International Journal of artificial intelligence research (IJAIR)
Not a member yet
271 research outputs found
Sort by
Hyperparameter Tuning in Machine Learning to Predicting Student Academic Achievement
Get PDFPrediction of student academic achievement is a very important research area; this can be seen from the many researchers who conduct research in this area. To make predictions, a machine learning model is needed. Along with their parameters, the majority of machine learning models have associated hyperparameters. However, knowing the right mix of hyperparameters is essential for robust model performance. A methodical procedure called hyperparameter optimization (HPO) aids in determining the appropriate values for them. In this study we compared four hyperparameters tuning techniques, namely HyperOpt, Random Search, Optuna and Grid Search. The results of the hyperparameters from each of these techniques are then used in machine learning algorithms to predict student academic achievement. Validation uses the 5-fold cross validation method while performance testing uses Mean absolute error. From the experimental results it was found that the hyperparameter technique The best method for predicting student academic achievement in machine learning models is gridsearchcv
Development of Digital Flashcards Assisted by Augmented Reality on Doppler Effect and Polarization Material
Get PDFAugmented reality-assisted digital flashcards on doppler effect and polarisation materials that are valid and practical have been successfully developed. This research uses Rowntree's development procedure which consists of three stages: planning stage, development stage and evaluation stage. The evaluation stage in this study uses Tessmer's formative evaluation stage which consists of stages: self evaluation, expert review, one to one evaluation, and small group evaluation. Data collection techniques used walkthroughs and questionnaires. The validity level of this digital flashcard was assessed by three experts, namely material aspect experts, digital flashcard design aspect experts, and augmented reality design aspect experts. The results of the digital flashcard expert validation test at the expert review stage obtained data on the material aspect of 97.75% with a very valid category, the digital flashcard design aspect of 95.75% with a very valid category, and the augmented reality design aspect of 81.5% with a valid category. While the teacher's response was 94.67%, at the one to one evaluation stage an average rating of 86% was obtained in the practical category. At the small group evaluation trial stage, the average assessment result was 87% with a very practical category. Thus, digital flashcards assisted by augmented reality on Doppler effect and polarisation material are declared valid and practical
Identifying Improvement Strategic from User Application Reviews Group Using K-Means Clustering and TF-IDF Weighting
No full textPT ABC is one of the companies that provide online ticket-purchasing facilities amidst the rise of the digitalization era. So, companies need to see how application users complain as a form of evaluation and improvement. The rating results given by application users show a score of 3.3 from 172,000 reviews. The review results that will be examined are user reviews from January 2022 to April 1, 2023, which is more or less the last year of user comments. This research aims to form a review group using K-Means Clustering, the Elbow method, TF-IDF weighting, and analysis of review improvement strategies. The Elbow method is used to determine the optimal number of clusters so as not just to use assumptions. The success of the Elbow method in processing categorical data can be supported by assigning weights based on word frequency sequences using TF-IDF. The research analysis results show the formation of 4 clusters, with two tending to have negative sentiment, one neutral sentiment, and one positive sentiment. Mapping is carried out on each cluster to find out the characteristics of each cluster and possible causes of reviews, as well as providing solutions and strategies as a form of improvement. The problem of negative reviews appearing in each review group is different. It can be corrected with the proposed strategies, such as improving the appearance of features at the registration, ordering, and payment stages, adding payment methods, and carrying out regular system maintenance
Performance Comparison of Support Vector Machine Algorithm and Logistic Regression Algorithm
Get PDFAccording to the World Health Organization (WHO), there are around 7 million breast cancer patients each year, with about 5 million of them dying. Based on Globocan 2018 data, the death rate from breast cancer averages 17 per 100,000 people with incidents of 2.1 per 100,000 people attacking women in Indonesia. Hence breast cancer causes spread genetic mutations in the DNA of breast epithelial cells that radiate to the ducts. The purpose of this study was to classify the type of cancer (benign or malignant) that was suffered. The difference between previous research and this research is in the algorithm testing method chosen. In this study the algorithm used is SVM and Logistic Regression by applying the SMOTE technique. The K-fold cross validation method is used in testing this research. The accuracy results obtained are 1.0, precision 1.0 and recall 1.0.While the highest evaluation results for the model without SMOTE were Accuracy 0.97, precision 1.0 and recall 0.90 with the LR method. So based on the results of the comparison, it shows that the evaluation of models using SMOTE tends to be higher than models without SMOT
Knowledge Capture in Agile Organizations: Methods and Strategies for Enhancing Effective and Efficient Process
Get PDFThe competitive landscape of modern organizations relies on efficient knowledge utilization and management, underscoring the crucial role of knowledge capture in effective Knowledge Management (KM). This study explores the relationship between knowledge capture, organizational agility, and employee proficiency within KM, pinpointing critical gaps in understanding the optimal utilization of knowledge capture methods within agile-based setups. By addressing these gaps, the study aims to identify effective knowledge capture methods and propose strategies for their seamless integration into agile organizations. The research investigates five hypotheses, affirming the positive impacts of expert interviews, focus groups, interviews, surveys, and questionnaires on the efficiency and effectiveness of knowledge capture processes in agile contexts. Utilizing a mixed-method approach, this study evaluates qualitative and quantitative data derived from interviews and questionnaires. The results highlight the importance of various knowledge capture methods in augmenting the efficiency and efficacy of the knowledge capture process. Additionally, the study outlines implementation strategies customized for each method's application within agile-based organizations. The objective of this research is to provide practical solutions that narrow the disparity between the potential of knowledge capture and the particular needs of agile setups
Progress in Non-Invasive Cognitive Brain-Computer Interface and Implications for Mind-Uploading
Get PDFMind-uploading, the vision of transferring human consciousness into a digital realm, relies on a profound comprehension of the brain and cutting-edge technology. Non-invasive cognitive Brain-Computer Interfaces (BCI) offer a promising avenue for delving into neural activity and bridging the brain-machine gap. This research explores the potential of non-invasive cognitive BCI in realizing mind-uploading through a systematic literature review (SLR), analyzing recent research that focuses on its current progress and implications for mind-uploading. The SLR unveils significant strides in non-invasive cognitive BCI, demonstrating increased precision in recording and decoding cognitive processes and fostering a deeper understanding of these processes. This progress is attributed to a diverse range of emerging feature extraction and decoding methods, transforming subtle neural signals into interpretable commands. Notably, advancements in signal processing and neuroimaging techniques enhance communication speed and clarity between the brain and computer. Furthermore, the development of cost-effective methods, frameworks, and hardware holds the promise of broader accessibility to BCI technology. However, significant hurdles remain. The computational demands of current cognitive BCI systems pose a substantial challenge, while the scarcity of high-quality training datasets hampers algorithm development and accuracy. The poor signal quality causes difficulties in recording neural complexity and hampers accuracy. In conclusion, non-invasive cognitive BCI has significant potential to pave the way for mind-uploading. However, its limitations, make their capabilities remain insufficient to fully realize this ambitious vision. This highlights the critical need for sustained research and innovation to bridge the gap between current understanding and the exciting realm of mind-uploading
The Role of NGOs in Indonesia - Australia Cooperation Through the KOMPAK Program to Support the SDGs of Quality Education in Papua and West Papua
Get PDFThis paper discusses the role of Non-Governmental Organizations (NGOs) in bilateral cooperation between Indonesia and Australia through the KOMPAK program, with a focus on supporting the Sustainable Development Goals (SDGs) for quality education in Papua and West Papua. KOMPAK, which is supported by the Australian government, aims to improve the quality of life in Indonesia by strengthening basic services, including education. NGOs play an important role in implementing this program by leveraging local expertise to build capacity, increase access to education, and empower communities. This program is in line with the global commitment to SDG 4, which emphasizes inclusive and equitable quality education for all children, especially in remote and underserved areas. This collaboration shows the shared commitment between the two countries and highlights the important role of NGOs in improving the educational landscape in Papua and West Papua, with the aim of ensuring a better future for the region's young generatio
Blockchain Application On Independent Smart Agriculture
Get PDFThe agricultural supply chain is currently facing challenges such as lack of transparency, uncertainty in product origin, and difficulty in accurately tracking products. This article discusses the application of blockchain technology as a solution to enhance agricultural supply chain management. It analyzes how blockchain can improve transparency, reliability, and security in agricultural supply chain management by recording and verifying information in a decentralized manner. Through blockchain, information such as product origin, production methods, shipping details, and storage conditions can be easily traced and verified by the involved parties. The implementation of blockchain also enables smart contracts to automatically execute agreements and payments based on predefined conditions, reducing bureaucracy and enhancing efficiency. The article also addresses challenges in implementing blockchain in the agricultural supply chain, such as data standardization and collaboration among stakeholders. By implementing blockchain technology, it is expected to create a more transparent, efficient, and trusted agricultural supply chain, benefiting farmers, producers, distributors, and consumers by ensuring product authenticity, improving compliance with quality standards, and minimizing the risks of counterfeiting or contamination. Â
Application Of Time Token Type Cooperative Learning Method In Improving The Ability To Write Poetry (Classroom Action Research)
Get PDFThis research aims to improve student learning outcomes in understanding poetry, namely through the Time Token Type method. The important role in improving students' ability to write poetry has become the main focus in replacing traditional teaching methods that have been going on for a long time. This research uses a classroom action research (PTK) approach, which includes descriptive analysis to motivate activity levels and achievement of learning outcomes by calculating average scores and percentages. In this research, the instruments used were observation sheets and tests. The learning process uses a time token type cooperative method which focuses more on understanding analysis and studying poetry. This method can also be applied by focusing on psychological aspects. The source of this research consisted of 30 students with 14 male students and 16 female students as part of the research sample. Based on the results of the research and discussion carried out, the researcher can conclude the following: it can be seen that the results of the implementation of classroom action (PTK) in cycle I are considered not successful and not in accordance with what was expected, that is, they have not reached the maximum level of learning completeness, so Efforts were made to improve learning in the second cycle and after the improvement efforts were made in this research, the results were significant changes, namely students' abilities were increasing, they were better at learning using the Time Token Type method. Based on the results of research in the pre-cycle, they got a percentage score of 36.66%, then learning In cycle I there was a change, namely getting a percentage score of 63.33% and in cycle II again there was a very significant increase, namely to 83.33%. The following can be described as several improvements in learning using the Time Token Type cooperative learning method as follows: 1). Students have a higher interest in reading poetry. 2). students' ability to write poetry becomes higher. 3). The interactive and communicative influence in learning on students becomes higher. 4). It is hoped that students' ability to create examples of poetry will increase, in this way it is hoped that this research will become literature or a reference to encourage experts in making policies to improve the quality of student learning, with several alternative learning models that refer to educational factors, namely cognitive, affective and psychomotor, especially the emphasis on student attitudes and behavior values, will be bette
Analysis of Critical Success Factors for KM Foundation in a Consulting Company
Get PDFIn the business world, Knowledge Management (KM) is increasingly recognized as a crucial factor for organizational success, especially within consulting firms. This research investigates the Critical Success Factors (CSFs) necessary for the effective implementation of KM in consulting firms. Faced with the complexities and challenges of a dynamic business environment, where efficient KM is vital for delivering high-quality services, this study conducts a thorough review of the CSFs related to KM foundations in consulting firms. The aim is to identify the CSFs essential to KM foundations. Using a Systematic Literature Review (SLR) based on the PRISMA methodology, the study synthesizes findings from five databases. From an initial pool of 1,173 papers, the selection was narrowed down to 20 papers with the most relevant content for analysis, detailing the CSFs essential to KM foundations. These factors are categorized into several dimensions, including technology, strategy, leadership, organizational culture, and regulatory policies, each contributing uniquely to the effective implementation of KM in consulting firms