Article Per Year (5 Year)
p-Index From 2019 - 2024
1.756
P-Index
This Author published in this journals
All Journal Jurnal Teknologi Informasi dan Ilmu Komputer InfoTekJar (Jurnal Nasional Informatika dan Teknologi Jaringan) Jurnal Komputer Terapan INTECOMS: Journal of Information Technology and Computer Science jurnal teknik informatika dan sistem informasi Journal of Applied Engineering and Technological Science (JAETS) INFOKUM Jurnal Sistem Informasi dan Teknologi Jaringan (SISFOTEKJAR) JITER-PM (Jurnal Inovasi Terapan - Pengabdian Masyarakat)
Khairul Umam Syaliman
Politeknik Caltex Riau
Civil Engineering, Building, Construction & Architecture Computer Science & IT Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Health Professions Industrial & Manufacturing Engineering Social Sciences

Published : 12 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 12 Documents
Search

 1   2 
Analisis Sentimen pada Data Saran Mahasiswa Terhadap Kinerja Departemen di Perguruan Tinggi Menggunakan Convolutional Neural Network Yuliska Yuliska; Dini Hidayatul Qudsi; Juanda Hakim Lubis; Khairul Umum Syaliman; Nina Fadilah Najwa
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 8 No 5: Oktober 2021
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2021854842

Abstract

Review atau saran dari customer dapat menjadi sangat penting bagi penyedia layanan, begitu pula saran dari mahasiswa mengenai layanan sebuah unit kerja di perguruan tinggi. Review menjadi penting karena dapat menjadi indikator kinerja penyedia layanan. Pengolahan review juga sangat penting karena dapat menjadi referensi untuk pengambilan keputusan dan peningkatan layanan yang lebih baik ke depannya. Penelitian ini menerapkan analisis sentimen pada data saran atau review mahasiswa terhadap kinerja unit kerja atau departemen di perguruan tinggi, yaitu Politeknik Caltex Riau. Analisis sentimen dilakukan dengan menggunakan Convolutional Neural Network (CNN) dan word embedding Word2vec sebagai representasi kata. CNN merupakan metode yang memiliki performa yang baik dalam mengklasifikasi teks, yaitu dengan teknik convolutional yang menggabungkan beberapa window kata pada kalimat dan mengambil window yang paling representative. Word2Vec digunakan sebagai representasi data saran dan inputan awal pada CNN, dimana Word2Vec merupakan dense vectors yang dapat merepresentasikan hubungan antar kata pada data saran dengan baik. Saran mahasiswa dapat mengandung kalimat yang sangat panjang, karena itu perpaduan Word2Vec sebagai representasi kata dan CNN dengan teknik convolutional, dapat menghasilkan representasi yang representative dari kalimat panjang tersebut. Penelitian ini menggunakan dua arsitektur CNN, yaitu Simple CNN dan DoubleMax CNN untuk mengidentifikasi pengaruh kompleksitas arsitektur terhadap hasil klasifikasi sentimen.  Berdasarkan hasil pengujian, DoubleMax CNN dapat mengklasifikasi sentimen pada saran mahasiswa dengan sangat baik, yaitu mencapai Akurasi tertinggi sebesar 98%, Recall 97%, Precision 98% dan F1-Score 98%. AbstractStudent’s reviews about department performance can be essential for a college for it can be used to evaluate the department performance and to take an immediate action to improve its performance. This research applies sentiment analysis in the student’s reviews of college department in Politeknik Caltex Riau. Convolutional Neural Network and Word2Vec are employed to analyze the sentiment. CNN is known for its good performance in text classification by applying a convolutional technique to the input sentences. Word2Vec is used as word representation and as an input to the CNN. Word2Vec are dense vectors which can represent the relationship between words excellently. Student’s reviews can be a long sentence; hence the combination of Word2Vec as word representation and CNN with convolutional technique can produce a representative fiture from that long sentence. This research utilizes two CNN architectures, which are Simple CNN dan DoubleMax CNN to identify the effect of the complexity of CNN architecture to final result. Our experiments show that DoubleMax CNN has a great performance in classifying sentiment in the student’s reviews with the best Accuracy value of 98%, Recall 97%, Precision 98% and F1-Score value of 98%.
Perbandingan Rapid Centroid Estimation (RCE) — K Nearest Neighbor (K-NN) Dengan K Means — K Nearest Neighbor (K-NN) Khairul Umam Syaliman; M. Zulfahmi; Aldi Abdillah Nababan
InfoTekJar : Jurnal Nasional Informatika dan Teknologi Jaringan Vol 2, No 1 (2017): InfoTekJar September
Publisher : Universitas Islam Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30743/infotekjar.v2i1.166

Abstract

Teknik Clustering terbukti dapat meningkatkan akurasi dalam melakukan klasifikasi, terutama pada algoritma K-Nearest Neighbor (K-NN). Setiap data dari setiap kelas akan membentuk K cluster yang kemudian nilai centroid akhir dari setiap cluster pada setiap kelas data tersebut akan dijadikan data acuan untuk melakukan proses klasifikasi menggunakan algoritma K-NN. Namun kendala dari banyaknya teknik clustering adalah biaya komputasi yang mahal, Rapid Centroid Estimation (RCE) dan K-Means termasuk kedalam teknik clustering dengan biaya komputasi yang murah. Untuk melihat manakah dari kedua algoritma ini (RCE dan K-Means) yang lebih baik memberikan peningkatan akurasi pada algoritma K-NN maka, pada penelitian ini akan mencoba untuk membandingkan kedua algoritma tersebut. Hasil dari penelitian ini adalah gabungan RCE—K-NN memberikan hasil akurasi yang lebih baik dari K-Means—K-NN pada data set iris dan wine. Namun dalam perubahan nilai akurasi RCE—K-NN lebih stabil hanya pada data set iris. Sedangkan pada data set wine, K-Means—K-NN terlihat mendapati perubahan akurasi yang lebih stabil dibandingkan RCE—K-NN.
Sistem Prediksi Keberhasilan Siswa Menggunakan Metode Nearest Cluster Classifier Khairul Umam Syaliman; Edwil Jafri
Jurnal Sistem Informasi dan Teknologi Jaringan (SISFOTEKJAR) Vol 2 No 2 (2021): September : 2021
Publisher : Pustaka Timur Publisher

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

Abstract

According to present curriculum, every unit of elementary education conduct 4 (four) evaluation stages. The first stage is the first midterm evaluation which is done at the first quarter year. Second, the first semester evaluation is done at the second quarter year. Third, the second midterm evaluation is done at the third quarter year. The last is the second semester evaluation which is done at the fourth quarter year. The first midterm evaluation, the first semester evaluation and the second midterm evaluation are done to see the students’ ability in learning. Moreover, to determine the students’ success or failure in learning process at each grade is the score of the second semester which is compared to their minimum passing grade. If the students’ score is higher than the minimum passing grade decided, the students are determined to be successful. In contrary, if the students’ score is lower than minimum passing grade, they will be determined to be failed in learning process.by considering the above condition, the writer is interested in designing a system which can predict the potential failure of students earlier. This system is built by analyzing the first midterm score, the first semester score and the second midterm score by using Nearest Cluster Classifier (NCC) Method. By the result of this prediction, parents and teachers still have time for about 3 months to help and guide students who are predicted to be potentially failed in learning process.
Seleksi Fitur Menggunakan Pendekatan k-Nearest Neighbor (k-NN) Khairul Umam Syaliman; Yuliska; Nina Fadilah Najwa
Jurnal Sistem Informasi dan Teknologi Jaringan (SISFOTEKJAR) Vol 3 No 1 (2022): Maret : 2022
Publisher : Pustaka Timur Publisher

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

Abstract

Data preprocessing merupakan salah satu tahapan yang penting dalam proses data mining. Salah satu proses pada tahapan ini adalah seleksi fitur atau disebut juga dengan seleksi variabel. Seleksi fitur adalah proses pemilihan fitur yang paling relevan serta membuang fitur yang tidak relevan, ambigu, redudan dan noisy feature. Proses seleksi fitur sangat menentukan performa metode pada tahapan mining, artinya salah dalam memilih metode pada proses seleksi fitur tidak akan menghasilkan pengetahuan yang benar dan sesuai dengan harapan. Ada banyak metode yang dapat digunakan untuk melakukan seleksi fitur, diantranya Principal Component Analysis (PCA), Informasi Gain dan Gain Ratio, akan tetapi banyak metode dari seleksi fitur yang memiliki kompleksitas dan computation cost yang tinggi.Karena hal tersebut penelitian kali ini menyarankan seleksi fitur dengan pendekatan k-Nnearesst Neighbor (k-NN). Adapun hasil dari penelitian ini terbukti bahwa data yang telah melwati seleksi fitur dengan pendekatan k-NN mampu memberikan hasil akurasi yang lebih baik.
Enhance the Accuracy of k-Nearest Neighbor (k-NN) for Unbalanced Class Data Using Synthetic Minority Oversampling Technique (SMOTE) and Gain Ratio (GR) Khairul Umam Syaliman
INFOKUM Vol. 10 No. 1 (2021): Desember, Data Mining, Image Processing, and artificial intelligence
Publisher : Sean Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (339.581 KB)

Abstract

k-Nearest Neighbor (k-NN) has very good accuracy results on data with almost the same class distribution, but on the contrary for information whose class distribution is not the same, the accuracy of k-NN will generally be lower. In addition, k-NN does not separate information for each class, implying that each class has an equal influence in determining the new information class, so it is important to choose a class that generally applies to information before characterizing the class assignments process. To overcome this problem, we will propose a structure that uses the Synthetic Minority Oversampling Technique (SMOTE) strategy to address class distribution problems and Gain Ratio (GR) to perform attribute selection to generate a new dataset with a reasonable class spread and significant class information attributes. E-Coli and Glass Identification were among the datasets used in this review. For objective results, the 10-fold-cross validation method will be used as an evaluation method with k values 1 to 10. The results of the research prove that SMOTE and GR can increase the accuracy of the k-NN method, where the highest increase occurred in the Glass Identification dataset by a difference increase of 18.5%. The lowest increase in accuracy occurred in the E-Coli dataset with an increase of 11.4%. The overall proposed method has given better performance, although the value of precision, recall, and F1-Score is not better than original k-NN when used in dataset E-Coli. To all datasets, an improvement from precision is 41.0%, recall is 43.4% and F1-Score is 41.5%.
Analisa Jenis Interaksi Masyarakat dengan Akuisisi Data Sosial Media Pemerintah KAB/Kota Provinsi Riau: Analisa Jenis Interaksi Masyarakat dengan Akuisisi Data Sosial Media Pemerintah Nina Fadilah Najwa; Yuliska Yuliska; Khairul Umam Syaliman
Jurnal Komputer Terapan  Vol. 6 No. 1 (2020): Jurnal Komputer Terapan
Publisher : Politeknik Caltex Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (387.19 KB) | DOI: 10.35143/jkt.v6i1.3468

Abstract

This study aims to analyze the type of interaction which is done by acquiring City/District Government’s Facebook Fan page. The acquisition of Facebook Fan page is performed by identifying the number of followers, the number of likes of the page, the number of postings, the number of comments, the number of shared postings and the number of likes of postings. We perform the acquisition in 90 days. Based on the result of data acquisition on 13 Cities/Districts in Riau Province, it indicates that 100% City/District Governments have performed One-Way Push Interaction and 70% of them classified as Two-Way Pool interaction. As for network co-designer of service Interaction, we found that Bengkalis District is the most active in implementing this type of interaction. Based on the results of analyzing the type of interaction between citizens and local governments in Riau Province, most of the Social media Fan Page of local governments are passive. The Collaboration of governments and citizens, which is based on the number of shared postings is classified as low. The next study may discuss the strategy that can be implemented by the governments to maximize the use of social media as media to interact and communicate with the citizens.
Educational Game as An Effort to Accelerate Learning After The Covid-19 Pandemic Khairul Umam Syaliman; Nina Fadilah Najwa; Jan Alif Kreshna
Journal of Applied Engineering and Technological Science (JAETS) Vol. 4 No. 1 (2022): Journal of Applied Engineering and Technological Science (JAETS)
Publisher : Yayasan Riset dan Pengembangan Intelektual (YRPI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37385/jaets.v4i1.1322

Abstract

The Covid-19 pandemic that occurred forced us to carry out the learning process through the internet network (online or online). Learning carried out online creates many problems, so it is considered ineffective and causes learning loss. Various methods have been taken to overcome this learning loss, including collaborating with various parties and issuing various regulations. In addition, teachers are also required to provide a new spirit in creating and innovating to provide effective, efficient, and competitive learning media. One way is to do educational game-based learning. Educational games are considered adequate for overcoming learning losses because learning media with educational games require players to participate in determining outcomes, have an entertainment side, and can increase creativity and problem-solving skills. The planned research method stages for collecting the required data are observation, interviews, and literature study. As for the development of educational games in this study, the prototype development method will be used. This study's result is that the Educational Game design has produced output that meets the needs. In future research, when this design is implemented, it is hoped that it will be an alternative medium for accelerating post-pandemic learning.
The Implementation of Deep Learning Techniques in Developing Conversational Chatbot as The Source of Vaccination Information Yuliska Yuliska; Nina Fadhilah Najwa; Khairul Umam Syaliman
Journal of Applied Engineering and Technological Science (JAETS) Vol. 4 No. 1 (2022): Journal of Applied Engineering and Technological Science (JAETS)
Publisher : Yayasan Riset dan Pengembangan Intelektual (YRPI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37385/jaets.v4i1.1340

Abstract

The Covid-19 pandemic has hit Indonesia for more than 2 years. To overcome Covid-19, Indonesian government implemented a vaccination program with a target of 70% of the population being vaccinated. However, the recorded population that has been vaccinated to reduce the risk of being exposed to Covid-19 is still low. Several studies have stated that information and invitations to vaccines through mass media are considered insufficient to convince the population to vaccinate. Residents who are still unsure and do not even want to vaccinate need really comprehensive information from experts. To answer this problem, a chatbot that can replace experts in explaining everything related to vaccines can be one solution. This is evidenced by a study which states that the interaction between people who have not been vaccinated with a chatbot that explains about vaccination can reduce the level of doubt of the population about the vaccine by up to 20%. The purpose of this research is to build a chatbot using deep learning technique. Meanwhile, the deep learning technique used to build a conversational chatbot is the Multilayer Perceptron Network (MLP). Based on the result of our study, our chatbot can answer 83% questions correctly out of 30 questions.
Peringkasan Dokumen Teks Otomatis Berdasarkan Sebuah Kueri Menggunakan Bidirectional Long Short Term Memory Network Yuliska Yuliska; Khairul Umam Syaliman
INTECOMS: Journal of Information Technology and Computer Science Vol 5 No 2 (2022): INTECOMS: Journal of Information Technology and Computer Science
Publisher : Institut Penelitian Matematika, Komputer, Keperawatan, Pendidikan dan Ekonomi (IPM2KPE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31539/intecoms.v5i2.4729

Abstract

Query-focused summarization atau peringkasan teks otomatis berdasarkan sebuah kueri adalah sebuah bidang penelitian pada natural language processing yang bertujuan untuk menghasilkan sebuah dokumen pendek atau ringkasan dari sekumpulan dokumen panjang, dimana ringkasan yang dihasilkan harus relevan dengan sebuah kueri yang diberikan. Hingga saat ini, berbagai metode deep learning telah digunakan untuk menghasilkan ringkasan dari sebuah maupun banyak dokumen dengan pendekatan abstraktif maupun ekstraktif. Pada penelitian ini, peneliti menggunakan Bidirectional Long Short Term Memory Network (Bi-LSTM) untuk menghasilkan sebuah ringkasan berdasarkan sebuah kueri dari beberapa dokumen dengan pendekatan ekstraktif. Bi-LSTM merupakan salah satu metode deep learning yang sering digunakan dalam klasifikasi teks. Dataset yang peneliti gunakan adalah DUC 2005-2007 dataset, yang merupakan dataset yang umum digunakan pada text summarization. Berdasarkan eksperimen yang peneliti lakukan, Bi-LSTM mampu menghasilkan ringkasan yang baik, yang dibuktikan dengan skor ROUGE-1 = 43.53, skor ROUGE-2 = 11.40 dan skor ROUGE-L = 18.67.
Analisa Nilai Lamda Model Jarak Minkowsky Untuk Penentuan Jurusan SMA (Studi Kasus di SMA Negeri 2 Tualang) Syaliman bin Lukman, Khairul Umam; Labellapansa, Ause
Jurnal Teknik Informatika dan Sistem Informasi Vol 1 No 2 (2015): JuTISI
Publisher : Maranatha University Press

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.28932/jutisi.v1i2.583

Abstract

SMA Negeri 2 (SMAN 2) is located in Tualang. So far the data report student majors only stored in a database as a final report. Data from the report of the majors could be used as guidelines to determine the students' decision majors for the following year. To take advantage of the data stored in that particular database, we can use data mining disciplines. The method used to make the determination of students majoring done by using Nearest K-Nearest Neighbor (K-NN) algorithm. On the other hand, the method for calculating the distance between the data used models Minkowsky distance with a value of lambda (λ) as a parameter. Lambda values that were analyzed were lambda 1, 2 and 3. Lambda with the value of 1 can generate increasing accuracy in the 11th experiment or with a large amount of data equal to 276 data. Lambda 2 will produce increasing accuracy by the 16th experiment or with the number of training data equal to 356 data while lambda 3 can also produce accuracy continuously increasing by the 11th experiement or with the amount of training data equal to 276 data. The accuracy of the lambda value of 1 is better than lambda 2 and lambda 3. This was proven in 25 experiments at lambda 1 which produces the highest accuracy value for 20 times.Keywords — Classification, Data Mining, K-Nearest Neighbor, Lamda (λ), Minkowsky.
Co-Authors Aldi Abdillah Nababan Ardianto Wibowo Ause Labellapansa, Ause Dini Hidayatul Qudsi Edwil Jafri Jan Alif Kreshna Juanda Hakim Lubis Kartina Diah M. Zulfahmi Najwa, Nina Fadilah Nina Fadhilah Najwa Sahid, Dadang Syarif Shihabudin Satria Perdana Arifin Yohana Dewi Lulu Widyasari Yuliska Yuliska Yuliska Yuliska Yuliska