Jurnal Teknologi Informasi: Jurnal Keilmuan dan Aplikasi Bidang Teknik Informatika

PREDIKSI HARGA SAHAM MENGGUNAKAN ALGORITMA NEURAL NETWORK

2023-10-25T07:53:08+00:00

In recent years, the development of technology and artificial intelligence has brought forth new opportunities in analyzing and predicting stock prices. One of the approaches used is the Neural Network algorithm, which is a part of the branch of artificial intelligence known as Deep Learning. This algorithm can learn complex patterns and relationships among data by modeling inspired by the human neural network. This research utilizes the Neural Network for stock price prediction and aims to understand the application of Neural Network in predicting stock prices, which can benefit investors and market participants. Additionally, historical stock price data can be used as input for the Neural Network algorithm. The Neural Network is a frequently used algorithm for accurate predictions and is widely employed in prediction-based or forecasting research. The result of this research is the Root Mean Squared Error (RMSE) value of 19.734 +/- 0.000. The use of the Neural Network as an algorithm for stock price prediction provides investors with valuable information for making investment decisions for companies..

PERBANDINGAN MODEL PREDIKSI DATA MINING DALAM MEMPREDIKSI KONSENTRASI POLUTAN KARBON MONOKSIDA (CO) DI JAKARTA

2024-01-22T05:37:40+00:00

DKI Jakarta, as the capital of Indonesia, faces serious challenges in terms of air quality. Carbon monoxide (CO) is one of the main air pollutants in Jakarta that is harmful to human health and the environment. Data mining is a method that can be used to predict situations based on a model. The study aims to compare data mining models with the best-performing methods to predict carbon monoxide pollutants in Jakarta. The predictive data mining model of the python library is tested and evaluated based on the evaluation metrics of MASE, RMSSE, MAE, RMSE, MAPE and SMAPE values. The model test results showed that K Neighbors with the Conditional Deseasonalize & Detrending model had the best metric evaluation value to predict CO concentration with the value evaluation metrics of MASE 0.2942, RMSSE 0.2483, MAE 2.7362, RMSE 3.3863, MAPE 0.1975 and SMAPE 0.01993. Overall, K Neighbors with the Conditional Deseasonalize & Detrending model shows good performance to predict CO concentrations in Jakarta, but further adjustments are needed to improve accuracy.

PERANCANGAN PROTOTIPE DAPUR PINTAR BERBASIS IOT MENGGUNAKAN NODEMCU ESP8266 DAN APLIKASI BLYNK

2023-10-21T14:49:39+00:00

Industrial revolution 4.0 allows the integration of digital technology with human life through the Internet of Things. One form of IoT application is in kitchen devices. In this case, kitchen safety is the main concern. In this research, an IoT device was developed that can detect gas leaks in the kitchen. The success of previous studies using gas sensors Arduino Uno and MQ2, MQ3 and MQ5 proved to be able to detect gas leaks, but there are still some deficiencies in these devices such as not being connected to mobile devices and efforts to reduce gas levels. Therefore this study adds a feature to monitor room temperature and humidity using the DHT11 sensor, as well as a remote connection feature via a smartphone. In addition, an automatic fan feature is also added to suck up excess gas levels. So that this research is expected to facilitate the process of monitoring the kitchen and reduce the risk of gas leaks which are harmful to health and safety.

PERBANDINGAN ALGORITMA MACHINE LEARNING UNTUK ANALISIS SENTIMEN PADA ULASAN HOTEL

2024-01-29T14:30:23+00:00

The paper extensively explores machine learning algorithms for evaluating sentiments in hotel reviews, particularly within the tourism and hospitality industry. It underscores the importance of precise reviews in utilizing artificial intelligence for improved operational efficiency, revenue optimization, and heightened customer satisfaction. Notably, supervised machine learning algorithms like Gradient Boosting, Support Vector Machine, and K-Nearest Neighbor are highlighted for offering recommendations based on reviews to predict user preferences. The research methodology involves data scraping, cleaning, preprocessing, and labeling, followed by training and testing the chosen machine learning algorithms. Results indicate that the Support Vector Machine algorithm demonstrated superior performance with accuracy 0.8553, precision 0.8433, recall 0.8553, dan F1-score 0.8424, suggesting its appropriateness for sentiment analysis in hotel reviews. The paper concludes by recommending the implementation of the Support Vector Machine model for sentiment analysis in hotel reviews in Palangka Raya, Indonesia, and proposes avenues for further industry development and enhancement.

IMPLEMENTASI CONTENT-BASED FILTERING MENGGUNAKAN TF-IDF AND COSINE SIMILARITY UNTUK SISTEM REKOMENDASI RESEP MASAKAN

2024-01-27T19:18:12+00:00

Many housewives are still confused about what dishes they will cook with existing food ingredients. Most housewives get recipe ideas from the website. Recipes from the website have the advantage of being easily accessible, but the disadvantages are sometimes troublesome for users because they have to choose a recipe from which site because there are many sites that contain the same recipe, and most of the recipe websites on the internet do not have a feature to search recipes based on the ingredients they have. The aim of this research is to implement a content-based filtering method using TF-IDF and cosine similarity for a recipe recommendation system. The TF-IDF and cosine similarity models are used to find similarity values between material data in the database and the query entered by the user in the search form. The sample data used in this research is 30 recipe data points taken from the website makapahariini.com. As a result, this system displays recipe recommendations that match the query of ingredients inputted by the user on the search form, and based on the test results using root mean square error (RMSE), it can be said that the recommendation system with the content-based filtering method that has been implemented produces quite good recommendations with a value of 0.356359182.

PENGGUNAAN ALGORITMA HEBB DALAM POLA PENGENALAN HURUF

2024-01-28T07:26:27+00:00

Dalam ilmu komputer, Jaringan Syaraf Tiruan (JST) adalah pendekatan populer yang bertujuan untuk menyelesaikan berbagai permasalahan, seperti pengenalan pola atau klasifikasi, melalui pembelajaran. Penelitian ini mengeksplorasi penggunaan algoritma Hebb Rule dalam konteks pengenalan pola huruf menggunakan jaringan syaraf tiruan. Jaringan syaraf tiruan adalah model pemrosesan informasi yang terinspirasi oleh struktur jaringan syaraf biologis manusia. Algoritma Hebb Rule digunakan untuk melatih jaringan agar dapat mengidentifikasi dan membentuk asosiasi antara pola input dan output. Penelitian ini fokus pada penggunaan algoritma Hebb Rule dalam mengenali pola huruf “T” dan “U” dalam format matriks 5x5 dengan representasi data bipolar, di mana “X” diwakili sebagai -1 dan “O” diwakili sebagai 1. Metodologi penelitian mencakup identifikasi masalah, tujuan penelitian, pengenalan pola huruf, penerapan algoritma Hebb Rule, dan hasil pola. Hasil penelitian menunjukkan bahwa pola pada huruf “T” dan “U” dapat diidentifikasi menggunakan algoritma Hebb dengan nilai bersih 32 dan -32, masing-masing. Penelitian ini juga mencakup perubahan bobot dan bias pada jaringan Hebb melalui serangkaian iterasi, serta perhitungan nilai aktivasi jaringan untuk menentukan keberhasilan pengenalan pola. Kesimpulannya, penelitian ini memberikan wawasan yang lebih dalam tentang penggunaan algoritma Hebb dalam pengenalan pola huruf dan potensinya dalam pengembangan aplikasi praktis.

RANCANG BANGUN APLIKASI ABSENSI GURU DAN STAF TU DENGAN PENERAPAN GEOLOCATION DAN FINGERPRINT BERBASIS ANDROID DI SMK GKE MANDOMAI

2024-01-30T14:58:43+00:00

Attendance is one of the work assessments and as proof of attendance is very important. At this time, the attendance system used by SMK GKE Mandomai is still implementing a manual attendance system, which is every day to sign at every date of entry to work, and attendance is done 2 times, namely entry attendance and return attendance.

This manual attendance system has the potential to cause some problems, such as attendance papers that are easily lost or scattered and the possibility of manipulating attendance data.

As a solution, namely by designing an attendance application with the application of geolocation and fingerprint on android as security when doing absences, in order to prevent teachers and TU staff who are outside the school location to fill absences. The development method used in designing this system is the Waterfall model with its stages, namely Software Requirements Analysis, Design, Coding, and testing. System design using UML model, implement coding using JavaScript, React Native framework and React JS, backend using Firebase. the results of this system design, produce Android-based attendance system for teachers and staff TU attendance in school areas.