Garuda - Garba Rujukan Digital

Pengembangan Aplikasi Human Resource Management pada PT. HJMB Menggunakan JS, React Native, dan GraphQL Devi Dwi Purwanto; Eric Sugiharto Honggara; Suhatati Tjandra; Setya Ardhi; Nathaniel Tjoa
Journal of Information System,Graphics, Hospitality and Technology Vol. 5 No. 2 (2023): Journal of Information System, Graphics, Hospitality and Technology
Publisher : Institut Sains dan Teknologi Terpadu Surabaya (d/h Sekolah Tinggi Teknik Surabaya)

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

Sumber daya manusia sudah menjadi salah satu elemen terpenting dalam suatu perusahaan. Akan tetapi untuk mengelola sumber daya manusia yang sudah terbilang banyak dalam suatu perusahaan, Tentu saja hal itu sudah menjadi suatu masalah bagi perusahaan. Untuk mengatasi masalah tersebut perusahaan membuat sebuah divisi HRD (Human Resource Division) untuk membantu dalam melakukan pengelolaan sumber daya manusia yang terdapat di perusahaan. Untuk itu dikembangkan aplikasi yang membantu perusahaan dalam melakukan pengelolaan sumber daya manusia. Pada aplikasi ini, akan terdapat fitur pencatatan kinerja karyawan yang dulunya masih menggunakan cara konvensional menggunakan kertas dalam pelaporan sehingga dapat menimbulkan beberapa resiko seperti hilang atau rusaknya pencatatan pelaporan yang dilakukan oleh karyawan. Uji coba yang dilakukan yaitu compability, usability dan functional testing, dengan hasil 52,8% pengguna menjawab mudah dan 30,6% oengguna menjawab sangat mudah dalam menggunakan aplikasi ini. Hasil pengujian compatibility juga menunjukkan aplikasi dapat berjalan dengan baik di berbagai jenis perangkat Android.

Pemanfaatan Deep Learning pada Video Dash Cam untuk Deteksi Pengendara Sepeda Motor Stephen Ekaputra Limantoro; Yosi Kristian; Devi Dwi Purwanto
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 7 No 2: Mei 2018
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1738.3 KB)

The number of motorcyclists in Indonesia was 105.15 million in 2016. It made the Indonesian government difficult to monitor motorcyclists on the highways. Dash cam could be used as the alternative tool to detect motorcyclists when given the intelligence. One of the typical drawbacks in detecting objects is complex and varied feature. A convolutional neural networks (CNN) that was capable of detecting motorcyclists was proposed. CNN successfully classified the ship object with f1-score of 0.94. Sliding window and heat map were used in thispaper to search the localization and region of motorcyclists. Two experiments had been done in this paper. The goal of this paper was to set the best combination of CNN architecture and parameter. The first experiment consisted of three trained weights while the second experiment consisted of one trained weight. Weight peformances against test data in experiment 1 and experiment 2 were measured using f1-score of 0.977, 0.988, 0.989, and 0.986, respectively. From the experimental results using the sliding window, experiment 2 had a lower error rate to predict motorcyclists than experiment 1 because the training data on experiment 1 contained more and various images.

Decision Support System untuk Penentuan Pemberian Beasiswa Prestasi di Perguruan Tinggi Devi Dwi Purwanto
Jurnal Informatika dan Sistem Informasi Vol. 2 No. 1 (2016): Jurnal Informatika dan Sistem Informasi
Publisher : Universitas Ciputra Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (512.96 KB)

Tiap perguruan tinggi biasanya memberikan beberapa beasiswa untuk mahasiswa, baik itu beasiswa prestasi, beasiswa ekonomi lemah, maupun beasiswa yang lain. Penentuan pemberian beasiswa tersebut kadang menjadi sedikit sulit, dikarenakan bukan hanya faktor prestasi akademik saja yang dipertimbangkan. Pada penelitian ini akan dibahas decision support system untuk penentuan pemberian beasiswa prestasi dengan menggunakan metode simple additive weighting (SAW). Dimana faktor yang mempengaruhi pemberian beasiswa prestasi tersebut meliputi hasil studi (IPK), tidak menerima beasiswa yang lain, poin kegiatan kemahasiswaan, dan jumlah sks yang akan diambil. Faktor-faktor yang mempengaruhi tersebut nantinya akan menjadi atribut yang digunakan pada proses perangkingan pada metode ini. Dengan menggunakan SAW, penentuan pemberian beasiswa prestasi menjadi lebih mudah karena dapat menentukan bobot atribut yang penting yang akan diberi nilai lebih tinggi, sehingga proses perangkingan kandidat penerima beasiswa dapat dilakukan secara otomatis dan dipilih top-N mahasiswa yang akan menerima beasiswa prestasi tersebut.

FURNITURE ORDERING MARKETPLACE WITH TENDER SYSTEM USING TOPSIS FOR PICKING WINNER RECOMMENDATION Devi Dwi Purwanto; Kevin - Hongary
Research In Management and Accounting (RIMA) Vol 7, No 1 (2024): June
Publisher : Faculty of Business, Widya Mandala Surabaya Catholic University, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33508/rima.v7i1.5768

The use of technology in custom furniture sales is still not utilized to its full potential. A problem is going on inside society, namely that no application helpsthe custom furniture ordering process. There is a problemwhere the buyer has difficulty finding a craftsmanto accept custom furniture according to their wishes in large quantities at competitive prices and quality, and vice versa. Craftsmen had difficulty finding willing buyersto make purchases of custom furniture. This marketplace canhelp with these problems by helping buyersand craftsmen carry out custom furniture transactions safely. Consumers can offer custom orders to craftsmen through the application by stating the specifications, and interested craftsmen can submit offers in terms of price, processing time, quantity, and other agreements, which will be stated in the contract when the transaction occurs. This contract will protect the rights and obligations of customers and craftsmen. On the other hand, consumers are given recommendations for craftsmen using the TOPSIS method, considering the quality of work obtained from the rating, the price offered, working time, and the credibility of the craftsmen's experience.With this marketplace, 60% agree that it makes it easier to bring together customers and craftsmen to make custom furniture. 70% satisfied that the working progress feature helps buyers to know custom furniture progress status and reduce ordering errors. The TOPSIS method helps customers make decisions/selection of craftsmen with a precision of 67.58%.

FURNITURE ORDERING MARKETPLACE WITH TENDER SYSTEM USING TOPSIS FOR PICKING WINNER RECOMMENDATION Purwanto, Devi Dwi; Hongary, Kevin -
Research In Management and Accounting (RIMA) Vol. 7 No. 1 (2024): June
Publisher : Fakultas Bisnis Universitas Katolik Widya Mandala Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33508/rima.v7i1.5768

The use of technology in custom furniture sales is still not utilized to its full potential. A problem is going on inside society, namely that no application helpsthe custom furniture ordering process. There is a problemwhere the buyer has difficulty finding a craftsmanto accept custom furniture according to their wishes in large quantities at competitive prices and quality, and vice versa. Craftsmen had difficulty finding willing buyersto make purchases of custom furniture. This marketplace canhelp with these problems by helping buyersand craftsmen carry out custom furniture transactions safely. Consumers can offer custom orders to craftsmen through the application by stating the specifications, and interested craftsmen can submit offers in terms of price, processing time, quantity, and other agreements, which will be stated in the contract when the transaction occurs. This contract will protect the rights and obligations of customers and craftsmen. On the other hand, consumers are given recommendations for craftsmen using the TOPSIS method, considering the quality of work obtained from the rating, the price offered, working time, and the credibility of the craftsmen's experience.With this marketplace, 60% agree that it makes it easier to bring together customers and craftsmen to make custom furniture. 70% satisfied that the working progress feature helps buyers to know custom furniture progress status and reduce ordering errors. The TOPSIS method helps customers make decisions/selection of craftsmen with a precision of 67.58%.

Teknologi Virtual Reality untuk Media Informasi Kampus Saurik, Herman Thuan To; Purwanto, Devi Dwi; Hadikusuma, Jeremiah Irawan
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 6 No 1: Februari 2019
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Media informasi terus berkembang dengan hadirnya teknologi yang semakin membawa kemudahan bagi manusia agar sebuah pesan dapat tersampaikan dengan baik, tepat, cepat dan bermanfaat. Salah satu perkembangan teknologi pada mobile yang mendukung media informasi adalah Virtual Reality (VR). VR menjadi alternatif dikarenakan penyajian pesan yang interaktif dengan memberikan lingkungan yang imersif sebagai daya tarik pengguna. Media informasi pada lingkungan gedung kampus menjadi salah satu topik yang dibahas dalam penelitian ini. Permasalahan yang didapat adalah bagaimana memberikan sebuah lingkungan gedung kampus yang imersif kepada pengguna dengan penanganan media informasi yang dirancang agar dapat disampaikan secara interaktif dan komunikatif. Penelitian ini mengambil studi kasus gedung yang terdapat pada salah satu perguruan tinggi swasta di Surabaya. Tiap gedung memiliki ruang di tiap lantai yang menjadi pusat administrasi, kegiatan perkuliahan, ruang serbaguna, ruang dosen, dan ruang kegiatan mahasiswa. Tujuan penelitian ini adalah menghasilkan sebuah aplikasi VR dengan output mobile untuk gedung kampus beserta tata ruang secara imersif dan penanganan konten informasi dinamis didalamnya. Penanganan konten informasi dinamis dapat diwujudkan dengan penggunaan gyroscope untuk pergerakan VR dan konten penyedia informasi untuk teks dan gambar.AbstractMedia information continues to grow with the presence of technology that increasingly brings convenience for humans to a message can be delivered properly, precisely, quickly and useful. One of the technological developments in mobile that support information media is Virtual Reality (VR). VR is an alternative because of the interactive messaging presentation by providing an immersive environment as the user's appeal. The information media in the campus building is one of the topics discussed in this research. Problems gained is how to provide an immersive campus building environment to the user with the handling of information media designed to be delivered interactively and communicative. This research takes a case study of the building contained in private universities in Surabaya. Each building has rooms on each floor that become the administrative center, study activities, multipurpose room, lecture room and student activity room. The purpose of this study is to produce an immersive VR application with mobile output for campus buildings, and handling dynamic information content. Handling dynamic information content is realized through the use of gyroscopes for VR movement and information provider content for text and images.

Klasifikasi Kategori Hasil Perhitungan Indeks Standar Pencemaran Udara dengan Gausian Naïve Bayes (Studi Kasus: ISPU DKI Jakarta 2020) Purwanto, Devi Dwi; Honggara, Eric Sugiharto
Intelligent System and Computation Vol 4 No 2 (2022): INSYST: Journal of Intelligent System and Computation
Publisher : Institut Sains dan Teknologi Terpadu Surabaya (d/h Sekolah Tinggi Teknik Surabaya)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52985/insyst.v4i2.259

Pencemaran udara adalah masalah yang membahayakan manusia terutama untuk sistem pernafasan. Saat ini pencemaran udara selalu terjadi akibat beberapa hal seperti asap kendaraan, pembangkit listrik dan lainnya. Salah satu tempat di mana pencemaran udara terjadi adalah di kota besar di mana banyak orang berkumpul. Salah satu tempat yang menjadi perhatian adalah stasiun yang berada di daerah khusus ibukota jakarta. Stasiun adalah tempat di mana banyak orang berkumpul dan menunggu untuk melakukan perjalanan. Maka dari itu dinas lingkungan hidup DKI Jakarta membuka data pencemaran udara yang terjadi di stasiun agar dapat digunakan oleh masyarakat untuk diolah. Data tersebut akan dilakukan preprocessing yaitu penanganan missing value, normalisasi data, dan menggunakan one hot encoding. Data tersebut kemudian akan diklasifikasi dengan menggunakan algoritma Gausian Naïve Bayes. Setelah memperoleh hasil dari klasifikasi dapat disimpulkan bahwa atribut max dan critical yang berada dalam dataset tidak memiliki pengaruh terhadap hasil klasifikasi kategori ISPU. Atribut-atribut dari data yang berpengaruh terhadap klasifikasi kategori ISPU adalah PM10, SO2, CO, O3, dan NO2. Dengan menggunakan 5 atribut dan gausian naïve bayes, sistem dapat memberikan klasifikasi dengan akurasi sebesar 91,16% dan memiliki error rate sebesar 8,84%. Sedangkan nilai Weighted Average Recall 93,36%, Weighted Average Precision 93,92% , dan Weighted Average F1-Score sebesar 93,68%.

Comparison of Premium Rice Price Prediction in East Java with ARIMA and LSTM (Case Study: National Food Agency Data) Purwanto, Devi Dwi; Sitepu, Rasional; Honggara, Eric Sugiharto
Intelligent System and Computation Vol 6 No 2 (2024): INSYST: Journal of Intelligent System and Computation
Publisher : Institut Sains dan Teknologi Terpadu Surabaya (d/h Sekolah Tinggi Teknik Surabaya)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52985/insyst.v6i2.407

Rice price prediction plays a crucial role in maintaining economic stability and food security, especially in East Java, one of Indonesia's major rice production centers. This study aims to forecast premium rice prices in East Java using the ARIMA (AutoRegressive Integrated Moving Average) method. The data utilized in this research comprises premium rice prices obtained from the National Food Agency over the period from March 15, 2021, to October 17, 2024. The analysis process begins with data exploration to identify trends and seasonal patterns in the rice price data. Subsequently, the data is analyzed using ARIMA and LSTM methods, both recognized for their effectiveness in time-series forecasting. The ARIMA(1,1,1) model was selected due to its capability to capture price dynamics through its autoregressive, integrated, and moving average components, making it well-suited for linear data with minimal seasonal variation. LSTM was employed as a comparative model because it is a subset of Machine Learning that integrates computational models and neural network algorithms, offering potential improvements in prediction accuracy. The LSTM model used for prediction consists of four layers, each with 50 neurons, dropout rates of 20% and 30%, and a single output layer representing the predicted price. The results indicate the ARIMA model provides highly accurate price estimates with a Mean Absolute Percentage Error (MAPE) of 0.485%, whereas the LSTM model achieves a MAPE of 1.95%. These findings serve as a reference for policymakers and food industry stakeholders in formulating strategic measures to stabilize rice prices in East Java.

Title

Found 18 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 18 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 18 Documents
Search