Articles
6,850 Documents
Query Expansion Pada LINE TODAY Dengan Algoritme Extended Rocchio Relevance Feedback
Chandra Ayu Anindya Putri;
Indriati Indriati;
Ahmad Afif Supianto
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 1 (2019): Januari 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (387.742 KB)
LINE TODAY provides access to up-to-date news contents. Data on LINE TODAY are used to be able to do search engine feature. Query Expansion technique will be very useful if it is to be combined with search engine system where the queries inputted by users are combined with additional queries from the system. These additional queries will make queries generated by users more specific. In addition, users feedback (user judgement/explicit relevance feedback) assessing on each news can minimize ambiguous queries. The process begins with preprocessing technique consisting of several stages which are cleansing, case folding, tokenization, filtering, and stemming. And then, term weighting and cosine similarity. The next process is calculated using the Extended Rocchio Relevance Feedback method which is a traditional method from Rocchio Relevance Feedback to generate an additional queries. The results are obtained from implementation and testing process of Query Expansion on LINE TODAY with Extended Rocchio Relevance Feedback Algorithm resulted an average Precision value of 0.53308, Recall value of 0.81708, F-Measure value of 0.59553, and Accuracy value of 0.9574. The accuracy value obtained with Extended Rocchio Relevance Feedback method based on user judgement increase by 2% compared to automated search by the method of Rocchio Relevance Feedback.
Optimasi Komposisi Pakan Ternak Ayam Petelur Menggunakan Algoritme Genetika
Siti Fatimah Al Uswah;
Budi Darma Setiawan;
Dian Eka Ratnawati
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 1 (2019): Januari 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (611.631 KB)
Raising laying hens are considered a promising opportunity in Indonesia because the demand for eggs in the country continues to increase in line with the increasing human lifestyle and need for animal protein. Based on data from the ministry of agriculture in 2017 there is an increase in chicken egg consumption during the year 1987-2017 of 3.57% per year with an average consumption of 6.63 kg / kap / th in 2017. On the other hand, raising laying hens is costly especially when it comes to livestock feed, which can cost farmers 60% -70% of production costs. One way to reduce the cost of purchasing feed is by optimizing the feed composition, with purpose of achieving an optimal feed composition that also meets the nutritional needs, all obtained with as minimal cost as possible. The optimization method used in this research is Genetic Algorithm with permutation representation, single-point crossover, reciprocal exchange mutation, and elitism selection. This study used 50 feed data material of laying chicken and its nutritional content. From the results of the tests, the population parameters obtained with the highest fitness value in the population of 500 and 800 with the average fitness value of 2.573591, the optimal generation of 100 generations with an average fitness value of 2.479726 and a combination of probability of crossover 0.5 and the probability of mutation 0.3 with the average fitness value 2.58459. The final result is the composition of laying chicken feed that meets the nutritional needs with minimal cost.
Rancang Bangun Pengamatan pH Air Menggunakan Protokol MQTT
Cahyo Karya Basuki;
Dany Primanita Kartikasari;
Achmad Basuki
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 1 (2019): Januari 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (529.971 KB)
Water pH is the most important aspect in the field of fisheries, especially in fish cultivation in ponds. PH monitoring problems, currently very much talked about one of them is weather changes that make the management sometimes forget or are lazy to check. So that the role of technology is needed that can help overcome the problem, to convey water pH data to managers remotely. IoT or the Internet of Things is a technology concept whose application can be used to help overcome these problems, where the system works is to connect physical objects with internet communication. IoT requires a protocol to run data transmission that functions as data transport from sensors to users on a network. The protocol used is MQTT (Message Queuing Telemetry Transport) where the protocol is expected to work in low bandwidth and unrealiable networks. The mechanism applied to the system used is publish-subscribe. With a sensor node on Arduino microcontroller as a publisher. Then the Raspberry Pi microcomputer is a server that functions as a broker, time control middleware and data storage. Subscriber as the data requester adopts from java language as a simple interface to the user so that it is easy to read. From the implementation that has been made, it is obtained the results of system testing that matches expectations and obtains protocol kinerja protokolnce which refers to the average latency and delay values ​​below 1 ms, which are 0.31 ms and 0.71 ms with a test time of 3x24 hours.
Peramalan Status Siaga Banjir Berdasarkan Data Curah Hujan (ARR) dan Tinggi Muka Air (AWLR) Menggunakan Metode Fuzzy Time Series (Studi Kasus: Perum Jasa Tirta I)
Arina Rufaida;
Muhammad Tanzil Furqon;
Bayu Rahayudi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 12 (2018): Desember 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (828.995 KB)
Flood is a condition where water flow is higher than normal water level so it flooded the surrounding area. Floodwaves flow from upstream to downstream and interact with increasing water capacity of the estuary. Floods can occur due to high rainfall, overflow from the river, the destruction factor of Watershed (DAS). From that point on, a system that is able to forecast to make it easier to analyze the flood alert status in the future. Regression method used in this research is Fuzzy Time Series. The FTS method is a model usually used to forecast data in sequence. This research has a goal to forecast flood alert in Kambing Station DAS Brantas . The results of the test show the prediction of flood alert on the water level data (AWLR) that is in December 2016 got the error value (RMSE) of 2.89 and rainfall data (ARR) in February 2015 got the error value (RMSE) of 16.0. Both data resulted flood alert forecasting that shows Normal.
Implementasi Protokol UDP Pervasive Multi Device untuk Perangkat myRIO Berbasis LabVIEW (Studi Kasus : Security Box)
Octavian Metta Wisnu Wardhana;
Rizal Maulana;
Wijaya Kurniawan
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 1 (2019): Januari 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (429.447 KB)
Pervasive computing is one application of ubiquotous computing that is useful to facilitate the computer operation by minimizing the need for human interaction to the computer. While UDP Pervasive Multi Device is a UDP protocol developed using pervasive computing to be able to recognize the identity of other devices without the need for manual settings from the user. In this paper the UDP Pervasive protocol can be implemented on PC and NI myRIO devices using LabVIEW-based programs. UDP protocols are used because they do not require handshaking to reduce delay and smaller data sizes due to the absence of acknowledgment fields and sequence fields. Each device uses dual state machine system design that has function for detecting other devices automatically and as an application of using other devices address. When the program is first executed, the device broadcasts to all devices. Then the device does listening to receive broadcast data or replies from broadcast. When receiving broadcast data or replies then the device checks the duplication of the device and stores it. The device then sends a reply when receiving broadcast or back to listening. By using the same state machine to detect all device, the device can recognize other devices more than one on the same network. The results of the test obtained that all state-based testing succeeded 100%. Discovery time averaging 0.202754 seconds for 1 myRIO and 0.303201 seconds for 2 myRIO. Sending data delay from PC to myRIO not more than 2 second.
Optimasi Penjadwalan Ujian Akhir Semester Menggunakan Algoritme Genetika (Studi Kasus: SMAN 5 Malang)
Ni'mah Firsta Cahya Susilo;
Budi Darma Setiawan;
Agus Wahyu Widodo
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 1 (2019): Januari 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (467.466 KB)
Scheduling is an activity with detailed division of time for various purposes in various fields. Scheduling of the semester final exam at SMAN 5 Malang in practice there are still some obstacles such as limited examination supervisors and the distribution of the subjects tested is less suitable. SMAN 5 Malang has applied the exam schedule by dividing subjects based on national examination subjects and other subjects. This study aims to determine the effect of parameter changes on genetic algorithms and find a scheduling solution for the semester final exam at SMAN 5 Malang with a genetic algorithm. Scheduling the final semester exam in this study is divided into subject scheduling and scheduling of exam supervisors. The testing of individual subjects and supervisors is carried out 5 times with population size of 100, number of generations 500 and combination of crossover rate 0.5 and mutation rate 0.5. Testing results in an optimal population for 180 subjects while for supervisors a total of 150. In testing the combination of Cr and Mr values ​​found a combination of optimal values ​​for individual subjects is Cr = 0.7 and Mr = 0.3 and a combination of Cr = 0.6 and Mr = 0.4 for individual supervisors with an optimal number of generations in individual subjects is 200 generations while in individual supervisors is 400 generations.
Pengembangan Aplikasi Manajemen Perencanaan Bahan Baku Dan Pemesanan Pada Konveksi Sablon Malang
Fakhruzzahid Wahdah;
Bayu Priyambadha;
Denny Sagita Rusdianto
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 1 (2019): Januari 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (451.132 KB)
Sablon Malang is one of the examples of convection and screen printing business operates 24 hours per day, even more sablon malang split production layout apart from each other. Place the store sablon malang, production of the convection, and the production of screen printing process so that separate orders require time and effort for the workers. Sablon Malang in the record-keeping of raw materials also still using manuals so that the order in the machining process occurs frequently run out of raw materials which resulted in an order to be late. Overcoming these problems made the raw material management system and bookings are expected to facilitate and monitor all activities of the production process. This system uses the method Requirement Material Planning for the create all machining process both raw materials as well as the booking process. This research starts from the needs analysis system that is carried out by means of direct observation and interviews in Sablon Malang. Then done done stage design which contained the design architecture, designing interfaces, designing data structures and designing components while the implementation phase will implement all of the design already made, both performed with the Object Oriented approach. Testing phase using Unit testing, Non Functional Testing, and Validation Testing.The results of testing valid percentage i.e. 100%.
Diagnosis Penyakit Tanaman Melon Menggunakan Metode PROMETHEE
Dito Rizki Pramudeka;
Nurul Hidayat;
Randy Cahya Wihandika
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 12 (2018): Desember 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (426.924 KB)
Cultivation of melon plants requires optimal care and appropriate environmental conditions, as they are susceptible to pest and disease infections. This leads to crop failure due to errors from the handling and selection of the pesticides used in tackling them. The agricultural extensions at this time are still have some difficulty to identify the diseases that attacked the melon plants despite the clear differences between each melon plants and determine the solutions for handling and to eradicate the disease. Based on the said problems, a melon plants' diseases diagnosing system is designed. The Promethee method can be used as a decision-assisting method by comparing the symptoms of one disease with another using the criteria of preference. In the melon plants' diseases diagnosing system using Promethee method's main functions are calculating the value of paired comparison deviation for each disease and calculate the value of stream flow in the form of Entering Flow, Leaving Flow, and Net Flow. The melon plants' diseases diagnosing system using 30 test data resulted in an accuracy rate of 86.67% by using Usual and Gaussian preference criteria. The difference in the level of accuracy in each type of preference is determined by the weight of each symptom from each disease as well as the indifference threshold and the preference threshold used in the calculation.
Pengembangan Aplikasi Mobile Location Based Service Berbasis Android Untuk Pencarian Lokasi Rumah Sakit Di Kota Malang Berdasarkan Asuransi Kesehatan Dengan Metode Agile System Development
Sabil Prihastomo Seputro;
Herman Tolle;
Komang Candra Brata
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 1 (2019): Januari 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1249.735 KB)
Malang City is one of the big cities in East Java and its health development began to develop every year, and one of the health service that widely available is hospital. Now, people in Malang City can get treatment to the hospital easily with the existence of health insurance. But with the existence of various kinds of health insurance causes various troubles. People who own one kind of the health insurance confused when they want to search the hospital that received their health insurance because not all of the hospital will received all health insurance. People who were in emergency situation and require doctor attention immediately must find the nearest route to the hospital. If the targeted hospital does not receive their health insurance and the handling is late, it will be fatal and may even lead to death. To decrease those impact, people must able to search the hospital based on health insurance and routing from user location to the hospital location, with making an application that using GPS & API Google Maps with Agile System Development method that implemented on Android. The creation of Hospital Locator application intends to know the performance of each functional of the system, then it will be tested through validity testing as well as be testing with usability testing in the form of usability score and Likert scale to know the quality of the system. The result of the validity testing obtained that the functional of the system has been running well with 100% success rate. The result of the usability testing, the system gets score 92,91% which can be categorized as an A and user can operate the system easily and feel helpful about it.
Perolehan Informasi Rating Buku Berdasarkan Gambar Sampul Buku Menggunakan Metode Scale-Invariant Feature Transform
Hamim Fathul Aziz;
Yuita Arum Sari;
Randy Cahya Wihandika
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 1 (2019): Januari 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (573.188 KB)
Along with the development of technology, almost kinds of all information are available on media online. The expanding technology are expected to make it easier to access all kinds of information in media online. As an example by searching book's rating automatically in media online by utilizing book cover. With the existence of a system that can find the book's rating by using the image on the cover getting from camera phone hopefully can make it easier and make it more fast to get rating information from the book, so it can make the customer do less mistaken when buying a book. Based on explanation above this research will uses scale-invariant feature transform to recognize the book's object in an image. Before find the appropriate image of the book; First, preprocessing will be doing on the image by searching for scale space; Then, find the key point or key point localization; Next, by calculation of pixel's angle or orientation assignment; Finally, transforming of the image descriptor or key point descriptor. On this research the image will be tested of this effect on light intensity, image rotation, and scaling. The result by matching test the image of book's cover using scale-invariant feature transform method has high accuracy in condition of bright light intensity and it has low accuracy when using image rotation and image scaling. The average accuracy can obtain in bright light conditions, rotation, and scaling are 90%, 57.5%, and 46.6% respectively.