Publication Search

Gesture  recognition  technology  is  used  to  detect  movements  through  image processing,   enabling  computers  or digital devices to understand and interpret human  body  movements  as  input  or  commands.   This  technology  has  great potential  to bridge communication between the deaf community and individuals without   hearing   impairments,    enhancing  interaction  and  enriching  mutual understanding between the two.  However,  the accuracy ofgesture recognition is often  affected  by variations in the distance between hand landmarks.  Based on this problem,  this research proposes a methodfor stabilizing the measurement of distances between landmark points  in gesture recognition through a polynomial regression  approach.   Specifically,   the  distance  between  hand  landmarks  is calculated and stabilized using polynomial  regression to improve the accuracy of gesture recognition.  This method is implemented using the MediaPipeframework to detect and track hands in real-time,  and the OpenCV library to manage video. The  research  results  show  that  this  approach  can  significantly  improve  the stability  and accuracy  of gesture detection.   The developed system successfully detects gestures for  letters A  through F with a high accuracy  rate,  averaging above 98,3%.  The use ofpolynomial regression helps enhance detection accuracy by reducing noise in the landmark data.

This research critically investigates the circulation of disinformation concerning the instability of fuel prices on the digital platform X and its subsequent implications for the polarization of modern society. In an era where unverified economic news frequently dictates public reaction, fake news often acts as a potent catalyst for mass anxiety. By implementing a quantitative framework driven by lexicon-based computational sentiment analysis, this study effectively processed a dataset of 500 public opinion samples extracted via Google Colab spanning from April 2024 to April 2026. To ensure computational accuracy and eliminate textual noise, the data underwent a rigorous preprocessing phase encompassing case folding, alongside the systematic removal of URLs, account mentions, numbers, hashtags, and punctuation marks. The statistical outcomes revealed a highly disproportionate emotional landscape, overwhelmingly dominated by 451 negative reviews. In stark contrast, neutral observations and positive affirmations were nearly absent, recording only 40 and 9 instances, respectively. The data compellingly illustrates that the relentless influx of pessimistic narratives regarding economic instability directly induces financial panic, undermines rational discourse, and severely fragments cyberspace into deeply polarized factions.

This research aims to analyze the role and impact of PT Batujaya Bersama Sejahtera (PT BBS) on the socio-economic conditions of the community in Walandano Village, Balaesang Tanjung District. The background of this study is driven by the massive expansion of the mining industry in Central Sulawesi, which triggers a structural shift from traditional agriculture to an industrial economy. This study employs a qualitative method with data collection techniques including in-depth interviews, observation, and documentation. The findings indicate that PT BBS plays a significant role in local economic development by providing employment opportunities, increasing household income, and improving public infrastructure such as roads and jetties. However, the study also identifies social disruptions, including public protests regarding land issues and environmental concerns like dust and noise pollution. The implications of this research suggest that the company must strengthen its Corporate Social Responsibility (CSR) programs by focusing on sustainable community empowerment and more transparent communication to mitigate social risks. These findings contribute to the literature on regional economic development and social change in coastal mining areas.

This research is motivated by the negative impacts of production activities at a manufacturing company engaged in rubber processing, specifically at PTPN VII Unit Pematang Kiwah Natar, South Lampung. The factory's operations directly impact the environment, generating noise pollution, air pollution, unpleasant odors, and liquid waste. This situation requires the company to implement Environmental Management Accounting (EMA) to balance business sustainability with social and environmental responsibility. This is in line with Law No. 40 of 2007 concerning Limited Liability Companies and PSAK 1 of 2021. The main objective of the study was to evaluate the suitability of the implementation of environmental management accounting at PTPN VII Uni ;t Pematang Kiwah Natar, South Lampung, based on the International Guidance Document IFAC 2005 and PSAK 1 of 2021. This study used a qualitative descriptive method. Primary and secondary data were collected through interviews, observation, and documentation. The research results show that the company has implemented environmental management accounting using PSAK 1 of 2021, where the company has fulfilled the identification, presentation, measurement, recognition, and disclosure stages using the 2022 sustainability report and the 2022 financial statements of PTPN VII. Furthermore, PTPN VII Unit Pematang Kiwah Natar, South Lampung, has classified environmental costs by allocating environmental costs based on the International Guidance Document IFAC 2005 and Ikhsan (2008). Therefore, PTPN VII Unit Pematang Kiwah Natar, South Lampung, has demonstrated its commitment to environmental regulatory compliance.

Occupational Health and Safety (OHS) is an important element in creating a safe, healthy, and sustainable work environment. PT. X as a logistics and port operations company has potential occupational hazards originating from physical, chemical, and biological factors that need to be managed optimally. This study aims to evaluate the implementation of OHS at PT. X based on the results of measurements of physical, chemical, and biological factors of the work environment and their compliance with the provisions of the Minister of Manpower Regulation No. 5 of 2018. This study uses a descriptive method with an evaluative approach to work environment monitoring data in 2025 in the generator and office areas. The parameters analyzed include noise, lighting, hot work climate (ISBB), inhalable and respirable dust exposure, and microbiological air quality in the form of total bacteria and fungi. The results show that most parameters meet the specified standards, with the exception of the generator area which exceeds the noise limit and the hot work climate which exceeds the Action Level (AL). The implementation of OHS at PT. X has been running quite well, indicated by most of the work environment parameters that meet the standards. However, strengthening risk controls, particularly regarding noise and hot working conditions in operational areas, is still necessary. This evaluation is expected to serve as a basis for continuous improvement in the implementation of Occupational Health and Safety (OHS) to protect workers from potential occupational hazards and support the productivity and sustainability of company operations.

Digital images often experience noise disturbances that can reduce visual quality and interfere with the image analysis process. One common type of noise is salt and pepper noise, especially in grayscale images, which is characterized by the random appearance of black and white dots. This study applied the Deep Convolutional Autoencoder (DCAE) method with a skip connection mechanism to eliminate salt and pepper noise in grayscale images measuring 256×256 pixels. The dataset used consists of 300 pairs of clean images and noisy images that have gone through the preprocessing stage, including normalization and data augmentation. The model was trained using an Adam optimizer with a Mean Squared Error (MSE) loss function and validated through a train-test split scheme to avoid overfitting. Model performance was evaluated using Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) metrics. The test results showed that the DCAE model with skip connections was able to effectively reduce noise while maintaining the main structure of the image based on the PSNR and SSIM values obtained, and showed better performance than conventional median filters. In addition, the model was successfully implemented into a Streamlit-based application to perform the image denoising process interactively, making it easier for users to experiment and visualize results in real-time.

This study aims to develop an Indonesian traffic sign detection system using a transfer learning approach to improve road safety and traffic efficiency. The dataset was obtained from Kaggle and consists of 2,100 images across 21 traffic sign classes. The research stages include data collection, preprocessing to reduce noise and normalize image brightness, object detection using YOLOv5, and classification based on transfer learning with ResNet, VGG-16, and MobileNet architectures. Model performance was evaluated using accuracy, precision, recall, and F1-score metrics. Experimental results indicate that the YOLOv5 model is capable of detecting traffic sign objects; however, the classification performance remains relatively low, with a mean Average Precision (mAP) value of 0.17. These findings suggest that further optimization is required in data preprocessing, dataset quality, and model parameter tuning to achieve better performance. This study demonstrates that transfer learning has significant potential for developing computer vision-based traffic sign detection systems, although further improvements are necessary to ensure robustness under real-world Indonesian traffic conditions.

Pedestrian is one of the most important public spaces for urban areas. On the border of Muara Enim city has a pedestrian that attracts attention, namely the pedestrian welcome intersection kepur. Simpang Kepur pedestrian has a border gate that is the center of attention and the first impression when entering the city of Muara Enim so that it has the opportunity as a face or symbol of the identity of the city of Muara Enim. Visually, the existence of pedestrians and gates at the Kepur intersection looks quite attractive but functionally it is not in accordance with the characteristics of pedestrian activities on the pedestrian so that research is needed to rearrange the previous design so that the function of the pedestrian becomes even better. The method used is qualitative through observation based on facts and activities in the field. Analysis based on the impression of place and activity on the pedestrian. The results obtained that there is a need to change the appearance of the color processing so that the pedestrian becomes more alive, need to keep the pedestrian so that there is no loss or damage, the need for guardrails or vegetation / view barrier plants in the area behind or beside the pedestrian, rearrangement of plants that can absorb dust and can absorb noise, and arrangement of street furniture, namely visual recommendations for a wider bus stop design, replace permanent seating, replace permanent trash.

Big data platforms face significant challenges related to cybersecurity and privacy due to the vast volume, variety, and velocity of data they manage. Traditional static security measures often fail to address the dynamic and complex nature of big data environments. This research proposes an adaptive cybersecurity framework that integrates dynamic access control and differential privacy mechanisms to enhance both the security and privacy of big data platforms. The dynamic access control mechanism continuously adjusts access permissions in real-time based on changing risk and trust levels, ensuring that sensitive data remains secure even as user roles and data flows evolve. The differential privacy mechanism adds noise to data, preserving individual privacy while allowing for meaningful data analysis. Through simulations and case studies, the framework was evaluated in various real-world environments, including healthcare, IoT, and finance, where it demonstrated scalability, efficiency, and robust security performance. The results showed that the proposed framework significantly reduced unauthorized access attempts and maintained data privacy, while still enabling effective data analysis. Although there were some challenges regarding performance overhead, particularly in resource-constrained environments, the framework remained effective in large-scale systems. The findings highlight the importance of adaptive security practices in big data environments and suggest that future research should focus on refining dynamic security mechanisms and applying differential privacy in diverse real-world scenarios. These advancements are essential for ensuring that big data platforms can handle evolving cyber threats without compromising data utility or privacy.

Video steganography faces fundamental challenges in balancing embedding capacity, imperceptibility, and robustness, where conventional Least Significant Bit (LSB) methods often produce visual artifacts such as flickering. To address this, this research proposes an advanced method named Adaptive Multi-layer LSB, which dynamically adjusts the number of embedded bits in each pixel based on a multi-factor analysis of the video's spatial and temporal characteristics. This adaptation mechanism is evaluated through three primary criteria: brightness level, local texture complexity, and inter-frame motion stability. Quantitative evaluation using Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Frame Difference Stability Index (FDSI) metrics demonstrates that the proposed method achieves high visual quality, with an average PSNR of 42.15 dB and SSIM of 0.985. These results significantly outperform the non-adaptive approach, which only recorded a PSNR of 38.5 dB. More importantly, the FDSI value of this method (1.25) is much lower compared to the non-adaptive approach (3.40), demonstrating its superiority in maintaining temporal stability. Thus, this approach provides a significant contribution to enhancing security and quality in video steganography practices. Abstract: Video steganography faces fundamental challenges in balancing embedding capacity, imperceptibility, and robustness, where conventional Least Significant Bit (LSB) methods often produce visual artifacts such as flickering. To address this, this research proposes an advanced method named Adaptive Multi-layer LSB, which dynamically adjusts the number of embedded bits in each pixel based on a multi-factor analysis of the video's spatial and temporal characteristics. This adaptation mechanism is evaluated through three primary criteria: brightness level, local texture complexity, and inter-frame motion stability. Quantitative evaluation using Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Frame Difference Stability Index (FDSI) metrics demonstrates that the proposed method achieves high visual quality, with an average PSNR of 42.15 dB and SSIM of 0.985. These results significantly outperform the non-adaptive approach, which only recorded a PSNR of 38.5 dB. More importantly, the FDSI value of this method (1.25) is much lower compared to the non-adaptive approach (3.40), demonstrating its superiority in maintaining temporal stability. Thus, this approach provides a significant contribution to enhancing security and quality in video steganography practices.

Steganography is a technique for hiding secret data within digital media such as images, audio, and video without causing noticeable visual changes. In video media, this technique offers advantages because each frame can be utilized dynamically, resulting in a larger data embedding capacity. However, conventional methods such as fixed-number Least Significant Bit (LSB) embedding still face limitations in balancing visual quality, embedding capacity, and resistance to compression or noise. To address these challenges, this study proposes an Adaptive Video Steganography Method based on Multi-Bit LSB that employs brightness, texture, and motion analysis for each frame to determine the number of embedding bits adaptively. The system adjusts the embedding capacity according to the local characteristics of the video: areas with high texture or rapid motion are assigned more bits, while static or low-texture areas use fewer bits to preserve visual quality. After the embedding process, the video quality is evaluated using PSNR (Peak Signal-to-Noise Ratio) and SSIM (Structural Similarity Index Measurement) to assess its similarity to the original video. Experimental results show a PSNR value of 45.86 dB and an SSIM value of 0.9441, Thus, the proposed adaptive method proves to be efficient, robust against disturbances, and capable of maintaining data security without compromising visual quality, making it highly suitable for implementation in multimedia-based information security systems.

Steganography is a method to hide confidential messages in digital media so that they are not detected by unauthorized parties. Unlike cryptography which protects the content of messages through encryption, steganography hides the message itself. One popular technique is the Least Significant Bit (LSB), which replaces the least important bit on the pixel with a secret message bit. However, conventional LSB methods such as 1-bit or 3-bit have limitations due to the compromise between insertion capacity and visual quality of the media. This study proposes an LSB-based video steganography method with an adaptive multi-bit embedding approach. This technique determines the number and position of bits that are dynamically inserted based on the local brightness and texture levels of each video frame, with Laplacian operators used to analyze both high and low textured areas. The process includes frame and audio extraction, frame-by-frame embedding, inserted video reconstruction, and decoding using video cover references. The evaluation was carried out quantitatively using the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) metrics, as well as qualitatively through visual comparison. The results showed that the adaptive multi-bit method was able to maintain visual quality with a PSNR of 45.23 dB and SSIM of 0.9424, and increased the insertion capacity by up to 2–3 times compared to the 1-bit adaptive method. Thus, this approach effectively balances imperceptibility and insertion capacity on dynamic video steganography systems.  

The relatively high volatility of Robusta coffee prices creates uncertainty for farmers, business actors, and policymakers in making economic decisions. This study aims to analyze the price movement patterns of Robusta coffee, determine the most appropriate Autoregressive Integrated Moving Average (ARIMA) model, and conduct short- to medium-term price forecasting for Robusta coffee. The data used consist of monthly Robusta coffee price data from January 2023 to September 2025, sourced from the World Bank Commodity Price Data. The analytical method employed is ARIMA using EViews software, beginning with stationarity testing using the Augmented Dickey-Fuller (ADF) test, model identification through ACF and PACF, parameter estimation, and residual diagnostic testing. The results show that Robusta coffee price data are non-stationary at the level but become stationary at the first difference, indicating integration of order one I(1). Based on model identification and diagnostic testing, the ARIMA (0,1,0) model is found to be the most appropriate and satisfies the white noise assumption. Forecasting results indicate that Robusta coffee prices are projected to remain relatively stable with a moderate upward trend through December 2026. These findings are expected to serve as a reference for decision-making by farmers, business actors, and the government in responding to Robusta coffee price dynamics.

Background: Sleep disorders in adolescents are a significant health problem, with a global prevalence reaching 57.8% and particularly high rates in several cities in Indonesia. Poor sleep quality negatively impacts physical health, such as the risk of cardiovascular disease and anemia, as well as mental and cognitive health. Sleep behavior is influenced by a dynamic interaction between personal and environmental factors, as explained in Social Cognitive Theory (SCT). Research Objective: To identify the determinants of sleep deprivation in adolescents, specifically individual and environmental factors, based on a Social Cognitive Theory (SCT) perspective through a literature review from 2019 to 2025. Method: This study utilized a literature review. To obtain research data, the authors searched for scientific articles through Google Scholar, PubMed, and ScienceDirect databases, then analyzed 10 articles that met the inclusion criteria, published between 2020 and 2025. Results: Factors significantly associated with adolescent sleep quality were identified, with individual factors being the most dominant determinant (found in 7 studies), including academic stress and smartphone addiction. Furthermore, a positive association was found with environmental factors (found in 4 studies), such as bright lighting, noise, and uncomfortable room temperature. Conclusion: Within the framework of Social Cognitive Theory, adolescent sleep quality is the result of a reciprocal interaction between personal factors (perceived stress and self-control over gadgets), the physical environment, and sleep behavior. Individual factors such as stress and nighttime gadget use reduce self-efficacy for regular sleep, which is exacerbated by an unfavorable environment.

The scarcity of real-world data in Air-Conditioning (AC) fault diagnosis necessitates the use of synthetic data; however, rule-based synthetic datasets often suffer from a significant sim-to-real domain gap. To address this, we propose a Model-Data Coevolution (MDC) framework that employs a Simulated Annealing (SA) controller to optimize augmentation parameters. We introduce a novel technique, Stochastic Feature Decoupling (SFD), which applies independent noise to raw and derived features, contrasting it with traditional Logically-Consistent Augmentation (LCA). Empirical results show that SFD significantly outperforms LCA, achieving a weighted F1-score of 0.93 and increasing NORMAL class recall to 82%. We demonstrate that by breaking deterministic feature links, SFD acts as a robust regularizer, utilizing "physically impossible" data to enhance generalization in complex real-world environments.

Plastic waste detection in indoor environments is an essential challenge in the development of intelligent cleaning systems and robotic automation. Small and medium-sized plastic debris is often difficult to identify using conventional methods due to variations in color, shape, and reflectance. This study proposes an image-processing-based approach that combines thresholding and contour detection techniques to improve the accuracy of detecting plastic objects on floor surfaces. The initial stage involves converting the image into a color space that is more stable under varying illumination, such as HSV or grayscale, to reduce the influence of lighting intensity. Subsequently, adaptive thresholding is applied to separate plastic objects from the background by using dynamic threshold values tailored to the image’s conditions. The segmentation results are refined through morphological operations such as opening and closing, enabling the removal of small noise and enhancing the clarity of object boundaries. The core stage of the system employs contour detection to extract object shapes and areas, allowing the identification of plastic waste based on size, perimeter, and specific geometric characteristics. Experiments were conducted under different lighting conditions and various floor types, and the results demonstrate that the proposed approach successfully detects plastic debris with satisfactory accuracy and relatively fast processing time. Therefore, this method is suitable for implementation in robotic cleaning systems, indoor cleanliness monitoring devices, and other computer vision applications requiring real-time and efficient object detection.

This research is motivated by the high risk of fatigue experienced by ship crews during voyages, which directly affects occupational safety and mental well-being. Fatigue arises from long working hours, inadequate rest time, heavy workloads, and extreme environmental conditions such as high temperatures, engine noise, and vessel vibrations. On the MT. Sultan Mahmud Badaruddin II, the problem becomes more complex due to the tight work rhythm, short berthing periods, and fast, repetitive loading–unloading activities. Harsh weather conditions, short but intensive sailing distances, and limited relaxation facilities make the crew increasingly vulnerable to both physical and mental fatigue. In addition, a work culture that tends to be authoritarian and lacks communication exacerbates psychological pressure, especially when crew members find it difficult to report their fatigue to superiors. This study uses a qualitative method through direct observation and interviews with all crew members in the deck and engine departments. The aim is to analyze the influence of the work environment and work culture on fatigue levels onboard. The results show that environmental factors such as high temperatures, narrow workspaces, and vessel instability significantly affect physical fatigue. Meanwhile, mental fatigue is triggered by ineffective communication, hierarchical pressure, and an unsupportive work culture. These findings align with the perspectives of Mathis and Jackson and comply with the provisions of the STCW 2010 and MLC 2006, which emphasize the importance of regulating working hours and fatigue management. Overall, optimizing rest hours, improving the work environment, and reforming organizational culture are required to reduce fatigue risks.

Driven by the need for sustainable building materials with effective acoustic performance, this work investigates coconut-fiber-based cement-bonded particleboard as a bio-based alternative, evaluating its sound absorption and transmission characteristics to determine suitability for noise control in architectural and industrial applications while considering manufacturability, local material availability, and potential environmental benefits compared to conventional synthetic panels and providing guidance for designers and manufacturers across different climatic zones. This study aims to analyze the acoustic characteristics of coconut-fiber-based Cement-Bonded Particleboard (CBPB) through measurements of the Sound Absorption Coefficient (SAC, α) and Transmission Loss (TL). CBPB samples were fabricated with thickness variations of 12, 16, and 20 mm and tested using an impedance tube in accordance with ISO 10534-2:1998 and the ASTM E90-09 (2016) method. The results showed that the α value increased with both frequency and panel thickness, reaching a maximum of 0.78 at frequencies of 2500–3150 Hz for the 20 mm panel. The highest TL value reached 42 dB at a frequency of 4000 Hz. Coconut-fiber-based CBPB demonstrated strong potential as an eco-friendly structural acoustic material.

Accurate wind turbine power curve modeling plays a crucial role in performance evaluation, energy yield estimation, and data-driven control strategies. However, actual power curves often exhibit non-linear behavior influenced by atmospheric variability, measurement noise, and SCADA anomalies, making conventional modeling approaches less effective. This study proposes an optimized logistic power curve model whose parameters are tuned using Particle Swarm Optimization (PSO) to improve predictive accuracy. The analysis uses the Wind Turbine SCADA Dataset from Kaggle, which undergoes extensive preprocessing including physical rule filtering, outlier detection with the Interquartile Range (IQR) method, anomaly removal, and smoothing of the power signal. A three-parameter logistic model is selected due to its ability to capture the typical S-shaped relationship between wind speed and power output. PSO is applied to identify optimal model parameters by minimizing the Mean Squared Error (MSE), utilizing 40 particles over 200 iterations. The optimized model achieves strong predictive performance with RMSE of 404.09, MAE of 179.96, and R² of 0.904 on the test set, indicating that more than 90% of the variability in actual power can be explained by wind speed. Residual analysis reveals heteroscedastic patterns and slight overestimation in mid-range wind speeds, yet overall model consistency remains high. Comparative evaluation against Linear Regression, Random Forest, and logistic modeling using curve_fit shows that the Logistic–PSO approach provides the most accurate and stable predictions. These findings demonstrate that combining logistic modeling with PSO offers an effective and robust method for data-driven wind turbine power curve optimization.

An exhaust pipe is a tubular device used to channel combustion gases from a vehicle’s engine into the environment. In addition to this primary function, the exhaust also serves to reduce the noise level produced by engine combustion. The component of the exhaust system that significantly affects torque, brake mean effective pressure (BMEP), and noise level is the silencer. This study aims to compare the torque, BMEP, and noise levels produced by variations in the length and construction dimensions of elliptical filter designs in the silencer. The silencers used in this research have lengths of 280 mm, 300 mm, and 260 mm, with short ellipse filter diameters of 25 mm and long ellipse filter diameters of 30 mm, 40 mm, and 50 mm. The research employs an experimental quantitative method, and the data were analyzed using one-way Analysis of Variance (ANOVA). The experiment was conducted in a Mechanical Engineering workshop using a Yamaha R15 V3 155cc injection motorcycle (2021), a Super Dyno 50L dyno test, and a sound level meter, from February to April 2024. The engine speeds tested were 1500, 2500, 3500, 4500, 5500, and 6500 rpm. The results show that the variation of ellipse dimensions 25 mm × 50 mm × 260 mm produced a maximum torque of 12.77 N·m at 4500 rpm, a maximum BMEP of 1021 kPa at 4500 rpm, and a noise level of 80.3 dB. The variation 25 mm × 40 mm × 300 mm produced a maximum torque of 12.88 N·m, a BMEP of 1042 kPa, and a noise level of 75.60 dB, while the variation 25 mm × 30 mm × 280 mm produced a maximum torque of 12.67 N·m, a BMEP of 1013 kPa, and a noise level of 75.63 dB.