Journal of Innovation Information Technology and Application (JINITA)

Big Data Architectures and Concepts

Fri, 29 Dec 2023 11:21:20 +0700

Nowadays, the processing of big data has become a major preoccupation for businesses, not only for storage and processing but also for operational requirements such as speed, maintaining performance with scalability, reliability, availability, security, and cost control; ultimately enabling them to maximize their profits by using the new possibilities offered by Big Data. In this article, we will explore and exploit the concepts and architectures of Big Data, in particular through the Hadoop open-source framework, and see how it meets the needs set out above, in its cluster structure, its components, its Lambda and Kappa architectures, and so on. We are also going to deploy Hadoop in a virtualized Linux environment, with several nodes, under the Oracle Virtual Box virtualization software, and use the experimental method to compare the processing time of the MapReduce algorithm on two DataSets with successively one, two, and three and four Datanodes, and thus observe the gains in processing time with the increase in the number of nodes in the cluster

Machine Learning based on Probabilistic Models Applied to Medical Data: The Case of Prostate Cancer

Fri, 29 Dec 2023 11:21:55 +0700

The growth in the amount of data in companies puts analysts in difficulties when extracting hidden knowledge from data. Several models have emerged that focus on the notion of distances while ignoring the notion of conditional probability density. This research study focuses on segmentation using mixture models and Bayesian networks for medical data mining. As enterprise data becomes large, there is a way to apply data mining methods to make sense of it using classification methods. We designed different models with different architectures and then applied these models to the medical database. The algorithms were implemented for the real data. The objective is to classify individuals according to the conditional probability density of random variables, in addition to identifying causalities between traits from tests of conditional independence and a correlation measure, both based on χ2. After a quick illustration of several models (decision tree, SVM, K-means, Bayes), we applied our method to data from an epidemiological study (done at the University of Kinshasa University clinics) of case-control of prostate cancer. Thus, we found after interpretation of the results followed by discussion that our model allows us to classify a new individual with an accuracy of 96%.

Autocomplete recommendation plugin and Summarizing Text using Natural Language Processing

Fri, 29 Dec 2023 11:23:03 +0700

Expert-caliber documents, reports, letters, and resumes can be easily developed using Microsoft Office. Microsoft Office offers capabilities such as grammar check, text and font checking & formatting, HTML compatibility, advanced page layout, image support, and more in contrast to a plain text editor, however, it does not have the autocomplete abbreviations feature. The paper proposes an Autocomplete abbreviation Recommendation System that will integrate the benefits of getting automatic suggestions of either full forms, abbreviations, or both by clicking on the option that is being suggested. This will provide more flexibility to the user using existing Microsoft Office platforms. To create this feature, we have examined the JavaScript JQuery functions to implement a basic autocomplete feature. Information overloading is also one of the most important problems brought on by the Internet's explosive expansion. Massive quantities of text are difficult for people to manually summarise. Thus, there is now a greater need for summarizers that are more sophisticated and potent. Hence, Python's packages, methods, and NLP are used in this work to implement Text Summarization. By using this technique, the phrase's overall meaning is enhanced and the reader's comprehension is enhanced.

A Survey of Applications of Blockchain in Collective Decision-Making Scenarios in Swarm Robotics

Theviyanthan Krishnamohan — Fri, 29 Dec 2023 11:23:48 +0700

Blockchain is a distributed ledger that was introduced to decentralize monetary systems. However, with time, the applications of blockchain in different realms have been identified. Swarm robotics is a field that combines swarm intelligence and robotics to solve real-world problems that cannot be solved by monolithic robots. Collective decision-making is one of the major behaviors implemented by swarm robotics. This study analyzes existing literature on the applications of blockchain in the collective decision-making scenarios in swarm robotics. Consequently, this study introduces a novel taxonomy to study the different applications effectively. The taxonomy categorizes existing literature into (i) application of blockchain in other areas of swarm robotics, (ii) application of blockchain in continuous collective decision-making scenarios, (iii) application of blockchain in discrete collective decision-making scenarios, (iv) application of blockchain in other discrete collective decision-making scenarios, and (v) application of blockchain in the collective perception scenario. Finally, the limitations of existing work such as excessive resource consumption and violation of swarm robotics principles are discussed.

A Local Government Application Capability Level Information System Audit using COBIT 5 Framework

Bagus Dwi Andika, Sucipto Sucipto, Arie Nugroho — Fri, 29 Dec 2023 11:25:07 +0700

The ASN application stores State Civil Apparatus and Employee Work Target master data. ASN application has never been audited. This study aimed to measure the capability level of the ASN application using the COBIT 5 framework. The audit results contain current findings and expectations for the future, then analyze the gaps and make recommendations for improvement. Audit results based on domains DSS01, DSS02, DSS03, DSS04, DSS05, and DSS06 achieve capability level 1 performance process. The ASN application manager has successfully implemented a process that has achieved its goals by finding evidence of work product output. To achieve the expected level, namely level 2 managed process, it is recommended that you complete incomplete output documents and carry out activities that have not been carried out per COBIT 5.

Clustering Productive Palm Land using the K- Means Clustering Algorithm

Geofanny Widianto Sihite, Eka Prasetyaningrum — Fri, 29 Dec 2023 11:26:15 +0700

Indonesia is a country with a tropical climate that has many oil palm plantations. CV. Alkema Deo is one of the companies that manage oil palm plantations in Sampit City, East Kotawaringin Regency, Central Kalimantan. CV. Alkema Deo was founded in 2016 and has two plantation locations located on Jl. General Sudirman Km. 18, East Kotawaringin and Seibabi Village, Telawang District, East Kotawaringin. In this study, a qualitative approach was applied using a descriptive research pattern. In qualitative research, data is obtained from sources using various data collection techniques. Research using qualitative methods emphasizes the analysis of thought processes related to the dynamics of the relationship between observed phenomena, and always uses scientific logic. Based on the results of research for authors on a CV. Alkema Deo, the use of Excel in companies is quite good at processing data, but on a CV. Alkema Deo does not yet have land groupings based on productivity levels, so it is difficult to see the level achieved in 6 months based on the set target, and daily production control in terms of area and block area. Data obtained from CV. Alkema Deo is grouped based on area, block, and productivity. Application of data mining for grouping productive oil palm land on a CV. Alkema Deo with 4 variables, namely: land area, length, average production yield, percentage of achievement using the K-Means Algorithm to produce three clusters, namely 8 blocks or 50% including the high productive group (C2), 1 block or 6% blocks including the medium productive plantation group (C1), and 7 blocks or 44% including the small productive plantation group (C0).

From Text to Insights: NLP-Driven Classification of Infectious Diseases Based on Ecological Risk Factors

Saviour Inyang, Imeh Umoren — Fri, 29 Dec 2023 11:26:44 +0700

Numerous factors can affect the development of infectious diseases that emerge. While many are the result of natural procedures, such as the gradual emergence of viruses over time, certain ones are the result of human activity. Human activities form an integral part of our ecosystem, and especially the ecological aspect of human activities can encourage disease transmission. Additionally, Health ecologists examine changes in the biological, physical, social, and economic settings to understand how these alterations impact the mental and physical well-being of individuals. Hence, this research adopts a Framework-Based Method (FBM) in carrying out the task of classification of infectious diseases. The Framework-Based Method outlines all phases that this research follows to carry out the infectious disease classification process, providing a structured and reproducible approach. Results show that: XGB: Confusion matrix accuracy: 76%, Kappa: 73%, RF: Confusion matrix accuracy: 65%, Kappa: 60%, SVM: Confusion matrix accuracy: 63%, Kappa: 58%, ANN: Confusion matrix accuracy: 71%, Kappa: 67%, LDA: Confusion matrix accuracy: 76%, Kappa: 73%, GBM: Confusion matrix accuracy: 60%, Kappa: 53%, KNN: Confusion matrix accuracy: 43%, Kappa: 34%, and DT: Confusion matrix accuracy: 37%, Kappa: 29%. Furthermore, a Deep Learning model BERT was integrated with the best classification model XGBoots to create an interactive interface for users to carry out infectious disease classification. This integration enhances user experience and accessibility, contributing to the practical application of machine learning and Natural language processing in ecological disease classification

Expert System for Diagnosing Inflammatory Bowel Disease Using Certainty Factor and Forward Chaining Methods

Linda Perdana Wanti, Nur Wachid Adi Prasetya, Oman Somantri — Fri, 29 Dec 2023 11:27:02 +0700

Identification of inflammatory bowel disease quickly and accurately is motivated by the large number of patients who come with pain in the abdomen and receive minimal treatment because they are considered to be just ordinary abdominal pain. This study aims to identify inflammatory bowel disease which is still considered by some people as a common stomach ache quickly, and precisely and to recommend therapy that can be done as an initial treatment before getting medical action by medical personnel. The method used in this expert system research is a combination of forward chaining and certainty factors. The forward chaining method traces the disease forward starting from a set of facts adjusted to a hypothesis that leads to conclusions, while the certainty factor method is used to confirm a hypothesis by measuring the amount of trust in concluding the process of detecting inflammatory bowel disease. The results of this study are a conclusion from the process of identifying inflammatory bowel disease which begins with selecting the symptoms experienced by the patient so that the diagnosis results appear using forward chaining and certainty factor in the form of a percentage along with therapy that can be given to the patient to reduce pain in the abdomen. A comparison of the diagnosis results using the system and diagnosis by experts, in this case, specialist doctors, shows an accuracy rate of 82,18%, which means that the expert system diagnosis results can be accounted for and follow the expert diagnosis.

Decision Making for The Most Outstanding Students Award using TOPSIS: a Case Study at Institut Teknologi Sumatera

Fri, 29 Dec 2023 11:27:48 +0700

The internal selection of Pemilihan Mahasiswa Berprestasi, or known as Pilmapres, is an annual competition held by Institut Teknologi Sumatera (ITERA) to award the most outstanding student of the year which will be further sent to compete in regional and national event of Pilmapres held by Balai Pengembangan Talenta Indonesia. This study aimed to implement TOPSIS as a decision-making tool to determine the winner of Pilmapres ITERA in 2023. The criteria used in this study were general achievements, English competencies, and creative ideas, with weight of 50, 20, and 30, respectively. The scores for the criteria for each of the students are obtained from nine members of the board of jury in the final stage of Pilmapres ITERA in 2023. The calculation result using TOPSIS concluded that the 1^st, 2^nd, and 3^rd winners of the internal selection of Pilmapres ITERA in 2023 were Alpha, Beta, and Omega, with the final preference scores of 0.995, 0.799, and 0.795, respectively.

Traffic Image Analysis Based on Stacked Denoising Autoencoder Neural Network

Daehyon Kim — Fri, 29 Dec 2023 11:28:04 +0700

This study aims to explore major neural network models - Stacked Denoising Autoencoder (SDAE), Deep Belief Network (DBN), Backpropagation - that have recently garnered attention and propose the most suitable and reliable artificial neural network model for real-time road traffic information collection. In this study, to enhance the reliability of experimental results, numerous experiments were conducted under identical conditions (such as parameter values and network configuration) by setting different initial values for the weight vector. The results of the experiments were statistically validated to draw conclusions. The research results showed that the SDAE model exhibited the most superior performance, while the accuracy of the DBN was somewhat lower compared to the SDAE model. On the other hand, the Backpropagation model demonstrated a relatively low predictive accuracy compared to both models, particularly showing a significant influence of the initial values