cover
Contact Name
Yeni Kustiyahningsih
Contact Email
ykustiyahningsih@trunojoyo.ac.id
Phone
+6282139239387
Journal Mail Official
kursor@trunojoyo.ac.id
Editorial Address
Informatics Department, Engineering Faculty University of Trunojoyo Madura Jl. Raya Telang - Kamal, Bangkalan 69162, Indonesia Tel: 031-3012391, Fax: 031-3012391
Location
Kab. pamekasan,
Jawa timur
INDONESIA
Jurnal Ilmiah Kursor
ISSN : 02160544     EISSN : 23016914     DOI : https://doi.org/10.21107/kursor
Core Subject : Science,
Jurnal Ilmiah Kursor is published in January 2005 and has been accreditated by the Directorate General of Higher Education in 2010, 2014, 2019, and until now. Jurnal Ilmiah Kursor seeks to publish original scholarly articles related (but are not limited) to: Computer Science. Computational Intelligence. Information Science. Knowledge Management. Software Engineering. Publisher: Informatics Department, Engineering Faculty, University of Trunojoyo Madura
Articles 120 Documents
MULTIPLE DISCRIMINANT ANALYSIS WITH FUKUNAGA KOONTZ TRANSFOR AND SUPPORT VECTOR MACHINE FOR IMAGE-BASED FACE DETECTION AND RECOGNITION Asri, Sri Andriati; Setiawan, Widyadi
Jurnal Ilmiah Kursor Vol 7 No 2 (2013)
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

MULTIPLE DISCRIMINANT ANALYSIS WITH FUKUNAGA KOONTZ TRANSFOR AND SUPPORT VECTOR MACHINE FOR IMAGE-BASED FACE DETECTION AND RECOGNITION a Sri Andriati Asri, bWidyadi Setiawan aElectrical Engineering Dept., Bali State Polytechnic, Bukit Jimbaran, Kuta Selatan, Badung, Bali b Electrical Engineering Dept., Faculty of Engineering Udayana University, Bukit Jimbaran, Kuta Selatan, Badung, Bali 80361 E-Mail: andriati_s@yahoo.com Abstrak Pengenalan wajah dapat diterapkan pada banyak aplikasi potensial, seperti otentikasi identitas, information security, surveillance dan interaksi manusia komputer. Penelitian ini bertujuan membangun perangkat lunak berbasis Matlab untuk deteksi dan pengenalan wajah dengan masukan berupa citra. Sistem yang akan dibangun meliputi deteksi dan pengenalan wajah. Subsistem Deteksi Wajah memakai Principle Component Analysis (PCA) sebagai ekstraksi fitur dan Jaringan Syaraf Tiruan Perambatan Balik sebagai pengklasifikasinya. Pada Subsistem Pengenalan Wajah memakai metode Support Vector Machine salah satu algoritma kecerdasan buatan yang mampu mengklasifikasikan banyak wajah dengan baik. Metode Multiple Discriminant Analysis with Fukunaga Koontz Transform (MDA/FKT) dipakai sebagai ekstraksi fitur. Pelatihan dan pengujian sistem memakai basis data penelitian, dan basis data standar yaitu basis data ORL sebagai pembanding. Rancang bangun Aplikasi Deteksi dan Pengenalan Wajah telah berhasil diselesaikan pada penelitian ini. Subsistem Deteksi Wajah menghasilkan tingkat keakuratan pendeteksian wajah sebesar 99 %. Pada Subsistem Pengenalan Wajah, tingkat pengenalan basis data penelitian (UNUD) 82,76 %, sedangkan tingkat pengenalan pada basis data ORL 97,5%. Kata kunci: Deteksi Wajah, Pengenalan Wajah, Support Vector Machine, Multiple Discriminant Analysis with Fukunaga Koontz Transform. Abstract Face recognition can be applied to many potential applications, such as identity authentication, information security, surveillance and human computer interaction. This research aims to build a Matlab-based software for face detection and recognition application using an image input form. The system consist of face detection and recognition subsystem. Face detection subsystem using PCA as feature extraction and Back Propagation Neural Network as its classifier. In face recognition subsystem using Support Vector Machine as known as one of the good methods in the artificial intelligence algorithm that is able to classify many faces well. Multiple Discriminant Analysis Method with Fukunaga Koontz Transforms (MDA / FKT) is used as feature extraction. Training and Testing database systems using research (UNUD) database, and ORL database as a comparison. Face detection and recognition application has been successfully completed in this research, face detection subsystem produces face detection accuracy rate of 97.95 %, and for face recognition subsystem, the recognition rate is 82.76 % on research (UNUD) database, while the recognition rate on ORL database is 97.5 %. Key words: Face Detection, Face Recognition, Support Vector Machine, Multiple Discriminant Analysis with Fukunaga Koontz Transform
EVALUASI IMPLEMENTASI SISTEM INFORMASI DENGAN PENDEKATAN UTILITY SYSTEM (STUDI KASUS SISTEM E-CAMPUS UNIVERSITAS WIDYATAMA) Falahah, Falahah; Rijayana, Iwan
Jurnal Ilmiah Kursor Vol 6 No 2 (2011)
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Utility System adalah pendekatan untuk mengevaluasi implementasi sistem informasi yang pertama kali diusulkan oleh Kendall. Pendekatan ini berusaha menangkap persepsi sistem dari enam sudut pandang, yaitu possession, form, place, time, actualization dan goal. Informasi rinci tentang implementasi pendekatan ini tidak dapat diakses secara bebas sehingga menimbulkan keingintahuan untuk pengembangan lebih lanjut bagaimana menerapkan konsep ini untuk mengevaluasi sistem informasi, khususnya di lingkungan akademik. Penelitian ini bertujuan untuk mengusulkan sebuah metode alternatif dalam mengevaluasi sistem yang didasarkan pada pendekatan utility system. Metode ini terdiri atas sekumpulan paket kuisioner yang diturunkan dari pendekatan utility untuk mengungkapkan persepsi pengguna terhadap sistem. Kuisioner ini kemudian diterapkan untuk mengevaluasi sistem ecampus di Universitas Widyatama. Sistem e-campus dipilih karena kesederhanaan struktur dan kemudahan akses sistem tersebut oleh semua pengguna terkait. Hasil pengolahan data menunjukan beberapa temuan penting seperti perbedaan ekspektasi dari setiap jenis pengguna, dan adanya ekspektasi pengguna pada peningkatan fitur sistem. Pengolahan data kuisioner juga dapat memberikan rekomendasi yang berarti untuk peningkatan utility system dan dibutuhkan riset lebih lanjut untuk mengungkapkan fakta-fakta lain yang terkait dengan pengembangan sistem. Kata kunci: Evaluasi, Sistem, Implementasi, Utility. Abstract Utility System is an approach for evaluate system implementation, firstly proposed by Kendall. This approach captured the perception of the system based on 6 points of view, which are possession, form, place, time, actualization and goal. The detail information of this approach is limited and arising the curiosity to explore more detail how to implement this approach to evaluate the information system, especially for the system in academic environment. The aim of this research is to propose the alternative method for evaluate the system based on utility system approach. This method consists of a questionnaires package that derived from utility approach, to elicit the user perception. The questionnaires was implemented to evaluate the e-campus system at Widyatama University which is chosen because of the structure of the system that relatively simple and easy to access. The result gave some important facts, such as the difference of expectation from different user’s point of view and user’s expectations for enhancement. The results also derived some recommendations to improve the utility system and need more extended research to explore the uncover facts for system improvement. Key words: Evaluation, System, Implementation, Utility Approach.
Intelligent Imaging Technology Implementation as Terrorism Prevention in Retail Sectors in 21st Century Foster, Bob; Johansyah, Muhamad Deni
Jurnal Ilmiah Kursor Vol 10 No 2 (2019)
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/kursor.v10i2.188

Abstract

Terrorism is a very dangerous thing and has become a threat both on a national and international scale. Understanding terrorism seeks to instill the seeds of hostility towards a group, government agencies and even the state. Before entering the 21st century terror attacks are blatant in the business sector by sabotaging and damaging public facilities and vital objects. These physical attacks can be prevented by recording personal identities or conducting regular security patrols and placing a large number of security personnel in places of business and places that are considered strategic. However, this is still not optimal where the level of security and the number of personnel are limited in monitoring the place for a long time and are sustainable. The terrorist attacks in the 21st century are different and require different handling. Attacks can be physical or non-physical. On non-physical objects attacks are usually carried out by hacking networks that can damage internet network connections in one area and even one country. Ways to prevent attacks that are physical in nature by utilizing computer vision technology capabilities that are used to record all civil society. An additional feature in this technology lies in the face recognition and pattern matching techniques where a person's face will be searched for unique features. Then from these data will be biometric data, namely data that will not change and disappear. Computer vision algorithms can detect a person's face or object even though it has been modified or changed in physical and color conditions. The advantages of these algorithms are effectively used to record visitor identities and are optimal in recognizing an object with an accuracy of up to 90%. This system is able to help and improve a security feature of a business and tourist area.
A DATA ANALYSIS OF THE IMPACT OF NATURAL DISASTER USING K-MEANS CLUSTERING ALGORITHM Prihandoko, Prihandoko; Bertalya, Bertalya
Jurnal Ilmiah Kursor Vol 8 No 4 (2016)
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28961/kursor.v8i4.109

Abstract

Indonesia is one of the country with a lot of natural disasters occurred every year. The victims of natural disasters, are quite high in terms of the number of deaths, missing people, injuries, sufferings and the number of refugees. Unfortunately, the number of victims is growing from year to year in the last ten years. Thus, based on this condition, this research is carried out in order to analyze the data of the natural disasters and their victims for the last five years. The analysis is intended to know what is the main cause of natural disaster. The series of data about the natural disaster and the weather condition is collected from the government office website. The analysis was carried out by implementing clustering technique to the data, by using k-means algorithm, after data preprocessing completed. The result of the research shows that the weather condition is not the main cause of the occurrence of natural disaster, but the geographical condition is the main trigger of the problem. In addition, this research also found that the data published by the government need to be updated regularly.
NEAR-DUPLICATE REAL-LIFE FACE IMAGE Purbasari, Intan Yuniar; Nugroho, Budi
Jurnal Ilmiah Kursor Vol 7 No 1 (2013)
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

NEAR-DUPLICATE REAL-LIFE FACE IMAGE a Intan Yuniar Purbasari, bBudi Nugroho a,bTeknik Informatika, Fakultas Teknologi Industri, UPN “Veteran” Jawa Timur, Indonesia Jl. Raya Rungkut Madya, Gunung Anyar, Surabaya 60294 E-Mail: intan.yuniar@gmail.com Abstrak Content-based Image Retrieval (CBIR) merupakan metode temu kembali citra berdasarkan karakteristik numerik pada citra. Pencarian similaritas yang efisien pada ruang dimensi ultra-high telah diajukan menggunakan two-tier inverted file dan Local Derivative Patterns (LDP) sebagai metode ekstraksi fitur dengan tingkat keakuratan dan kinerja yang tinggi pada data set citra wajah eksperimental. Namun demikian, citra real-life memiliki ukuran dan resolusi yang berbeda serta noise bawaan. Masih belum diketahui apakah LDP dapat menunjukkan hasil yang sama memuaskan jika diberikan data set citra real-life. Penelitian ini merancang dan membangun search engine citra wajah untuk mencari citra nyaris duplikat pada citra real-life menggunakan metode LDP untuk ekstraksi fitur dan two-tier inverted file untuk pengindeks-an multidimensi. Sebuah metode ekpansi state juga diperkenalkan untuk lebih menangkap banyak detil dari histogram citra dengan mempertimbangkan informasi piksel tetangga. Eksperimen ini dilakukan pada 8083 citra wajah real-life dari berbagai ukuran antara 20x20 dan 80x80. Data set berisi kopi duplikat dari citra wajah setelah melalui beberapa proses transformasi. Hasil pencarian mengembalikan 20 citra yang memiliki kemiripan paling tinggi dengan citra query dan memiliki nilai presisi 0.75 atau 75%. Kata kunci: Content-Based Image Retrieval, Local Derivative Pattern, Two-tier Inverted File, Real-life Face Image. Abstract Content-based image retrieval (CBIR) is an image retrieval method based on the analysis of numerical characteristics of the image at the absence of text information. An efficient similarity search in ultra-high dimensional space has been proposed using two-tier inverted file and Local Derivative Patterns (LDP) as feature extraction method with high accuracy and high performance on experimental face image data sets. However, real-life images have different size, resolution and a potential noise. It is unknown whether LDP would show the same satisfactory result given real-life image data sets. This research designed and developed a face search engine to find near-duplicate face in real life images using LDP method to extract image features and two-tier inverted file for multidimensional indexing process. A state expansion method was also introduced to capture more detailed description of image histogram by considering neighbor information. The experiment was performed on 8,083 reallife face images of various sizes between 20x20 to 80x80. The data set contained duplicate copies of face images with some transformation processes. The search result returned top 20 images which had the most similarity with the query images and had an average precision rate of 0.75 or 75%. Keywords: Content-Based Image Retrieval, Local Derivative Pattern, Two-tier Inverted File, Real-life Face Image
FACIAL EXPRESSIONS RECOGNITION USING BACKPROPAGATION NEURAL NETWORK FOR MUSIC PLAYLIST ELECTIONS Setiawardhana, Setiawardhana; Ramadijanti, Nana; Rahayu, Peni
Jurnal Ilmiah Kursor Vol 6 No 3 (2012)
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Penelitian ini dibuat untuk mengenali ekspresi wajah sebagai indikator untuk menjalankan playlist musik. Sistem pengenalan ekspresi wajah berasal dari data masukan seseorang yang diambil secara offline, dengan posisi terdekat dengan kamera, dimana posisi wajah tidak boleh miring. Prosesnya dengan pengambilan citra wajah secara offline yang dikenali dengan kombinasi warna, dan mengekstrak fitur penting dari wajah berdasarkan lokasi alis, mata, dan bentuk mulut kemudian mengenali ekspresi wajah menggunakan Jaringan Saraf Tiruan Propagasi Balik (Backpropagation Neural Network). Ekspresi yang akan dikenali Data keluaran dari pengenalan ekspresi wajah berupa indek yang secara otomatis akan digunakan sebagai indikator untuk menjalankan musik, sehingga musik akan berubah mengikuti perubahan ekspresi wajah seseorang. Sistem yang telah dibuat dapat mengenali tiga jenis ekspresi yaitu: normal, marah, dan bahagia. Pengujian dengan pengambilan gambar wajah secara offline sebagai data masukan untuk Jaringan Saraf Tiruan Propagasi Balik, dimana pada saat pembelajaran diperoleh hasil yang konvergen dengan error terendah dengan jumlah neuron pada lapisan hidden sebanyak 10 unit, nilai laju pembelajaran sebesar 0.0625325 dan nilai mean square error sebesar 0.0135. Kata Kunci: Ekspresi Wajah, Backpropagation, Music Playlist. Abstract The objective of the research is to detect facial expression as indicator to cast a music playlist. Facial expression detection system input is performed offline by taking photograph of a subject with nearest position from the camera and facial position should not be tilted. The image is identified as a combination of color and feature extraction is performed based on location of eyebrow, eye, and mouth. Facial expression is detected with Artificial Neural Network Backpropagation method. The output data is an index, which automatically select and play the music. In this way, the music is modified according to the changes of facial expression. The system is designed to detect three facial expressions: normal, angry, and happy expression. The similarity between features values from each expression influence the ability to differentiate each expression. Offline system evaluation is performed with backpropagation neural network method,for learning process, it reaches convergent value with lowest error value when using 10 unit neuron on hidden layer, learning rate value is 0.0625325 and mean square error value is 0.0135.
SENTIMENT ANALYSIS OF ELECTRIC CARS USING RECURRENT NEURAL NETWORK METHOD IN INDONESIAN TWEETS Handayani, Felisia; Mustikasari, Metty
Jurnal Ilmiah Kursor Vol 10 No 4 (2020)
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21107/kursor.v10i4.233

Abstract

Sentiment analysis is computational research of the opinions of many people who are textually expressed against a particular topic. Twitter is the most popular communication tool among Internet users today to express their opinions. Deep Learning is a solution to allow computers to learn from experience and understand the world in terms of the hierarchy concept. Deep Learning objectives replace manual assignments with learning. The development of deep learning has a set of algorithms that focus on learning data representation. The recurrent Neural Network is one of the machine learning methods included in Deep learning because the data is processed through multi-players. RNN is also an algorithm that can recall the input with internal memory, therefore it is suitable for machine learning problems involving sequential data. The study aims to test models that have been created from tweets that are positive, negative, and neutral sentiment to determine the accuracy of the models. The models have been created using the Recurrent Neural Network when applied to tweet classifications to mark the individual classes of Indonesian-language tweet data sentiment. From the experiments conducted, results on the built system showed that the best test results in the tweet data with the RNN method using Confusion Matrix are with Precision 0.618, Recall 0.507 and Accuracy 0.722 on the data amounted to 3000 data and comparative data training and data testing of ratio data 80:20
BASIS PATH TESTING OF ITERATIVE DEEPENING SEARCH AND HELD-KARP ON PATHFINDING ALGORITHM Rahayuda, I Gede Surya; Santiari, Ni Putu Linda
Jurnal Ilmiah Kursor Vol 9 No 2 (2017)
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28961/kursor.v9i2.129

Abstract

This research is a continuation of previous research, where in previous research discussed about the implementation of both methods. Implementation is done using visual basic programming language. Both methods are compared based on the results obtained. While in the current study, research is more focused on the analysis of the program flow that has been made. Evaluation is done by using basis path method, there are several processes performed on the method, such as: flowgraph, independent path, cyclomatic complexity and graph matrix. In addition to the evaluation of program flow, evaluation is also done based on program performance. Performance tests are based, time, cpu and memory. Based on the evaluation using the base path, obtained flowgraph structure and independent path different, but obtained the result of CC and Graph Matrix calculation of the same between IDS and HK method is 4. Based on evaluation in terms of performance, process the program from entering data and until getting the result, the HK method takes a longer time than the IDS method. The IDS method takes 2.7 seconds while the HK method takes 2.8 seconds.
OPTIMASI FUNGSI MULTI-OBYEKTIF BERKENDALA MENGGUNAKAN ALGORITMA GENETIKA ADAPTIF DENGAN PENGKODEAN REAL Mahmudy, Wayan Firdaus; Rahman, Muh. Arif
Jurnal Ilmiah Kursor Vol 6 No 1 (2011)
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Multi-objective optimization problem is difficult to be solved as its objectives generally conflict with each other and its solution is not in the form of a single solution but a set of solutions. Genetic algorithms (GAs) is one of meta heuristic algorithms that may be used to solve this problem. However, a standard GAs is easily trapped in local optimum areas and searching process rate will be lower around the optimum points. This paper proposes a GAs with an adaptive mutation rate to balance the exploration and exploitation on the search space. A simple rule has been developed to determine wheter the mutation rate is increased or decreased. If a significant improvment of the fitness value is not achieved, the mutation rate is increased to enable the GAs exploring search space and escaping the local optimum area. In contrast, the mutation rate is decreased if significant improvment of the fitness value is achieved. This mechanism guide the GAs to exploit the local search area. The experiments show that by using the adaptive mutation, the GAs will move faster toward a feasible search space and achieving solutions on sorter time.
MODELLING AND SIMULATION OF INDUSTRIAL HEAT EXCHANGER ETWORKS UNDER FOULING CONDITION USING INTEGRATED NEURAL NETWORK AND HYSYS Biyanto, Totok R.; Roekmono, Roekmono; Rahmadiansyah, Andi; Aisyah, Aulia Siti; Darwito, Purwadi A.; Dhanardono, Tutug; Budiati, Titik
Jurnal Ilmiah Kursor Vol 8 No 1 (2015)
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28961/kursor.v8i1.70

Abstract

Fouling is a deposit inside heat exchanger network in a refinery has been identified as a major problem for efficient energy recovery. This heat exchanger network is also called Crude Preheat Train (CPT). In this paper, Multi Layer Perceptron (MLP) neural networks with Nonlinear Auto Regressive with eXogenous input (NARX) structure is utilized to build the heat exchanger fouling resistant model in refinery CPT and build predictive maintenance support tool based on neural network and HYSYS simulation model. The complexity and nonlinierity of the nature of the heat exchanger fouling characteristics due to changes in crude and product operating conditions, and also crude oil blends in the feed stocks have been captured very accurate by the proposed software. The RMSE is used to indicate the performance of the proposed software. The result shows that the average RMSE of integrated model in predicting outlet temperature of heat exchangerTH,out and TC,out between the actual and predicted values are determined to be 1.454 °C and 1.0665 °C, respectively. The integrated model is ready to usein support plant cleaning scheduling optimization, incorporate with optimization software.

Page 1 of 12 | Total Record : 120