistem Navigasi Otomatis Quadcopter Untuk Menghindari Obstacle Dengan Pengolahan Citra Menggunakan Metode Hough Transform ]]>
<![CDATA[Okke Rizki Kurniawan]]>;
<![CDATA[Gembong Edhi Setyawan]]>;
<![CDATA[Mochammad Hannats Hanafi Ichsan]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 9 (2019): September 2019 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (535.006 KB)
<![CDATA[Drones are vehicles that can be controlled by long-distance pilots. Drones are widely used by many companies to facilitate jobs that are difficult to achieve by humans. This research will apply image processing segmentation on quadcopter to avoid obstacles without manual control (automatic). Digital image processing will use two methods, namely canny edge detection and hough transform. This research will be use a quadcopter of type Parrot Ar.Drone 2.0. The results of the tests conducted in this study will get the accuracy of the quadcopter by using the distance from the width of the obstacle. Testing based on accuracy (errors) obtained from the purpose of this system is 0.07125%. The maximum detection distance on a quadcopter that can be detected is when the width of the obstacle has reached 294 pixels and 142 pixels. And for research time estimation will get an average quadcopter travel time of 7.464857 seconds.]]>
<![CDATA[Klasifikasi Tingkat Kematangan Susu Kefir dengan Metode K-Nearest Neighbor (KNN) menggunakan Sensor Cahaya dan Sensor Warna ]]>
<![CDATA[Faizal Ardiansyah]]>;
<![CDATA[Dahnial Syauqy]]>;
<![CDATA[Gembong Edhi Setyawan]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 9 (2019): September 2019 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (355.932 KB)
<![CDATA[Milk is a product that is classified as rare in Indonesian society and also the age of milk that is classified as short, making it difficult for the community to consume milk every day. Therefore, the prototype of the kefir milk fermentation process is designed using the K-nearest neighbor method. Starting from fresh cow's milk mixed with kefir seeds, after that the freshly mixed kefir milk will be inserted into the dark box in the box, there are color sensors and light sensors that are used to monitor color changes and the light intensity that occurs when fermentation is in progress. The readings obtained by the next two sensors will be determined using the K-nearest neighbor method. The test results obtained to determine the accuracy of the reading of the light sensor is worth 5.12% while the color sensor is worth 8.64% from the results of testing the two sensors, it can be concluded that the readings of the two sensors can be said to be quite good. The test results on the Kefir milk maturity level classification system using the K-nearest neighbor method with 10 times testing found an accuracy rate of 80%. And the average value of system computing time obtained after the calculation of the value of K obtained 353.3ms in 10 times the test.]]>
<![CDATA[Sistem Deteksi Rem Mendadak dan Tabrakan Pada Motor Menggunakan Sensor Akselerometer Dengan Metode K-Nearest Neighbour Berbasis Arduino ]]>
<![CDATA[Musada Teguh Andi Afandi]]>;
<![CDATA[Hurriyatul Fitriyah]]>;
<![CDATA[Gembong Edhi Setyawan]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 10 (2019): Oktober 2019 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (991.406 KB)
<![CDATA[Accident is incident that unpredictable both of victim and witness. But, the accident increased for every years. This is caused by increasing of vehicle unit that ciculate especially motor cycle. When accident happen, family of course doesn't know that an accident has occured to their family who drived the vehicle. So it's needed the system that give the information to the victim family in home. System designed used by many components like arduino mega that used for process datas, accelerometer sensor ADXL345 type for takes datas and GSM SIM900A module as sender of message for victim family. The system uses simple regression as fiture that will be used in K-Nearest Neighbour methode (K-NN) and classification methode K-NN to get incident class. Testing process of system by doing acceleration like brake and crashing and will be classified with K-NN methode so it will get value of accuracy 90% when the tragedy is sudden brake and 60% when accident use K value is 3 for both. While use K valueis 5, a precentage is obtained sytem to get right tragedy is 90% when sudden brake and 50% when accident. So as a whole precentage of system to get right tragedy is 83,33% when use K value 3 and 80% when value is 5.]]>
<![CDATA[Sistem Pembeda Daging Sapi dan Daging Babi berdasarkan Warna dan Kadar Amonia menggunakan Metode Jaringan Syaraf Tiruan Berbasis Android ]]>
<![CDATA[Muchamad Rafi Dharmawan]]>;
<![CDATA[Dahnial Syauqy]]>;
<![CDATA[Gembong Edhi Setyawan]]>
<![CDATA[ Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 11 (2019): November 2019 ]]>
Publisher : <![CDATA[Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (859.63 KB)
<![CDATA[Protein is a substance that is needed by humans to be able to carry out daily activities. Aside from being a source of energy, a lot of other benefits provided by the protein for the body of human. Beef is one of source by protein that's much favoured by the peoples. But, with the high interest making naughty seller take advantage of this situation by mixing pork with beef. These conditions occur because the lack of public knowledge about the difference between both of them coupled with the prices of beef relatively higher. This made the majority people of Indonesians are scared, especially Muslims. So we need a study of systems that can distinguish between beef and pork. With this research it's expected to be able to solve existing problems and minimize cheating by sellers and losses by consumers. This system is designed using TCS3200 color sensor and MQ135 gas sensor because in this study, parameters to distinguish two types of meat are color and ammonia levels. The results of the sensors are used as input for processing by Arduino Nano using Artificial Neural Network (ANN) method to get result of classification by system. The architecture of ANN used in this study consisted of 4 input neurons, 5 hidden layers, and 1 output layer. The main system will be only used for prediction process based on readings value of the sensor. The training process for getting weight values is running on other devices using MATLAB. The results of tests on 30 meat samples as test data produce an accuracy rate up to 90% with an average of computation time 45.3 millisecond.]]>
