Claim Missing Document
Check
Articles

PENERAPAN ALGORITMA CANNY DAN JARINGAN SYARAF TIRUAN BACKPROPAGATION DALAM MENGIDENTIFIKASI IKAN KOI Zain Zakaria, Robby; Yuana, Haris; Mawaddah, Udkhiati
JATI (Jurnal Mahasiswa Teknik Informatika) Vol. 7 No. 5 (2023): JATI Vol. 7 No. 5
Publisher : Institut Teknologi Nasional Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36040/jati.v7i5.7833

Abstract

Penelitian ini bertujuan menerapkan Algoritma Canny dan Jaringan Syaraf Tiruan Backpropagation dalam proses identifikasi Ikan Koi. Algoritma Canny digunakan untuk pengolahan citra, mengubah citra Ikan Koi menjadi citra biner guna mendeteksi tepi dan fitur utama. Sementara itu, Algoritma Backpropagation, yang merupakan algoritma pembelajaran terawasi dengan struktur multilayer, digunakan untuk melatih dan menguji model pengenalan Ikan Koi. Hasil pengujian menunjukkan tingkat keberhasilan yang memuaskan dalam mengenali jenis-jenis Ikan Koi yang berbeda. Dengan menguji model pada citra latih sebanyak 45, tingkat keberhasilan dikenali mencapai 63,33%, dengan 60 citra latih mencapai 66,67%, dan dengan 90 citra latih mencapai 70%. Hasil ini memberikan wawasan penting mengenai potensi teknologi dalam identifikasi Ikan Koi serta potensi peningkatan akurasi melalui pengembangan lebih lanjut.
RANCANG BANGUN SISTEM INVENTORY TOKO TAS FLOWER MENGGUNAKAN METODE LEAST SQUARE UNTUK PREDIKSI PRODUK TAS Kuncoro Timur, Bimo; Yuana, Haris; Wulansari, Zunita
JATI (Jurnal Mahasiswa Teknik Informatika) Vol. 7 No. 5 (2023): JATI Vol. 7 No. 5
Publisher : Institut Teknologi Nasional Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36040/jati.v7i5.7848

Abstract

Penelitian ini bertujuan untuk merancang dan mengimplementasikan sistem inventory yang efisien di toko tas Flower dengan menggunakan metode Least Square untuk melakukan prediksi terhadap produk tas yang akan terjual di masa mendatang. Metode Least Square dipilih karena dapat memberikan model matematis yang paling sesuai untuk menganalisis hubungan antara waktu dan penjualan produk tas. Data historis penjualan produk tas dikumpulkan dari periode sebelumnya untuk digunakan dalam analisis. Dengan menggunakan model hasil dari metode Least Square, sistem akan dapat memprediksi jumlah produk tas yang diperlukan berdasarkan penjualan masa lalu, memungkinkan pengaturan persediaan yang lebih efisien dan mengurangi risiko stok habis atau kelebihan stok. Berdasarkan penelitian maka hasil yang diperoleh adalah 9 perancangan sistem menggunakan HTML, PHP, dan CodeIgniter di dalam aplikasi Sistem Inventory Menampilkan Login, Dashboard, Data Tas Masuk, Jenis Tas, Harga Tas, Stok Tas, History Pemasukkan, History Penjualan, dan Penjualan serta hasil pengujian black box dan validasi sistem yang dikategorikan “Sangat Layak” yaitu 86,42% dengan pengujian black box memperoleh hasil persentase 94,06% dan validasi memperoleh hasil 78,78%.
RANCANG BANGUN ALAT MONITOR KETINGGIAN AIR BERBASIS INTERNET OF THINGS (IoT) MENGGUNAKAN ESP32 DAN FRAMEWORK BLYNK Eka Febri Anggara, Wahyu; Yuana, Haris; Dwi Puspitasari, Wahyu
JATI (Jurnal Mahasiswa Teknik Informatika) Vol. 7 No. 5 (2023): JATI Vol. 7 No. 5
Publisher : Institut Teknologi Nasional Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36040/jati.v7i5.7956

Abstract

Pemantauan tinggi air adalah aspek penting dalam manajemen sumber daya air dan mitigasi banjir. Penelitian ini menguraikan pengembangan sistem pemantauan tinggi air yang menggunakan sensor ultrasonik, mikrokontroler ESP32, serta mengintegrasikannya dengan aplikasi bynk untuk memungkinkan penggunaan yang mudah dan aksesibilitas jarak jauh. Penelitian ini memanfaatkan kemampuan ESP32 untuk mengambil data dari sensor ultrasonic, kemudian mengirimkannya ke server blynk melalui koneksi Wi-Fi. Aplikasi blynk, digunakan untuk memvisualisasikan data tinggi air dalam bentuk grafik yang mudah dipahami, dan dapat memberikan notifikasi kepada pengguna jika tinggi air melebihi ambang batas yang ditentukan. Metode penelitian menggunakan RnD (Research and Development). Rancang bangun alat monitor ketinggian air berbasis Internet of Things (IoT) menggunakan ESP32 dan framework blynk dapat dilakukan dengan merangkai sensor ultrasonik HCSR04 sebagai detector jarak, buzzer mini 3V sebagai indikator suara, dan lampu LED sebagai indikator lampu. Selanjutnya mikrokontroler di program sesuai framework blynk agar dapat terhubung online sebagai perangkat IoT. Hasil dari pemantauan tinggi air melalui sensor ultrasonik dapat dipantau secara real-time melalui aplikasi blynk. Sistem ini memberikan kontribusi positif dalam pemantauan dan manajemen sumber daya air. Dengan teknologi ini, diharapkan bahwa mitigasi banjir dan manajemen air akan menjadi lebih efisien dan responsif terhadap perubahan cuaca dan lingkungan.
Application of Single Exponential Smoothing and Double Exponential Smoothing in Forecasting Sales at Zoey Mart Stores Rochim, Bahrur; Yuana, Haris; Febrinita, Filda
AURELIA: Jurnal Penelitian dan Pengabdian Masyarakat Indonesia Vol 4, No 1 (2025): January 2025
Publisher : CV. Rayyan Dwi Bharata

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.57235/aurelia.v4i1.3711

Abstract

This research evaluates the Single Exponential Smoothing (SES) and Double Exponential Smoothing (DES) methods to predict sales of Fortune pillow oil at the Zoey Mart Store, which experiences sales fluctuations. SES with an alpha value of 0.5 produces a forecast of 285 items for January 2024, while DES with an alpha of 0.5 and beta 0.7 produces 338 items. Forecasting accuracy is measured using Mean Absolute Deviation (MAD) and Mean Absolute Percentage Error (MAPE). The results show that SES has a MAD of 73.82 and a MAPE of 28.81%, while DES has a MAD of 44.66 and a MAPE of 18.80%, but with lower responsiveness to changes in sales patterns. DES has lower accuracy and responsiveness , therefore this research recommends the use of DES for fluctuating sales at Zoey Mart, because DES is more suitable for these conditions. This guide helps Zoey Mart in better planning stock and estimating operational costs, especially in the face of uncertainty due to sales fluctuations.
PENERAPAN ALGORITMA K-NEAREST NEIGHBOR UNTUK KLASIFIKASI PENYAKIT DIABETES MELITUS: STUDI KASUS : WARGA DESA JATITENGAH Dwi Fasnuari, Happy Andrian; Yuana, Haris; Chulkamdi, M. Taofik
Antivirus : Jurnal Ilmiah Teknik Informatika Vol 16 No 2 (2022): November 2022
Publisher : Universitas Islam Balitar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35457/antivirus.v16i2.2445

Abstract

Diabetes is a disease characterized by high levels of sugar in the blood which causes this disease to be very dangerous. If diabetes is not controlled properly it will lead to death. The death rate due to diabetes mellitus is relatively high because the patient does not feel the symptoms of diabetes or does not understand the characteristics of diabetes. To determine a person suffering from diabetes mellitus, several medical tests are needed so that the diagnostic results can be guaranteed authenticity and the clinical trial process certainly takes a long time. long. Based on these problems, a program for the classification of diabetes mellitus was made using the K-Nearest Neighbor (KNN) algorithm. The KNN algorithm is a method for classifying new objects based on training data that has the closest neighbor to the object. This study uses 8 variables, namely easy thirst, weight loss despite regular food consumption, high blood pressure, there is a history of diabetes in the family, wounds that are difficult to heal, frequent urination at night, results of blood sugar checks and age. The data used are 108 training data and 27 testing data resulting in 93% accuracy at K=9, 100% precision, 60% recall and 75% F1-Score. With an accuracy rate of 93%, this study is considered to have succeeded in applying the KNN method to classify diabetes mellitus.
IMPLEMENTASI METODE SINGLE EXPONENTIAL SMOOTHING DALAM PERAMALAN PENJUALAN MINUMAN BOBA Sholikhatul Kasanah, Eka; Yuana, Haris; Nur Budiman, Saiful
Antivirus : Jurnal Ilmiah Teknik Informatika Vol 16 No 2 (2022): November 2022
Publisher : Universitas Islam Balitar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35457/antivirus.v16i2.2474

Abstract

Many competitors and the impact of covid-19 caused sales of boba drinks to be erratic. This creates problems for Boba Tresnatea drink sellers because they cannot know that Boba drinks will increase or decrease in sales in the future. To prepare for this, forecasting is necessary. One method that can be used for forecasting is Single Exponential Smoothing (SES). SES was chosen because it is good for short-term forecasting. SES can be used to forecast or predict something in the future by utilizing data from the past, to help make decisions in the future so as to minimize existing risks. Forecasting results for August 2022 with an alpha of 0.8 is 388 cups and 0.9 is 390 cups. The results of the MAD test with an alpha of 0.8 is 40.09180147 and an alpha of 0.9 is 39.12510214. MAPE with an alpha value of 0.8 is 11.95645923 and an alpha value of 0.9 is 11.63512324. The best used alpha value is 0.9. The results of SES forecasting in this case are categorized as good because based on the feasibility index the value of 10% to 20% is declared good.
Implementasi Algoritma Convolutional Neural Network Untuk Pengenalan Ekspresi Wajah Muttaqiin, Adhiyasa Khoirul; Yuana, Haris; Chulkamdi, Mukh Taofik
Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Vol 8, No 2 (2023): Edisi Agustus
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/jurasik.v8i2.656

Abstract

Recognizing human facial expressions has broad benefits in various fields. For example, in the field of psychology, by analyzing a person's facial expressions during the counseling process, a psychologist can understand a patient's emotional changes and identify psychological problems. One of the popular algorithms for facial expression recognition is the Convolutional Neural Network (CNN). In this study, an architectural model of the Convolutional Neural Network (CNN) is used which consists of three convolution layers. The test results show that the model drilled with ADAM optimization, batch size 32, and data augmentation achieved good accuracy, namely 70.16% for training data and 64.43% for data validation at the 100th epoch. This study also conducted tests using facial expression images from self-made datasets and achieved the highest accuracy of 67% after training the model up to the 100th epoch. The program we created succeeded in recognizing facial expressions well in real-time situations in 20 participants of various ages. However, this study shows several improvements that can be made, such as increasing the quality and quantity of facial expression data and developing the CNN model with additional features to improve accuracy and overcome overfitting.
SIBI (Sistem Bahasa Isyarat Indonesia) berbasis Machine Learning dan Computer Vision untuk Membantu Komunikasi Tuna Rungu dan Tuna Wicara Budiman, Saiful Nur; Lestanti, Sri; Yuana, Haris; Awwalin, Beta Nurul
Jurnal Teknologi dan Manajemen Informatika Vol. 9 No. 2 (2023): Desember 2023
Publisher : Universitas Merdeka Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26905/jtmi.v9i2.10993

Abstract

The Indonesian Sign Language System (SIBI) is used to translate sign language into text or speech. SIBI helps improve communication between people using sign language and those who do not understand it. Unlike commonly used languages, SIBI sign language is less known to most people due to a lack of interest. To address this, an artificial intelligence-based application was developed, focusing on deep learning to recognize SIBI sign language hand movements in real-time. The model was created with 20 epochs, a batch size of 16, and a learning rate of 0.001. It consists of 13 layers, with the ReLU activation function used for the input layer, while the output layer uses Sigmoid. The ADAM optimizer was used to expedite the model creation process. The image dataset used had a size of 300x300 pixels. In the classification testing of the SIBI alphabet results in this study, it was tested using distance tests. The distance between the webcam and the SIBI language speaker was divided into two categories: 40 cm and 60 cm. For a 40-cm distance, an accuracy of 87.50% was obtained, and for a 60-cm distance, an accuracy of 79.17% was achieved. One limitation of this study is that two alphabets, J and Z, were not included in the dataset. This is because recognition of these two alphabets requires not only finger pattern recognition but also recognition of their gesture patterns.
Application of the Combination of SMART and TOPSIS Methods in the Decision Support System for the Selection of KIP-K Recipients in Students of the Islamic University of Balitar Alwan Fauzaan; Haris Yuana; Udkhiati Mawaddah
Journal of Advances in Information and Industrial Technology Vol. 7 No. 1 (2025): May
Publisher : LPPM Telkom University Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52435/jaiit.v7i1.603

Abstract

This research aims to develop a decision support system that combines the Simple Multi-Attribute Rating Technique (SMART) method and the Technique for Order of Preference by Similarity to the Ideal Solution (TOPSIS) in the selection process for recipients of the Indonesia Smart Lecture Card (KIP-K) at the Islamic University of Balitar. The KIP-K program is an initiative of the Indonesian government to provide financial assistance to students with economic limitations but high academic potential, aiming to increase access to higher education for the underprivileged. However, in the implementation at the Islamic University of Balitar, there was an obstacle when several students who should have met the requirements and were entitled to receive the KIP-Lecture did not get it. The process without a structured calculation method and the calculation of data that is carried out individually are the main problems. This study collected and analyzed data on prospective KIP-K recipients with a decision support system developed. The research stages include data collection, normalization of criterion weights using the SMART method, and calculating priority scores using the TOPSIS method. The results of this system are measured using confusion matrix to evaluate the recommendation's accuracy. Using a confusion matrix shows that the resulting recommendation system has an accuracy rate of around 94.92%, precision of around 93.75%, recall of around 93.75%, and F1-score of 93.75, which is included in the excellent classification. This proves that combining methods can provide results based on the selection needs of KIP-K recipients at the Islamic University of Balitar.
Sistem Penyiram Tanaman Otomatis Menggunakan RTC Dan Sensor Hujan Yuana, Haris; Wulansari, Zunita; Chulkamdi, Mukh Taofik
J-INTECH (Journal of Information and Technology) Vol 11 No 2 (2023): J-Intech : Journal of Information and Technology
Publisher : LPPM STIKI MALANG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32664/j-intech.v11i2.1101

Abstract

A plant is a plant that is maintained or maintained in a medium to benefit or be harvested at any given time. The growth process requires regular watering so that plants can grow and bear good fruit. The automatic crop watering system is a study aimed at increasing the efficiency of irrigation management in agriculture automatically so that it can assist farmers in Indonesia. Where farmers are currently experiencing problems in the watering problem, there is a delay in watering the crops. This study integrated Real-Time Clock (RTC) and rain sensors as major elements in plant watering automation systems. RTC is used to set the watering schedule based on a predetermined time, while the rain sensor serves as an automatic controller to stop watering when rain is detected. The system development method involves designing well-integrated hardware and software. LCD display screens are also used in systems to provide additional information to optimize the amount of water required by plants. NodeMcu is used as a system controller so that no errors occur in scheduling plant watering. Research methods using RnD (Research and Development). The implementation of an automated crop watering system is expected to contribute to the management of water resources and energy, improve agricultural efficiency, and provide environmentally friendly and petrifying solutions for farmers across Indonesia to produce crops. Test results show that this system is capable of optimizing plant watering based on environmental conditions, thus reducing water waste and increasing plant productivity on a sustainable basis.