72 research outputs found
PENYULUHAN ALAT SPRAYER ELEKTRIK BAGI MASYARAKAT PETANI DESA WONODADI WETAN KABUPATEN PACITAN
No full text Sebagian besar masyarakat di desa Wonodadi Wetan bermatapencaharian sebagai petani. Beberapa penyuluhan yang terkait banyak dilakukan dengan tujuan untuk mengembangkan sektor pertanian di desa Wonodadi Wetan. Akan tetapi, beberapa penyuluhan jarang menyentuh aspek teknologi tepat guna yang efektif untuk mendukung pertanian di desa Wonodadi Wetan. Salah satu teknologi yang perlu dikembangkan di desa Wonodadi Wetan dalam mendukung pertanian adalah alat sprayer. Pengembangan ini diperlukan karena mayoritas masyarakat petani di desa Wonodadi Wetan masih menggunakan alat sprayer manual. Atas dasar inilah, dilaksanakan program pengabdian masyarakat penyuluhan perancangan alat sprayer elektrik bagi masyarakat petani desa Wonodadi Wetan. Tujuan dari program pengabdian masyarakat ini adalah agar masyarakat mampu melakukan proses perancanaan, perancangan, dan penggunaan alat sprayer elektrik secara tepat. Berdasarkan hasil evaluasi, kegiatan pengabdian masyarakat ini memperoleh respon yang sangat baik dari masyarakat petani di desa Wonodadi Wetan dengan tingkat kepuasan 75% sangat puas.</jats:p
Few-Shot Optimization for Sensor Data Using Large Language Models: A Case Study on Fatigue Detection
No full textIn this paper, we propose a novel few-shot optimization with Hybrid Euclidean Distance with Large Language Models (HED-LM) to improve example selection for sensor-based classification tasks. While few-shot prompting enables efficient inference with limited labeled data, its performance largely depends on the quality of selected examples. HED-LM addresses this challenge through a hybrid selection pipeline that filters candidate examples based on Euclidean distance and re-ranks them using contextual relevance scored by large language models (LLMs). To validate its effectiveness, we apply HED-LM to a fatigue detection task using accelerometer data characterized by overlapping patterns and high inter-subject variability. Unlike simpler tasks such as activity recognition, fatigue detection demands more nuanced example selection due to subtle differences in physiological signals. Our experiments show that HED-LM achieves a mean macro F1-score of 69.13 ± 10.71%, outperforming both random selection (59.30 ± 10.13%) and distance-only filtering (67.61 ± 11.39%). These represent relative improvements of 16.6% and 2.3%, respectively. The results confirm that combining numerical similarity with contextual relevance improves the robustness of few-shot prompting. Overall, HED-LM offers a practical solution to improve performance in real-world sensor-based learning tasks and shows potential for broader applications in healthcare monitoring, human activity recognition, and industrial safety scenarios
Sistem Pengenalan Pola Huruf Braille Berbasis Audio Menggunakan Metode Naïve Bayes
No full textBlind people currently have limitations in developing their knowledge. The limitation is due to blind people still using braille character in interacting. Thus, the information received by blind people is slower than the general public. To overcome this problem, we propose a braille character pattern recognition system. There are several steps to recognize the braille character, as follows the digital image processing and pattern recognition using the naïve Bayes method. In the digital image processing step, there are several processes, such as the image acquisition process, enhancement, filtering, segmentation, and feature extraction. In the pattern recognition phase, the naive bayes method is used to predict the results of recognizable braille character patterns. The pattern recognition result is then converted into audio form using a raspberry pi device. Based on the results of our evaluation, the system is outperformed to recognize braille character with an accuracy of 88.172% and the average response time of the device into audio form about 5 seconds. Keywords: Blind People, Braille Character, Naïve BayesPenyandang tuna netra saat ini memliki keterbatasan dalam mengembangkan pengetahuannya. Keterbatasan ini disebabkan penyandang tuna netra masih menggunakan huruf braille dalam berinteraksi. Sehingga, informasi yang diterima oleh penyandang tuna netra menjadi lebih lambat dibandingan dengan masyarakat pada umumnya. Untuk mengatasi permasalahan tersebut, dikembangkan sistem pengenalan pola huruf braille ke suara. Terdapat beberapa tahapan agar huruf braille dapat dikenali dengan baik, yaitu tahap pengolahan citra digital dan tahap pengenalan pola menggunakan metode naïve bayes. Pada tahap pengolahan citra digital, terdapat beberapa proses, yaitu proses akusisi citra, enhancement, filtering, segmentasi, dan ekstraksi fitur. Pada tahap pengenalan pola, metode naive bayes digunakan untuk memprediksi hasil pola huruf braille yang dikenali. Hasil pengenalan pola tersebut kemudian dikonversi kedalam bentuk audio menggunakan piranti raspberry pi. Berdasarkan hasil evaluasi, sistem ini memiliki kemampuan yang baik dalam mengenali huruf braille dengan akurasi 88,172% dan waktu rata-rata respon piranti kedalam bentuk audio sebesar 5 sekon. Kata kunci: Tuna netra, Huruf Braille, Naïve Baye
SISTEM KONVERSI UCAPAN KATA KE TEKS MENGGUNAKAN SUPPORT VECTOR MACHINE : SPEECH WORD RECOGNITION TO TEXT CONVERTER USING SUPPORT VECTOR MACHINE
Full text linkArtificial intelligence technology is developing very rapidly. Various fields have applied this technology to help human work. Speech recognition system is one of the artificial intelligence technologies that are widely applied in various fields. However, some research showed that it was still necessary to develop a method for a good speech recognition system. In addition, the development of speech recognition systems that can provide benefits needs to be developed, such as text recording. Based on this, the research focuses on developing a speech recognition system, in the form of spoken words and convert to text form. Speech words that have been recorded are then extracted features using linear predictive coding method. After that, the characteristic features of each sound are trained and tested using the Support Vector Machine (SVM) method for the process of recognition and convert it into text. Based on the evaluation results show that this system is able to recognize words with an accuracy rate of 71.875%. These percentages indicate that the system is able to recognize spoken words and transform them into text form properly
Penerapan dan Pelatihan Sistem Layanan Surat Bagi Masyarakat Desa Minggirsari Kecamatan Kanigoro Kabupaten Blitar
Full text linkLayanan publik yang prima dan efektif menjadi fokus utama di Indonesia. Dengan layanan publik yang baik, tingkat kepercayaan publik dapat meningkat di berbagai sektor. Salah satu upaya untuk meningkatkan layanan publik yang efektif adalah pengembangan sistem layanan surat berbasis teknologi informasi. Dengan teknologi informasi, permasalahan layanan publik yang tidak efektif, seperti tidak adanya kejelasan waktu pengurusan, dapat diselesaikan dengan optimal. Salah satu pemerintahan desa di Indonesia yang memiliki keinginan kuat untuk meningkatkan layanan publik secara optimal adalah Desa Minggirsari Kecamatan Kanigoro Kabupaten Blitar. Atas dasar hal tersebut, tim melaksanakan program kemitraan masyarakat untuk menerapkan sistem layanan surat berbasis teknologi informasi bagi masyarakat Desa Minggirsari Kecamatan Kanigoro Kabupaten Blitar. Selain penerapan sistem, program ini juga memberikan pendampingan melalui pelatihan penggunaan sistem layanan surat bagi masyarakat Desa Minggirsari Kecamatan Kanigoro Kabupaten Blitar. Hasil pelatihan yang telah dilaksanakan menunjukkan bahwa terdapat peningkatan pengetahuan masyarakat terhadap siistem layanan surat yang telah dikembangkan. Perangkat dan masyarakat Desa Minggirsari Kecamatan Kanigoro Kabupaten Blitar sangat mengapresiasi terhadap penerpan sistem layanan surat karena sangat bermanfaat dan mempermudah masyarakat dalam proses pengurusan surat di kantor desa
Pengenalan Ucapan Kata sebagai Pengendali Gerakan Robot Lengan secara Real-Time dengan Metode Linear Predictive Coding – Neuro Fuzzy
Full text linkSejak beberapa dekade terakhir ini, peran robot dalam industri maupun kehidupan sehari-hari semakin meningkat. Hampir tidak ada cabang industri teknologi tinggi yang tidak dibantu robot. Dalam kehidupan sehari-hari, berbagai bentuk robot diciptakan untuk membantu atau memudahkan aktivitas manusia. Namun seiring dengan tingkat kebutuhan manusia terhadap robot, tingkat resiko kesulitan manusia dalam menggunakan teknologi tersebut semakin tinggi. Hal ini ditunjukkan dengan banyaknya kecelakaan akibat tidak adanya teknologi yang memudahkan manusia dalam berinteraksi dengan robot secara interaktif. Pada umumnya robot-robot tersebut dikendalikan melalui input keyboard dari Personal Computer (PC) atau remote control analog, dan bukan melalui suara ucapan. Oleh karena itu perlu dirancang suatu robot yang bergerak sesuai perintah suara ucapan. Jika suara ucapan digunakan untuk mengendalikan suatu robot, maka sistem yang dipakai harus berjalan secara realtime sehingga robot dapat dikendalikan secara interaktif. Pada tugas akhir ini akan dikembangkan sebuah suatu perangkat lunak sistem pengenalan suara menggunakan metode Linear Predictive Coding (LPC) dan Neuro-Fuzzy. Perangkat lunak tersebut akan digunakan untuk mengendalikan robot lengan yang terhubung pada kabel serial RS-232 suatu PC melalui komunikasi serial. Dalam penelitian ini diharapkan dengan menerapkan metode Linear Predictive Coding (LPC) dan Neuro-Fuzzy pada sistem pengenalan suara dapat digunakan untuk mengidentifikasi perintah suara dengan tingkat keberhasilan yang tinggi sehingga dapat digunakan sebagai pengendali robot yang handal. Berdasarkan dari hasil pengujian yang dilakukan pengenalan jaringan untuk data baru lebih rendah terhadap data latihan. Prosentase pengenalan suara dari dalam database sebesar 100 %, dan prosentase untuk pengenalan suara dari luar database 12,5%
SISTEM PREDIKSI KEPRIBADIAN MANUSIA BERDASARKAN STATUS MEDIA SOSIAL MENGGUNAKAN SUPPORT VECTOR MACHINE
Full text linkCurrently, social media is a forum for exchanging information widely used by the public, such as Facebook and Twitter. Social media users exchange information to find out the condition of one another. Some companies use social media to explore the personality potential of prospective employees to be recruited. However, to dig up this information takes a very long time because the company has to open prospective employees' social media one by one. To dig up information automatically, a personality detection system is needed from social media users. This study develops a person's personality prediction system based on social media status using the support vector machine. The data sets evaluated in this study were 300 Facebook social media status data and 2067 Twitter social media status data. Based on the evaluation results, we obtained a high level of accuracy in detecting a person's personality based on social media status, namely 100% for Facebook user status and 99.3% for Twitter user status.Keywords: Personality, Social Media, Support Vector Machine, Facebook, Twitter ABSTRAKSaat ini, media sosial merupakan salah suatu wadah pertukaran informasi yang banyak digunakan oleh masyarakat, seperti Facebook maupun Twitter. Pengguna media sosial saling bertukar informasi untuk mengetahui kondisi satu dengan lainnya. Beberapa perusahaan memanfaatkan media sosial untuk menggali potensi kepribadian dari calon pegawai yang akan direkrut. Namun, untuk menggali informasi tersebut memerlukan waktu yang sangat lama karena perusahan harus membuka media sosial dari calon pegawai satu per satu. Agar dapat menggali informasi secara otomatis, maka diperlukan sistem deteksi kepribadian dari pengguna media sosial. Penelitian ini mengembangkan sistem prediksi kepribadian seseorang berdasarkan status media sosial menggunakan metode Support Vector Machine. Set data yang dievaluasi dalam penelitian ini yaitu 300 data status media sosial Facebook dan 2067 data status media sosial Twitter. Berdasarkan hasil evaluasi yang dilakukan diperoleh tingkat akurasi yang tinggi dalam mendeteksi kepribadian seseorang berdasarkan status media sosial, yaitu 100% untuk status pengguna Facebook dan 99,3% untuk status pengguna Twitter. Kata Kunci: Kepribadian, Media Sosial, Support Vector Machine, Facebook, Twitter
The Empirical Study On Algorithm Optimization In Expert Systems For Diagnosing Rice Plant Diseases
Full text linkRice is one of the most important cultivated plants for human survival. The activity of cultivating rice plants becomes a livelihood for most of these residents, so the success rate of the amount of rice harvested becomes very important because they depend on how much rice can be harvested, disease diagnosis is very important for farmers, this is very important to reduce economic losses due to diseases that cause crop failure. Therefore, when dealing with rice diseases, an expert is needed to make diagnoses or solutions to rice diseases. However, an expert does not know when to come to the village, and farmers also do not understand all rice diseases. Therefore, a web-based expert system application using the forward chaining method is proposed to represent an expert to help farmers diagnose and solve diseases of rice plants with existing symptoms.Rice is one of the most important cultivated plants for human survival. The activity of cultivating rice plants becomes a livelihood for most of these residents, so the success rate of the amount of rice harvested becomes very important because they depend on how much rice can be harvested, disease diagnosis is very important for farmers, this is very important to reduce economic losses due to diseases that cause crop failure. Therefore, when dealing with rice diseases, an expert is needed to make diagnoses or solutions to rice diseases. However, an expert does not know when to come to the village, and farmers also do not understand all rice diseases. Therefore, a web-based expert system application using the forward chaining method is proposed to represent an expert to help farmers diagnose and solve diseases of rice plants with existing symptoms
Pump Control System Using Microcontroller and Short Message Service (SMS) Gateway for Flood Prevention
No full textExtending the Expectation Confirmation Model to Examine Continuous Use Mobile Banking: Security, Trust, and Convenience
Full text linkBackground: Mobile banking adoption continues to grow, but user retention remains a challenge. Understanding the factors influencing continuance intention is crucial for improving long-term engagement. Prior research highlights the importance of confirmation, perceived usefulness, security, satisfaction, trust, and convenience, yet their interrelationships require further exploration. Objective: This study examines key determinants of users\u27 intention to continue using mobile banking services, focusing on how confirmation, perceived usefulness, security, satisfaction, trust, and convenience influence this decision. Methods: A quantitative study was conducted using structural equation modeling (SEM) to analyze relationships among these factors. Data were collected from mobile banking users and assessed for statistical significance. Results: Confirmation significantly impacts perceived usefulness (0.576) and satisfaction (0.527). Perceived usefulness influences satisfaction (0.289) and continuance intention (0.396), while satisfaction also affects continuance intention (0.240). Trust plays a role (0.211), and perceived security strongly influences trust (0.651). Perceived convenience also impacts continuance intention (0.304), emphasizing its importance in user experience. Conclusion: Confirmation and security are critical for satisfaction and trust, which drive continued mobile banking use. Strengthening security, improving perceived usefulness, and fostering trust can enhance user retention. Future studies should explore additional variables, test the model across demographics, and assess the impact of emerging technologies like AI and blockchain. Longitudinal and experimental research may offer deeper insights into these evolving relationships
- …
