Hermawati Hermawati’s scientific contributions

Energi yang sebelumnya terbuang tanpa disadari dapat dimanfaatkan untuk menciptakan bentuk tenaga listrik yang ramah lingkungan. Sumber daya listrik dapat diperoleh dengan konversi yang dihasilkan dari tekanan kaki manusia saat berjalan atau berlari dengan konsep penuaian energi piezoelektrik. Penelitian ini melibatkan analisis teoritis dan eksperimental untuk mengevaluasi efisiensi serta nilai keluaran dari konfigurasi rangkaian seri dan paralel dengan variasi langkah kaki. Prototipe piezoelektrik menghasilkan keluaran berupa tegangan dan arus AC yang kemudian dikonversikan menjadi tegangan dan arus DC dengan memanfaatkan rangkaian penyearah dioda bridge. Berdasarkan hasil pengukuran dan perhitungan yang telah dilakukan dengan menggunakan 2 konfigurasi rangkaian dan 10 variasi langkah kaki didapatkan nilai keluaran terbesar pada konfigurasi rangkaian paralel dengan langkah kaki sebanyak 250 langkah dengan tegangan sebesar 5,11 V dan arus sebesar 1,54 mA, dengan daya yang dihasilkan sebesar 78,694 x10-4 Watt. Dari penelitian yang telah dilakukan dapat disimpulkan bahwa rangkaian paralel menghasilkan nilai tegangan dan arus keluaran yang lebih baik dibandingkan dengan rangkaian seri, serta nilai tegangan dan arus keluaran yang dihasilkan masing-masing konfigurasi rangkaian berbanding lurus dengan banyaknya langkah kaki.

Tanjung Pinang II Village is one of the districts in Tanjung Batu, Ogan Ilir Regency, South Sumatra, which is currently developing its potential to become a tourist village through an agro-park. However, the process of transforming the village into a tourism and educational area for the community has not yet implemented technology. Therefore, in this community service, a smart greenhouse was developed and implemented in Tanjung Pinang II Village. The methods used in this community service included situational analysis, greenhouse construction, counseling and training, as well as evaluation, analysis, and conclusion. The constructed greenhouse is equipped with temperature and humidity sensors to measure the conditions inside the room. The greenhouse is built with a steel frame and uses UV plastic for its roof and walls. The results of the community service showed that the village residents and the community benefited from the greenhouse in the process of developing Tanjung Pinang II Village as an ecotourism area.

Writing Mandarin characters is considered the most challenging component for beginners due to the rules and character formations. This paper explores the potential of a machine learning-based digital learning tool to write Mandarin characters. It also conducts a comparative study between MobileNetV2 and MobileNetV3, exploring different configurations. The research follows the Multimedia Development Life Cycle (MDLC) method to create both application and machine learning models. Participants from higher education institutions that offer Mandarin courses in Batam, Indonesia, participated in a User Acceptance Test (UAT). Data were collected through questionnaires and analyzed using the System Usability Scale (SUS) methods. The results show positive user acceptance, with an SUS score of 77.92%, indicating a high level of acceptability. MobileNetV3Small was also preferred for recognizing user handwriting, due to comparable accuracy size, rapid inference time and smallest model size. Although the application was well received, several participants provided constructive feedback, suggesting potential improvements.

A robot is capable of mimicking human beings, including recognizing their faces and emotions. However, current studies of the humanoid robot have not been implemented in the real-time system. In addition, face recognition and emotion recognition have been treated as separate problems. Thus, for real-time application on a humanoid robot, this study proposed a combination of face recognition and emotion recognition. Face and emotion recognition systems were developed concurrently in this study using convolutional neural network architectures. The proposed architecture was compared to the well-known architecture, AlexNet, to determine which architecture would be better suited for implementation on a humanoid robot. Primary data from 30 respondents was used for face recognition. Meanwhile, emotional data were collected from the same respondents and combined with secondary data from a 2500-person dataset. Surprise, anger, neutral, smile, and sadness were among the emotions. The experiment was carried out in real-time on a humanoid robot using the two architectures. Using the AlexNet model, the accuracy of face and emotion recognition was 87 % and 70 %, respectively. Meanwhile, the proposed architecture achieved accuracy rates of 95 % for face recognition and 75 % for emotion recognition, respectively. Thus, the proposed method performs better in terms of recognizing faces and emotions, and it can be implemented on a humanoid robot.

Mobil merupakan sebuah kebutuhan dan alat transportasi yang memudahkan dalam berpergian. Banyak jenis dan produk mobil yang telah dikembangkan sekarang, salah satunya adalah mobil listrik dikarenakan Bahan Bakar Minyak fosil sudah mulai menipis ketersediaannya. Pengembangan berikutnya adalah mobil listrik yang otomatis. Namun sistem kontrol otomatis seperti kemudi (steering) dan kontrol kecepatan adalah tugas kompleks serta sulit sehingga memerlukan sistem kendali yang tepat, presisi dan kuat. Oleh karena itu pada paper ini dikembangkan suatu sistem kendali yang menggunakan metode logika fuzzy dengan memanfaatkan input dari sensor Ultrasonic. Sensor ini mampu mendeteksi objek dengan jarak terjauh sebesar 10 meter dan terderak 0.3 meter, keluaran dari sistem kendali ini adalah derajat putar steer pada Hardware In The Loop yang dapat berbelok menghindari objek terdeteksi.. Berdasarkan pengujian sistem ini, ketelitian derajat putar steer adalah 5° dan putaran maksimalnya adalah 30°, sedangkan untuk kecepatan tertinggi roda belakang adalah 15 km/jam. Sistem steering pada Hardware In The Loop ini memiliki ketelitian yang cukup bagus untuk meningkatkan kehalusan (smoothness) ketika berbelok.

Perkembangan mobil listrik sangat pesat seiring dengan semakin berkurangnya sumber energi fosil. Untuk mampu bergerak otomatis identifikasi dan deteksi jalan sangat diperlukan. Namun proses ini sulit dikarenakan jalan yang ada tidak memiliki garis sebagai acuan. Banyak metode yang telah digunakan salah satunya dengan menggunakan Fully Convolutional Networks (FCNs). Metode ini berhasil dalam melakukan identifikasi terhadap jalan yang ada pada kampus Universitas Sriwijaya. Berdasarkan hasil pengujian didapatkan nilai Intersection over Union (IoU) 90%. Sehingga, model yang dihasilkan oleh FCNs dapat digunakan untuk identifikasi jalan yang dilalui. Selain itu parameter lain yang diperhitungkan yaitu nilai akurasi 98,12% pada data latih dan 97,87% pada data uji. Sedangkan error yang dihasilkan sebesar 6 % pada data latih dan 7% pada data uji. Kata kunci: Fully Convolutional Networks (FCNs), Intersection over Union, Jalan kampus, Mobil ListrikABSTRACTThe development of electric cars is very rapid along with the decreasing source of fossil energy. To move automatically, the electric car is needs identification and detection of roads. But this process is difficult because the existing road does not have a line as a reference. Many methods have been used, one of them is using Fully Convolutional Networks (FCNs). This method is successful in identifying existing roads on the Sriwijaya University campus. Based on the results of testing, it obtained Intersection over Union (IoU) value of 90%. So, the model produced by FCNs can be used to identify the path traveled. In addition, other parameters taken into account are the accuracy value of 98.12% in the training data and 97.87% in the test data. While the resulting error of 6% in training data and 7% in test data.