Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control
Not a member yet
424 research outputs found
Sort by
Performance Evaluation of LoRa in Farm Irrigation System with Internet of Things
Get PDFLong Range (LoRa) Communication is one of the emerging Internet of Things (IoT) technologies and has been widely discussed by researchers. LoRa is also part of the Low Power Wide Area Networks (LPWAN) technology where this technology focuses on communication systems on energy efficiency, wide coverage, low data rates, and long battery life. LoRa uses industrial, scientific, and medical (ISM) radio frequencies. These frequencies can be used for free without paying for a license. Theoretically and under ideal conditions, the LoRa range can reach < 3 km in urban areas and > 3 km in rural areas. However, only a few studies discuss the evaluation and analysis of LoRa performance, which is implemented in the real world with particular case studies. This article aims to evaluate and analyze the performance of LoRa, which is applied to a case study of an IoT-based agricultural irrigation system. Several parameters will be assessed and analyzed, including distance, received signal strength indication (RSSI), spreading factor, coding rate, power transmission, and packet delivery ratio (PDR). Experimental and measurement results show that LoRa can transmit data packets up to a distance of 2.5 km but with a very low PDR rate of around 5-7%. The results also show that LoRa can work optimally if the distance is > 1 km with a PDR rate of about 70-100%
Review of Technique and Algorithm for Educational Data Mining: Trend and Challenge in Games Design
Get PDFThis study reviews techniques and algorithm models often used in the analysis of educational data mining. The review in this study is based on previous studies to provide researchers knowledge about trends and challenges analysis Educational data mining in game design meaningful. However, there is a lot of games design developed without analysis Educational data mining which then will not answer the student problem. The analysis needed periodic data and developing the game required actual student conditions, this is a combination inseparable. Determine Research questions, Search Terms, and filtering for the selection and analysis of the article review. There are some student problems on analysis review, namely prediction student performance, student behavior, student at-riks, and student dropout. The number of Articles in the study was 33 with 21 Articles of research and 12 of Article review. The number of studies 8 with percent 38% used techniques Confusion matric with 33% percent used algorithms Decision Tree in 7 of studies. The section in this study consists of techniques evaluation, model selection, outcome, subject, and algorithm method. Which are recommended techniques and algorithms for analysis Educational data mining and in ideal game design to further research
Convolutional Neural Network (CNN) Models for Crop Diseases Classification
Get PDFCrop diseases have a significant impact on agricultural production. As a result, early diagnosis of crop diseases is critical. Deep learning approaches are now promising to improve disease detection. Convolutional Neural Network (CNN) models can detect crop disease using images with automatic feature extraction. This study proposes crop disease classification considering ten pre-trained CNN models. Fine-tuning for each model was conducted in the Plant Village dataset. The experimental results show that fine-tuning improves the model’s performance with an average accuracy of 8.85%. The best CNN model was DenseNet121, with 94.48% and 98.97% accuracy for freezing all layers and unfreezing last block convolution layers. Moreover, fine-tuning produces less time-consuming with an average of 2.20 hours. VGG19 is the less time-consuming reduction by 8 hours. On the other hand, MobileNetV2 is the second-best performance model with less time-consuming than DenseNet121, and produces fewer parameters, which is affordable for embedding it to mobile devices
PID Controllers Performance On Dual Axis Tracking With Tetrahedron Based Sensor
Get PDFThis study compares control systems applied to a dual-axis tetrahedron-based sensor tracker. A tetrahedron-based sensor is a tracking sensor that can detect the coordinates of a light source. This study aims to determine a control system that can control sensors with high accuracy and precision and has a fast-tracking ability. Tests are carried out periodically by providing light at certain coordinates. After carrying out the testing and analysis process, it is concluded that the P controller is a better control system than the other controllers. This controller can control sensors with high accuracy and precision compared to PI, PD, and PID control systems. The P controller can also control the sensor to move towards the light coordinates with a travel time of 1.6 seconds on the X-axis and 3.1 seconds on the Y-axis, with a MAE value of 1.1 on the X-axis and 0.3 on the Y-axis. While the RSME value obtained is 1.33 on the X-axis and 0.55 on the Y-axis
Adoption of Mobile Learning at Universities Using the Extended Technology Acceptance Model
Get PDFThis study aims to contribute to the proof of factors likely to determine the success of M-learning adoption based on previous research. This is done because there are many different theoretical models proposed. However, there is not yet a model that can be generally accepted as an established theoretical model for the adoption of M-learning in universities. This research is expected to make a significant contribution to the development of a better theoretical understanding of the determinants that influence the adoption of M-learning using the Technology Acceptance Model (TAM). To collect the data, researchers distributed questionnaires to respondents using google forms. Forms are distributed via WhatsApp and Telegram. The data used was 515 M-learning users. Theoretical model research was carried out with Structural Equation Model (SEM) analysis, then SPSS and Amos as support for analysis. There are six factors that determine the results of acceptance of M-leaning adoption in this study, namely Social Influence, Perceived Enjoyment, Facilitating Condition, Self-Efficacy, Perceived Usefulness, and Perceived Ease of Use. The five factors that show positive and significant relationships are Social Influence, Perceived Enjoyment, Self-Efficacy, Perceived Usefulness, and Perceived Ease of Use. Perceived Usefulness has the first strongest positive and significant value, and then Social Influence has the second strongest value. Each factor has a medium influence value on Behavioral Intention. That factor is the most influential in the application of M-learning in universities
Performance Evaluation of 198 Village Governments using Fuzzy TOPSIS and Intuitionistic Fuzzy TOPSIS
Get PDFCurrently, volatility, uncertainty, complexity, and ambiguity (VUCA) have become unavoidable problems. In addition, knowledge or information that is not managed properly can result in inappropriate decision-making processes within an organization. Business Intelligence conception is then becoming an essential view for converting unstructured data and information into a more actionable strategic plan that allows organizations to make competitive decisions. Village Government (VG) is the smallest organization in the Indonesian government system because VG implemented regulation and development programs in all areas of a national government. VG executes a series of tasks every year starting from planning, budgeting, administrating, executing, and reporting. However, the important role of VG in the development of a country brings also some drawbacks such as corruption and other domino effects. Several factors have been identified that cause those problems such as lack of capabilities in managing village organization and human resources quality. Monitoring and evaluation regarding those VG performances normally have been done each year. However, measurable evaluation standard for VG performance until recently has not been determined nationally. This study is intended to make a comprehensive standard of village government performance assessment through a Good Governance Framework approach. This study involved 198 villages from Madiun Regency as a case study. Seventy-four measured parameters were proposed to evaluate VG performance mapping. Fuzzy TOPSIS is implemented to rank those 198 villages into 4 groups of VG performance levels. The fuzzy TOPSIS classification result has been validated by using manual scoring and the accuracy reached 86,4%
A Study on Visual Understanding Image Captioning using Different Word Embeddings and CNN-Based Feature Extractions
Get PDFImage captioning is a task that can provide a description of an image in natural language. Image captioning can be used for a variety of applications, such as image indexing and virtual assistants. In this research, we compared the performance of three different word embeddings, namely, GloVe, Word2Vec, FastText and six CNN-based feature extraction architectures such as, Inception V3, InceptionResNet V2, ResNet152 V2, EfficientNet B3 V1, EfficientNet B7 V1, and NASNetLarge which then will be combined with LSTM as the decoder to perform image captioning. We used ten different household objects (bed, cell phone, chair, couch, oven, potted plant, refrigerator, sink, table, and tv) that were obtained from MSCOCO dataset to develop the model. Then, we created five new captions in Bahasa Indonesia for the selected images. The captions might contain details about the name, the location, the color, the size, and the characteristics of an object and its surrounding area. In our 18 experimental models, we used different combination of the word embedding and CNN-based feature extraction architecture, along with LSTM to train the model. As the result, models that used the combination of Word2Vec + NASNetLarge performed better in generating Indonesian captions than the other models based on BLEU-4 metric
Low-Rate Attack Detection on SD-IoT Using SVM Combined with Feature Importance Logistic Regression Coefficient
Get PDFThe evolution of computer network technology is now experiencing substantial changes, particularly with the introduction of a new paradigm, Software Defined Networking (SDN). The SDN architecture has been applied in a variety of networks, including the Internet of Things (IoT), which is known as SD-IoT. IoT is made up of billions of networking devices that are interconnected and linked to the Internet. Since the SD-IoT was considered as a complex entity, several types of attack on vulnerabilities vary greatly and can be exploited by careless individuals. Low-Rate Distributed Denial of Service (LRDDoS) is one of the availability-based attack that may affect the SD-IoT integration paradigm. Therefore, it is necessary to have an Intrusion Detection System (IDS) to overcome the security hole caused by LRDDoS. The main objective of this research was the establishment of an IDS application for resolving LRDDoS attack using the SVM algorithm combined with the Feature Importance method, namely the Logistic Regression Coefficient. The implemented approach was developed to reduce the complexity or resource’s consumption during the classification process as well as increasing the accuracy. It could be concluded that the Linear kernel SVM algorithm acquired the highest results on the test schemes at 100% accuracy, but the training time required for this model was longer, about 23.6 seconds compared to the Radial Basis Function model which only takes about 1.5 seconds
Image Captioning using Hybrid of VGG16 and Bidirectional LSTM Model
Get PDFImage captioning is one of the biggest challenges in the fields of computer vision and natural language processing. Many other studies have raised the topic of image captioning. However, the evaluation results from other studies are still low. Thus, this study focuses on improving the evaluation results from previous studies. In this study, we used the Flickr8k dataset and the VGG16 Convolutional Neural Networks (CNN) model as an encoder to generate feature extraction from images. Recurrent Neural Network (RNN) uses the Bidirectional Long-Short Term Memory (BiLSTM) method as a decoder. The results of the image feature extraction process in the form of feature vectors are then forwarded to Bidirectional LSTM to produce descriptions that match the input image or visual content. The captions provide information on the object’s name, location, color, size, features of an object, and surroundings. A greedy Search algorithm with Argmax function and Beam-Search algorithm are used to calculate Bilingual Evaluation Understudy (BLEU) scores. The results of the evaluation of the best BLEU scores obtained from this study are the VGG16 model with Bidirectional LSTM using Beam Search with parameter K = 3 and the BLEU-1 score is 0.60593, so this score is superior to previous studies
QSAR Study on Aromatic Disulfide Compounds as SARS-CoV Mpro Inhibitor Using Genetic Algorithm-Support Vector Machine
Get PDFCOVID-19 is a type of pneumonia caused by the Severe Acute Respiratory Syndrome Coronavirus-2 (SARS-CoV-2). This virus causes severe acute respiratory syndrome and 2 million active cases of COVID-19 have been found worldwide. A new strain of the SARS-CoV-2 virus emerged that proved to be more virulent than its predecessor. Regarding the design of a new inhibitor for this strain, SARS-CoV Main Protease (Mpro) was used as the target inhibitor. In the in silico development, the Quantitative Structure-Activity Relationship (QSAR) method is commonly used to predict the biological activity of unknown compounds to improve the process of drug design of a disease, including COVID-19. In this study, we aim to develop a QSAR model to predict the activity of aromatic disulfide compounds as SARS-CoV Mpro inhibitors using Genetic Algorithm (GA) – Support Vector Machine (SVM). GA was used for feature selection, while SVM was used for model prediction. The used dataset is set of features of aromatic disulfide compounds, along with information on the toxicity activity. We found that the best SVM model was obtained through the implementation of the polynomial kernel with the value of R2train and R2test scores are 0.952 and 0.676, respectively