Publication Search

The rapid growth of social media platforms has generated massive volumes of unstructured textual data containing valuable information about public opinions and sentiments. Extracting meaningful insights from this data has become increasingly important for decision-making in various domains, including business, politics, and social analysis. This study aims to evaluate the effectiveness of deep learning techniques for sentiment analysis of social media data, focusing on Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and a hybrid CNN-LSTM model. A quantitative experimental approach is employed, where datasets are preprocessed through text cleaning, tokenization, and feature representation using word embeddings. The models are trained and evaluated using standard performance metrics, including accuracy, precision, recall, and F1-score. The results indicate that all models perform effectively in sentiment classification tasks, with the hybrid CNN-LSTM model achieving the highest performance due to its ability to capture both local textual features and long-term contextual dependencies. This demonstrates that combining CNN and LSTM architectures enhances classification accuracy compared to individual models. Furthermore, the findings confirm that deep learning approaches are more robust in handling the complexity and noisiness of social media data compared to traditional methods. This study contributes to the development of more adaptive and accurate sentiment analysis models and highlights the potential of hybrid deep learning architectures for real-world applications.

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.

The rapid growth of big data has significantly increased the demand for efficient and scalable data processing methods, particularly within cloud computing environments. This study aims to evaluate the effectiveness of distributed computing frameworks, specifically Apache Hadoop and Apache Spark, in optimizing big data processing. A qualitative approach using a Systematic Literature Review (SLR) method is employed to analyze existing studies related to distributed systems, cloud computing architectures, and performance optimization techniques. The analysis focuses on key performance indicators, including processing speed, resource utilization, and scalability, as well as the suitability of each framework for different data processing scenarios. The findings indicate that Apache Hadoop is highly effective for batch processing and storage-intensive tasks due to its disk-based architecture, while Apache Spark demonstrates superior performance in real-time and iterative processing through its in-memory computing capabilities. Additionally, system configuration factors such as cluster size, memory allocation, and network bandwidth are identified as critical elements influencing overall performance. The study also highlights emerging trends, including the adoption of hybrid cloud environments, the integration of artificial intelligence and machine learning, and the utilization of edge computing to enhance real-time data processing. In conclusion, distributed computing frameworks play a vital role in improving the efficiency and scalability of big data processing in cloud environments. The selection of an appropriate framework, combined with optimized system configuration, can significantly enhance operational performance and support data-driven decision-making.

The integration of augmented reality (AR) technology in education is advancing, as seen in a project at Atisa Dipamkara School. This project developed a chemistry learning application using Unity, Android XR Plugin, and ARCore to address laboratory limitations. The app uses interactive 3D visualizations to help students grasp complex chemistry concepts. Blackbox testing showed that all main modules work well, except for a bug in the compound reset module. The app effectively improves students' understanding, interest, and motivation in chemistry, making abstract concepts more tangible. This application is both a learning aid and an educational innovation, promoting a more interactive and enjoyable learning experience.

Cloud-based resource allocation and VM/container orchestration play a crucial role in ensuring performance, scalability, and energy efficiency in modern distributed computing environments. This study investigates the effectiveness of centralized and decentralized scheduling models combined with heuristic and optimization-based allocation strategies in container-based cloud infrastructures. A quantitative experimental approach was employed to evaluate system performance under varying workload intensities. Key evaluation metrics included response time, throughput, resource utilization, SLA violation rate, and energy consumption. The experimental results indicate that centralized scheduling mechanisms experience scalability limitations and increased latency under high workload conditions. Although optimization-based allocation improves performance within centralized architectures, coordination bottlenecks remain significant. In contrast, decentralized scheduling models demonstrate superior adaptability, reduced response time, and improved throughput due to distributed decision-making and reduced control overhead. The integration of intelligent optimization techniques further enhances resource utilization and energy efficiency, achieving the lowest SLA violation rates and highest system stability. Overall, the findings confirm that combining decentralized scheduling with optimization-driven resource allocation provides a more scalable and sustainable orchestration strategy for modern cloud environments. This approach is particularly suitable for dynamic, large-scale, and latency-sensitive applications in container-based and edge-integrated cloud systems.

The rapid advancement of deep learning technologies has significantly transformed healthcare analytics, particularly in medical data prediction and classification. This study proposes a hybrid Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM) framework for multi-modal healthcare data analysis, integrating medical imaging, structured electronic health records (EHRs), and IoT-generated time-series physiological signals. The proposed architecture combines spatial feature extraction through CNN with temporal dependency modeling via LSTM to enhance predictive accuracy and clinical decision support. A quantitative experimental design was employed, utilizing multi-source healthcare datasets that underwent preprocessing, normalization, and feature engineering prior to model training. The performance of the hybrid model was evaluated using Accuracy, Precision, Recall, F1-Score, AUC-ROC, and Mean Absolute Error (MAE), and compared with conventional machine learning models and standalone deep learning architectures. Experimental results demonstrate that the proposed CNN–LSTM model achieves superior performance, with improved classification accuracy and reduced prediction error, while maintaining strong generalization capability. The findings indicate that integrating spatial and temporal feature learning significantly enhances disease detection, risk stratification, and personalized treatment planning. This approach supports the development of intelligent clinical decision support systems and scalable smart healthcare environments. The proposed framework offers a reliable and efficient solution for advanced healthcare analytics in IoT-enabled systems.

The era of globalization brings changes by causing religion, which was originally a public issue, to turn into a privacy issue. The development of religion which has become a private matter makes teenagers as identity seekers tend to implement it. The purpose of this activity is to preserve Walisongo so that it is not eliminated from the historical facts of the spread of Islam. The method applied in this service is Participatory Action Research (PAR). The results of this service activity have a positive impact on teenagers because know more about the nine saints of God who spread Islam in the archipelago and increase their understanding of the character of the saints and their struggles. The impact of getting to know the teenagers in Bebekan Tengah Village, Taman District, Sidoarjo Regency increased their admiration for the walisongo struggle which resulted in an increase in pilgrimages to the walisongo graves.

The fire suppression ability of this sprinkler installation compared to other fire extinguishing equipment has been proven to be more effective. Because the sprinkler system does not require an operator when operating, fires can be prevented earlier before causing greater losses. For this reason, the implementation of sprinkler systems in buildings is crucial. According to KEPMEN PU NO. 10/KPTS/2000, a building must have elements that can maintain structural stability to a certain level during a fire. This research was conducted directly in the field, and the necessary data was obtained independently through interviews with relevant parties. The author conducted research observations in the archive warehouse to obtain both primary and secondary data. Primary data included field documentation and calculations. Planning calculations were done directly by calculating the number of sprinklers, water requirements, and reservoirs to determine the precise needs. Based on the survey, it was found that the size of the archive warehouse is 48 x 48 m, totaling 2304 m2. The maximum distance between sprinklers used was 4.6 m. Therefore, the effective distance between sprinkler heads is 193 units. The result of the calculation for the water supply for the sprinkler system obtained 34,139.77 liters, with the total overall cost for the equipment and materials used being Rp. 63,121,925.74. Based on the data and calculation results regarding the planning and design of fire protection equipment in open active spaces adhering to the NFPA-13 Standard for the Year 2019, it is expected to provide comfort and safety against the threat of fire incidents.

Flooding is one of the disasters that often occurs in Indonesia, there are several cities that are always subscribed to flooding, one of which is Bandung Regency. On this occasion the author analyzed the vulnerability map in Bandung Regency using ArcGIS software by processing annual rainfall data, land use parameters, slope data, land elevation, and soil texture with this data the author obtained a percentage value of the level of flood vulnerability in Bandung Regency. Areas that have low elevations tend to experience flooding every year. From the processed data, there are 8 sub-districts in Bandung Regency with a flood prone percentage of more than 50%, namely Ketapang, Margahayu, Dayeuh Kolot, Pameungpeuk, Bojong Soang, Margaasih, Rancaekek, and Baleendah sub-districts. Based on the analysis of the flood prone map, most of Bandung Regency has a flood prone level classified as 'Less Prone', with an area of 64,277.228 hectares.

Archives is a record of activities or a source of information in various forms created by institutions, organizations, or individuals in the context of their activities. Archives can take the form of letters, documents, deeds, charters, books, and others, which can serve as valid evidence for actions and decisions. With the advancement of technology, archives can also take the form of audio, video, and digital content. This research was conducted at one of the government institutions, namely the BMKG office in Palembang, SMB II Meteorology Station. The archiving procedure applied here is still done manually or semi-manually. The purpose of this research is to design an archive classification system at the BMKG office in Palembang, SMB II Meteorology Station, to assist in the development of the existing archiving system in the institution. The result of the research is an interface design that illustrates how the archive information system can be implemented in the institution. In this information system design, the author provides an overview and a simple display of the archive classification system, which is expected to help the institution manage its company archives

Photography is one of the new avenues of service and business, some have made a hobby of photography a lucrative profession. They should be prepared to compete with other companies of the same kind by creating a good image of the consumer, providing quality of service and increasing innovation and creativity in order to create different photo concepts and attract consumers. The strategy became the main idea of Hero Photography to develop a business in photographic services. Hero Photography tried to adapt and compensate by coming up with a strategy that would attract consumers.These research methods use descriptive qualitative, with the aim of providing an idea and an explanation as to how startegi services Hero Photography in the interest of consumers. The study uses primary data sources as data obtained from informers and secondary data from archive or documents, journals, and various archival files of Hero Photography. Data collection techniques through observation, interview and documentary. At verifying data data using triangulation of methods and source triangulation using data analysis techniques of reposing data, presenting data, and summarizing data.Research has shown that the concept of sustainable excellence is influenced by the quality of the product, in this case, a superior photograph of adequate human resources capable with an obvious market target. The performance of the sale of Hero Photography was influenced by a marketing strategy with a concept of 4P (Price, Place. Product, Product), among other things is photographic quality, aesthetic quality good photo quality in terms of aesthetically pleasing clients who are less likely to use hero photography services. Strategic places like the old city become the attraction of visitors to capture the moment. Promotion became a strategy by using social media asa tool for promotion and offering online photo services by viewing affordable prices as one of the preferred customers to use the Hero Photography photo service.      

Arcangelisia flava Merr, which has been known empirically by the Dayak community in Central Kalimantan as natural herbs. This study aimed to determine the antibacterial effect of the Arcangelisia flava Merr extract against Escherichia coli. This study used two concentration of 25% and 50%, Ciprofloxacin as a positive control and water for injection as a negative control. The existence of the effect of the Arcangelisia flava Merr. extract against bacteria Escherichia coli is characterized by the formation of inhibition zone at a concentration of 25% obtained by the mean 2,005 mm, concentration of 50% obtained by the mean 2,435 mm, positive control obtained mean 7,975 mm, while for the negative control has no effect on Escherichia coli. The results showed that the Arcangelisia flava Merr. can significantly inhibit the growth of Escherichia coli bacteria. And there was the tendency of an increase in the concentration of Arcangelisia flava Merr. The higher concentration of Arcangelisia flava Merr. Extract the higher the resulting inhibit zone.

The aim of this research is to find out more about the Labuhanbatu Regency Library and Archives Service's approach to static archive preservation, as well as the challenges faced and the steps taken to overcome them.  To ensure the security and protection of archives, static archive preservation is carried out.  This type of research uses qualitative descriptive techniques.  This research uses the Miles & Huberman data analysis approach, which specifically focuses on data reduction, data presentation, and drawing conclusions.  Through observation, interviews, and documentation, researchers collect information for data analysis.  Two people participated in this research as informants.  Using a purposive sampling approach, these informants were selected from among those who met the requirements of the research subjects, namely, archivists who had knowledge of archival preservation. The research findings show that although the static archive preservation of the Labuhanbatu Regency Library and Archives Service is good, it still does not meet the expectations of the theory that guides the research.  Archives activists are of the opinion that despite their best efforts, archives are still not optimally maintained due to various obstacles, including inadequate funding, inadequate facilities and infrastructure, and human resources who do not understand archives.  Efforts made by archivists include providing special archival training on archival science, building inadequate facilities and infrastructure with allocated funds, and prioritizing the use of the budget for crucial tasks to achieve archive maintenance in good condition.

Indonesia is a country that has a high potential for natural disasters.  This is because Indonesia is located in the ring of fire which forms an archipelago.  Program from Beneran Indonesia in the form of Service Learning (SL) is a volunteer action carried out to increase the effectiveness of disaster prevention and mitigation by optimizing public awareness strategies so that community participation can increase in carrying out disaster prevention and mitigation, research and spatial and land planning.  The form of this program is in the form of educational videos sent via social media, Instagram.  The purpose of this research is to analyze the effectiveness of disaster education videos to increase disaster knowledge and attitudes in the community.  With a qualitative descriptive analytic observation method with a cross sectional approach through data collection techniques in the form of observation and documentation.  Thus, the results of this research also show that this disaster education video media is effective for increasing disaster knowledge and attitudes.  Because the effective and efficient dissemination is accompanied by packaging of video content that is concise, solid and enjoyable.    

Indonesia is a country that has a high potential for natural disasters.  This is because Indonesia is located in the ring of fire which forms an archipelago.  Program from Beneran Indonesia in the form of Service Learning (SL) is a volunteer action carried out to increase the effectiveness of disaster prevention and mitigation by optimizing public awareness strategies so that community participation can increase in carrying out disaster prevention and mitigation, research and spatial and land planning.  The form of this program is in the form of educational videos sent via social media, Instagram.  The purpose of this research is to analyze the effectiveness of disaster education videos to increase disaster knowledge and attitudes in the community.  With a qualitative descriptive analytic observation method with a cross sectional approach through data collection techniques in the form of observation and documentation.  Thus, the results of this research also show that this disaster education video media is effective for increasing disaster knowledge and attitudes.  Because the effective and efficient dissemination is accompanied by packaging of video content that is concise, solid and enjoyable.    

This research delves into the crucial aspect of diversity within generative models, exploring both its understanding and potential enhancement. Diversity in generative models refers to the ability of the model to produce a wide range of outputs that cover the variability present in the underlying data distribution. Understanding diversity is fundamental for assessing the quality and applicability of generative models across various domains, including natural language processing, computer vision, and creative arts. We discusses existing methods and metrics for evaluating diversity in generative models and highlights the importance of diversity in promoting fairness, robustness, and creativity. It explores strategies for enhancing diversity in generative models, such as regularization techniques, diversity-promoting objectives, and novel architectures. By advancing our understanding of diversity and implementing techniques to enhance it, generative models can better capture the complexity and richness of real-world data, leading to improved performance and broader applicability.

This research aims to determine the transfer of archival media as a preservation effort. The research method used is a qualitative method with descriptive research that uses interview methods to describe data obtained directly by researchers. The research results show that the media transfer processing process as a preservation effort must use guidelines, namely SOP (standard operational procedure) or media transfer processing workflow issued by the National Archives of the Republic of Indonesia. With this SOP (standard operational procedure), it will be easier for archives to transfer documents. This SOP was prepared to provide guidance or stages in implementing the media transfer process and is expected to make it easier for archivists to carry out the media transfer process. The obstacles/constraints faced in the process of transferring archival media as a preservation effort are the obstacles faced by archivists in processing media transfer collections in a preservation effort, namely the lack of human resources, many archivists in the North Labuhanbatu Library and Archives Service do not yet know about media transfer processing, only 2 archivists who can process transfer of media and also inadequate facilities and infrastructure.

Porous concrete has high porosity so that water can pass through the cavities in the concrete. The application of porous concrete is usually for parking areas, pedestrian sidewalks, road shoulders, drainage, roads with low traffic volume. Indonesia is an archipelagic country, most of Indonesia's territory is by the sea so it is very possible to use sea water as a substitute for fresh water for porous concrete. This research aims to determine the comparison of compressive strength of porous concrete mixed with sea water and normal porous concrete with variations in the water cement (fas) factor. In this study, a concrete mixture with a water cement (fas) factor of 0.30 and 0.35 was used. The test object used was a 15x30 cm cylindrical concrete test object for the compressive strength test. The test on porous concrete was carried out during the curing period of 28 days. The test results for the compressive strength of normal porous concrete with a water cement (fas) factor of 0.30 and 0.35 are 6.658 Mpa and 4.435 Mpa, then for porous concrete mixed with sea water with a water cement (fas) factor of 0.30 and 0, 35, namely 6,700 Mpa and 3,374 Mpa. The test results show that the sea water mixture in porous concrete does not affect the compressive strength of porous concrete, whereas the use of variations in the water cement factor (fas) shows that the compressive strength of porous concrete, both normal porous concrete and porous concrete mixed with sea water, has decreased. as the value of the water cement (fas) factor used increases.

The Indonesian Bible Institute can be abbreviated as LAI. LAI has taken part in all Christian congregations by collaborating with the Bible. Which struggles to translate the entire Bible into the archipelago according to its regional language. Furthermore, LAI over time published after being translated and distributed to remote areas. With various developments in the journey of Bible translation, it involves a lot of history and covers various languages, cultures, and social contexts, making the Bible central in the lives of Christians around the world. This study uses qualitative research with direct observation at the LAI headquarters in Jakarta. The headquarters shows the preservation and dissemination of the Bible that has been hundreds of years from old events to new events. In conclusion, LAI has many strategies for development in preserving manuscripts so that they can still be read and available for future generations.

Archives for organizations or institutions have a role as a center for reminders, decision making, evidence and supervision, but many organizations or institutions have not maximized in records management and lack of awareness of archives so that it has an impact on retrieval of archives that are quite long and found to lose records resulting in decreased organizational performance and service quality. To overcome the condition, the Community Service Team held archive management training activities as a form of contribution to the community and helped partners overcome problems faced in organizations or institutions. The activity partners are 25 people from the Student Council Board of SMK Ma'arif NU Doro Pekalongan Regency. The method used is participatory and the material is delivered using the lecture method. This activity was welcomed by the Principal, Student Council Supervisor and Student Council Administrator because it could increase knowledge and skills for Student Council administrators in archive management. The student council board is very enthusiastic about participating in a series of activities and it is hoped that this activity can be sustainable.