Nur Alamsyah’s research while affiliated with Telkom University and other places

The closing price of natural gas stocks greatly influences investment decisions and the energy industry. Predicting prices correctly can greatly help investors, market participants, and all parties involved, as it allows for making better decisions and optimizing investment portfolios. By using deep learning methods to role model various LSTM activation functions, such as Sigmoid, ReLU, and Tanh, this exploration will hopefully help understand complex patterns in time series data. By finding an appropriate forecasting method, all parties involved can reduce the environmental impact. The experimental results show that the model with ReLU activation function has the highest R2 value of 0.960 in both the training and test sets, and the model with Tanh activation function is also successful, with R2 values of 0.950 in the training set and 0.949 in the test set, and an MSE of 0.002. The model with the sigmoid activation function was slightly lower, with R2 values of 0.931 in the training set and 0.943 in the test set, and an MSE of 0.003. These findings indicate that the LSTM model with the ReLU activation function is considered better for predicting the closing price of natural gas stocks. These findings may help investors, stakeholders, and market participants choose the most accurate model to predict the closing price of natural gas stocks.

Analisis sentimen merupakan proses identifikasi emosional seseorang terhadap suatu objek yang akan menghasilkan sentimen positif, negatif dan netral. Kemajuan teknologi ini tentu memberikan pengaruh terhadap berbagai pelaku bisnis untuk saling mengintegrasikan sistem bisnisnya satu sama lain, salah satunya Tiket.com. Hal tersebut tentu menghasilkan sentimen dari masyarakat Indonesia yang diunggah pada platform media sosial Twitter, sehingga membantu individu maupun organisasi dalam mengambil keputusan. Penelitian ini dilakukan untuk mengetahui klasifikasi sentimen masyarakat Indonesia terhadap Tiket.com menggunakan algoritma Naïve Bayes Classifier (NBC), K-Nearest Neighbor (KNN), Support Vector Machine (SVM) dan Random Forest (RF). Berdasarkan perhitungan data sentimen terhadap Tiket.com terdapat 90.3% sentimen positif dan 9.7% sentimen negatif. Persentase tersebut menunjukkan bahwa Tiket.com cukup berpengaruh positif terhadap penggunanya. Berdasarkan hasil pengujian algoritma klasifikasi, diketahui NBC memperoleh tingkat akurasi sebesar 88%, KNN dengan nilai k = 11 mendapatkan akurasi sebesar 91%, SVM menghasilkan tingkat akurasi sebesar 92%, dan tingkat akurasi RF mencapai 93% dengan n_estimators = 100. Kesimpulan pada penelitian ini, Random Forest merupakan algoritma yang memiliki tingkat akurasi paling tinggi dibanding dengan algoritma klasifikasi lain.

Dynamic pricing of airline tickets in competitive markets requires innovation that responds to market changes. Dynamic pricing is also influenced by public events, such as sporting events, music concerts, and more. This study aims to increase airline ticket revenue by optimizing flight occupancy during events. The data used is obtained from social media platform Twitter (X), with eight event classifications: soccer events, music concerts, volcanic eruptions, earthquakes, riots, floods, motorcycle racing, and others (non-events). We used a stacking ensemble method for data labeling and fine-tuned the BERT model for event detection. The stacking ensemble method achieved an accuracy rate of 0.99, while the fine-tuned BERT model produced an accuracy rate of 0.94. These results show a significant contribution to improving the accuracy and effectiveness of dynamic pricing. These findings not only offer a solution to the dynamic pricing challenge but also open opportunities to increase revenue by understanding event sentiment, providing competitiveness and flexibility in a dynamic market. With a focus on accurate event detection, this research paves the way for the development of more intelligent and adaptive dynamic pricing models by combining the strengths of the Stacking Ensemble labeling technique and BERT model fine-tuning to improve model accuracy.

The increasing population level of society makes the level of public consumption of natural resources also increase, in this case the increase occurs in the use of LPG (Liquefied Petroleum Gas) fuel. With the increasing use of LPG fuel, it is possible for fires to occur caused by LPG gas leaks. However, not all LPG gas cylinder providers provide additional safety systems on the LPG cylinders they sell. So an LPG gas leak detection device and a system that can provide information in the event of an LPG cylinder leak are needed. For this reason, an LPG gas leak detection device is made using a Telegram notification system, and an MQ-2 Sensor that can detect LPG gas and provide an alarm sound and LED indicator and LCD display display. so that it can provide a warning if the owner of the LPG cylinder is outside the house. All of these components are controlled using a Nodemcu Microcontroller. This tool has the advantage of being easy to use and compatible with all Telegram-based communication devices.

This research aims to create a web-based purchasing application. With the current purchasing system, there are often errors in data processing and also difficulties in searching for documents because there is no use of databases in the system. Therefore, an application is needed in the management of web-based purchasing data with the warerfall development method. While the analysis and design of the application is done with an object-oriented approach described by UML notation. This system is made using the php programming language and MySql database, the result of this research is the creation of a web-based data processing application that can be used by companies to facilitate the data processing process.