Willy Anugrah Cahyadi

The increase in the elderly population in Indonesia raises concerns about fall accidents. Many mitigation strategies are available to reduce fall accidents among the elderly. Two main strategies have been widely explored, i.e., fall detection and impact reduction. Despite its disadvantages, fall detection devices remain useful and important for future research. In addition, it is also urgent to address the impact reduction method by providing cushioning to minimize the physical impact on the subject of the fall. This study proposes a wearable safety vest equipped with a pre-impact fall-detection system and an automatically inflating airbag to protect the wearer during a fall. The main contributions of this study are the design and implementation of a lightweight wearable airbag vest for elderly protection, the development of a machine-learning-based pre-impact fall detection, and a quantitative evaluation of impact reduction using accelerometer-based measurements. The proposed safety vest with airbag has been trained, validated, and tested, with the subject achieving fall detection accuracy beyond 90% and the airbag deployment delay of less than 1 second after detection. The experiment results also show that the use of the airbag could reduce the impact shock down to 40-50% based on the accelerometer measurements.

This work presents the design of a compact wireless temperature and airflow sensing method using a complementary split ring resonator (CSRR)-loaded microstrip transmission line integrated with thermistors. The sensing principle relies on the temperature-dependent resistance of the thermistor, where varying airflow temperature modulate the heating and cooling dynamics, resulting in measurable changes in the slope and amplitude of the CSRR-loaded transmission line response. To establish a predictive relationship between these dynamic features and actual air temperature variation, a linear regression model is utilized and validated using experimentally obtained datasets. The model achieves a mean square error (MSE) of less than 0.15 dB and sensitivity of 0.2 dB/°Celcius over 18% frequency bandwidth with less than 0.05 dB sensitivity variation. Further validation confirms that such a sensing mechanism can be utilized to distinctively measure airflow rate by monitoring the time-dependent variation of the transmission response and mapping these dynamic features to actual flow rate measurements. The fabricated prototype is characterized under controlled hot-air flows in the range of 11.3 – 22.1 standard liters per minute (SLPM) at a constant source temperature of 100° C. With its low-profile architecture and compatibility with low-cost fabrication techniques, the proposed sensing mechanism offers a scalable, robust, and easily integrable solution for real-time airflow monitoring in industrial ventilation, distributed sensing, and internet of things (IoT) applications.

Obesity is known to disrupt motor control and biomechanics; however, detailed gait alterations in individuals with obesity remain underexplored, particularly in dynamic and real-world walking conditions. This study aims to quantitatively characterize gait differences between individuals with obesity and those of normal weight by analyzing postural and temporal gait parameters. The investigation focuses on pitch, roll, and cadence dynamics using body-worn inertial sensors, with phase transition modeling via Hidden Markov Models. This work proposes a novel framework that integrates multi-location Inertial Measurement Unit (IMU) sensors and a Hidden Markov Model–Supervised Marginal (HMM-SM) approach to detect and classify gait phases with high accuracy, offering practical value for clinical gait assessment and personalized rehabilitation. IMU sensors were placed on the waist, thigh, calf, and heel to record gait data from participants in both obese and normal-weight groups. Gait segmentation and phase modeling were conducted using 4-, 5-, and 8-state HMMs. Quantitative analysis revealed significantly greater postural variability in the obese group during slow walking, with standard deviations in roll and pitch reaching 20.68° and 9.23°, respectively—much higher than the normal-weight group (0.60° and 0.26°). Hidden state transitions from 5-state pitch HMMs showed a very strong effect size for the obese group (Cramér’s V = 0.72) compared to a moderate effect for the normal-weight group (V = 0.33). Similar patterns were observed for roll and cadence. In terms of segmentation accuracy, the 4- and 5-state HMMs outperformed the 8-state model, achieving accuracy levels above 99%, while the 8-state model reached only ~93%. The findings demonstrate that obesity significantly alters gait dynamics, particularly in postural stability and gait phase transitions. The proposed IMU-based HMM-SM framework effectively captures these changes, offering a reliable tool for gait analysis in clinical and biomechanical applications.

The majority of railway operators still implement conventional maintenance for railway point machines (RPMs), which is one of the most vital pieces of equipment for ensuring the safety of train operation. The conventional maintenance method lacks accuracy, is less efficient, and has high labor costs. This study developed a cost-effective and accurate fault diagnosis (FD) method based on current data to increase the overall efficiency of RPM maintenance. The FD method for RPM equipment discussed in this paper consists of three working conditions: normal, working, and failure. The method was proposed based on time-series current signals, which were gathered when the RPM was in operation. Time-series data were extracted and filtered using time-domain feature extraction based on scalable hypothesis testing. The selected features became the datasets for machine learning modeling. Six machine learning algorithms were compared in order to find the algorithm with the best FD accuracy. The results showed 100% accuracy for the Decision Tree and Random Forest algorithms in the FD method. The results of the FD method could be important for maintenance teams in determining suitable maintenance activities based on RPM working conditions.

Lung sound is one indicator of abnormalities in the lungs and respiratory tract. Research for automatic lung sound classification has become one of the interests for researchers because lung disease is one of the diseases with the most sufferers in the world. The use of lung sounds as a source of information because of the ease in data acquisition and auscultation is a standard method in examining pulmonary function. This study simulated the potential use of Higuchi fractal dimension (HFD) as a feature extraction method for lung sound classification. HFD calculations were run on a series of k values to generate some HFD values as features. According to the simulation results, the proposed method could produce an accuracy of up to 97.98% for five classes of lung sound data. The results also suggested that the shift in HFD values over the selection of a time interval k can be used for lung sound classification.

A foot posture index (FPI-6) measurement is well presented as a straightforward clinical tool for diagnosing foot posture in patients. However, the FPI-6 diagnosis is mostly performed by a medical practitioner manually utilizing both palpation and rulers. Digital photos of the feet had been considered to digitize the FPI-6 assessment, unfortunately, the two-dimensional image is inadequate to identify two-palpation based on six criteria of FPI-6. This paper proposes a mechanical platform design for generating a three-dimensional (3D) model of the patient’s foot. The design is aimed to ease the test process of a large number of samples or participants as statistical data to estimate the foot posture based on the FPI-6 method. The 3D-generated models of the foot belonging to 37 children aged below 12 years old show that the FPI-6 Criteria 1 and 4 can be evaluated more clearly in the 3D models compared with flat 2D photos.

Tenis meja merupakan salah satu cabang olahraga bola kecil yang diminati banyak orang. Dalam latihan tenis meja, seorang pemain akan menggunakan banyak bola sebagai alat latihan. Perlu usaha lebih bagi para pemain yang berlatih untuk mengumpulkan bola-bola yang berserakan setelah latihan. Ada banyak alat yang diciptakan untuk mempermudah pengambilan bola-bola tersebut, namun proses pengambilannya masih manual karena menggunakan tenaga pemain itu sendiri. Untuk meringankan usaha pemain, diperlukan suatu sistem yang otomatis dalam pengumpulan bola tenis meja. Hal itu akan diwujudkan dengan perancangan robot otonom pengumpul bola tenis meja. Robot ini akan menggunakan pengolahan citra dalam pendeteksian bola tenis meja. Proses ini berguna untuk menentukan jarak robot ke bola, dan juga menjadi acuan untuk pembuatan path planning. Robot ini akan mengumpulkan bola tenis meja yang berserakan berdasarkan jalur yang sudah dibuat. Dengan begitu, pemain tidak perlu mengeluarkan usaha lebih untuk mengambil bola-bola yang berserakan. Tingkat akurasi pada penelitian ini dalam pendeteksian bola dan jarak mencapai 80%. Kata Kunci: tenis meja, robot otonom, pengolahan citra

Beras merupakan bahan makanan pokok bagi sebagian besar masyarakat Indonesia. Konsumsi beras pada tahun 2018 mencapai 13,81 juta ton [1]. Pada umumnya beras ditanak menggunakan penanak nasi yang saat ini umum dipasaran. Tetapi karena persiapan yang dilakukan untuk menanak nasi cukup memakan waktu, membuat banyak orang malas untuk melakukannya. Karena untuk menanak nasi pengguna harus melakukan banyak proses. Mulai dari menuangkan beras dan air pada panci, lalu memasukannya pada penanak nasi hingga menekan tombol mode warm menjadi cook yang semuanya masih dilakukan secara manual. Sehingga diperlukan rancangan suatu sistem baru pada penanak nasi saat ini. Dalam sistem baru yang dirancang, pengguna dapat mengatur banyaknya beras yang ingin dimasak dengan pilihan yang bervariasi, melakukan pengisian beras dan air secara otomatis, memantau kapasitas beras dan air yang tersedia , sekaligus dapat memasak nasi secara otomatis di lokasi manapun selama smartphone terhubung dengan internet. Dari hasil pengujian sistem, diperoleh bahwa sistem dapat bekerja dengan sangat baik dengan tingkat keberhasilan mencapai 96,4% dari 54x pengujian.