The growing pursuit of sustainable agricultural development has driven efforts to combine renewable energy systems with Internet of Things (IoT) technology to improve efficiency and productivity in farming operations. This research focuses on the design and realization of a smart farming system powered primarily by solar energy. IoT-based sensing devices are integrated to continuously monitor parameters such as soil moisture, ambient temperature, and humidity, enabling automated irrigation management that conserves both water and energy resources. The photovoltaic (PV) module supplies stable electrical power, while collected data are transmitted to a cloud platform for remote access through a mobile interface. Experimental evaluation indicates that the proposed system decreases energy usage by approximately 35%, improves irrigation precision by 28%, and boosts crop yield by 20%. These outcomes demonstrate that the synergy between solar power and IoT technology plays a vital role in achieving sustainable agricultural systems and advancing the global objectives of energy transition and climate change mitigation.

This study aims to analyze user sentiment toward the NU Online application by applying a Long Short-Term Memory (LSTM) model. The research was based on 13,576 user reviews collected from the Google Play Store, which underwent preprocessing, sentiment labeling, and Exploratory Data Analysis (EDA). To ensure balanced classification, undersampling was used, resulting in 6,612 reviews equally divided into positive and negative classes. The text data was processed using tokenization and padding before being input into the LSTM model. Model training involved the use of binary crossentropy, Adam optimizer, EarlyStopping, and ReduceLROnPlateau techniques. The model achieved 93% precision, recall, and F1-score, with low error rates and strong generalization ability. EDA results showed that positive feedback mainly focused on worship features like salat schedules, while negative reviews addressed technical issues such as the azan sound. User review peaks occurred during religious periods and major updates. A Gradio-based web interface was also developed to display results and enable user-friendly access to visual sentiment insights. This implementation proves the practical potential of integrating LSTM with an interactive platform for effective sentiment analysis

An autoclave is a sterilization device that operates using high-pressure steam to eliminate microorganisms. However, in conventional systems, pressure regulation is still performed manually, which can lead to inconsistencies in the sterilization process and reduced effectiveness. This study developed an automatic pressure control system based on a digital pressure sensor, controlled by an Arduino Uno microcontroller and equipped with an ESP8266 module for real-time monitoring via the Internet of Things (IoT). The system also utilizes a MAX6675 temperature sensor, a solenoid valve as a pressure actuator, and an LCD as a local interface. Testing was conducted at three pressure settings (10, 15, and 25 psi) for a duration of 15 minutes. The results showed that the system was able to maintain pressure with a fluctuation tolerance of ±0.3 psi and successfully transmitted temperature and pressure data to a cloud dashboard in real-time. This system is considered effective in improving the efficiency, accuracy, and safety of the sterilization process, and has the potential to be implemented in medical and laboratory facilities.

This study aims to develop an efficient chili grinding machine that utilizes a hybrid system combining wind and solar energy as a sustainable solution to address the issue of dependence on conventional energy sources, which are often expensive, environmentally unfriendly, and limited in rural areas. The main challenge is how to provide a grinding machine that can operate independently in regions with limited electricity access and high energy costs. The primary objective of this research is to design a machine capable of providing reliable power in these areas. The research involved the design and assembly of a prototype, integrating wind and solar power systems to drive a DC motor for grinding chilies. Testing was conducted to measure the power output from each energy source, with results showing that the wind turbine generates an average power of 6.715 mW, while the photovoltaic (PV) system produces an average power of 14.77 W. Combined, these sources yield a total average power output of 16.466 W. However, observations revealed that the battery charging time was longer than the operational duration of the DC motor. This hybrid-powered chili grinding machine provides a practical application of renewable energy technology, particularly suited for rural areas, and supports broader efforts to reduce carbon emissions.

The increase in the use of electrical energy is increasing in the development of technology at this time. At present in Indonesia, power plants still use non-renewable energy sources that will eventually run out. The purpose of this study is to provide a source of electricity with solar energy sources, so that dependence on PLN electricity can be reduced. The method used is planning and simulating using PV*SOL software. The planned location for the installation of Solar Power Plant (SPP) is in the Gayamsari District, Semarang City, Central Java. The location of the SMA Building has an area of 1773 m2 with coordinates of Latitude -6.9830564° N, 110.4494686 ° E. In the planning, the stages are determining the location of the PLTS, identifying solar radiation intensity data, identifying electrical load data, determining solar panel capacity, determining battery capacity, determining inverter capacity, and determining the capacity of the Solar Charge Controller (SCC). The planned SPP operates in an off-grid system. In carrying out this planning with stages. The results of the study showed that the amount of daily electricity consumption was 18,402 Wh and the electricity consumption for one month was 552,060 Wh. The simulation showed that solar panels effectively produced an average of 1300 kWh of electricity. The production of large solar panels occurred from April to October, with an average energy of 130 kWh. The results of the study showed that the amount of electricity consumption was large but could be served by solar power plants.

Ada beberapa tanaman obat yang popular, salah satunya yaitu Cabai Jawa yang juga merupakan salah satu komuditas ekspor yang cukup tinggi dengan nilai jual yang fantastis, namun di Indonesia terutama di wilayah Madura pengetahuan masyarakat tentang hal tersebut masih minim karena memang tidak adanya pembudidayaan dari pemerintah sekitar. Oleh karena itu penelitian bertujuan untuk melakukan Clustering daerah yang membudidayakan tanaman ini sehingga ditemukan daerah yang masuk kategori rendah, sedang dan tinggi dipamekasan. Metode K-Means Clustering adalah metode yang cocok untuk penelitian ini dan alur kerjanya ialah mengelompokkan data n ke dalam cluster yang serupa dan berbeda dengan data cluster yang lainnya. Metode ini dikombinasikan dengan metode Algoritma Genetika sebagai optimasi pada centroid awal sehingga hasil dari clustering ini bisa optimal. Berdasarkan hasil evaluasi menggunakan Silhouette Coefficience didapatkan nilai sebesar 0. 52156 menggunakan GA dan K-Means

Transformator daya adalah perangkat penting dalam sistem listrik yang berperan dalam meningkatkan atau menurunkan tegangan AC. Gangguan pada transformator dapat menyebabkan pemadaman yang meluas, oleh karena itu, keandalan transformator perlu dipertahankan. Salah satu penyebab gangguan pada transformator adalah kera, yang merupakan binatang yang sangat mempengaruhi kinerja perangkat tersebut. Kera sering kali masuk ke wilayah transformator yang dapat menyebabkan terjadinya hubung singkat hingga ledakan pada transformator. Maka, diperlukan sistem keamanan khusus guna mencegah gangguan yang disebabkan oleh kehadiran hewan kera pada transformator. Beberapa kasus di Indonesia bahwa salah satu penyebab padam nya listrik karna ulah hewan yang mengakibatkan hingga ledakan trafo. PT. PLN UPT Kaltimtara merupakan perusahaan distribusi listrik berada di Balikpapan yang masih banyak hutan disekitar nya yang rentan dengan gangguan hewan pada trafo gerdu induk. Kebiasaan operator untuk mengusir kera atau monyet yaitu dengan berteriak dan melempari batu setiap pagi hingga sore. Penelitian ini menggunakan metode eksperimen yang bertujuan untuk menciptakan inovasi baru untuk mengusir kera perusak trafo menggunakan PIR (Passive Infra Red) Motion Sensor, gelombang frekuensi, ultrasonik dan Sirine Alarm. Ketika ada kera/monyet masuk di area trafo gardu induk dan terdeteksi sensor pir serta ultrasinik, maka mikrokontroler mendapat inputan dari sensor dan memberikan output gelombang frekuensi untuk mengusir kera. Sensor ultrasonik dapat menyalakan buzzer klakson 220 Volt AC ketika sensor ultrasonik mendeteksi adanya objek di jarak 1 sampai 4 meter dan arduino uno mengiriman perintah ke relay menjadi kondisi High apabila ultrasonik mendeteksi dan Klakson 220Volt AC akan menyala. Sensor PIR dapat bekerja dengan baik dalam jangkauan 1 sampai 6 meter. Memungkinkan arduino uno untuk mengirimkan perintah dengan baik ke modul pembangkit frekuensi dan mengaktifkan Speaker Tweeter pada frekuensi 4K Hz sampai 49,94K Hz.

Analisis sentimen merupakan bidang yang penting dalam pengolahan bahasa alami dan aplikasi sosial media modern. Penelitian ini menginvestigasi pengaruh dari variasi komposisi split data terhadap performa akurasi model analisis sentimen menggunakan SVM dan Naive Bayes. Metode eksperimen menggunakan variasi dari teknik k-fold cross-validation untuk membandingkan hasil dari berbagai proporsi pembagian data latih dan uji. Hasil eksperimen menunjukkan bahwa komposisi split data memiliki dampak signifikan terhadap performa akurasi kedua algoritma, dengan beberapa proporsi split data menghasilkan hasil yang lebih konsisten dan stabil dibandingkan dengan yang lain. Temuan ini memberikan wawasan yang berharga dalam pengaturan praktis untuk pelatihan model analisis sentimen yang lebih efektif dan andal. Teknik ekstraksi fitur yang digunakan Term Frequency-Inverse Document Frequency (TF-IDF), dengan algoritma klasifikasi Naive Bayes dan Support Vector Machine (SVM). Performa model dievaluasi menggunakan metrik seperti akurasi, presisi, recall, dan F1-score. Hasil penelitian menunjukkan bahwa signifikan model SVM dengan rasio 80:20 mencapai akurasi 76,66% dan F1-score 77 %, dibandingkan metode SVM dan Naïve Bayes dengan rasio lainnya.

Asthma is a serious chronic disease that affects the airways, and the occurrence of this disease depends on many factors, including psychological ones, and others because of specific foods, and others depend on weather conditions such as the ambient temperature and relative humidity of the air. In this research, the disease was diagnosed by identifying one of its causes, which is air humidity, which is an important factor for exacerbation of asthma, using one of the algorithms of artificial intelligence, which is the genetic algorithms, which depend on the symptoms of the disease and the degree of humidity in the air. Examples were extracted from contaminated and also non-infected individuals, and also the formula was related to them as well as the success price was 95%.

Berdasarkan analisis karakteristik siswa di tengah pandemi COVID-19, studi ini menggunakan analisis diskriminan dan regresi multinomial untuk mengeksplorasi dampaknya terhadap prestasi akademik. Faktor-faktor seperti usia, jenis kelamin, tingkat stres, dan transisi ke lingkungan pembelajaran virtual diperiksa untuk memahami pengaruhnya terhadap hasil pendidikan. Temuan ini menyoroti peran penting manajemen stres dan tantangan yang ditimbulkan oleh lingkungan pembelajaran virtual, serta menekankan perlunya intervensi yang ditargetkan untuk mendukung kesejahteraan siswa dan keberhasilan akademik. Analisis diskriminan mengidentifikasi faktor-faktor utama yang membedakan tingkat prestasi akademik, sementara regresi multinomial memodelkan hubungan kompleks di antara variabel-variabel yang mempengaruhi pencapaian siswa. Penelitian ini berkontribusi pada strategi pendidikan yang disesuaikan dengan kebutuhan siswa yang terus berkembang di lanskap pendidikan yang ditransformasi secara digital.