Publication Search

This study compares different machine learning models for time series forecasting in financial data analysis. Models including ARIMA, LSTM, and GRU are applied to predict stock price movements. We measure the accuracy and computational efficiency of each model on various datasets and discuss their strengths and weaknesses in financial forecasting contexts. The findings suggest that deep learning models show significant improvement in capturing complex temporal patterns over traditional methods.

The rapid growth of digital technologies has significantly increased the complexity and frequency of cyber threats, making network security a critical concern in modern information systems. Traditional security approaches, such as rule-based and signature-based systems, are often limited in detecting sophisticated and unknown attacks. Therefore, this study proposes an Anomaly-Based Intrusion Detection System (AbIDS) utilizing machine learning and deep learning techniques to enhance detection capabilities. The research adopts a Design Science Research approach, involving stages of problem identification, data collection, preprocessing, model development, system implementation, and evaluation. Several models, including Decision Tree (DT), Support Vector Machine (SVM), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM), are implemented and compared. The results indicate that deep learning models, particularly LSTM and CNN, outperform traditional machine learning methods in terms of accuracy, precision, recall, and F1-score, while maintaining a lower false positive rate. Additionally, the integration of incremental learning enables the system to adapt to new attack patterns without requiring complete retraining, improving scalability and real-time performance. Despite the promising results, challenges such as computational complexity and false positives remain. Overall, the proposed IDS model demonstrates strong potential as an effective and adaptive solution for enhancing network security in dynamic environments.

The rapid growth of data-intensive applications has posed significant challenges for classical machine learning (ML) algorithms, particularly in terms of computational efficiency and scalability. This study explores the role of quantum computing in optimizing machine learning performance through the implementation of Quantum Machine Learning (QML), specifically using the Quantum Support Vector Machine (QSVM) model. The research adopts a Design Science Research approach, involving problem identification, model development, system implementation, and performance evaluation. Both classical Support Vector Machine (SVM) and QSVM models are developed and tested using benchmark classification datasets. The results indicate that QSVM outperforms the classical SVM model across multiple evaluation metrics, including accuracy, precision, recall, and F1-score. Additionally, QSVM demonstrates improved computational efficiency by reducing training time, particularly when handling high-dimensional data. These improvements are attributed to the ability of quantum computing to utilize quantum kernel methods and map data into higher-dimensional feature spaces, enabling better pattern recognition and classification performance.  Despite these promising outcomes, the study also identifies several limitations related to current quantum hardware, such as noise, decoherence, and limited qubit availability, which may affect scalability and practical implementation. Therefore, further research is required to enhance quantum hardware reliability and develop hybrid quantum-classical models. In conclusion, quantum machine learning offers a promising solution to overcome the limitations of classical approaches, providing enhanced performance and efficiency for complex data processing tasks in future intelligent systems.

This study aims to analyze purchasing patterns in online transactions using the Apriori algorithm to support sales strategy optimization. The research was conducted on transactional data from an online store selling household and daily-use products. The Apriori method was applied to identify associations between items based on minimum support and confidence thresholds. Four experimental scenarios were tested to compare the reliability of generated rules and determine the strongest item relationships. Data preprocessing included item grouping, transaction coding, and elimination of non-frequent items. The results show several strong association rules with lift ratio values above 1, indicating meaningful item relationships. The strongest rule identified was the association between forks and spoons, forming a highly relevant combination for product bundling strategies. The findings demonstrate that the Apriori algorithm can assist online stores in planning stock, designing product bundling, and improving marketing effectiveness. The research contributes practical insights for business decision-making and highlights the significance of data mining in e-commerce environments.

This study explores the development and evaluation of an adaptive Intrusion Detection and Response System (IDRS) driven by Reinforcement Learning (RL) for securing 5G networks. The RL-based IDS is designed to overcome the limitations of traditional security systems by dynamically learning from real time network traffic and adapting to emerging cyber threats. Introduction: The rapid growth of 5G networks, with their increased number of connected devices and complex traffic patterns, necessitates advanced security solutions that can detect and respond to evolving cyberattacks. Literature Review: Traditional Intrusion Detection Systems (IDS), including signature based and anomaly based methods, are not equipped to handle the dynamic nature of 5G networks, leading to high false positives and low detection accuracy. In contrast, RL offers significant improvements in adaptability, detection accuracy, and response time. Materials and Method: The study simulates 5G network traffic and develops an RL-based IDS using Deep Q-Networks (DQN) and Proximal Policy Optimization (PPO) techniques. The performance of the RL-based system is compared to traditional IDS systems, focusing on detection accuracy, false positive rates, and response times. Results and Discussion: The RL-driven IDS demonstrated superior performance, achieving higher detection accuracy (95%) and faster response times (30 milliseconds) compared to traditional methods. However, challenges such as computational cost and model interpretability were identified. The study emphasizes the importance of adaptive learning mechanisms and the integration of RL into Zero Trust Architecture (ZTA) to enhance the security of 5G networks.

Applying ergonomic principles in work tool design for manufacturing industries is a crucial factor in improving productivity while maintaining worker health. This research aims to analyze the effectiveness of adaptive work tool design models based on cognitive and physiological ergonomic principles, identify interaction patterns between workstation design and operational performance, and develop a conceptual framework for integrating ergonomic principles into production cycles. The research method adopts a cognitive-physiological approach with qualitative analysis of human-machine interactions, biomechanical simulations using digital human modeling, and muscle load measurements through electromyography. Implementation was conducted using a participatory ergonomics approach and IMU sensor-based real-time monitoring systems. Results show that using materials with controlled deformation capabilities (15-20%) in work tools reduces muscle work by up to 27%, while adaptive automation system integration improves assembly accuracy by 18%. Workstations with ergonomic adjustments increase assembly speed by an average of 12%, and low-cost ergonomic interventions effectively improve productivity by 11-15% in resource-limited environments. Longitudinal analysis reveals that evidence-based ergonomic investments yield a 230% ROI through increased productivity, reduced injury compensation costs, and decreased employee turnover. IMU-based posture monitoring systems integrated with adaptive feedback loops reduced musculoskeletal disorder incidents by up to 41%. In conclusion, ergonomic optimization based on cognitive-physiological principles creates synergy between production efficiency and worker well-being, making it an essential component in achieving sustainable productivity.

This research aims to analyze the impact of globalization and digitalization on civic participation in the modern era. Globalization and digitalization have changed various aspects of life, including the way citizens participate in political and social processes. This research uses a literature study method by reviewing various relevant literature, such as scientific journals, books and research reports, to understand how developments in information and communication technology (ICT), as well as global connectedness, influence patterns of civic participation. The research results show that globalization has expanded access to information and increased political awareness at the global level, while digitalization has made it easier for citizens to interact with governments and communities through digital platforms. However, this research also found challenges in the form of the digital divide, disinformation, and uneven engagement across various groups in society. Thus, this research provides insight into the opportunities and challenges in promoting inclusive civic participation in the digital era.

The transformation of media and communication in the digital era has reshaped how people interact, share information, and build social relationships. The digitalization of communication not only introduces new platforms such as social media and the internet of things (IoT) but also impacts communication culture and social relationship patterns within society. This study aims to examine the dynamics of communication theory in the context of digitalization, understand how these concepts adapt, and explain their impact on social and cultural life. The research method used is a literature review, analyzing internationally indexed journals, along with relevant national journals. The findings indicate that digitalization encourages faster interactions and wider access to information but also presents challenges, such as discrepancies between online and real identities and the erosion of local cultural values. In conclusion, a critical understanding of the dynamics of communication theory in the digital era is essential to harness this transformation positively without overlooking existing social and cultural values.

WHO 2021 reports that more than 300 million children under 5 years of age do not fulfill their development potential and most of them are children living on the Asian and African continents. Data from Hermina Hospital, the prevalence of Speech Delay in 2023 is 150 cases. In one day of research, 15 respondents were obtained. The aim of this research was to determine the relationship between parenting patterns and parental knowledge and speech delay in preschool-aged children at Hermina Hospital. Padang.This type of research uses quantitative methods with a cross sectional analytical design. The research was conducted in March – August 2023 at Hermina Padang Hospital. The research population was all mothers who had preschool children aged 3-5 years at Hermina Padang Hospital. The sampling technique was Accedental Sampling. Data collection used primary and secondary data. Univariate analysis used descriptive statistical tests and Bivariate analysis used the chi square test.The results of this research are based on the results of the Chi square test (α= 0.005) showing that there is no significant relationship between Parenting Patterns (p-value = 0.188) and there is a significant relationship between Parental Knowledge (p-value 0.032) and Speech Delay.It was concluded that there was still a lack of maternal knowledge about the importance of parenting styles and parental knowledge in children's growth and development. It is hoped that from the results of this research, parents can pay more attention to children's growth and development and that health workers can serve as a reference for improving services in reducing the incidence of speech delays.

Background: Modern agriculture often relies on the use of pesticides to control pests and plant diseases. However, the use of this pesticide can have a negative impact on the environment, especially on the quality of soil and river water in agricultural areas. This research aims to investigate the impact of pesticide use on soil and river water quality, with a focus on the type of pesticide used, usage patterns, and its impact on the environment and human health. Method: The journal research method with the literature review method is an approach used to collect, broadcast and synthesize information from various relevant literature sources Results: The use of pesticides in agriculture has a significant impact on the environment and human health. Appropriate methods of using pesticides, such as the correct dose and application time, as well as sustainable agricultural approaches such as organic farming, can reduce the negative impacts of pesticides. Farmer education about the safe use of pesticides is also important. In addition, soil and water quality must be considered in agriculture to maintain soil fertility and air ecosystems. River protection and rehabilitation efforts are also needed to maintain good river water quality.

The aim of this research is to describe the perspective of culinary traders in the Sipinsur tourist area regarding the benefits of attending Sunday worship. Sunday worship is our response to the work of salvation that God has given us and as a sign of thanksgiving and respect which is carried out by praising and glorifying His name. This shows how important it is to worship together with fellow believers as a form of gratitude for God's work in each person's life. The benefits of worship are also much greater because they contain promises, both for this life and the life to come. The consequences of a life of worship are blessings that can already be felt (Rom.14:17) because the kingdom of God is not about eating and drinking but about righteousness and happiness by the holy spirit. This study used descriptive qualitative method. Data was collected through in-depth interviews with 8 traders who actively trade in the Sipinsur Geosite tourist area. Data analysis was carried out by identifying thematic patterns and interpreting the meaning of traders' answers. The results of this research show that the majority of culinary traders in the Sipinsur Geosite tourist area have not felt and do not even understand the benefits of attending Sunday worship in their lives. So this is what causes the culinary traders to be absent from Sunday services. Therefore, in this article the author provides an explanation to church ministers to provide a better understanding regarding the meaning and benefits of Sunday worship.      

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder that has certain characteristics. One of them is the diagnosis of autistic comorbidity, namely Attention Deficit Hyperactivity Disorder (ADHD), nonpharmacological treatments are considered quite effective including dietary interventions. Hyperactive behavior in autistic children that has an impact in the form of difficulty in poor attention span to impulsiveness. Gluten free diet, casein free diet is recommended in the application of therapy in autistic people, this diet is one type of complementary therapy, which is carried out by regulating consumption patterns in autistic children. Objective: to determine the difference in the level of hyperactivity of autistic children between groups who apply gluten free, casein free diet with not applying gluten free, casein free diet. Method: comparative study by looking at the comparison between two groups with a total sampling technique of 20 people. Results: The level of hyperactivity in children on a gluten free diet, casein free as many as 9 (45%) respondents and 11 (55%) respondents did not do a gluten free diet, casein free obtained Mann Whitney U test results with a p-value of 0.027 where the p-value <0.05 or (0.027<0.05). Conclusion: Autistic children who apply a gluten free, casein free diet seem to have quite good attention than autistic children who do not apply a gluten free casein free diet. Suggestion: It is hoped that parents who have autistic children can adopt a gluten free diet, casein free as an alternative therapy.

Becoming a student is a blessing that not everyone can experience, where you start far from your hometown and then have to adjust to new activities, environments and even friends.  It is not uncommon to find students who have irregular lifestyle habits, unhealthy eating patterns, often stay up late and rarely exercise.  This study aims to determine the type of activity, frequency, duration and level of motivation for cycling sports activities carried out by boarding students at Surabaya State University.  The type of research used is descriptive research with a quantitative approach.  The population in this study were students living in the Surabaya State University dormitory.  The research was conducted in February-March, the data collection technique used was by distributing questionnaires.  The research results show that 50% of students more often do light activities such as sweeping, mopping, walking or playing chess, 38% do moderate activities such as jogging, cycling and gymnastics, and 12% of students do heavy activities such as swimming, football and martial arts. Data on the frequency of cycling activities carried out by dormitory students shows that 55% of students do cycling with a frequency of 1-2 times a month, 32% with a frequency of 1-2 times a week, 6% with a frequency of 3-5 times a week, 1% 6  -7 times a week, and 6% have never done cycling in the last month.  The majority of students (43%) do cycling for 16-30 minutes.  The goals of cycling carried out by students based on health management received the highest index value, namely 82.81 (M=3.37), skills development with a value of 76.56 (M=3.07), social affiliation with a value of 76.16 (M=2.97), image with a value of 70.12 (M  =2.87), as well as social recognition with a value of 63.68 (M=2.54).    

Computational Thinking is a way of thinking that refers to the ability to solve problems using concepts used in computing. Computational thinking is a way of thinking in solving problems that students must develop in the digital era. This research aims to examine the importance of computational thinking in improving students' mathematical problem solving abilities. The type of research used is qualitative research using a literature study approach in the form of books, notes, journals, reports of relevant research results, as well as the results of observations. The results of the analysis show that it is very important for students to have computational thinking in order to improve their mathematical problem solving abilities. Computational thinking involves solving problems using a logical and systematic mindset that involves selecting and using algorithms, data representation, problem decomposition, abstraction, pattern recognition and hypothesis testing. Computational thinking has become an important and essential skill for humans in the 21st century. Educators must advocate the importance of integrating learning with computational thinking concepts into the educational curriculum. Computational thinking has an important role in learning. This can be useful for improving mathematical problem solving abilities. Apart from that, computational thinking can also develop critical, creative and analytical thinking skills in solving complex problems, both in the context of computing and everyday life.    

Women as perpetrators of circular mobility (circular migrants) in the city of Semarang are generally involved in independent businesses in the informal sector. Working independently in the informal sector provides economic freedom and power in decision making. The informal sector does not require a lot of skills or working capital, and is suitable for domestic activities. The motivation for circular migrant women to leave their area of origin is because the unfavorable socio-economic conditions in the village encourage village women to engage in independent business in the trade sector, as well as because it is difficult to get work in the village. A shift in family roles occurs in the families of circular migrant women, when women as mothers have to leave the house to earn a living, then childcare patterns are entrusted to parents in the village, even though the existence of circular migrant women remains the hope of all family members, there is a role that is lost in both themselves and family.

This research aims to determine the position and role of music aggregators in the digital music industry and the legal liabilities of music aggregators towards the copyright of music creators. This is a normative legal research of a prescriptive nature with a statutory approach. The legal materials used are primary and secondary legal materials, through literature study, and the technical analysis of legal materials using syllogism with a deductive thinking pattern. Based on the research results and discussions, it can be seen that music aggregators have a position as partial copyright holders of music that has been entrusted to them and play a role as distributors and managers of music royalties that have been entrusted to them. Meanwhile, the legal liabilities of music aggregators as stipulated in the Copyright Law are the recording of licensing agreements, determination of royalties in accordance with prevailing industry practices and fairness, and other liabilities that arise along with licensing agreements.    

The research was conducted to determine students' mathematical communication skills and their influence on mathematics education, consisting of 3 questions about number patterns. The instrument has gone through question validation, then given to class VIII students at one of the Pekanbaru MTS with procedures including: 1). Planning, 2). Implement, and 3). Assessing Results. The subjects in this research were 14 eighth grade students from the MTS Pekanbaru school. The approach to this research is descriptive and quantitative, and uses data collection techniques such as observation, data collected from test instruments, and errors in completion. The student's communication skills are in the "medium" category as shown by the research results.

Project based learning is a learning method that uses projects/activities as media. Students carry out exploration, assessment, interpretation, synthesis and information to produce various forms of learning outcomes. The objectives of this research are (1) To determine the application of the project based learning model to making skirt grading patterns, (2) To determine the response of class XI students at SMK Negeri 3 Pamekasan to learning to make skirt grading patterns using the project based learning method, (3) To find out the learning outcomes of class XI students at SMK Negeri 3 Pamekasan after implementing learning using the project based learning method in making skirt grading patterns. The type of research applied is classroom action research (CAR). The research was conducted at SMK Negeri 3 Pamekasan with 31 students in class XI Fashion Design 1 consisting of 30 women and 1 boy. Class XI Fashion Design 2 has 34 students consisting of 34 women and 0 men at SMK Negeri 3 Pamekasan. The data collection methods used were (1) observation, (2) student learning outcomes tests. The research instruments used were (1) observation sheet, (2) test sheet. The data analysis technique uses quantitative descriptive analysis. The research results showed (1) Teacher activity in cycle 1 obtained a score of (70.6%) and experienced an increase in cycle 2 (82.9%) which was very good, (2) student activity in cycle 1 obtained a score of (70.8%) and experienced an increase in cycle 2 (83.8%), the increase in score was declared successful, (3) Student learning outcomes in cognitive, affective and psychomotor assessments from cycle 1 to cycle 2 experienced an increase with the completeness score reaching a total of (97%) which can be categorized as very good.

This research aims to analyze the effect of using Web Wordwall in training students' computational thinking skills in mathematics learning with a qualitative approach. The research subject is the Director General of Teachers and Education Personnel, while the object is education that is liberating and pro-student. Data obtained from online and offline information sources is recorded in a structured manner, then analyzed to be synthesized into a systematic conceptual framework. Conclusions are drawn by taking the essence of the conceptual framework that can answer the research questions posed. The research method used is a case study with a focus on participatory observation, in-depth interviews and document analysis. Data was collected through literature study and analysis of learning materials. Data analysis was carried out using an inductive approach, by looking for patterns of findings and main concepts from the data collected.

This research aims to analyze the effect of using Web Wordwall in training students' computational thinking skills in mathematics learning with a qualitative approach. The research subject is the Director General of Teachers and Education Personnel, while the object is education that is liberating and pro-student. Data obtained from online and offline information sources is recorded in a structured manner, then analyzed to be synthesized into a systematic conceptual framework. Conclusions are drawn by taking the essence of the conceptual framework that can answer the research questions posed. The research method used is a case study with a focus on participatory observation, in-depth interviews and document analysis. Data was collected through literature study and analysis of learning materials. Data analysis was carried out using an inductive approach, by looking for patterns of findings and main concepts from the data collected.