Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control
Not a member yet
424 research outputs found
Sort by
Fuzzy C-Means Algorithm Modification Based on Distance Measurement for River Water Quality
Get PDFRiver water quality could be determined by understanding the capacity of pollutants in a water body. Fuzzy C-Means (FCM) is one of the fuzzy clustering methods for determining river water quality by measuring water quality parameters, that is, dissolved oxygen (DO) and total dissolved solids (TDS). The FCM algorithm is an effective fuzzy clustering algorithm for grouping data but often produces local and inconsistent optimal solutions due to the partition matrix's random initialisation process. Therefore, this study proposes to modify the FCM algorithm to be precise in the partition matrix initialisation process using several distance concepts. The purpose of the proposed algorithm modification is to get more consistent FCM clustering results and minimise stop iterations. The validation process for the clustering results uses the FCM algorithm, and the FCM modification algorithm uses three parameters, namely the Partition Coefficient Index (PCI), Partition Entropy Index (PEI) and Silhouette Score (SS). The experiments were conducted with three replications and using various distance concepts. The results showed that the number of iterations stopped in the FCM algorithm has different values for PCI, PEI, SS, and stop iterations and objective functions in each trial. On the contrary, the FCM modification algorithm has consistent PCI, PEI, and SS values, and the number of iterations stops with fewer iterations. Therefore, the modified algorithm for initialising the partition matrix can be used in the fuzzy C-means clustering algorithm
Comparison between Power Dissipation and Propagation Delay on 6T SRAM Cell Design Using GDI Logic with Transmission Gate VMSA and Voltage Divider
Get PDFThe rapid evolution of the semiconductor industry has witnessed shrinking portable and mobile devices alongside an increasing demand for extended battery life. Addressing the critical challenges of speed and battery life in digital devices, this paper investigated the effectiveness of innovative low-power design techniques. Focusing on the Gate Diffusion Input (GDI) approach, a recent advancement in the field, a comprehensive analysis revealed its significant potential for reducing power consumption in digital circuits. Additionally, a comparative analysis was conducted to evaluate the performance of conventional 6T GDI SRAM cells and their Modified 6T GDI SRAM with Voltage Divider, considering the influence of Sense Amplifiers. Simulation data demonstrated that Modified 6T SRAM designs, particularly the Voltage Divider and TGVMSA variants, achieved significantly lower power dissipation and delay despite having a larger cell area. Remarkably, the proposed design substantially improved power dissipation and propagation delay, achieving 1.3 ps, and 889.41mV at 1.8V shows that the suggested design enhances power dissipation and propagation delay. These findings suggest that the proposed design offers a promising strategy for enhancing power efficiency and performance in digital devices, thereby mitigating the limitations of battery life and speed in the modern technological landscape
Mental Health Prediction Model on Social Media Data Using CNN-BiLSTM
Get PDFSocial media has transformed into a global platform for expression and interaction where users can share photos, images, and videos. The rapid development and widespread use of social media afford the opportunity to analyze the construction of social life in societies and communities. As a result of alterations in lifestyle during the COVID-19 pandemic, mental health disorders increased. Mental health is a complex disease involving numerous individual, socioeconomic, and clinical variables. Natural language processing and analysis methods are required to address this complexity. The classification of mental health-related texts, which can serve as early warnings and early diagnoses, is facilitated by analytical and natural language processing techniques. In this investigation, a CNN-BiLSTM model was utilized, which was aided by a FastText-based word weighting method. The utilized data set consists of texts on mental health with labels such as borderline personality disorder (BPD), anxiety, depression, bipolar, mentalillness, schizophrenia, and poison. There are 35000 training records and 6108 test records. The data will undergo a data cleansing procedure, which will include lower text stages, number removal, reading mark removal, and stopword removal. Modeling with CNN-BiLSTM and FastText weighting yielded an F1-Score and accuracy of 85% and 85%, respectively. In comparison to the Bi-LSTM model, the F1-Score and accuracy were both 83%
Hybrid Fuzzy-PID Design Based on Flower Pollination Algorithm for Frequency Control of Micro-Hydro Power Plant
Get PDFMicro-Hydro Power (MHP) Plant System is the renewable energy resource that utilizes water potential energy. In MHP, the energy flows depend on the rotation speed of the generator which cause instability and nonlinearity in the frequency of electrical power. It is also supported by the fluctuation on the electricity load. Therefore, this study used Fuzzy Logic Controller combined with FPA-tuned PID to control the power frequency of the load. This test consisted of 4 stages, namely testing the system without a controller, testing the system using PID, testing the MHP system with a PID controller tuned to the Flower Pollination Algorithm, and testing the system using a Fuzzy PID tuned by the Flower Pollination Algorithm. Based on these tests, the Micro-Hydro Power Plant system response using a Fuzzy PID-tuned FPA controller performed best, especially in accelerating the time to a steady state, reducing overshoot and undershoot with the fastest rise time. As for the output signal from the controller used in the MHP, optimizing the Flower Pollination Algorithm for the Kp, Ki, and Kd parameters is effective and smooth in improving all elements in the Micro-Hydro Power Plant frequency stabilization. Meanwhile, the role of the fuzzy logic controller (FLC) is not very significant, and there is relatively a lot of noise in the output signal of the Fuzzy PID controller itself in terms of stabilizing the load frequency on the Micro-Hydro Power Plant
Optimized Support Vector Machine with Particle Swarm Optimization to Improve the Accuracy Amazon Sentiment Analysis Classification
Get PDFText mining is a valuable technique that empowers users to gain a deeper understanding of existing textual data, ultimately allowing them to make more informed decisions. One important application of text mining is in the field of sentiment analysis, which has gained significant traction among companies aiming to understand how customers perceive their products and services. In response to this growing need, various research efforts have been made to improve the accuracy of sentiment analysis classification models. The purpose of this article is to discuss a specific approach using the Support Vector Machine (SVM) algorithm, which is often used in machine learning for text classification tasks and then combined with the application of Particle Swarm Optimization (PSO), which optimizes the SVM model parameters to achieve the best classification results. This dynamic combination not only improves accuracy but also enhances the model's ability to efficiently handle large amounts of text data to achieve better results. The research findings highlight the effectiveness of this approach. The application of the SVM algorithm with PSO resulted in an outstanding accuracy performance of 94.92%. The substantial increase in accuracy compared to previous studies shows the promising potential of this methodology. This proves that the SVM algorithm model approach with Particle Swarm Optimization provides good performance
Sensorless Field-Oriented Control (FOC) using Sliding Mode Observer for BLDC Motor
Get PDFMotor Brushless Direct Current (BLDC) has become the preferred choice in various engineering applications. However, BLDC motor control involves high complexity, and motor performance depends on the control algorithms used. This research discusses the use of sensorless control methods, specifically the Sliding Mode Observer (SMO) for rotor position and speed estimation in BLDC motors within the context of Field-Oriented Control (FOC), validated through simulations using Matlab/Simulink. Simulation results indicate that SMO provides rapid dynamic response to current changes, albeit with slight delays at high speeds. Rotor position estimation with SMO is also reasonably accurate in both steady-state and transient conditions, affirming the iveness of SMO in sensorless control for BLDC motors. SMO can be experimentally implemented to enhance sensorless control in BLDC motors by reducing the cost of installing Hall sensors while maintaining comparable performance
Aspect-level Sentiment Analysis on GoPay App Reviews Using Multilayer Perceptron and Word Embeddings
Get PDFThe increasing use of smartphone in Indonesia has encouraged the development of digital wallet applications, one of which is GoPay. Nowadays, GoPay has gained significant popularity among the public in Indonesia. Therefore, this research conducts aspect-level sentiment analysis to analyze user reviews of the GoPay application in more detail and depth. The sentiment analysis process in this study utilizes the Multilayer Perceptron (MLP) with fastText and word2vec as word embeddings. The dataset used is GoPay application reviews, which consist of 15,000 reviews collected from Google Play Store. The dataset is categorized into three main aspects: Feature and functionality, App Interface, and User Satisfaction. The stages of the research include data preparation, data preprocessing, word embeddings, model training, and model testing and evaluation. This research explores the effect of fastText and word2vec as word embeddings on model performance. Furthermore, this research examines the application of oversampling techniques, such as SMOTE and Random Oversampling. Based on the experiments conducted, utilizing fastText as word embeddings in MLP with a balanced dataset resulted the best model performance, with an F1-Score of 97%, Recall of 96%, and Precision of 95% for category classification. Then, for sentiment classification, using fastText on MLP with a balanced dataset resulted in a value of 98% for each of the F1-score, Recall, and Precision metrics. This research validates that MLP is effective for aspect-level sentiment analysis, delivering strong evaluation results
Ant Colony Optimization for Efficient Distance and Time Optimization in Swarm Drone Formation
Get PDFOne of the challenges in swarm drone formation is achieving fast and effective formation with optimal distances. In this paper, we propose a swarm drone formation approach utilizing Ant Colony Optimization (ACO) for achieving it. We conducted simulations involving the formation of three or more drones, aiming to identify the best formation based on distance, acceleration, and time criteria. Simulation results demonstrate that formation time is significantly reduced when employing ACO optimization compared to non-optimized methods. Additionally, the optimized formations exhibit shorter inter-drone distances compared to non-optimized formations. By implementing this approach, swarm drone formations can be rapidly established with minimized distances, resulting in substantial battery savings. The simulation encompassed various patterns formed by 3, 5, 10, 15, 20, and 25 drones. The findings indicate that the approach can reduce formation time by varying degrees, ranging from 12% to 51%, across 66% of the conducted experiments, notably for patterns created with a substantial drone count. The degree of diversity observed among the proposed solutions reached 60%, with minimal variances of less than 1% for each
Kinematic of 3-Wheels Swerve Drive Using BLDC Motor
Get PDFThe stability of the robot's performance is very important, especially for the wheeled mobile robots that use swerve drives, which need kinematic control to reach the destination point. The study of robot movement known as kinematics is based on an examination of the geometric structure of the robot, with no consideration given to the mass, force, or acceleration that the robot experiences during movement. This study aims to model and simulate the kinematic control design of a wheeled robot that uses a swerve drive. This robot uses BLDC motor actuator so that the robot can reach its destination very quickly and steadily. The test is carried out by simulating and comparing the performance response using BLDC motors and DC motors. According to the testing and trials, the robot can reach its destination by modeling its kinematic control, and BLDC motors are found to be more reliable and efficient for driving and steering than DC motors
Optimizing Social Media Promotion Strategy to Increase Customer Retention Rate (CRR) with GKG Customer Engagement
Get PDFIn the digital age, businesses are increasingly relying on social media platforms to engage with their customers and foster brand loyalty. This paper presents a comprehensive study aimed at optimizing social media promotion strategies to enhance Customer Retention Rate (CRR) while utilizing the GKG (Get Keep Growth) Customer Engagement framework. By examining the interplay between social media promotion tactics and customer engagement metrics, we investigate how businesses can leverage data-driven insights to improve customer retention. Our research showcases the importance of tailoring social media campaigns to individual customer preferences and behavior, ultimately leading to increased customer satisfaction and loyalty. The results of the analysis of the development of the Customer Retention Rate graph were produced on FMIPA social media with an average CRR of 71% in the base case. Through a combination of data analysis and case studies, we provide actionable recommendations for businesses seeking to maximize the effectiveness of their social media promotion efforts and elevate their CRR with GKG customer engagement