Articles
6,923 Documents
Sistem Penghitung Protein Telur Berdasarkan Volume Menggunakan Komputasi Citra Metode Cakram Berbasis Raspberry Pi Dan Perangkat Android
Muhammad Riyyan Royhan;
Hurriyatul Fitriyah;
Agi Putra Kharisma
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 3 (2019): Maret 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (841.894 KB)
Inappropriate daily intake of protein can cause various diseases. Information about protein content of a food is very useful because with that information, people can know and regulate the level of proteins that they consume. Therefore, chicken eggs as a cheap and easy source of animal protein are important foods to know about their protein value. Research on eggs that have been widely made makes information about egg protein content can be known from the weight of the egg itself. Egg weight can also be found based on its volume. Egg volume can be calculated from the surface area of the egg using disk method. The surface area, and volume of egg can be known by computing the image of the egg. The Image computation to find egg volume can be done by using Raspberry Pi which is assisted with an Android device as an image taker, and also as a system interface. This research embodies a system that is capable of processing egg images to calculate the value of volume, weight, and protein content of the eggs. The system is tested for its accuracy based on its measurement results of the volume and the weight of the eggs, compared to the measurement results of ordinary measuring instruments. The final results of the test show that the system has an accuracy value of 95.76% for measurement of egg weight and 93.94% for measurement of egg volume.
Pengembangan Sistem Monitoring Aset Berbasis Lokasi Pada Platform Mobile
Muchammad Rizal;
Herman Tolle;
Lutfi Fanani
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 2 (2019): Februari 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1267.067 KB)
In an organization or company certainly has assets to support its operational activities, so it is very important to do the maintenance of the asset itself. Asset maintenance aims to track the status of the asset, including the location and condition of the asset. Maintenance of high-level assets with integrated systems is needed to increase effectiveness in carrying out asset maintenance. At the Faculty of Computer Science asset maintenance activities are carried out manually, namely by the staff tasked with examining assets directly, then the damaged assets are written in the book for later making reports manually. The manual bookkeeping causes data loss and poor data grouping. Location-based asset monitoring systems are designed and built to improve the effectiveness and efficiency of manual asset maintenance processes. This system is built on a mobile basis. This system uses location based service that will make it easier in the process of mapping the location of scattered assets and matching the location of monitoring and location of assets. Based on the results of usability testing shows that 89.8% of users agree that the system is worthy of being used and applied. Whereas in the functional and non-functional test results that this system is valid and feasible to use. This shows that this system has been successfully implemented in the asset maintenance section to produce applications that can be accepted by users, especially users in the Equipment Division of Faculty of Computer Science.
Pengembangan Sistem Pengumpulan Promo E-Commerce Berbasis Website Dengan Menerapkan Teknik Web Scraping Dalam Proses Pengambilan Data Promo
Fegreit Rizda Wibowo;
Denny Sagita Rusdianto;
Achmad Arwan
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 3 (2019): Maret 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (699.394 KB)
Shopping is an important activity in fulfilling everyday human needs. Currently the Indonesian people are changing their behavior in shopping by choosing to transact online rather than conventionally. Online transactions known as e-commerce. The growth of e-commerce in Indonesia is currently very high, judging by the large number of e-commerce available. In this study identified problems in e-commerce where there are many promos available, causing consumers to check e-commerce promos one by one. After observing and surveying the questionnaire in this study, respondents needed a system to collect promos from various e-commerce. Based on these problems, research was conducted to build a system that can provide information related to promos found on e-commerce, the system can collect promos from various e-commerce websites using the web scraping method. The development of this system follows the software development process that starts from the stage of needs analysis, design, implementation, and testing of the system. This system is expected to facilitate consumers in e-commerce promo searches and provide appropriate promo information. The results of unit testing, integrase testing and validation testing produce a 100% valid value. In compatibility testing the results show that the system can run on 8 different types of browsers.
Klasifikasi Jenis Makanan dari Citra Smartphone Berdasarkan Ekstraksi Fitur Haralick dan CIE Lab Color Moment Menggunakan Learning Vector Quantization
Akhmad Muzanni Safi'i;
Yuita Arum Sari;
Sigit Adinugroho
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 3 (2019): Maret 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1388.279 KB)
Choosing a food becomes something important for sufferers of certain diseases. However, choosing a food is a problem for people who taste a food for first time or tourists who are visiting a country for first time. To overcome these problems, research needs to be done to identify / classify a food image. The Haralick and CIE Lab Color Moments features are proven to produce good features for classification cases. The Learning Vector Quantization method is also an alternative for classification process. Based on the k-fold cross validation with k = 10 and accuracy as evaluation method, the maximum accuracy is 0.642051 with learning rate parameter value is 0.2, the learning rate multiplier is 0.8, the m value is 0.1, the epsilon value is 0.4, maximum iteration is 10 and minimum learning rate is 0.000001. This result shows that food image classification based on Haralick feature extraction and CIE Lab Color Moment using Learning Vector Quantization produces fairly good accuracy. In addition, the use of both texture (Haralick) and color features (CIE Lab Color Moments) has an effect on the results of accuracy. This is indicated by all the test results which show that the highest accuracy results are achieved using texture and color features.
Pencarian Berita Berbahasa Indonesia Menggunakan Metode BM25
Khalisma Frinta;
Indriati Indriati;
Putra Pandu Adikara
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 3 (2019): Maret 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (881.297 KB)
Rapid technological developments have resulted in increased use of the internet as a source of online information providers from around the world. Users use a search engine for searching information. These developments also make digital document storage increase. News is a source of information about an event or opinion that has important and interesting value to be widely publicized through the mass media. The unlimited reach of readers and the efficiency of time makes the various media reports turn to online media. Information retrieval aims to produce documents that are relevant to the needs of users of a collection of information automatically based on keywords in the queries given by users. The application of information retrieval is expected to facilitate information retrieval and obtain accurate results. BM25 is a system in the ranking process that is used to sort the results of a match (similarity) to all training documents based on the query. The BM25 method is categorized as the best method in the best match class. Tests are based on precision @k values ​​and r-precision values ​​for 12 queries. The best test results for precision @k values ​​when k=5, which is 0.83. While the best results for r-precision values ​​are 1.
Sistem Penghitung Jumlah Orang Melewati Pintu Menggunakan Metode Background Subtraction Berbasis Raspberry Pi
Diego Yanda Setiawan;
Hurriyatul Fitriyah;
Issa Arwani
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 2 (2019): Februari 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1128.578 KB)
The center state of the crowd such as shopping centers, libraries and so on are the places that many people visit. This data is very important because it can be used as interest indicator. In this research is needed a system which can provide an information about the number of visitor so manager can do monitoring of the place. Possible technologies in making this system is to uses digital image processing and computer vision. Background Subtraction Method useful to detect moving objects. From the test results, the Background Subtraction method can detect moving objects very well, opening and closing can improve image results. The success rate when one person enter is 87,5% and exit is 87,5%, The Accuracy when two persons enter at the same time is 87,5% and exit is 100%. Overall the Average accuracy obtained by this system with a certain angle camera when one person enter is 75% and exit is 78.75%, The Accuracy when two persons enter and exit at the same time is 71% and 71%. Also the best camera angle while capture images when one person pass is 70°,80°, 90°. when two person pass at the same time 50°, 70°.
Implementasi Protokol MQTT Untuk Sistem Monitoring Perangkat IoT
Zavero Brillianata Abilovani;
Widhi Yahya;
Fariz Andri Bakhtiar
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 (1146.976 KB)
Internet era at this time has developed a technology called Internet of Things as known as IoT. Where IoT is able to transmit data automatically from computer to computer without the initiation from humans. However, with size and number of data that increased will be transmitted make IoT devices performance has a negative result. Efforts are being made to overcome these problems, namely the need for a system that is able to manage devices and can monitor and maintain availability of IoT devices. One way is to make an IoT device monitoring system that aims to monitor when there is a disruption to the device. By implementing the MQTT protocol which is a protocol that implements the publish-subscribe mechanism and runs on the application layer. The MQTT protocol can process the send and receive of messages to manage and monitor according to the user's wishes, because the send and receive of messages by predetermined topics. Based on results rather than testing, the MQTT protocol has a smaller resource requirement than the UDP protocol and has a smaller data packet size than the SNMP protocol. The IoT device monitoring system that uses the MQTT protocol also has a small delay of 0.008634 sec and a throughput value of 9.2 MBit / sec. So that the system can run on low bandwidth and high latency.
Sistem Diagnosis Penyakit Kelamin Pada Pria Menggunakan Metode Forward Chaining Dan Dempster-Shafer
Kukuh Bhaskara;
Nurul Hidayat;
Lailil Muflikhah
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 3 (2019): Maret 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (675.279 KB)
According to the World Health Organization (WHO), more than 1 million sexually transmitted infections (STIs) occur every day. In one year there were an estimated 357 million new cases of sexually transmitted infections (STIs) worldwide. Sexually transmitted infections are all infections both bacteria, viruses, and fungi that are transmitted from one individual to another through sexual activity or through genital organs. For example, a newborn baby can contract gonorrhea from his mother as a result of passing through the vagina infected with N. Gonorrhoeae. According to WHO, more than 30 types of bacteria, viruses and parasites have been identified that can cause sexually transmitted diseases. 8 of these 30 species are known to have the greatest risk of causing sexually transmitted diseases. The purpose of this study was to implement the Forward Chaining and Dempster-Shafer method and testing the accuracy of the Forward Chaining and Dempster-Shafer method in identifying venereal disease in men. The results of the study shows that the accuracy of the expert system based on 35 data tested is 94.2% indicating that this expert system can function properly, namely the diagnosis of the system in accordance with expert diagnosis.
Seleksi Fitur Information Gain Pada Temu Kembali Citra Jenis Makanan Menggunakan Dominant Color Descriptor Dan Gray Level Co-occurence Matrix
Sulaiman Triarjo;
Yuita Arum Sari;
Sigit Adinugroho
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 3 (2019): Maret 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (511.887 KB)
Nutritional information on social media is supported by image of food being reviewed. It requires hard work to explore similar foods that have almost same nutrition. Therefore an information search system is needed to speed up the information search process. This research has been conducted to be able to search for similar informations based on a query in form of image. It uses Dominant Color Descriptor method for color feature extraction and Gray Level Co-occurence Matrix method for texture feature extraction and information gain selection feature to select texture features. The data used were 29 types of food imaged with total is 435 images which each type has 15 images. Testing is done by comparing the performance of calculation of Euclidean distance, Chebyshev distance, and Manhattan distance for texture feature and Quadratic distance and Yang distance for color feature. The evaluation uses MAP value, test result using only the texture feature obtained MAP value of 0,5542 using Euclidean distance and without feature selection. The test result using only color feature obtained MAP value of 0,7488 when using Yang distance. And testing using color feature and texture feature obtained a value of 0,7118 by using Manhattan distance and Yang distance with 10 features. In this research, the use of DCD was more effective than GLCM by producing higher MAP value.
Pengembangan Aplikasi Native Pelaporan Kerusakan Jalan Pada Platform iOS
Alfin Taufiqurrahman;
Fajar Pradana;
Fitra Abdurrachman Bachtiar
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 3 (2019): Maret 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1033.041 KB)
Road damage is a common thing found on city streets. Not a bit of road damage causes discomfort in driving to cause accidents. Not a few people are anxious about the road conditions. The amount of public desire to be able to report road damage so that roads can be repaired quickly is quite high. Therefore, a facility is needed for the community to be able to easily and quickly convey their concerns regarding road damage. The Laporjalan application offers these conveniences. By using the geotagging feature and taking pictures with an iOS-based smartphone camera. Using the Firebase database as online storage, users can also find out which roads have road damage, from the level of minor damage to severe damage and monitor the progress of damaged road reports that have been sent. The road damage report sent by the user will be used by the relevant agency as additional information for road repairs. Developed with an iterative method, Laporjalan applications can easily adjust its features to user needs. Based on the results of testing with usability testing, obtained a value of 74 for Laporjalan application, where this value falls into the category of acceptability rating with the level is good so that this application can be said according to user needs.