Indonesian Journal of Electrical Engineering and Computer Science
Not a member yet
9109 research outputs found
Sort by
Indonesian sentiment analysis in natural environment topics
Get PDFIndonesia is one of the countries that is rich in biodiversity and has a high population growth. This condition can cause Indonesia to have problems related to the natural environment that are more complex than other countries. Hence, this has created a lot of discussions regarding natural environmental issues in Indonesia on social media platforms. In this case, stakeholders like the government in general can utilize sentiment analysis (SA) to comprehend the public’s views to allow them to better fit the public’s expectations when formulating a particular policy that related to the environmental sustainability (ES) issues. This paper built the first open dataset of Indonesian SA dataset in ES topics collected from Instagram. As the benchmark of our dataset, we used IndoBERT model variant for constructing the model and the experiment result shows that model based on IndoBERT-large-p2 obtained the best performance with 72.44% of F1-score
A comprehensive access control model integrating zero trust architecture
Get PDFIn contemporary IT landscapes, trust in entities, whether internal or external, within organizations has become obsolete. Establishing and enforcing strict access controls, alongside continuous verification, is imperative to safeguard organizational resources from potential insider and outsider threats. The emergence of zero trust architecture (ZTA) addresses this need by advocating for a paradigm shift in security. This research proposes a comprehensive access control model aligned with the fundamental ZTA security principles, namely least privilege, conditional access, and continuous monitoring. The model integrates well-established access control paradigms, including role-based access control (RBAC) to uphold the least privilege principle, attribute-based access control (ABAC) to support conditional access, and trust-based access control (TBAC) to enable continuous monitoring. To determine the trust level of a user requesting access, an analysis of the user's log activities is conducted using the Nmedian outlier detection (NMOD) technique. This analysis aids in evaluating the trustworthiness of the user seeking access to resources. Furthermore, this research assesses the efficiency and efficacy of the proposed integrated access control model in comparison to existing access control models, primarily focusing on their respective functionalities
Design and implementation of an automatic irrigation system for plants in Lima-Perú
Get PDFIn many regions of the world, water used in agriculture becomes a scarce and costly resource over time. It is necessary to make efficient use of this vital resource. For this reason, we opted for an innovative project that can be of great use for agriculture, incorporating information and communication technologies such as the internet of things (IoT), databases, and smartphone applications. The research proposes an IoT system to control and monitor crops in a specific area based on the ESP32 microcontroller, using the DHT11 sensor to collect temperature and relative humidity data. The sensors send the information to the central node for the wireless communication part. The central node activates the actuators to control and store the information in a database for corresponding monitoring. The mobile application displays the results from the database and causes them to be turned on and off manually. The system was implemented for home plant cultivation but can be used for other types of cultivation due to its flexibility
Enhanced performance and efficiency of robotic autonomous procedures through path planning algorithm
Get PDFTo optimize surgical routes for better patient outcomes and more efficient operations, we want to test how well these algorithms work. Finding the best algorithms for different types of surgeries and seeing how they affect things like time spent in surgery, precision, and patient safety is the goal of this exhaustive study. By shedding light on the effectiveness of route planning algorithms, this work aspires to aid in the development of autonomous robotic surgery. To find out how well various algorithms work in actual surgical settings; this study compares them. The results of this work have the potential to enhance robotic surgery efficiency and improve surgical outcomes by informing the creation of more efficient route planning algorithms. The overarching goal of this study is to provide evidence that autonomous robotic surgery can benefit from using sophisticated route planning algorithms, which might lead to more accurate, faster, and safer procedures. The surgical patient dataset exhibits a wide variety of medical variables, including ages 38–62, weight 65–85 kg, height 160–180 cm, blood pressure 110–140/90 mm Hg, heart rate 70–85 bpm, hemoglobin 12–14 g/DL, and body mass index (BMI) 25.4–29.4
Secure data transmission towards mitigating potentially unknown threats in wireless sensor network
Get PDFWireless sensor network (WSN) is known for its wider range of applications towards sensing physical attributes over human-inaccessible regions. With consistently rising concerns of security threats, WSN is the pivotal topic of network security. A literature review showcases the shortcomings of conventional data transmission schemes in WSN. This manuscript introduces an innovative approach to mitigating the potentially vulnerable and unknown threats. The implemented model promotes a group-based communication followed by a newly introduced threat onlooker node capable of identifying the malicious request of a newly designed adversary module. The scheme also hybridizes symmetric and asymmetric encryption at the end to cipher the aggregated data. The validation of the model is carried out considering standard scores of simulation parameters related to system variables. Further, the scheme has been compared with frequently adopted real-world encryption algorithms. Scripted in MATLAB, the model is assessed to confirm 35% of increased residual energy, 57% of better threat detection, 27% of enhanced throughput, and 68% of reduced processing time in contrast to existing secure data transmission schemes
Enhancing accessibility: deep learning-based image description for individuals with visual impairments
Get PDFTechnological developments in artificial intelligence, namely in the area of deep learning, have created new avenues for enhancing accessibility for those with visual impairments. In order to improve the capacity of people who are blind or visually impaired to understand and interact with visual material, this research investigates the creation and use of deep learning-based image description systems. We provide a comprehensive method that uses recurrent neural networks (RNNs) to generate natural language descriptions and convolutional neural networks (CNNs) and Autoencoders for extracting picture features. Our technology automatically creates comprehensive, context-aware descriptions of photographs by incorporating these models, giving users a better knowledge of their surroundings. We show the accuracy and reliability of the system on a wide range of photos through comprehensive testing. According to our research, deep learning-based picture description systems and converting the description in audio and making a promise to empower people who are visually impaired and foster diversity in the digital sphere
Potential field-based approaches for nanobotics in drug delivery
Get PDFNanorobotics has transformed targeted drug delivery by enhancing therapeutic efficacy, minimizing off-target effects, and increasing precision. However, navigating complex biological environments is challenging. In the field of macroscopic robotics, potential field (PF)-based approaches that utilize attractive and repulsive virtual forces provide a promising framework that can be applied to path planning for nanorobots. This study modifies PF algorithms for nanorobotic navigation to address challenges such as avoiding dynamic obstacles, escaping local minima, and optimizing trajectories in real time. We evaluated the movement of the nanorobot through simulations under static and dynamic conditions for the targets and obstacles. The results demonstrate that nanorobotics with hybrid PF methodologies enhance navigation performance, enabling nanorobots to successfully navigate through biological barriers and efficiently reach their target locations. This work is a significant step towards intelligent and autonomous nanorobotic drug delivery systems and contributes to practical biomedical applications
Maximizing QoS in railway radio networks: leaky cable and ray-tracing for optimal BER on bridges
Get PDFThe future railway mobile communication system (FRMCS) standard is crucial for advancing railway communication and implementing intelligent train control systems. This research focuses on development of an efficient modeling method to evaluate and optimize FRMCS performance on railway bridges, particularly under high-density modulation and radio noise interference. The key aspect of this study involves computer modeling of the deployment of a leaky coaxial cable (LCX) and comparison of its performance to traditional methods of radio coverage modeling. Using the single-slot radiation pattern, we evaluate the quality of radio communication by comparison of the bit error rate (BER) metrics for the Ray Tracing propagation model with and without the use of LCX. The results show that the use of LCX significantly reduces BER values, providing a much clearer and more reliable signal. This improvement is crucial for the safety and reliability of railway operations, ensuring effective communication for train control and reducing the risk of accidents in complex and high-demanding transport networks. This research contributes to the optimization of railway information infrastructure, with the aim of ensuring safe, reliable, and efficient operations
A TOT: tri-optimized-tariff based strategic residential load management with greedy optimization in IEEE33-bus system: a case study with renewable energy penetration
Get PDFThe efficiency of a load management system in terms of its energy performance index (EPI) depends on its capacity to enhance the reliability, resilience, and cost effectiveness of the existing system. Artificial intelligence (AI) is crucial in this shift from classical to AI-based power system planning, optimizing renewable energy (RE) and reducing gridstress. On the other hand, proper placement of resources is essential to achieve benefits and reduce transmission losses. Utility sectors of different states has revealed that in certain areas amongst different type of loads, domestic loads accounts for a substantial proportion of energy consumption. Therefore, the present work deals with optimum load scheduling, integration of RE, energy storage (ES) and proposed tri-optimized-tariff (TOT) for prosumers. We have found that the weighted-K-nearest-neighbor (KNN) method excels in selecting features for household appliances and ES scheduling. The composite greedy optimization (CGO) technique outperforms existing methods in optimization. These results demonstrate the efficiency and real-world potential of our model. We have conducted a case study and developed an AI-based strategic-residential-load-managementsystem (SRLMS), which we have tested on the IEEE33 bus system, showing cost effectiveness and improved EPI for prosumers. This work encourages the development of a harmonious relationship between utility-sectors and prosumers
Quality of services LoRaWAN satellite communication
Get PDFThis research discusses research that focuses on the capabilities of satellitebased LoRa, for satellite positions orbiting in low earth orbit (LEO). The expectation of low power wide area network (LPWAN) satellite can find the quality of transmitting data using LoRaWAN which is part of LPWAN and can provide quality of service (QoS) with high-quality real-time sensor data, low latency, long-range, low-power, no attenuation signal, no problem with obstacles in terrestrial areas, and other benefits that can be widely optimized. This article uses a comprehensive analysis of mathematical calculations as well as precise and accurate simulations for the actual development of satellite-based LPWAN. The satellite-based IoT is unlimited in terms of distance, to provide good services to all IoT users in the world. The comparison with terrestrial measurements is analyzed in detail, especially the signal attenuation factor that causes a lot of signal loss and data is not well received. Several methods are used to help reduce collision data, such as adaptive data rate (ADR) which can reduce collisions by 30%