The demand for a better and more capable telecommunication system continues to increase as other technologies advance. Telecommunication systems are facing a major problem in order to achieve higher capacity. To address this problem, a more capable system with higher capacity, yet reliable is required. This research offers a solution to this problem by improving the Fiber-FSO system using WDM technology. The key is to achieve larger capacities using multiple canals in the WDM method. This research proposes the usage of the 4 canal WDM component (193.1–193.4 THz) for the Fiber-FSO system. The design of the WDM Fiber-FSO system using EDFA and FBG proposed in this research reaches up to 80 Gb/s of data rate. This result is significantly higher when compared to other regular Fiber-FSO systems. One of many implementations of this system is the interbuilding communication system. For this implementation, a long-range system is necessary. This research provides an interbuilding communication system with fiber optic range extending up to 10 km per side and FSO media range reaching up to 10 km. The performance of the system will be measured mainly using the Q factor and minimum BER. At normal attenuation of 1 dB/km, the proposed design system reaches the best result averagely when given 10 dBm of power input. The average performance result in this scenario reaches Q Factor 6.78 on average. This performance result is in accordance with the standard given for the proposed design with the Q factor that requires the value of 6. The proposed design will be tested in several weather conditions in metropolitan cities, with attenuation in the FSO media reaching 20 dB/km for the worst conditions. The result of the design test under several conditions shows that the system will need to sacrifice the FSO media range as conditions worsen to achieve acceptable results.
Social media is growing exponentially, it has become a place where people can express themself freely. However, not often that hate speech can be found in the expressions. It is important to prevent hate speech as it is harmful for our society. There has been a lot of research about the detection of hate speech using artificial intelligence however most of this research focuses on the models, there is a few research that focuses on the data rather than the model. Our research aims to find the effects of the data itself towards the performance of the models. We achieve this by having two separate datasets: hate speech in Indonesian and hate speech in English which is translated into Indonesian using Google translate Service. We use these datasets separately into several machine learning models including Logistic Regression (LR), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Tree (DT), and Random Forest (RF). The best result was achieved by the RF model with 75% accuracy and weighted average F1 score for the Indonesian dataset and 58% accuracy and weighted average F1 score for the translated dataset. The Indonesian dataset is proven to be superior than the translated dataset.
In the rigorous environments of industrial furnaces, accurate measurement of Furnace Coil Outlet Temperature (COT) is crucial for maintaining efficiency, safety, and product quality. Traditional thermocouple, while commonly used, suffer from degradation and drift due to harsh conditions, leading to inaccurate measurements and frequent maintenance needs. This paper presents a comparative study of the performance of advanced dual-wavelength pyrometer versus traditional Type-K thermocouple in measuring COT. It explores the response time, accuracy, stability against thermal cycles, and maintainability of these measurement technologies. The study reveals that dual-wavelength pyrometer not only provide faster response times in conditions of rapid temperature changes, but also offer superior accuracy and stability under thermal cycling, reducing the need for frequent recalibration. The pyrometer exhibited response times approximately 2 minutes faster than the thermocouple in reaching temperature stabilization. Over extended periods, the thermocouple showed deviations up to 18°C of average difference, especially after thermal cycling events. Despite its higher cost and the increased complexity in setup, due to the need for external power supplies and precise alignment, the pyrometer demonstrates significant benefits in high-temperature industrial settings. These findings are pivotal for industries where precise temperature control is essential, recommending a shift toward non-contact pyrometry for reliable, long-term temperature monitoring in challenging furnace operations.
Object detection speed and accuracy are critical aspects of the perception system in autonomous vehicles. Speed improvement helps the object detector model achieve performance close to real-time, while accuracy enhancement ensures robust detection across various scenes. Balancing these improvements enhances the safety of autonomous vehicles, particularly in mixed and dense traffic conditions, such as those in Indonesia. This study develops a detection model using local datasets to reflect real-world conditions. It achieved balanced improvements in frames per second (fps) and mean Average Precision (mAP@50–95) through a modified YOLOv5 deep learning model. The key enhancements of the model include the integration of GhostConv and Transformer layers into the YOLOv5 architecture, referred to as YOLOv5s-GT, as well as the application of image augmentations with various scenarios to the training data. Experimental results show that the modified YOLOv5 outperformed the baseline model in both fps and mAP metrics, achieving 82.6 fps and 80.1% mAP@50–95, compared to the baseline performance of 75.8 fps and 77.7% mAP@50–95.
Heart rate variability (HRV), a well-established marker of cardiovascular health and autonomic nervous system function, exhibits dynamic fluctuations throughout the day. This study aimed to characterize these diurnal HRV patterns with high precision and detail, utilizing 30 days of continuous heart rate monitoring (Polar H10) in a cohort of 35 healthy adults. The cumulative sum of population standard deviations (SDNN) was employed as the HRV metric, capturing both short-term and long-term variations.A cubic polynomial model was used to characterize the relationship between HRV and time of day, revealing a statistically significant and non-linear pattern. HRV peaked during sleep and early morning hours, gradually declining throughout the day and reaching its lowest point in the evening. This pattern was consistent across participants, yet significant inter-individual variability was observed in the specific shape and magnitude of the diurnal curves. The model demonstrated excellent fit to the data (R-squared = 0.98) and good predictive validity on a separate dataset (Mean of Absolute Error = 58.5 ms).These findings underscore the complex interplay of circadian rhythms, sleep-wake cycles, and behavioral factors in shaping diurnal HRV patterns. The cubic polynomial model effectively captured the non-linearity and individual variability in these patterns, highlighting the importance of using statistical models for characterizing this nuanced physiological measure. The observed inter-individual variability emphasizes the need for personalized health monitoring and intervention strategies that consider an individual’s unique HRV profile for optimizing cardiovascular health and overall well-being.
