Claim Missing Document
Check
Articles

Analisis Konsumsi Energi Protokol Routing Fisheye State Routing (FSR) Pada Mobile Ad Hoc Network (MANET) Wildan Aulia Rachman; Primantara Hari Trisnawan; Mochammad Ali Fauzi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 5 (2019): Mei 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1036.721 KB)

Abstract

Mobile Ad Hoc Network (MANET) is a type of ad hoc network that has a dynamic and fast-changing topology in which nodes on MANET are dynamically connected in an orderly manner. In this study Fisheye State Routing (FSR), a routing protocol uses a link state algorithm optimization using the fisheye approach. From the use of these techniques, each node will be grouped according to the distance or hop. In this case the use of energy becomes a matter that needs to be considered in the consumption of energy used in the simulation using NS-2.35. By using energy models, the simulations can produce presentations of energy consumption at nodes with different mobility. the total consumption scenario with the number of nodes 20,30 and 50 in each mobility shows that static mobility has the largest total energy consumption in 2 node scenarios namely 20 and 30 nodes namely 19997,969 and 29995,565 joules but static mobility has less in total energy consumption compared to the other 2 mobility with the use of 50 nodes, which is 499973,065 Joules. In the scenario the average energy consumption has the same results as the total energy consumption scenario. Increasing and decreasing energy consumption in mobility used by different nodes can be influenced by changes in the number of nodes and changes in mobility of each node.
Prediksi Rating pada Reveiw Produk Kecantikan Menggunakan Metode Contextual Valence Shifters dan Regresi Linear Nanda Firizki Ananta; Mochammad Ali Fauzi; Sutrisno Sutrisno
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 5 (2019): Mei 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (323.841 KB)

Abstract

At present there are various kinds of beauty products. With a variety of products, the selection of beauty products in accordance with the needs must be done to get the best results. One way to choose beauty products for consumers is to look at reviews along with ratings of the products to be purchased. But with the existence of various review sources, it is not uncommon for the review not to be accompanied by a rating, making it difficult for the consumers to see whether the product to buy is a good product or not. Therefore, this research aims to categorize the review into a rating so that it is easier for consumers to determine the selected product. The system built in this research uses the Contextual Valence Shifters and Linear Regression methods and the use of n-grams includes taking the word bigram, trigram, and review sentences. In system testing, the highest results for the tolerance 0 testing model are 21,6% for bigram and trigram, the tolerance 1 test model the highest accuracy is 66,5% for bigram and for sentiment review is 62,4% for bigram. From the results of the tests, the use of n-gram especially bigram had a positive impact on the results of system accuracy.
Identifikasi Jenis Penyakit Mental Ansietas Menggunakan Metode Modified K-Nearest Neighbor Zubaidah Al Ubaidah Sakti; Budi Darma Setiawan; Mochammad Ali Fauzi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 5 (2019): Mei 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1057.689 KB)

Abstract

On every levels of society and age must have experienced anxiety, from early state to disorder state. Not everyone knows how to deal with it, if it not treated it would become dangerous mental illness for mental and physical condition. There are six kind of anxiety , that is General Anxiety Disorder, Panic Disorder, Social Anxiety Disorder, Specific Phobia, Obsessive Compulsive Disorder, and Post Traumatic Stress Disorder. In this research will be conducted the identification for kind of anxiety based on Hamilton Rating Scale of Anxiety (HIRS) questionnaire with Modified K-nearest Neighbor (MKNN) for the research method. Unlike K-Nearest Neighbor (KNN), MKNN is another version of that where on MKNN training data must be validated first and for the class voting would be weighted. This research indicates that MKNN could identify anxiety better on unbalanced data used 96 training data and 24 test data with value of h=1 and optimum value of K=3 with best average result 95%, while on balanced data with optimum value of K=2 best average result is 93,333%. This research also indicates as comparison with KNN that in this case resulted on KNN has better result processing balanced and unbalanced data because of noisy data on weighted process, and the result from K-fold Cross Validation that conclude the system is capable enough.
Peringkasan Review Konsumen Restoran Menggunakan Weighted Frequent Itemset Mining Moh Iqbal Yusron; Fitra Abdurrachman Bachtiar; Mochammad Ali Fauzi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 5 (2019): Mei 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (491.844 KB)

Abstract

Review written by customer toward a restaurant can be useful for prospective customer or owner of the restaurant to knows the others opinion about the restaurant. However, this can cause a problem if customer review comes in large number. Automatic text summarization system can be a good solution to this problem. One of the best known method for automatic text summarization is TF-IDF weighting. Yet, this method also has a weakness for having tendency to extract long sentences as summary which has high score for contaning many words. In this research, writer propose an approach to use automatic text summarization which not only extract sentences based on its weight but also the ones which covered some words. This is because in the sentences which considered as summary, exist some words which appear together frequently (frequent itemset). Therefore, in this research Weighted Frequent Itemset method is used to summarize customer review for restaurant. This method summarize text by extracting sentences which covered many frequent itemsets and has high sentence relevance score. The result from the test shows that summarization using Weighted Frequent Itemset Mining method archieve average F-measure 0.279.
Analisis Perbandingan Kinerja Multiprotocol Label Switching dengan Mekanisme Label Distribution Protocol dan Traffic Engineering Rahmat Yani; Primantara Hari Trisnawan; Mochammad Ali Fauzi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 5 (2019): Mei 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (684.849 KB)

Abstract

MPLS is a forwarding method to forward a package together with the label attached to each package, this process is called label switching. Routing protocol mechanism to distribute label on MPLS is divided into two types; those are Label Distribution Protocol (LDP) and Traffic Engineering (TE). LDP is a basic routing protocol used in MPLS network, using label switching. TE is a technique to manipulate network traffic to control the traffic load on the network. With the differences of MPLS mechanism using LDP and TE, indubitably the way of working and the performance of those routing protocol are also different. Graphical Network Simulator 3 (GNS 3) is employed to simulate MPLS using LDP and TE with Brawijaya University (UB) topology. Examination scenario are performed by sending package between 2 local networks outside the main network of UB's topology. The parameters are round trip delay to find out delivery speed and convergence time to know the speed of choosing the best route to reach destination when dead link occurs at delivery process. The purpose of this research is to compare the performance of MPLS using LDP and TE on the computer network routers. The results are, MPLS using TE has better performance because the delivery uses the explicit route on the tunnel. There's no need to search for designated router as used in MPLS LDP that makes the router looking for the best path when branching occurs. Using backup route also helps MPLS using TE to reduce convergence time when failure occurs at the delivery of the package.
Penerapan Term Frequency - Modified Inverse Document Frequency pada Analisis Sentimen Ulasan Barang menggunakan Metode Learning Vector Quantization Moch. Yugas Ardiansyah; Mochammad Ali Fauzi; Sigit Adinugroho
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 6 (2019): Juni 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (456.314 KB)

Abstract

In online stores there are reviews of items that contain comments about feedback from previous buyers that are useful for subsequent buyers as well as sellers at online stores. Reviews Usually consist of negative comments or positive comments. The number of reviews is very much. In overcoming this problem, sentiment analysis is needed. This study uses the Learning Quantization Vector and Term Frequency-Modified Inverse Document Frequency methods. The LVQ method was chosen because it has the advantage of being able to summarize the dataset into a codebook vector. The data used consisted of 250 positive comments and 250 negative comments. The data will be preprocessing, weighting the word using TF-mIDF and consequently using the LVQ method. The results of testing the LVQ parameters obtained an accuracy value of 75.11%, recall of 75.11% precision of 77,80%, f-measure of 76.43% with parameter values ​​of learning rate 10-3, dec α 10-6, and values maximum epoch 19. Based on the final test results, obtained the value of the Learning Vector Quantization method with TF-mIDF resulted in an average accuracy of 72.47%, recall of 72.47%, precision of 76.39%, and f-measure of 74.33 % and using the Learning Vector Quantization method with TF-IDF resulted in an average accuracy of 54.80%, recall of 54.80%, precision of 54.30%, and f-measure of 52.61%.
Prediksi Rating pada Ulasan Produk Kecantikan menggunakan Metode SO-CAL in an Inheritance-based Lita Handayani Tampubolon; Mochammad Ali Fauzi; Yuita Arum Sari
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 6 (2019): Juni 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (430.203 KB)

Abstract

The development of technology as an access to information about beauty products offered through internet is getting faster, especially about the review of beauty products that can help manufacturers to find out feedback about products from users, and help consumers to choose the appropriate beauty products easily. The product user can provide ratings and reviews on the sites that have been provided. Sometimes manufacturers and consumers have difficulty in differentiating and categorizing reviews into a rating as a determinant of the quality of a product. Therefore, a system is needed to simplify the right prediction of consumers or users of products on beauty products. In this study, a system was built using the calculation of the SO-CAL in an Inheritance-based method which applied on the K-NN algorithm and linear regression in the rating prediction. Results shows that the study using the SO-CAL in Inheritance-based method by testing using the Cross Validation / k-fold method obtained the average linear regression accuracy of 66% while the highest average accuracy of k-NN is 50% at Tolerance testing model 1. The average RMSE results in linear regression is 1.3628 while the k-NN algorithm is 2.1314. Hence, it can be concluded that the SO-CAL in Inheritance-based method is preferably applied to linear regression compared to the k-NN algorithm in the predicted rating.
Prediksi Rating Otomatis pada Review Produk dengan Metode Contextual Valence Shifters, K-Nearest Neighbor (K-NN), dan Regresi Linear Ahmad Galang Satria; Mochammad Ali Fauzi; Sutrisno Sutrisno
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 8 (2019): Agustus 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (365.006 KB)

Abstract

The growing use of communication media makes information easy to obtain including information on products provided in online stores. The rating feature on the website is a way to see the quality of the product to be purchased so as not to make a wrong choice when purchasing a product that can have a bad impact. Abundant data about product reviews in various online sources are useful as study material for producers in improving product quality. The existence of review data that is found without accompanying the rating makes it difficult for producers to determine the review into a particular sentiment. In this study can accelerate the determination of reviews into sentiment in the form of rating. This study uses a linear regression method and k-nearest neighbor as a prediction method and the method of weighting the contextual valence shifter based on the lexicon dictionary after pre-processing. The use of n-gram includes unigram, bigram, and trigram aimed at increasing the accuracy of the system. The greatest percentage is obtained at tolerance 1 with the results obtained by trigrams greater than bigram or unigram with linear regression method, namely 77% accuracy while k-NN gets 75% accuracy at k = 20 and k = 30. The test results show the use of n-grams, especially bigram and trigram has a positive impact on the results of system accuracy.
Klasifikasi Tweets Pada Twitter Menggunakan Metode K-Nearest Neighbour (K-NN) Dengan Pembobotan TF-IDF Rakhman Halim Satrio; Mochammad Ali Fauzi; Indriati Indriati
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 8 (2019): Agustus 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1258.626 KB)

Abstract

Twitter is a microblog that is currently favored by many people and has turned out to be a very fast spreader of information at this time. Information released and circulates through this media is very free and has many variations, like news, opinions, questions, criticisms, comments either positive or negative. Classification is a rule in text mining that collects content based on the similarity of the script. With this classification allows a tweets on Twitter to be grouped into one based on the category. For example, football, basketball and chess content are grouped into sports categories. Prosedure of classification begins using preprocessing, then term weighting is done, then categorization consists of cosine similarity calculations. Preprocessing itself consists of several phases, that is document cleaning, tokenizing, stopword removal, and stemming. The word weighting method used in this thesis is Term Frequency - Inverse Document Frequency (TF-IDF) & using K-Nearest Neighbor (K-NN) for its classification method. The KNN method is a classification of a set of data based on data learning that has been previously classified. Accuracy testing of the classification of tweets on Twitter with step of K-Nearest Neighbor (K-NN) theorem resulted in accuracy where the total data amounted to 140, with descriptions of 100 training data and 40 testing data and the values of k entered were 1, 3, 5, and 7, each the result is when k = 1, the accuration is 75.0%; k = 3, accuration is 72.5%; k = 5, accuration is 62.5%; k = 7, accuration is 55.0%.
Mekanisme Pembobotan Server Menggunakan Algoritme Fuzzy Pada Sistem Load Balancing di Software Defined Network Hasbi Razzak; Widhi Yahya; Mochammad Ali Fauzi
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 9 (2019): September 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1093.804 KB)

Abstract

Load balancing is used to distribute workloads evenly to multiple servers. To achieve an optimal load balancing system must consider the workload received by the server based on the server's ability. As for what affects server performance includes resources such as CPU, memory and disk. If the workload received exceeds the server's capability, the server may be overloaded. To overcome this problem, we can utilize load balancing by implementing an algorithm that can take into account CPU, memory and disk variables. For this research, implementing a server weighting system uses a fuzzy algorithm on a load balancing system to distribute server workloads based on CPU, memory and disk variables. From the results and analysis for testing on this system, Fuzzy algorithms are able to distribute traffic based on the lowest server weights. Then a comparison with the Response time (RT) algorithm and the Least Connection (LC) algorithm with traffic distribution parameters, CPU and Memory Usage, Response Time and Throughput. When testing with a number of requests 360, Fuzzy algorithms charge more for distribution to servers the lowest server weight. Then in testing memory usage, the response time algorithm has the lowest memory usage on each server, server1 18.7%, server2 32.4% and server3 62.2%. Furthermore, testing with loads at the level of 360 RT algorithm has a high response time of 393 m/s. In testing throughput algorithm the response time has the largest throughput with a value of 93.6 KB.
Co-Authors Adi Sukarno Rachman Adinugroho, Sigit Aditya Kresna Bayu Arda Putra Agnes Rossi Trisna Lestari Agung Setiyoaji Agus Wahyu Widodo Agus Zainal Arifin Ahmad Galang Satria Ahmad Wildan Attabi' Akbar, Aldi Fandiya Alvandi Fadhil Sabily Amalia Kusuma Akaresti Andika Indra Kusuma Andro Subagio Anita Sumiati Annam Rosyadi Annisya Aprilia Prasanti Annisya Aprilia Prasanti Anny Yuniarti ari kusyanti Bayu Rahayudi Billy Sabilal Budi Darma Setiawan Budi Kurniawan Chusnah Puteri Damayanti Claudio Fresta Suharno Claudio Fresta Suharno Dahnial Syauqy Desfianti, Ruri Dhimas Anjar Prabowo Dian Eka Ratnawati Dimas Joko Haryanto Dwi Damara Kartikasari dwi taufik hidayat Edy Santoso Eka Dewi Lukmana Sari Elisa Julie Irianti Siahaan Eti Setiawati Fachrul Rozy Saputra Rangkuti Fakhruddin Farid Irfani Fathor Rosi Ferly Gunawan Ferly Gunawan Figgy Rosaliana Fitra Abdurrachman Bachtiar Galih Nuring Bagaskoro Gosario, Sony Hadiyan Hadiyan Hasbi Razzak Hidayat, Hasannudin Hilmy Khairi Idris Hurriyatul Fitriyah I Wayan Sudira Imam Cholissodin Imam Cholissodin Indriati Indriati Irma Pujadayanti Irwin Deriyan Ferdiansyah Ismiarta Aknuranda Isnan . Joda Pahlawan Romadhona Tanjung Komang Candra Brata Lailil Muflikhah Laksono Trisnantoro Liana Shinta Dewi Liana Shinta Dewi Lita Handayani Tampubolon M Yusron Syauqi Dirgantara M. Rizzo Irfan M. Rizzo Irfan Mahdarani Dwi Laxmi Mahendra Data Malahayati, Salsabila Nur Maulana, Muhammad Afif Moch. Yugas Ardiansyah Moh Fadel Asikin Moh Iqbal Yusron Muhammad Fhadli Muhammad Hakiem Muhammad Khaerul Ardi Muhammad Khatib Barokah Muhammad Mishbahul Munir Muhammad Sholeh Hudin Muhammad Tanzil Furqon Nanda Firizki Ananta Ni Made Gita Dwi Purnamasari Ni Made Gita Dwi Purnamasari Nining Nahdiah Satriani Nur Hijriani Ayuning Sari Nurul Dyah Mentari Nurul Dyah Mentari Nurul Hidayat Prananda Antinasari Primantara Hari Trisnawan Putra Pandu Adikara Qiindil, Audry Rachmad Indrianto Rahmat Yani Rakhman Halim Satrio Randy Cahya Wihandika Ratih Diah Puspitasari Rekyan Regasari Mardi Putri, Rekyan Regasari Mardi Resti Febriana Ria Ine Pristiyanti Rika Raudhotul Rizqiyah Rizal Maulana Rizal Maulana, Rizal Rizal Setya Perdana Ro'i Fahreza Nur Firmansyah Robertus Santoso Aji Putro Rodhiya, Hanif Robby Rosy Indah Permatasari Safier Yusuf Saiful Bahri Shandy, Ryo Shima Fanissa Silalahi, Gifo Armando Silvia Aprilla Sonny Christiano Gosaria Sudin, Mahmudin Suryani Agustin Sutrisno Sutrisno Thio Marta Elisa Yuridis Butar Butar Tibyani Tibyani Tibyani Tibyani Tri Afirianto Tri Afirianto Ulfa Lina Wulandari Umi Rofiqoh Ummah Karimah, Ummah Uswatun Hasanah Utaminingrum, Fitri Veronica Kristina Br Simamora Vina Adelina Wahyuni Lubis Widhi Yahya Wildan Aulia Rachman Winda Estu Nurjanah Winda Fitri Astiti Yessivha Imanuela Claudy Yuita Arum Sari Yuita Arum Sari Zafran, Muhammad Abyan Zubaidah Al Ubaidah Sakti