Articles
<![CDATA[PENERAPAN METODE TERM FREQUENCY (TF) - INVERS DOCUMENT FREQUENCY (IDF) UNTUK PENCARIAN SINONIM KATA DALAM KAMUS BAHASA DAYAK NGAJU KALIMANTAN TENGAH ]]>
<![CDATA[Karolita, Devi]]>;
<![CDATA[Saputra, Ade Chandra]]>
<![CDATA[ JURNAL TEKNOLOGI INFORMASI Vol 12 No 1 (2018): Jurnal Teknologi Informasi (JTI) ]]>
Publisher : <![CDATA[Universitas Palangka Raya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (489.421 KB)
<![CDATA[The available Bahasa Dayak Ngaju dictionary only in hardcopy form and only consisted of the list of words andthe meaning of them. The dictionary didn?t provide the synonym of the word we are looking for. If we want toknow the paraphrase of one particular word, we have to do it manually by searching it on all of the list of wordsin the dictionary. Therefore, this research proposed to develope a Dayak Ngaju dictionary that provide wordsynonym search. We use Term Frequency (TF) - Invers Document Frequency (IDF) algorithm that will helpsynonym searching by comparing the term emergence in the meaning of the word that we are going to look thesynonym for in all of the meaning of the words listed on the dictionary. This method will calculate the weight inall the documents based on the input query. To evaluate the methodology accuracy, we used precision and recallmethod. The results showed that after searching synonym of 100 queries, we founded that 33 queries hadsynonyms with precision = 1 and recall = 1 and all the synonyms that are found are relevant based on expert?sjustification.]]>
<![CDATA[APLIKASI PENJADWALAN MATA KULIAH JURUSAN TEKNIK INFORMATIKA FAKULTAS TEKNIK UNIVERSITAS PALANGKA RAYA DENGAN ALGORITMA GENETIKA ]]>
<![CDATA[Saputra, Ade Chandra]]>;
<![CDATA[Saragih, Agus Sehatman]]>
<![CDATA[ JURNAL TEKNOLOGI INFORMASI Vol 12 No 2 (2018): Jurnal Teknologi Informasi (JTI) ]]>
Publisher : <![CDATA[Universitas Palangka Raya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
Full PDF (1268.357 KB)
<![CDATA[Scheduling courses in informatics engineering is needed to arrange an optimalschedule so that there is no conflict when teaching courses. In this journal of informaticsengineering has a problem in making a schedule because of frequent clash of teachinghours and the room used.Based on the problem, then to solve the above problem is to use the geneticalgorithm method. The genetic algorithm method is used for scheduling optimization.The final result of this research is the website program of Scheduling Courses inthe Department of Informatics, Faculty of Engineering, Palangkaraya University, whichcan display information about course schedules and this will be a tool for departments toprocess scheduling data through the course scheduling application.]]>
<![CDATA[PROTOIPE SISTEM PAKAR UNTUK MENDIAGNOSA PENYAKIT GIGI DAN MULUT ]]>
<![CDATA[Saputra, Ade Chandra]]>
<![CDATA[ Jurnal Teknologi Informasi: Jurnal Keilmuan dan Aplikasi Bidang Teknik Informatika Vol. 9 No. 2 (2015): Jurnal Teknologi Informasi Jurnal Keilmuan dan Aplikasi Bidang Teknik Informati ]]>
Publisher : <![CDATA[Universitas Palangka Raya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47111/jti.v9i2.1437
<![CDATA[Reluctance and fear of society in dental treatment can cause diseases that attack the body's other organs. Research through the creation of expert systems that can help users to deal with complaints of dental and oral diseases can be applied to address the above problems. The research followed by tests on 20 people with gum disease to test the accuracy of the system and display interface system based on subjective assessment. The test results of 20 patients will be analyzed again by the expert to prove the accuracy of the rules used in the system.Less precise method of forward chaining expert system implemented in the case of diagnosis, because more doctors reasoning leads to the backward chaining. However, in its implementation forward chaining method can be applied in this system well based on expert analysis with probability 0.9 accuracy, the accuracy of the diagnosis by the doctor to the user similarity of 0.8, as well as a subjective assessment by the average user 8.03125.]]>
<![CDATA[PROTOTIPE SISTEM PAKAR DENGAN METODE VARIABLE CENTERED INTELLIGENT RULE SYSTEM UNTUK MENDIAGNOSA PENYAKIT PADA ANJING ]]>
<![CDATA[Saputra, Ade Chandra]]>
<![CDATA[ Jurnal Teknologi Informasi: Jurnal Keilmuan dan Aplikasi Bidang Teknik Informatika Vol. 9 No. 1 (2015): Jurnal Teknologi Informasi Jurnal Keilmuan dan Aplikasi Bidang Teknik Informati ]]>
Publisher : <![CDATA[Universitas Palangka Raya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47111/jti.v9i1.1514
<![CDATA[In this research, design and manufacture a prototype of expert system are used to help to determinethe dog diseases. This prototype is intended to provide an access information about type of dog diseasesand therapeutic advice to owner, physician assistants and veterinarians themselves. The prototype of anexpert system is developed using Variable-Centered Intelligent Rule System and certainty factor method.A Variable-Centered Intelligent Rule System method is able to knowledge development, update knowledgeand consultation or process of inference. Certainty factor method itself is used to give consideration tothe weighting process on the symptoms of the disease so that the weighting process has been able toprovide the results of diseases with a value of confidence from the system. The input of developmentknowledge is results of knowledge representation that have been made based on interview with an expertin veterinary. In the knowledge development process each symptoms/variables will be calculated and willgeneralize the symptoms/variables on update knowledge based on its results. In the consultation process,input on expert system is the symptoms of disease which given by user and displayed by system, then theoutput of the system is the diseases based on its answer.The final result of this research is a prototype ofexpert system for diagnosing diseases of the dog and its value of confidence of the disease that indicatesthe level of confidence in the system against the disease therapeutic advice that should be given. Theresult of this research shows that the method of Variable-Centered Intelligent Rule System and certaintyfactor could be implemented in prototype of expert system for diagnosing diseases in dog]]>
<![CDATA[RANCANG BANGUN SISTEM PREDIKSI KELULUSAN MAHASISWA JURUSAN TEKNIK INFORMATIKA UNIVERSITAS PALANGKA RAYA ]]>
<![CDATA[Saragih, Agus Sehatman]]>;
<![CDATA[Saputra, Ade Chandra]]>
<![CDATA[ Jurnal Teknologi Informasi: Jurnal Keilmuan dan Aplikasi Bidang Teknik Informatika Vol. 11 No. 2 (2017): Jurnal Teknologi Informasi Jurnal Keilmuan dan Aplikasi Bidang Teknik Informat ]]>
Publisher : <![CDATA[Universitas Palangka Raya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47111/jti.v11i2.537
<![CDATA[The department is the leading part in the implementation of education from a college, so that it always conducts an evaluation to improve the quality and efficiency of higher education includingthe improvement of graduate quality. The length of student study is one of the reference variables ofsuccess level of the teaching process.The graduation prediction system using the data mining classification method is DecisisionTree C4.5. Data attributes used include; Gender, Religion, SKS, IPS, Graduated Semester, and TAType. The Graduated Semester attribute is used as a predictive target attribute. Where the attributevalue pass semester is made into 2 values that is 8-10 Semesters (<= 5 Years) and 11-14 Semesters(> 5 Years). The prediction test was performed using k-fold cross-validation method and linearregression measurement.The highest accuracy score on the prediction system was obtained in the 6th experiment andthe 7th experiment was 61.54%. While for the lowest accuracy value obtained in the 5th experimentof 30.77%. From the value of ????2 from experiment 1 to experiment 10 shows the highest value of 0.40and the lowest 0.29. The value of ????2 obtained is so small that it can further explain the result ofprediction accuracy with decision tree C4.5 algorithm is very small value.]]>
<![CDATA[IMPLEMENTASI ALGORITMA RIJNDAEL DALAM ENKRIPSI DAN DEKRIPSI GAMBAR DIGITAL BERBASIS WEB ]]>
<![CDATA[Saputra, Ade Chandra]]>;
<![CDATA[Saragih, Agus Sehatman]]>
<![CDATA[ Jurnal Teknologi Informasi: Jurnal Keilmuan dan Aplikasi Bidang Teknik Informatika Vol. 14 No. 1 (2020): Jurnal Teknologi Informasi Jurnal Keilmuan dan Aplikasi Bidang Teknik Informat ]]>
Publisher : <![CDATA[Universitas Palangka Raya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47111/jti.v14i1.609
<![CDATA[More and more abuse of digital images, data or information that is personal in nature can be easily known by others who are not entitled through digital images. This can cause material and immaterial losses to people whose personal information is misused by others. Then the application applies the Rijndael algorithm to secure digital image images which contain information or data that is personal in nature. In securing digital images, the Rijndael algorithm is used to protect the information contained in these images, this algorithm runs with processes such as SubBytes, ShiftRows, MixColumns, and AddRoundKey. The methodology applied is data collection methods such as field studies and literature studies, then methods of developing Waterfall software (Communication, Planning, Modeling, Construction, and Deployment) for system design. The results of the test analysis get an accuracy value of 100% from the 14 image files tested, all of them were successfully encrypted and decrypted so that it returned to the original form of the original image. For further development, this application can input the data files of other documents and increase the key length to 196 bits and 256 bits]]>
<![CDATA[PENENTUAN PARAMETER LEARNING RATE SELAMA PEMBELAJARAN JARINGAN SYARAF TIRUAN BACKPROPAGATION MENGGUNAKAN ALGORITMA GENETIKA ]]>
<![CDATA[saputra, ade chandra]]>
<![CDATA[ Jurnal Teknologi Informasi: Jurnal Keilmuan dan Aplikasi Bidang Teknik Informatika Vol. 14 No. 2 (2020): Jurnal Teknologi Informasi Jurnal Keilmuan dan Aplikasi Bidang Teknik Informat ]]>
Publisher : <![CDATA[Universitas Palangka Raya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47111/jti.v14i2.1141
<![CDATA[One of the weakness in backpropagation Artificial neural network(ANN) is being stuck in local minima. Learning rate parameter is an important parameter in order to determine how fast the ANN Learning. This research is conducted to determine a method of finding the value of learning rate parameter using a genetic algorithm when neural network learning stops and the error value is not reached the stopping criteria or has not reached the convergence. Genetic algorithm is used to determine the value of learning rate used is based on the calculation of the fitness function with the input of the ANN weights, gradient error, and bias. The calculation of the fitness function will produce an error value of each learning rate which represents each candidate solutions or individual genetic algorithms. Each individual is determined by sum of squared error value. One with the smallest SSE is the best individual. The value of learning rate has chosen will be used to continue learning so that it can lower the value of the error or speed up the learning towards convergence. The final result of this study is to provide a new solution to resolve the problem in the backpropagation learning that often have problems in determining the learning parameters. These results indicate that the method of genetic algorithms can provide a solution for backpropagation learning in order to decrease the value of SSE when learning of ANN has been static in large error conditions, or stuck in local minima]]>
<![CDATA[RANCANG BANGUN APLIKASI UNTUK MEMPREDIKSI TINGKAT PENGANGGURAN DI KOTA PALANGKA RAYA MENGGUNAKAN METODE ALGORITMA GENETIKA ]]>
<![CDATA[Karolita, Devi]]>;
<![CDATA[Saputra, Ade Chandra]]>
<![CDATA[ Jurnal Teknologi Informasi: Jurnal Keilmuan dan Aplikasi Bidang Teknik Informatika Vol. 10 No. 2 (2016): Jurnal Teknologi Informasi Jurnal Keilmuan dan Aplikasi Bidang Teknik Informat ]]>
Publisher : <![CDATA[Universitas Palangka Raya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47111/jti.v10i2.1426
<![CDATA[Pengangguran adalah sebuah masalah yang sulit di pecahkan di negara manapun terutama di negara berkembang seperti indonesia. Angka pengangguran yang tinggi disebabkan oleh semakin banyaknya jumlah penduduk yang memasuki usia produktif dan masuk dalam kategori angkatan kerja tetapi tidak diikuti pertambahan jumlah lapangan kerja. Angka pengangguran yang tinggi juga disebabkan oleh karena tidak stabilnya kondisis sosial politik suatu negara sehingga negara tersebut tidak dapat menciptakan lapangan kerja yang cukup atau dapat juga disebabkan karena penduduk yang masuk dalam angakatan kerja tersebut tidak memenuhi standart kualitas tenaga kerja.Data yang tercatat di Dinas Tenaga Kerja dan Transmigrasi Kota Palangkaraya tahun 2011 ada sebanyak 7.128 orang pencari kerja, dari jumlah ini permintaan tenaga kerja hanya 625 orang, sehingga masih ada sisa pencaker 6.503 orang. Struktur penduduk di Kota Palangkaraya berupa diagram piramida yang 57 persen lebih berusia 0-15 tahun yang didalamnya termasuk 22 persen angkatan kerja. Sementara usia produktif hanya sekitar 29,85%. Pertumbuhan ekonomi notabene akan memberikan lapangan kerja yang lebih luas. Namun diakui, pertumbuhan tenaga kerja di Kota Palangkaraya masih belum diimbangi dengan lapangan kerja yang ada.Untuk dapat menentukan jumlah lapangan kerja yang harus dalam setiap tahunnya maka diperlukan sebuah sistem yang dapat memprediksi jumlah angkatan kerja yang ada.Algoritma Genetika merupakan evolusi atau perkembangan dunia komputer dalam bidang kecerdasan buatan (artificial inteligent). Sebenarnya algoritma genetika ini terinspirasi oleh teori evolusi Darwin (walaupun pada kenyataannya teori tersebut terbukti keliru).Jaringan Syaraf Tiruan (JST) adalah sistem komputasi yang didasarkan atas permodelan sistem syaraf biologis (neurons) melalui pendekatan dari sifat-sifat komputasi biologis (biological computation). Dalam memecahkan permasalahan sebuah sistem yang menggunakan Jaringan Syaraf Tiruan akan dilatih terlebih dahulu untuk mengenali pola-pola yang ada pada permasalahan kemudian sistem akan mengerti dan dapat menyelesaikan permasalahan yang sesuai dengan pola yang sudah dilatihkan dengan otomatis. Perkembangan Algoritma Genetika dapat digabungkan dengan Jaringan Syaraf Tiruan untuk menyelesaikan permasalahan prediksi dan optimasi. Algoritma Genetika dapat digunakan untuk membantu pencarian bobot-bobot dari Jaringan Syaraf Tiruan sehingga diperoleh hasil yang optimal. Hasil optimal ditunjukan dengan kesalahan prediksi yang minimal. Karena itu maka penelitian ini akan menggabungkan Algoritma Genetika dan Jaringan Syaraf Tiruan yang akan digunakan untuk memprediksi jumlah pengangguran pada tahun-tahun mendatang berdasarkan data pengangguran pada tahun-tahun sebelumnya.]]>
<![CDATA[APLIKASI SENTIMENT MONITORING UNTUK TWITTER DENGAN ALGORITMA NAIVE-BAYES CLASSIFIER ]]>
<![CDATA[Ade Chandra Saputra]]>;
<![CDATA[Agus Sehatman Saragih]]>
<![CDATA[ Jurnal Teknologi Informasi: Jurnal Keilmuan dan Aplikasi Bidang Teknik Informatika Vol. 15 No. 1 (2021): Jurnal Teknologi Informasi : Jurnal Keilmuan dan Aplikasi Bidang Teknik Inform ]]>
Publisher : <![CDATA[Universitas Palangka Raya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47111/jti.v15i1.1902
<![CDATA[Every day there are millions of opinion spread across social networks. This is often utilized by various parties to determine the opinion and sentiment of the public towards the product, brand or figures that they hold. Given the abundance of data and opinions, it is not possible to do sentiment analysis manually. In this research, author performs design and implementation of sentiment monitoring application, that could monitor people’s sentiment about a particular keyword, so it is known how the people response to those keywords, whether positive, negative or neutral. From various existing social networks, Twitter is chosen as the source of data that will be monitored. Classification algorithm used here is Naive-Bayes Classifier with Boolean Multinomial model, and feature extraction using unigram word. The training data used is 400,000 data for each type of sentiment, so the total is 1.200.000 data. In the process of classification and training, application will perform stemming to take the root words contained within the tweet. Stemming algorithm used here is Confix Stripping. The methodology of application development that used here is staged delivery. Implementation of application is done using PHP programming language. The result of this research is a sentiment monitoring application that can monitor public sentiment about a particular keyword in a particular time frame. From testing using k-fold cross validation, obtained accuracy rate for sentiment classification amounted to 85%.]]>
<![CDATA[RANCANG BANGUN WEBSITE BADAN PENGAWAS PEMILIHAN UMUM (BAWASLU) KALIMANTAN TENGAH ]]>
<![CDATA[Ade Chandra Saputra]]>;
<![CDATA[Agus Sehatman Saragih]]>
<![CDATA[ Jurnal Teknologi Informasi: Jurnal Keilmuan dan Aplikasi Bidang Teknik Informatika Vol. 13 No. 1 (2019): Jurnal Teknologi Informasi Jurnal Keilmuan dan Aplikasi Bidang Teknik Informat ]]>
Publisher : <![CDATA[Universitas Palangka Raya ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.47111/jti.v13i1.279
<![CDATA[The misuse of digital image images is increasing, data or information that is of a personal nature can easily be known by others who are not entitled through digital images. This can cause material and immaterial losses to people whose personal information is misused by others. Then the application applies the Rijndael algorithm to secure digital image images which contain information or data that is of a personal nature. In securing digital image images, Rijndael's algorithm is used to protect the information contained in the image, the algorithm runs with processes such as SubBytes, ShiftRows, MixColumns, and AddRoundKey. The methodology applied is data collection methods such as field studies and literature studies, then Waterfall software development methods (Communication, Planning, Modeling, Construction, and Deployment) for system design]]>
