Claim Missing Document
Check
Articles

Perancangan Sistem Pakar Untuk Mendiagnosa Penyakit Diabetes Mellitus Menggunakan Metode Certainty Factor Design Expert System for Diagnosing Diabetes Mellitus Using Certainty Factor Method Musthofa Galih Pradana; Bondan Wahyu Pamekas; Kusrini Kusrini
CCIT Journal Vol 11 No 2 (2018): CCIT JOURNAL
Publisher : Universitas Raharja

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (425.849 KB) | DOI: 10.33050/ccit.v11i2.586

Abstract

Diabetes mellitus is a chronic metabolic disorder caused by the pancreas that does not produce enough insulin, so the body works to be disturbed. But by knowing the symptoms that exist, prevention of diabetes mellitus disease can be done as early as possible with the help of expert systems.One method of expert system used to diagnose symptoms of Diabetes Mellitus is Certainty Factor. The process undertaken in this research starts from literature studies, system design, system implementation and the last is testing the system. In the system design process is done by designing the database required by the expert system and also design the system interface design. After the design process is done then the next step is to implement the design into an expert system application. By using this method, the system gives results of possible symptoms experienced, presentation of beliefs, and treatment solutions based on the facts and the value of confidence given by users in filling out questions that have been given by the system.The results of this system are used to help medical personnel and patients in order to identify the symptoms of diabetes mellitus
ANALISA MATURITY LEVEL PENCAPAIAN OPTIMASI LAYANAN TI PERGURUAN TINGGI Friden Elefri Neno; Kusrini Kusrini; Henderi Henderi
CCIT Journal Vol 12 No 1 (2019): CCIT JOURNAL
Publisher : Universitas Raharja

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (133.825 KB) | DOI: 10.33050/ccit.v12i1.601

Abstract

Information technology (IT) is a very important requirement for all activity activities because it is believed to increase the effectiveness and efficiency of the work process. To achieve this, it is necessary to optimize the IT servants' good and correct so that the existence of IT can support the success of work in private agencies. government and education in achieving its goals. Therefore Stella Maris SimStimikom wants to know the success of the existence of information technology that supports the process of optimization of service to all academics in a university which is an unavoidable demand, the existence of a college academic information system that serves to serve the academic process of students and lecturers is a must. Measurements of the purpose of information systems is to contribute to information technology on business performance at Stella Maris Sumba Stimicom College to measure the extent of alignment between business processes, it is necessary to need an information system audit that requires a standard, then the standard used is COBIT 4.1 with the final result obtained at the maturity level value of the IT service level is at 2.51 with the description Repeatable but intuitive
Deteksi Tingkat Kesegaran Daging Ayam Menggunakan K-Nearest Neighbor Irfan Purwanto; M. Afriansyah; Kusrini Kusrini
CCIT Journal Vol 12 No 2 (2019): CCIT JOURNAL
Publisher : Universitas Raharja

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (377.83 KB) | DOI: 10.33050/ccit.v12i2.688

Abstract

The high demand for meat and the limited availability of meat on the market, make the price of meat become expensive and more and more traders are mixing rotten meat into fresh meat. To avoid risk, the public as consumers must be aware and know the characteristics of rotten meat and the difference with fresh meat. This study developed a fresh meat detection device using the TCS-230 RGB color sensor. The tool works by measuring the composition of RGB colors in identified meat and comparing with the reference composition of fresh meat RGB color. K-Neirest Neighbor as a method for introducing the freshness of chicken meat tested. The input used in the K-Neirest Neighbor is in the form of RGB color values ​​obtained from the color sensor.In this study, meat freshness was tested using TCS-230 color sensor with an accuracy rate of 87% with a positive precision of 92% and negative precision of 67%
Perancangan Sistem Pendukung Keputusan Penentuan Impor Bawang Merah Wiwi Widayani; Kusrini Kusrini; Hanif Al Fatta
Creative Information Technology Journal Vol 2, No 3 (2015): Mei - Juli
Publisher : UNIVERSITAS AMIKOM YOGYAKARTA

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (949.759 KB) | DOI: 10.24076/citec.2015v2i3.47

Abstract

Pertambahan jumlah penduduk Indonesia serta meningkatkannya permintaan industri akan bawang merah yang tidak diimbangi dengan jumlah produksi mendorong pemerintah membuka impor bawang merah. Impor dilakukan untuk menjaga keseimbangan harga dan pasokan bawang merah sehingga inflasi yang diakibatkan kenaikan harga bawang merah dapat ditekan, namun impor yang tidak tepat jumlah akan mengakibatkan kerugian bagi pihak petani, perlu adanya sistem pendukung dalam menentukan volume impor guna menjaga keseimbangan harga pasar dan pemenuhan kebutuhan bawang merah. Sistem pendukung keputusan yang dirancang menerapkan Fuzzy Inference System (FIS) Tsukamoto. Sistem yang dirancang memungkinkan pengguna untuk melakukan training data dan testing data, proses dalam training data yaitu : 1)Clustering data latih, menggunakan algoritma K-Means 2)Ekstraksi Aturan, 3)Testing data latih, hitung nilai impor dengan fuzzy Tsukamoto, 4)Menganalisa error hasil fuzzy menggunakan MAPE(Means Absolute Percentage Error), 5)Testing Data Uji dan menganalisa hasil error data uji. Hasil Uji Model menunjukan penentuan impor bawang merah dengan parameter input harga petani, harga konsumen, produksi, konsumsi, harga impor dan kurs terhadap 60 data latih menghasilkan error terendah sebesar 0.07 pada 12 cluster, hasil uji mesin inferensi terhadap data uji menghasilkan error sebesar 0.25. Indonesian population growth and increase industrial demand shallot is not matched with number of production prompted the government to opened shallot imports. Import done to maintain the balance price and supply of shallot so inflation caused by rising prices of onion can be suppressed, but not the exact amount of imports would result in losses for the farmers, support system in determining volume imports is need to maintain balance of market price and needs of shallot. Decision support system designed to apply Fuzzy Inference System (FIS) Tsukamoto. The system is allows the user to perform the training data and testing data, the training process performs are: 1) Clustering training data, using the K-Means algorithm 2) Extraction Rule, 3) Testing data, calculate imports value by fuzzy Tsukamoto, 4) analyze the results error using MAPE (Means Absolute Percentage error), 5) testing test data and analyze the results error. The results show the determination of imported shallot with input parameters producer prices, consumer prices, production, consumption, import prices and the exchange rate against 60 training data produces the lowest error of 0:07 in 12 clusters, the inference engine test resulted in an error of 0.25.
Sistem Pendukung Keputusan Kredit Usaha Rakyat PT. Bank Rakyat Indonesia Unit Kaliangkrik Magelang Agung Nugroho; Kusrini Kusrini; M. Rudyanto Arief
Creative Information Technology Journal Vol 2, No 1 (2014): November - Januari
Publisher : UNIVERSITAS AMIKOM YOGYAKARTA

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (816.472 KB) | DOI: 10.24076/citec.2014v2i1.33

Abstract

Banyak faktor dan variabel yang mempengaruhi risiko kredit dalam pengambilan keputusan pada permasalahan Kredit Usaha Rakyat (KUR). Faktor-faktor yang digunakan sebagai dasar penilaian Kredit Usaha Rakyat pada PT.Bank Rakyat Indonesia Unit Kaliangkrik menggunakan prinsip dasar yang dikenal dengan prinsip “5 of Credit” yaitu Character, Capacity, Capital, Condition dan Collateral. Dari factor-faktor yang digunakan sebagai dasar penilaian kredit, digunakan metode Mining Classification Rule dalam membuat Sistem Pendukung Keputusan pemberian KUR. Terdapat beberapa algoritma yang dapat digunakan dalam data mining untuk metode klasifikasi salah satunya adalah algoritma k-nearest neightbor. Konsep sistem pendukung keputusan pemberian KUR ini dirancang dapat melakukan klasifikasi terhadap objek berdasarkan data pembelajaran yang jaraknya paling dekat dengan objek tersebut dan memberikan solusi nasabah yang layak menerima KUR berdasarkan masukan dari user dengan menggunakan metode k-nearest neighbors (knn). Data-data transaksi pembayaran nasabah lama akan dijadikan sebagai data training dimana sebelumnya akan ditentukan kelasnya terlebih dahulu. Penentuan kelas dilakukan dengan proses klasifikasi data berdasarkan kategori status nasabah sesuai jumlah tunggakan pembayaran kreditnya. Dari hasil perhitungan kemiripan kasus antara data calon nasabah baru dengan nasabah lama atau data training menggunakan algoritma K-Nearest Neighbor, hasil dengan nilai tertinggi akan dijadikan acuan seorang decision maker dalam mengambil keputusan.Many factors and variables that affect credit risk in decision-making on issues People's Business Credit (KUR). The factors are used as the basis of assessment of the People's Business Credit Unit at PT Bank Rakyat Indonesia Kaliangkrik using basic principle known as the principle of "5 of Credit" ie Character, Capacity, Capital, Collateral Condition and. Of the factors that are used as a basis for credit assessment, Classification Rule Mining method used in making the administration of KUR Decision Support Systems. There are several algorithms that can be used in data mining for classification methods one of which is the k-nearest algorithm neightbor. The concept of the provision of decision support system is designed KUR can perform the classification of objects based on distance learning data that is closest to the object and provide a viable solution customers receive KUR based on input from the user by using the k-nearest neighbors (KNN). Payment transaction data will be used as a customer long training data which will be determined prior to first class. Grading is done with the data classification process based on customer status categories according to the amount of credit outstanding payments. From the calculation of the similarity between the case of data with prospective new customers or old customers training data using the K-Nearest Neighbor algorithm, the results with the highest scores will be used as a reference to a decision maker in making decisions.
Implementasi Metode Bayes untuk Menentukan Potensi Diri Beserta Pengaruhnya Terhadap IPK Mahasiswa Agung Jasuma; Kusrini Kusrini; M Rudyanto Arief
Creative Information Technology Journal Vol 6, No 1 (2019): Januari - Juni
Publisher : UNIVERSITAS AMIKOM YOGYAKARTA

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (255.11 KB) | DOI: 10.24076/citec.2019v6i1.228

Abstract

Tingginya minat siswa untuk melanjutkan sekolah ke jenjang yang lebih tinggi berpengaruh pada tingginya jumlah mahasiswa yang terdaftar di Indonesia. Kesulitan dalam menyelesaikan perkuliahan menjadi masalah yang sering terjadi, salah satu penyebabnya adalah ketidak-sesuaian potensi diri dengan program studi yang dipilih. Penelitian ini menjadikan FIK Universitas Amikom Yogyakarta sebagai tempat studi kasus untuk mencari tahu korelasi potensi diri dengan IPK mahasiswa, mencari potensi diri terbaik pada masing-masing program studi serta mencari tahu akurasi metode naive bayes dalam mengklasifikasi potensi diri mahasiswa. Responden yang digunakan dalam penelitian ini berjumlah 50 orang yang terdiri dari mahasiswa minimal semester 4, alumni dan 1 pakar. Pengumpulan data menggunakan metode wawancara dan koesioner, sedangkan pengolahan data menggunakan metode naive bayes classifier, confusion matrix untuk pengujian, dan korelasi pearson product moment untuk mencari tahu ada tidaknya korelasi. Penelitian ini mendapatkan hasil bahwa potensi diri kemampuan logika, visual dan interpersonal berpengaruh terhadap tingginya IPK mahasiswa dimana nilai signifikansi logika=0.043<0.05, interpersonal=0,029<0.05 dan visual=0,05<0.05. Kemampuan logika cenderung akan berdampak baik pada IPK mahasiswa prodi S1-SI, S1-IF, serta S1-TK, sedangkan kemampuan visual berdampak baik pada program studi S1-TI, D3-MI dan D3-IF. Naive bayes juga diketahui memiliki tingkat akurasi sebesar 90,625% dalam mengklasifikasikan mahasiswa berdasarkan potensi diri. Kata Kunci — bayes, IPK, mahasiswa The high interest of students to continue their education has an effect on the high number of students in Indonesia. Difficulties in completing lectures become a problem that often occurs, one of the reasons is incompatibility study program and student talents. This research made FIK Amikom University Yogyakarta as a case study to find out the correlation of Grade Point average (GPA) and student talents, best talents that’s needed in each study program and the accuracy of naive bayes in classifying students' talents, 50 people consisting of students at least semester 4, alumni and 1 expert as respondents. Data collection uses interview and questionnaire methods, while data processing uses the naive bayes classifier, confusion matrix for testing, and Pearson product moment correlation to find out whether there is correlation. This study found that the self-potential logic, visual and interpersonal abilities influence the high GPA of students where the significance value of logic=0.043<0.05, interpersonal=0.029<0.05 and visual=0.05<0.05. Logical ability tends to have a good impact on the GPA of S1-SI, S1-IF, and S1-TK study program, while visual abilities have an impact on S1-TI, D3-MI and D3-IF. Naive Bayes is also known to have an accuracy rate of 90.625% in classifying students based on their talents. Keywords — bayes, GPA, students
Perancangan Sistem Pendukung Keputusan Dalam Memilih Sekolah Tinggi Ilmu Kesehatan di Yogyakarta Norhikmah Norhikmah; Kusrini Kusrini; M. Rudyanto Arief
Creative Information Technology Journal Vol 1, No 2 (2014): Februari - April
Publisher : UNIVERSITAS AMIKOM YOGYAKARTA

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (602.148 KB) | DOI: 10.24076/citec.2014v1i2.18

Abstract

Seorang calon mahasiswa yang ingin melanjutkan jenjang pendidikannya ke sekolah tinggi ilmu kesehatan bukan suatu persoalan yang mudah, banyak pertimbangan yang harus dipertimbangkan seperti biaya selama perkuliahan, lowongan perkerjaan, kerjasama kampus tersebut dengan instansi terkait, dan lain-lain. Sampel kriteria yang digunakan dalam perancangan prototipe sistem pendukung keputusan dalam memilih Sekolah Tinggi Ilmu Kesehatan (STIKES) adalah kriteria yang didapatkan dari jawaban kuesioner sesuai dengan hasil uji validitas disetiap variable kriterianya. Proses pengambilan keputusan dalam memilih sekolah tinggi ilmu kesehatan ini menggunakan penggabungan 2 metode yaitu AHP dan F-AHP yang memiliki tujuan agar dapat mengurangi penilaian secara subyektivitas dan mengecek konsistensi logic antar kriteria maupun subkriteria, sehingga dapat menghasilkan ranking sekolah tinggi ilmu kesehatan yang lebih objektif, serta dapat membantu memberikan rekomendasi STIKES mana yang layak untuk dipilih.A prospective student who wants to continue his education to high school health science is not an easy matter, many considerations that must be taken into account as expenses for tuition , job vacancies , the campus co-operation with relevant agencies , and others . Sample criteria used in the design of a prototype decision support system in choosing the College of Health Sciences ( STIKES ) is the criterion obtained from the results of the questionnaire were tested for validity every variable criteria. The decision making process in choosing a high school health science using two methods , namely the incorporation of F - AHP and AHP which has the aim to reduce the subjectivity of assessment and check the consistency between the criteria and sub-criteria , so as to produce a high- ranking school objectives of health sciences , as well as STIKES can help provide recommendations which are feasible for selected.
Analisis Akurasi Jaringan Syaraf Tiruan Dengan Backpropagation Untuk Prediksi Mahasiswa Dropout Eka Yulia Sari; Kusrini Kusrini; Andi Sunyoto
Creative Information Technology Journal Vol 6, No 2 (2019): Juli - Desember
Publisher : UNIVERSITAS AMIKOM YOGYAKARTA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24076/citec.2019v6i2.235

Abstract

Universitas ABC yogyakarta selalu melakukan evaluasi kinerja mahasiswa guna mengetahui pencapaian pada masing-masing mahasiswa.Mahasiswa yang melampaui masa studi dan tidak melakukan perpanjangan akan dikenakan sanki berupa dropout.Kasus dropout tersebut dapat diminimalisir dengan pendeteksian secara dini terhadap mahasiswa yang beresiko dropout. Pendeteksian dapat dilakukan dengan memanfaatkan tumpukan data untuk memprediksi dropout mahasiswa. Pada penelitian ini bertujuan untuk memprediksi mahasiswa yang berpotensi dropout dengan masa studi maksimal yang harus diselesaikan pada jenjang Sarjana dengan mengimplementasikan Metode Backpropagation. Data yang digunakan dalam penelitian ini adalah data akademik prodi S1 Informatika Universitas ABC pada tahun 2016-2019 denganjumlah dataset sebanyak 129.Tujuan penelitian ini untuk mengukur analisis prediksi dropoutdengan percobaan penggunaan beberapa arsitektur jaringan. Hasil yang diperoleh dari modelyang diusulkan yaitu model arsitektur 12-5-2 merupakan model arsitektur terbaik yangdidapatkan. Learning rate terbaik sebesar 0,4 dengan momentum terbaik sebesar 0,95. Akurasi yang diperoleh dari prediksi mahasiswa dropout dengan arsitektur, learning rate, dan momentum terbaik sebesar 98,2%.ABC University of Yogyakarta always evaluates student performance in order to find out the achievements of each student. Students who have exceeded the study period and not extended would be subject to sanctions in the form of a dropout. The dropout case can be minimized by early detection of students who are at risk of dropout. Detection can be done by utilizing a pile of data to predict student dropouts. In this study aims to predict students who have the potential to drop out with a maximum study period that must be completed at the Undergraduate level by implementing the Backpropagation Method. The data used in this study are academic data of S1 University Informatics Study Program of ABC University in 2016-2019 with the number of datasets as much as 129. The purpose of this study is to measure the dropout prediction analysis with the experiments of using several network architectures. The results obtained from the proposed model, namely architectural models 12-5-2, are the best architectural models obtained. The best learning rate is 0.4 with the best momentum of 0.95. The accuracy obtained from the prediction of dropout students is 98.2%.
PREDIKSI MAHASISWA DROP OUT MENGGUNAKAN METODE SUPPORT VECTOR MACHINE Siti Nurhayati; Kusrini kusrini; Emha Taufiq Luthfi
SISFOTENIKA Vol 5, No 1 (2015): SISFOTENIKA
Publisher : STMIK PONTIANAK

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (510.86 KB) | DOI: 10.30700/jst.v5i1.25

Abstract

AbstrakTingginya tingkat keberhasilan mahasiswa dan rendahnya tingkat kegagalan mahasiswa dapat mencerminkan kualitas dari suatu perguruan tinggi. Salah satu indikator kegagalan mahasiswa adalah kasus drop out. Untuk mengatasi permasalah, dilakukan prediksi menggunakan metode support vector machine. Support Vector Machine berusaha mencari hyperplane yang optimal dimana dua kelas pola dapat dipisahkan dengan maksimal, parameter yang di gunakan pada Support Vector Machine hanya parameter kernel dalam satu parameter C yang memberikan pinalti pada titik data yang di klasifikasikan secara acak. Dalam Support Vector Machine bobot (w) dan bias (b) merupakan solusi global optium dari quadratic programming sehingga cukup dengan sekali running akan menghasilkan solusi yang akan selalu sama untuk pilihan kernel dan parameter yang sama. Melalui penerapan support vector machine diharapakan untuk mendapatkan parameter Support Vector Machine yang digunakan tepat untuk memperoleh margin terbaik dalam memprediksi mahasiswa drop out.Kata Kunci— prediksi drop out, kernel, support vector machine, unified modeling language
Implementasi Decision Tree Untuk Prediksi Kelulusan Mahasiswa Tepat Waktu Christin Nandari Dengen; Kusrini Kusrini; Emha Taufiq Luthfi
SISFOTENIKA Vol 10, No 1 (2020): SISFOTENIKA
Publisher : STMIK PONTIANAK

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (345.866 KB) | DOI: 10.30700/jst.v10i1.484

Abstract

Students who are accepted every year are increasing, but not all students can graduate on time. In achieving graduation, of course, there are stages or processes that must be passed by each student such as following a number of courses, conducting fieldwork practices, real work lectures and final assignment seminars. These processes are carried out within a period of time determined by the University. For this reason, a prediction system for student graduation is needed in order to minimize students who graduate not on time. In predicting student graduation on time using 50 sample data for the 2013 graduation year with gender, IPK, graduation and toefl attributes. This study carried out the application of the CRISP-DM method with the C4.5 algorithm in predicting student graduation. The use of the C4.5 algorithm is supported by simulations carried out using the WeKa application and gets an accuracy value of 60%. With the existence of this research, it is expected to be able to help the Informatics Engineering Program at Universita Mulawarman so that students can graduate on time.