Garuda - Garba Rujukan Digital

Perancangan Sales Prediction Model Menggunakan Metode Neural Network Kristiawan Nugroho; Wiwien Hadi Kurniawati; Raden Mohamad Herdian Bhakti
Jurnal Teknik Informatika UMUS Vol 4 No 02 (2022): November
Publisher : Universitas Muhadi Setiabudi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46772/intech.v4i02.870

Datamining merupakan fenomena penting pada bidang ilmu teknologi informasi yang telah membantu manusia pada berbagai bidang kehidupan. Datamining merupakan bidang ilmu yang menarik untuk diteliti apalagi pada saat ini dimana Big Data yang dihaslilkan dalam berbagai kehidupan manusia mempunyai volume yang sangat besar namun kurang memberikan arti bagi kehidupan. Penelitian datamining mengenai sales prediction memberikan kontribusi positif bagi para pengambil keputusan dalam melakukan prediksi penjualan barang yang dilakukan secara online berdasarkan beberapa fitur antara lain usia,jenis kelamin,minat,impresi maupun jumlah uang yang dibelanjakan. Penelitian ini berkontribusi dalam membangun sebuah model regresi sales prediction menggunakan metode Neural Network yang dapat dipergunakan sebagai alat bantu dalam pengambilan keputusan untuk menjual jenis produk yang diminati berbagai macam segment pada toko online. Metode Neural Network yang merupakan salah satu metode yang bekerja berdasar pola berpikir syaraf manusia terbukti memberikan hasil terbaik dalam membangun model sales prediction dibandingkan metode Random Forest dan AdaBoost. Sales prediction model menggunakan Neural Network menunjukkan hasil kinerja yang diukur dengan Mean Squared Error (MSE) sebesar 0.831, Root Mean Square Error (RMSE) sebesar 0,911 dan Mean Absolute Error (MAE) sebesar 0,650.

Pemetaan Kepribadian Sarana Pemetaan Performansi Kerja Lie Liana; Suhana Suhana; Kristiawan Nugroho; Kasmari Kasmari
Jesya (Jurnal Ekonomi dan Ekonomi Syariah) Vol 6 No 2 (2023): Article Research Volume 6 Number 2, Juni 2023
Publisher : LPPM Sekolah Tinggi Ilmu Ekonomi Al-Washliyah Sibolga

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36778/jesya.v6i2.1114

Penelitian ini bertujuan untuk melakukan pemetaan kepribadian sebagai sarana untuk memetakan performansi kerja dari responden. Responden dari penelitian ini adalah mahasiswa semester satu yang sedang mulai mempersiapkan dirinya menghadapi dunia kerja. Instrumen yang digunakan adalah personality test yang memetakan kepribadian seseorang dalam 16 kepribadian. Berdasarkan hasil penelitian didapatkan orang-tipe kepribadian: 3 orang-Turbulent Mediator, 3 orang-Assertive Protagonist, 10 orang-Turbulent Protagonist, 3 orang-Turbulent Campaigner, 1 orang-Turbulent Logician, 2 orang-Assertive Commander, 1 orang-Turbulent Commander, 1 orang-Assertive Executive, 2 orang-Turbulent Executive, 2 orang-Assertive Consul, 1 orang-Turbulent Consul dan 1 orang-Turbulent Entertainer. Masing-masing tipe kepribadian ini mempunyai role, strategy, mind, energy, nature, tactics dan identify yang berbeda-beda. Berdasarkan hasil pemetaan tipe kepribadian ini maka pemetaan pekerjaan dapat dilakukan pada masing-masing mahasiswa untuk mencapai performa kinerja yang optimal. Selain itu perusahaan dapat menggunakan pemetaan tipe kepribadian ini pada saat melakukan rekrutmen pegawai atau dengan kata lain pemetaan kepribadian bisa menjadi satu instrumen untuk rekrutmen pegawai.

Multi-Accent Speaker Detection Using Normalize Feature MFCC Neural Network Method Kristiawan Nugroho; Edy Winarno; Eri Zuliarso; Sunardi
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 7 No 4 (2023): August 2023
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v7i4.4652

Speaker recognition is a field of research that continues to this day. Various methods have been developed to detect the human voice with greater precision and accuracy. Research on human speech recognition that is quite challenging is accent recognition. Detecting various types of human accents with different accents and ethnicities with high accuracy is a research that is quite difficult to do. According to the results of the research on the data preprocessing stage, feature extraction and selection of the right classification method play a very important role in determining the accuracy results. This study uses a preprocessing approach with normalizing features combined with MFCC as a method to perform feature extraction and the neural network (NN), which is a classification method that works based on the workings of the human brain. Research results obtained using the normalize feature with MFCC and neural network for multiaccent speaker recognition, the accuracy performance reaches 82.68%, precision is 83% and recall is 82.88%.

Prediksi Ujaran Kebencian Berbasis Text Pada Sosial Media Menggunakan Metode Neural Network Kristiawan Nugroho; Endang Tjahjaningsih; Lie Liana; Raden Mohamad Herdian Bhakti
Jurnal Teknik Informatika UMUS Vol 5 No 1 (2023): Mei
Publisher : Universitas Muhadi Setiabudi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46772/intech.v5i1.1063

Currently information technology has helped in various forms of human life. They can communicate with each other through various electronic media, including using social media. The number of social media users is increasing from year to year in Indonesia. However, the development of the use of social media has also resulted in various problems, including hate speech, which will eventually lead to legal consequences. Various methods have been taken to limit the development of hate speech, including by blocking users who write hate speech on social media applications. Limiting the use of social media for hate speech can be more optimally carried out by detecting text-based words that have the potential to become hate speech. This study uses the Neural Network (NN) method to predict words that contain hatespeech on social media with an accuracy rate of 73% better than other methods such as Decission Tree and K-Nearest Neighbor (KNN) which only achieve an accuracy rate of 68.5 %.

ANALYSIS OF USER EXPERIENCE TESTING STMIK AKI WEBSITE USING SUPR-Q IN PERSPECTIVE HUMAN-COMPUTER INTERACTION Eko Prasetyo; Kristiawan Nugroho; Kristophorus Hadiono
SOSCIED Vol 6 No 1 (2023): SOSCIED - Juli 2023
Publisher : LPPM Politeknik Saint Paul Sorong

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32531/jsoscied.v6i1.645

Human-Computer Interaction (HCI) is a scientific field that studies human-computer interaction in order to design systems that satisfy user requirements and enhance the user experience (UX). HCI is very important in the development of websites because a good user experience is necessary to improve user satisfaction, efficiency, and effectiveness. The motivation behind this study is to recognize the qualities and shortcomings of the STMIK AKI site as far as client experience, as the need might have arisen to further develop client UX. From a HCI perspective, SUPR-Q is one way to use a questionnaire to measure user experience. To analyze various UX dimensions, UX testing will use Task Level Satisfaction methods like Single Ease Question (SEQ), Scenario Testing, and System Usability Scale (SUS) in addition to the SUPR-Q method. The SUPR-Q Loyalty variable had a low value, but the SEQ, SUS, and SUPR-Q methods produced results with an average grade of B, supporting the hypothesis that respondents were satisfied with their use of the STMIK AKI website. The worth got was 59.1% with Grade C and the speculation was adequate in utilizing and suggesting the STMIK AKI site page. Furthermore, in the Situation Testing strategy, the typical worth got is 57.5% with Grade C, with the speculation that the respondent or client is very able in finishing jobs or working the STMIK AKI page framework.

Analisis Penerimaan Teknologi Aplikasi Pemesanan Makanan Gofood dengan Technology Acceptance Model dan Pearson Correlation Aliyatul Munna; Kristiawan Nugroho; Kristophorus Hadiono
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 7, No 2 (2023): EDISI SEPTEMBER
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v7i2.682

Technology has proven itself as a powerful tool to ease human work in many ways, including food ordering technology. GoFood is a popular and innovative food ordering application that has brought convenience and comfort to users in Indonesia. This research aims to analyze the technology acceptance of the Gofood food ordering application using the Technology Acceptance Model (TAM). TAM is a framework used to understand the factors that influence the acceptance and use of technology. In the context of food ordering apps, user acceptance of the app is critical to the success and growth of the business. This research method involves collecting data through online surveys among Gofood application users. Respondents were asked to assess relevant factors in the TAM, including perceived usefulness, perceived ease of use, as well as attitudes toward use and behavioral intention to use. ), and test the correlation between constructs using Pearson correlation. The results of the analysis show that these findings indicate that perceived usefulness and perceived ease of use of the GoFood application contribute to attitudes toward use and interest in utilizing and using the application. .

Usability of Brain Tumor Detection Using the DNN (Deep Neural Network) Method Based on Medical Image on DICOM Niken Puspitasari; Kristiawan Nugroho; Kristhoporus Hadiono
CESS (Journal of Computer Engineering, System and Science) Vol 8, No 2 (2023): July 2023
Publisher : Universitas Negeri Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24114/cess.v8i2.48727

Deteksi tumor otak merupakan bidang penelitian yang menarik untuk diteliti. Perkembangan teknologi informasi menghasilkan berbagai metode yang dipergunakan antara lain menggunakan CT (Computed Tomography) scan atau dikenal dengan teknologi CT scan. CT Scan mempunyai berbagai macam keunggulan dalam mendeteksi tumor otak antara lain pada sisi kecepatan, kemampuan memvisualisasikan citra 3 dimensi dan kemampuan membedakan antar jaringan yang berbeda. Keunggulan CT Scan tersebut membuat para peneliti tertarik untuk mengembangkan berbagai jenis metode yang dipergunakan untuk menganalisis dan memprediksikan hasil CT scan tersebut. Salah satu metode yang dipergunakan adalah menggunakan pendekatan Machine Learning (ML). ML dapat digunakan untuk deteksi tumor otak dengan CT scan. Prosesnya melibatkan penggunaan algoritma ML untuk mengidentifikasi pola-pola yang terdapat pada gambar CT scan pasien dengan tumor otak. Dalam hal ini, CT scan pasien dengan tumor otak digunakan sebagai dataset pelatihan untuk membangun model ML. Namun penggunaan Machine Learning juga memiliki keterbatasan dalam hal kurang handal nya Model dan kesulitan hasil deteksi yang diinterpretasikan dokter. Metode ML akan mengalami ketidakakuratan prediksi dengan model training data yang semakin besar sehingga membutuhkan metode lain yang bisa menghasilkan tingkat akurasi yang tinggi. Deep Learning (DL) merupakan fenomena baru pada dunia teknologi informasi dan telah berhasil diimplementasikan pada berbagai macam bidang penelitian. DL memberikan tingkat akurasi yang semakin tinggi jika didukung data yang semakin besar. Penelitian ini mengaplikasikan salah satu metode DL yaitu Deep Neural Network (DNN) untuk memprediksi tumor otak dari hasil CT Scan yang akan disimpan pada cloud server sehingga bisa diakses kapanpun dan dimanapun juga sepanjang tersedia teknologi Internet. Hasil penelitian ini akan bermanfaat bagi para tenaga medis dalam memprediksi tumor otak dengan lebih akurat berdasarkan gambar citra dari CT scan.Detection of brain tumors is an interesting field of research to study. The development of information technology has resulted in various methods being used, including using a CT (Computed Tomography) scan or known as CT Scan technology. CT Scan has various advantages in detecting brain tumors, including in terms of speed, the ability to visualize 3-dimensional images and the ability to distinguish between different tissues. The superiority of the CT Scan makes researchers interested in developing various types of methods used to analyze and predict the results of the CT Scan. One of the methods used is the Machine Learning (ML) approach. ML can be used to detect brain tumors with CT scans. The process involves using ML algorithms to identify patterns present in the CT scan images of patients with brain tumors. In this case, CT scans of patients with brain tumors are used as a training dataset to construct the ML model. However, the use of Machine Learning also has limitations in terms of the lack of reliability of the model and the difficulty of interpreting the results of detection by doctors. The ML method will experience prediction inaccuracies with the larger training data model, requiring other methods that can produce a high level of accuracy. Deep Learning (DL) is a new phenomenon in the world of information technology and has been successfully implemented in various research fields. DL provides a higher level of accuracy if it is supported by larger data. This study applies one of the DL methods, namely Deep Neural Network (DNN) to predict brain tumors from CT Scan results which will be stored on a cloud server so that they can be accessed anytime and anywhere as long as Internet technology is available. The results of this study will be useful for medical personnel in predicting brain tumors more accurately based on images from CT scans.

Improving Indonesian multietnics speaker recognition using pitch shifting data augmentation Kristiawan Nugroho; Isworo Nugroho; De Rosal Igniatus Moses Setiadi; Omar Farooq
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 12, No 4: December 2023
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v12.i4.pp1901-1908

Speaker recognition to recognize multiethnic speakers is an interesting research topic. Various studies involving many ethnicities require the right approach to achieve optimal model performance. The deep learning approach has been used in speaker recognition research involving many classes to achieve high accuracy results with promising results. However, multi-class and imbalanced datasets are still obstacles encountered in various studies using the deep learning method which cause overfitting and decreased accuracy. Data augmentation is an approach model used in overcoming the problem of small amounts of data and multiclass problems. This approach can improve the quality of research data according to the method applied. This study proposes a data augmentation method using pitch shifting with a deep neural network called pitch shifting data augmentation deep neural network (PSDA-DNN) to identify multiethnic Indonesian speakers. The results of the research that has been done prove that the PSDA-DNN approach is the best method in multi-ethnic speaker recognition where the accuracy reaches 99.27% and the precision, recall, F1 score is 97.60%.

Analisis Penerimaan Teknologi Aplikasi Pemesanan Makanan Gofood dengan Technology Acceptance Model dan Pearson Correlation Aliyatul Munna; Kristiawan Nugroho; Kristophorus Hadiono
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 7, No 2 (2023): EDISI SEPTEMBER
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v7i2.682

Technology has proven itself as a powerful tool to ease human work in many ways, including food ordering technology. GoFood is a popular and innovative food ordering application that has brought convenience and comfort to users in Indonesia. This research aims to analyze the technology acceptance of the Gofood food ordering application using the Technology Acceptance Model (TAM). TAM is a framework used to understand the factors that influence the acceptance and use of technology. In the context of food ordering apps, user acceptance of the app is critical to the success and growth of the business. This research method involves collecting data through online surveys among Gofood application users. Respondents were asked to assess relevant factors in the TAM, including perceived usefulness, perceived ease of use, as well as attitudes toward use and behavioral intention to use. ), and test the correlation between constructs using Pearson correlation. The results of the analysis show that these findings indicate that perceived usefulness and perceived ease of use of the GoFood application contribute to attitudes toward use and interest in utilizing and using the application. .

PENENTUAN PEMILIHAN VARITAS UNGGUL PADA TANAMAN PADI MENGGUNAKAN LOGIKA FUZZY TSUKAMOTO BERBASIS WEB Yoga Ryan Fatony; Kristiawan Nugroho
Elkom : Jurnal Elektronika dan Komputer Vol 16 No 2 (2023): Desember : Jurnal Elektronika dan Komputer
Publisher : STEKOM PRESS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/elkom.v16i2.1389

Rice plants (Oryza sativa L.) are rice-producing plants which are a source of carbohydrates for most of the world's population. Almost 95% of Indonesia's population consumes rice as a staple food, so every year the demand for rice increases as the population increases. Therefore, farmers must choose quality seeds. In this era of fast and efficient technological progress, this is a very good thing for all progress in various fields. more and more fields of knowledge are developing, one of which is the existence of a decision-making system. a set of model-based procedures for processing and valuing data to help managers make decisions. This decision-making system uses several variables as input consisting of: type of variety, seed shape, seed color, root, seed age. The method used by the author is Fuzzy Tsukamoto. In the Tsukamoto method, it is explained that each consequence in IF-Then must be explained with a fuzzy set that has a membership function that does not change or is monotonous and for programming it uses PHP. The results obtained from the research that the authors conducted were in the form of a decision-making system to get the best seed yields.

Title

Found 12 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 12 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 12 Documents
Search