Journal Cover
MATICS
Number of Followers: 1  

  This is an Open Access Journal Open Access journal
ISSN (Print) 1978-161X - ISSN (Online) 2477-2550
Published by UIN Maulana Malik Ibrahim Malang Homepage  [9 journals]
  • Eggs Fertilities Detection System on the Image of Kampung Chicken Egg
           Using Naive Bayes Classifier Algorithm

    • Authors: Aris Diantoro, Irwan Budi Santoso
      Pages: 53 - 57
      Abstract: Losses in chicken eggs hatchery make breeders income declined. The main cause of these things because it is less effective and efficient in distinguishing the state of fertilities in the eggs. The detection of fertile and infertile eggs will automatically provide ease of selection and removal of the eggs are fertile and infertile eggs. This will bring more profits for breeder as well as time efficiency more and selling power. Infertile eggs will give breeders the sale price if it is known as early as possible in order not to fail hatching. A method fuzzy c means and naive bayes classifier is designed to identify the state of the fertility of eggs. By putting eggs near the source light and black background in a dark room, then taked of image with a high qualities camera. From the resulting camera image, then extracted features or take characteristics that distinguish between fertile and infertile eggs. The total amount of data used in this study of 450 eggs image sourced from the field survey. Training data is used   250 data, 125 fertile eggs image data and 125 infertile eggs image data. As for testing the data using the 200 data, the image data 150 fertile eggs and 50 infertile eggs image data. Based on trial results of training data is obtained the best accuracy is equal to 80% at intervals of 5, 86.4% at intervals of 5 and dimensions 70x60, and 99.6% on 1x2 resize. The accuracy of the results obtained by 78%, 82% and 94% in trials testing data.
      PubDate: 2017-12-31
      DOI: 10.18860/mat.v9i2.4198
      Issue No: Vol. 9, No. 2 (2017)
       
  • Aplikasi Market Matching Berbasis Fuzzy sebagai Penunjang Keputusan Ekspor
           Produk UMKM

    • Authors: Bambang Nurdewanto
      Pages: 58 - 61
      Abstract: Determining the exact location of the export market with the right amount in the marketing process is expected to reduce the number of losses due to the stagnancy of product turnover. Appropriate target market system using fuzzy control on MSMEs. Fuzzy control method is used to overcome the determination of a market that is influenced by the subjectivity of marketing actors. Online market matching application which is the right decision support system of the right export destination and the right amount so efficient. The result of market matching application of fuzzy method is recommendation of destination and quantity that can be exported.
      PubDate: 2017-12-31
      DOI: 10.18860/mat.v9i2.4372
      Issue No: Vol. 9, No. 2 (2017)
       
  • Ekstraksi Ciri Sinyal EEG Untuk Gangguan Penyakit Epilepsi Menggunakan
           Metode Wavelet

    • Authors: WIWIT PUTRI ANI
      Pages: 62 - 66
      Abstract: Abstrak- Epilepsy terjadi karena ada gangguan sistem saraf otak pada manusia, yang terekam dari sinyal Elektroensephalogram. Sinyal Elektroensephalogram memiliki informasi aktivitas listrik pada otak, termasuk kondisi gangguan kelistrikan dan pikiran pada syaraf. Sinyal Elektroensephalogram mempiliki bentuk yang kompleks, mudah tertimbun noise , amplitudo kecil dan tidak memiliki pola yang baku, sehingga analisa secara visual tidak mudah[1] Untuk meningkatkan akurasi dan menghilangkan noise dari sinyal EEG, penelitian ini menggunakan metode Wavelet sebagai proses ekstraksi ciri dan Backpropagation untuk klasifikasi. Data sinyal Elektroensephalogram didapat dari Universitas Bonn yang terdiri dari 5 kelas dataset yaitu A, B, C, D, dan E. Tiap dataset berisi 100 segmen EEG saluran tunggal dengan durasi selama 23.6 detik. Peneliti menggunakan dataset B dan E. Pada tahap pelatihan (training) menggunakan 80 naracoba , sedangkan pada tahap pengujian (testing) menggunakan 100 naracoba. Proses ini dilakukan setelah ekstraksi ciri sinyal EEG dengan Wavelet. Hasil ekstraksi ciri digunakan sabagai nilai input, pada penelitian ini menggunakan metode back propagation (16-35-2) yaitu 2 input sinyal EEG,  satu hidden layer dengan 35 unit dan dua target epilepsy dan non epilepsi . dari pengujian data tersebut didapat nilai akurasi sebesar 100%. Kata kunci : Backpropagation, Wavelet, epilepsy, EEG
      PubDate: 2017-12-31
      DOI: 10.18860/mat.v9i2.4376
      Issue No: Vol. 9, No. 2 (2017)
       
  • Pendeteksian Ketidaklengkapan Kebutuhan Dengan Teknik Klasifikasi Pada
           Dokumen Spesifikasi Kebutuhan Perangkat Lunak

    • Authors: Suci Nurfauziah
      Pages: 67 - 71
      Abstract: Dokumen Spesifikasi Kebutuhan Perangkat Lunak (SKPL) dihasilkan dari proses rekayasa kebutuhan dan merupakan tahapan yang kritis pada pengembangan perangkat lunak. Kesalahan yang terjadi pada proses rekayasa kebutuhan akan mempengaruhi ketidakberhasilan produk tersebut. Dokumen SKPL sering kali ditulis dengan bahasa alamiah. Salah satu karakteristik spesifikasi kebutuhan yang baik adalah lengkap. Kualitas spesifikasi kebutuhan bisa dinilai berdasarkan pernyataan kebutuhan atau dokumen kebutuhan. Spesifikasi kebutuhan yang lengkap secara jelas mendefinisikan semua situasi yang dihadapi sistem dan dapat dipahami tanpa melibatkan atau terkait pada kebutuhan lain. Penelitian ini bertujuan untuk membangun model klasifikasi pendeteksian ketidaklengkapan kebutuhan pada dokumen spesifikasi kebutuhan perangkat lunak yang ditulis dengan bahasa alamiah. Penelitian ini membuat corpus kebutuhan yang berisi pernyataan kebutuhan lengkap dan pernyataan kebutuhan tidak lengkap. Corpus ditulis secara manual oleh tiga orang ahli. Dari Corpus akan dilakukan ekstraksi fitur, pemilihan fitur yang valid, dan pembangkitan kata kunci.  Nilai performansi Gwet’s AC1 digunakan untuk mengetahui apakah classifier yang dibangun dapat diandalkan dan dapat mendeteksi adanya ketidaklengkapan pada dokumen spesifikasi kebutuhan perangkat lunak.Berdasarkan hasil ujicoba dengan menggunakan kombinasi metode adaboost dan C4.5 diperoleh rata-rata indek kesepakatan pada level moderate dengan nilai tertinggi 0.52 pada saat penggunaan enam fitur teratas. Enam fitur teratas yang paling berpengaruh antara lain bad_jj, bad_rb, jml_kt_penegasan, jml_kt_penghubung, bad_prp dan jml_kt_negatif.
      PubDate: 2017-12-31
      DOI: 10.18860/mat.v9i2.4291
      Issue No: Vol. 9, No. 2 (2017)
       
  • Performance Comparison of Rule Generation Method Substractive Clustering
           and Fuzzy C-Means Clustering on Sugeno's Inference for Stroke Risk
           Detection

    • Authors: Rekyan Regasari Mardi Putri, Edy Santoso
      Pages: 72 - 79
      Abstract: Abstract - Fuzzy Inference is one method that can
      solve the problem of uncertainty in a decision-making
      or classification well. In inference, fuzzy rules that
      represent the need of expert knowledge in the relevant
      fields, so that the classification given decision or be
      appropriate expert knowledge. However there are times
      when experts are less able to represent the rules of the
      appropriate knowledge or knowledge that there is need
      of too many rules, so we need a method that can
      generate rules based on the data given expert.
      At issue troke s disease risk detection, it also occurs
      because of the research that has been done by taking the
      direct rule of experts, it turns out less than the maximum
      accuracy, still 82.89%. Substractive methods
      Clustering and Fuzzy C-Means (FCM) could generate
      rules by grouping algorithm, in which the existing
      training data are grouped in common and the rules of
      the group raised. Differences in the two methods are in
      determining the center of the cluster and assign each
      incoming data which groups.
      Based on research that has been done, substractive
      average Clustering membrika better accuracy is
      84.46%, while 73.81% FCM. However, in the
      processing time FCM faster at 16.75 seconds to give an
      average processing time of 13:02 seconds.
      PubDate: 2017-12-31
      DOI: 10.18860/mat.v9i2.4587
      Issue No: Vol. 9, No. 2 (2017)
       
  • Pendukung Keputusan Penentuan Jumlah Order Menggunakan Fuzzy Mamdani

    • Authors: Elta Sonalitha
      Pages: 80 - 85
      Abstract: To get customer satisfaction, a restaurant should always provide raw materials in accordance with the menu. Each raw material has a different demand based on an uncertain customer interest. Purchasing managers have difficulty in determining the number of orders for each raw material, due to the uncertainty of demand and supply. Therefore we built decision support system for determining the number of orders using fuzzy mamdani. From decision support system we get ROP and recommendation of the number of orders accompanied by the total purchase price for each raw material. This system helps the purchasing managers in determining the amount of orders quickly and precisely by considering the losses, especially in the field of financial management.
      PubDate: 2017-12-31
      DOI: 10.18860/mat.v9i2.4373
      Issue No: Vol. 9, No. 2 (2017)
       
 
 
JournalTOCs
School of Mathematical and Computer Sciences
Heriot-Watt University
Edinburgh, EH14 4AS, UK
Email: journaltocs@hw.ac.uk
Tel: +00 44 (0)131 4513762
Fax: +00 44 (0)131 4513327
 
Home (Search)
Subjects A-Z
Publishers A-Z
Customise
APIs
Your IP address: 54.80.219.236
 
About JournalTOCs
API
Help
News (blog, publications)
JournalTOCs on Twitter   JournalTOCs on Facebook

JournalTOCs © 2009-