Knowledge Discovery In Databases Research Articles

Application of machine learning and data mining in manufacturing industry

With the rise of machine learning in various industries, the traditional manufacturing industry is facing a new disruption, which requires the use of different technologies and tools to achieve its production targets; In this regard, machine learning (ML) and data mining (DM) play a key role. This paper provides a statistical understanding of the main methods and algorithms used to improve manufacturing processes over the past 20 years by dividing them into four main themes: Scheduling, Monitoring, Quality and Failure, presents previous ML research and the latest advances in manufacturing, followed by a comprehensive discussion of existing problem solutions in manufacturing from multiple aspects, It includes tasks (i.e., clustering, classification, regression), algorithms (i.e., support vector machines, neural networks), learning types (i.e., ensemble learning, deep learning), and performance indicators (i.e., accuracy, mean absolute error). In addition, the main steps of database knowledge discovery (KDD) process that should be followed in manufacturing applications are described in detail, and the methods to overcome some problems and the advantages of machine learning applied to manufacturing industry are briefly described. Finally, the paper summarizes and further looks forward to the future development direction.

A gradient boosting machine-based framework for electricity energy knowledge discovery

Knowledge discovery in databases (KDD) has an important effect on various fields with the development of information science. Electricity energy forecasting (EEF), a primary application of KDD, aims to explore the inner potential rule of electrical data for the purpose to serve electricity-related organizations or groups. Meanwhile, the advent of the information society attracts more and more scholars to pay attention to EEF. The existing methods for EEF focus on using high-techs to improve the experimental results but fail to construct an applicable electricity energy KDD framework. To complement the research gap, our study aims to propose a gradient boosting machine-based KDD framework for electricity energy prediction and enrich knowledge discovery applications. To be specific, we draw on the traditional knowledge discovery process and techniques to make the framework reliable and extensible. Additionally, we leverage Gradient Boosting Machine (GBM) to improve the efficiency and accuracy of our approach. We also devise three metrics for the evaluation of the proposed framework including R-square (R2), Mean Absolute Error (MAE), and Mean Absolute Percentage Error (MAPE). Besides, we collect the electricity energy consumption (EEC) as well as meteorological data from 2013 to 2016 in New York state and take the EEC prediction of New York State as an example. Finally, we conduct extensive experiments to verify the superior performance of our framework and the results show that our model achieves outstanding results for the three metrics (around 0.87 for R2, 60.15 for MAE, and 4.79 for MAPE). Compared with real value and the official prediction model, our approach also has a remarkable prediction ability. Therefore, we find that the proposed framework is feasible and reliable for EEF and could provide practical references for other types of energy KDD.

Student performance prediction with BPSO feature selection and CNN classifier

Educational Data Mining (EDM) is gaining great importance as a new interdisciplinary research field related to some other areas. It is directly related to data mining (DM), the latter being a fundamental part of knowledge discovery in databases (KDD). This data is growing more and more and contains hidden knowledge that could be very useful for users (both teachers and students). It is convenient to identify such knowledge in the form of models, patterns, or any other representation scheme that allows better exploitation of the system. Data mining is revealed as the tool to achieve such discovery, giving rise to EDM. In this complex context, different techniques and learning algorithms are usually used to obtain the best results. Recently educational systems are adopting artificial intelligent systems, especially in the educational context, specific areas for extracting relevant information, such as EDM, which integrates numerous techniques that support the capture, processing, and analysis of these sets of records. The main technique associated with EDM is Machine Learning, which has been used for decades in data processing in different contexts, but with the advent of Big Data, there was an intensification in the application of this technique to extract relevant information from a huge amount of data. This paper proposes the student performance prediction using CNN (Convolution Neural Network) and BPSO (Binary Particle Swarm Optimization) based feature selection method. In this study, classifiers are made for 2-class and 5-class predictions. The proposed system claims an outperforming accuracy of 96.6% with various previous research works as well as found that the majority of attributes related to school activities as compared to data on demographic and socioeconomic characteristics.

Knowledge Discovery in Health Domain using Deep Neural Network Algorithms

Knowledge discovery in databases (KDD) primarily depends on finding a strategy for effectively processing data. Data mining is a critical phase in the KDD process for extracting a valuable pattern from a dataset. Pattern extraction and discovery are complex processes that often require a vast dataset. Several applications and systems are used for health care and clinical data to diagnose and record patient records. The installed systems' primary goal is to extract a relevant pattern capable of improving healthcare services. To improve healthcare services, data mining necessitates the right design and execution of data mining algorithms to detect a unique pattern from large amounts of data. As a result, we propose using patient information from the Hewa Hospital in Sulamani, which is in charge of cancer and blood diseases, as a case study for our research. The primary goal of this research is to look at deep neural networks (DNN) and artificial neural networks (ANN) as classification algorithms that can assist us in making better judgments. The results show that the DNN algorithm outperforms the ANN method. When utilizing a 70:30 training and testing dataset, the score can reach 87.84.

Perbandingan Algoritma Klasifikasi Data Mining Untuk Prediksi Penyakit Stroke

Data mining is often called knowledge Discovery in Database (KDD). Data mining is usually used to improve future decision making based on information obtained from the past. For example for prediction, estimation, association, clustering, and description. Stroke is the second most deadly disease in the world according to WHO. The sufferer has an injury to the nervous system. Because of this, health experts, especially in the field of nursing, need special attention. Currently, the development of the Industrial Revolution Era 4.0 is collaborating in the fieldsof technology and health science so that it becomes something useful by using Machine Learning. There are so many benefits that are used in predicting several diseases that can be anticipated. In this study the dataset is dividedinto 2 parts, namely training data and testing data using split validation. Based on the results of the test that have been carried out in this study, the algorithm that has the highest accuracyvalue on balanced data is Logistic Regression with an accuracy rate of 75.65%, while for unbalanced data, the algorithm that has the highest accuracy results is Logistic Regression, Random Forest, SVM, and KNN with an accuracy rate of 98.63%. This testing process is carried out to identify stroke with data mining algorithms

Research on the Fusion Trend of Artificial Intelligence and VR Based on Data Mining

The definition and research background of artificial intelligence, data mining, and VR, and the application of data mining artificial intelligence, such as system design applications and intelligent service applications, are scientifically expounded, which reflects the knowledge economy. In order to further broaden the application scope and efficiency of AI, we should constantly strengthen the application research of data mining in AI. In database knowledge discovery, the interpretation and evaluation of data mining results in an important link.

Diabetes Prediction System

Abstract: This model of retrieving useful information and models from the data is also called database knowledge discovery, which involves certain phases such as data selection, classification and transformation evaluation. Machine learning algorithms are primarily classified as supervised and unsupervised. A supervised learning algorithm uses past experience to make predictions about new or invisible data, whereas unsupervised algorithms can draw interferences from data sets. Supervised learning is also described as classification. This study uses classification technique to produce a more accurate belong to class. The classification algorithms have been applied to the Indian Diabetes Dataset of the PIMA of the National Institute of Diabetes, Digestive and Kidney Disease which contains data on diabetic women.

Clustering Hasil Belajar Menggunakan Algoritma K-Means Dengan Optimize Parameter Dalam Menjamin Mutu Pendidikan Di Era Pandemi Covid-19

The COVID-19 pandemic has greatly affected the learning environment, with the excuse of stopping the spread of COVID-19 infection. Teaching and learning activities that have generally been completed on campus face-to-face now have to be transferred to distance learning. However, one of the drawbacks of implementing distance learning is that it makes students less active, so that KBM feels tiring. The purpose of this study is to classify student learning outcomes during the COVID-19 Pandemic. The method used is the Knowledge Discovery Database (KDD) using the K-Means Algorithm. The number of clusters selected is the number of clusters with the smallest Davies Bouldin Index (DBI). The results of this study obtained 3 clusters with a DBI value of 1.379 and a centroid distance of 0.342. Cluster_1 is the data group with the highest quality index, Cluster_2 is the data group with the second highest quality index, and Cluster_0 is the data group with the lowest quality index of all clusters. By knowing the clusters of PJJ learning outcomes, it will make it easier for universities to take improvement steps to improve the quality of learning in accordance with the characteristics of each existing cluster

Penerapan Data Mining Menggunakan Metode Clustering Untuk Mengetahui Kelompok Kepatuhan Wajib Pajak Bumi dan Bangunan

Local taxes are taxes set by local governments whose collection authority and tax proceeds are used to fund regional expenditures. One of the taxes included in the authority of local governments is the Land and Building Tax (PBB). Land and Building Tax is one of the taxes that can be paid through the village government. With the increasing number of taxpayers in the village, the data on payment of tax contributions that go directly to the state treasury causes the Kendal Village government, Astanajapura District, Cirebon Regency not to know how many taxpayers are obedient and disobedient. This study uses data mining techniques namely the Clustering Method using the K-Means method. This study uses the Knowledge Discovery in Database (KDD) stage with the amount of data used as much as 1,159 in the form of taxpayer data for the Kendal Village community in 2021. The results of the RapidMiner test using the Davies Bouldin Index calculation obtained a cluster determination value with a value of 4 (0.862). Cluster 0 contains members who have a low level of compliance in paying PBB, Cluster 1 contains members of taxpayers with a moderate level of compliance in paying PBB, Cluster 2 has a high level of taxpayer compliance and Cluster 3 is a cluster with a very high level of taxpayer compliance. By having the most dominant average price determined by PBB in each cluster is Rp. 18.000,-.

Data Mining Menggunakan Algoritma K-Means Clustering dalam Analisis Tingkat Potongan Harga Terhadap Harga Jual Sepeda Motor Honda

Knowledge Discovery in Database (KDD) has a structured analysis process to obtain the latest information. Data mining plays a role in extracting hidden information with one method, namely clustering. The purpose of this study was to determine the appropriate level of discount for each type of Honda motorcycle. The data processed in this study were sourced from the Marketing Main Dealer for Honda Motorcycles, West Sumatra. Furthermore, this data is processed by the Data Mining technique using the K-Means Clustering Algorithm. The processing stage is to determine the number of clusters and centroids, then calculate the distance between the centroid point and each object in the data. Predefined objects are grouped to determine cluster members based on distance. The calculation is continued until the resulting centroid value remains and the cluster members do not move to another cluster. The results of testing this algorithm are 3 clusters with 42 test data, in cluster 1 there are 34 types of vehicles that get discounted prices, then cluster 2 of 7 types of vehicles can get discounts and cluster 3 of 1 type of vehicles can not get discounts. The analysis of the test results has been able to determine the level of discount on the selling price of Honda motorcycles. By grouping customer interest data, it can be recommended to provide discounted sales prices in order to help marketing management increase sales of Honda motorcycles.

SALES LEVEL ANALYSIS USING THE ASSOCIATION METHOD WITH THE APRIORI ALGORITHM

The company does not yet know the pattern of consumer purchases because so far, the sales transaction data has not been used correctly and does not have a unique method to determine consumer buying patterns. To overcome the problems on the company, this research was done to reprocess sales transaction data for 2018-2019 using data mining techniques with association methods and apriori algorithms. RapidMiner is a supporting application used to find association rules derived from transaction data. Processed transaction data using the Knowledge Discovery in Database (KDD) approach. Thus, the company can determine consumer habits in buying goods derived from sales transaction data for 2018-2019. The results of this study are that in 2018, nine association rules were obtained, of which the best were CT G-246 ⇒ CT G-250 and CT G-250 ⇒ CT G-246. In 2019, nineteen association rules were obtained, of which the best were PN 0441, SK 0175 ⇒ SK 0530 and SK 0175, SK 0283 ⇒ SK 0530. From the best association rules, the goods in the Coat (imported), Pants, and Skirt categories are categories that are often bought together.

Data Reduction Techniques: A Comparative Study

Data preprocessing in general and data reduction in specific represent the main steps in data mining techniques and algorithms since data in real world due to its vastness, the analysis will take a long time to complete .Almost all mining techniques including classification, clustering, association and others have high time and space complexities due to the huge amount of data and the algorithm behavior itself. That is the reason why data reduction represent an important phase in Knowledge Discovery in Databases (KDD) process. Many researchers introduced important solutions in this field. The study in this paper represents a comparative study for about 22 research papers in data reduction fields that covers different data reduction techniques such as dimensionality reduction, numerisoty reduction, sampling, clustering data cube aggregation and other techniques. From the conducted study, it can be concluded that the appropriate technique that can be used in data reduction is highly dependent on the data type, the dataset size, the application goal, the availability of noise and outliers and the compromise between the reduced data and the knowledge required from the analysis

AI federated learning based improvised random Forest classifier with error reduction mechanism for skewed data sets

PurposeReferred data set produces reliable information about the network flows and common attacks meeting with real-world criteria. Accordingly, this study aims to focus on the use of imbalanced intrusion detection benchmark knowledge discovery in database (KDD) data set. KDD data set is most preferably used by many researchers for experimentation and analysis. The proposed algorithm improvised random forest classification with error tuning factors (IRFCETF) deals with experimentation on KDD data set and evaluates the performance of a complete set of network traffic features through IRFCETF.Design/methodology/approachIn the current era of applications, the attention of researchers is immersed by a diverse number of existing time applications that deals with imbalanced data classification (ImDC). Real-time application areas, artificial intelligence (AI), Industrial Internet of Things (IIoT), etc. are dealing ImDC undergo with diverted classification performance due to skewed data distribution (SkDD). There are numerous application areas that deal with SkDD. Many of the data applications in AI and IIoT face the diverted data classification rate in SkDD. In recent advancements, there is an exponential expansion in the volume of computer network data and related application developments. Intrusion detection is one of the demanding applications of ImDC. The proposed study focusses on imbalanced intrusion benchmark data set, KDD data set and other benchmark data set with the proposed IRFCETF approach. IRFCETF justifies the enriched classification performance on imbalanced data set over the existing approach. The purpose of this work is to review imbalanced data applications in numerous application areas including AI and IIoT and tuning the performance with respect to principal component analysis. This study also focusses on the out-of-bag error performance-tuning factor.FindingsExperimental results on KDD data set shows that proposed algorithm gives enriched performance. For referred intrusion detection data set, IRFCETF classification accuracy is 99.57% and error rate is 0.43%.Research limitations/implicationsThis research work extended for further improvements in classification techniques with multiple correspondence analysis (MCA); hierarchical MCA can be focussed with the use of classification models for wide range of skewed data sets.Practical implicationsThe metrics enhancement is measurable and helpful in dealing with intrusion detection systems–related imbalanced applications in current application domains such as security, AI and IIoT digitization. Analytical results show improvised metrics of the proposed approach than other traditional machine learning algorithms. Thus, error-tuning parameter creates a measurable impact on classification accuracy is justified with the proposed IRFCETF.Social implicationsProposed algorithm is useful in numerous IIoT applications such as health care, machinery automation etc.Originality/valueThis research work addressed classification metric enhancement approach IRFCETF. The proposed method yields a test set categorization for each case with error reduction mechanism.

Classification of Covid-19 vaccine data screening with Naive Bayes algorithm using Knowledge Discovery in database method

Acute Respiratory Syndrome Coronavirus-2 (SARS-Cov-2) known as covid-19 was detected and caused a very large number of deaths due to a mysterious respiratory disease. With the death toll continuing to rise, the government was forced to take swift action to break the chain of spread and reduce the number of deaths by taking vaccinations. An adequate vaccine against Covid-19 is expected to vaccinate at least 70% of the population. Therefore, this study was carried out as a step to help break the chain of the spread of the Covid-19 virus, by classifying the Covid-19 vaccine screening data. The research method applied in this study is the Knowledge Discovery in Database (KDD) method, in which there are several processes, namely selection, pre-processing, transformation, data mining, and evaluation. The application of the Naive Bayes method is expected to be able to classify Covid-19 vaccine screening data with vaccine class values, no, and delay. The results of the research on the classification of the Naive Bayes method show that there are 959 data with Vaccine data 695, No 200, and Delay 64. Processed using the Rapidminer application, the accuracy is 96.56%, Precision is 92.46%, and Recall is 92.13%.

A Review of Data Mining and Knowledge Discovery Approaches for Bioinformatics

This review explores the Knowledge Discovery Database (KDD) approach, which supports the bioinformatics domain to progress efficiently, and illustrate their relationship with data mining. Thus, it is important to extract advantages of Data Mining (DM) strategy management such as effectively stressing its role in cost control, which is the principle of competitive intelligence, and the role of it in information management. As well as, its ability to discover hidden knowledge. However, there are many challenges such as inaccurate, hand-written data, and analyzing a large amount of variant information for extracting useful knowledge by using DM strategies. These strategies are successfully applied in several applications as data warehouses, predictive analytics, business intelligence, bioinformatics, and decision support systems. There are many DM techniques that are applied for disease diagnostics and treatment, for example cancer diseases that are investigated using multi-layer perception, Naïve Bayes, Decision Tree, Simple Logistic, K-Nearest Neighbor. As will be explored in this paper. Consequently, for future perspectives there is research in progress for real Iraqi data of Breast Cancer using Data Mining techniques, specifically the Tree decision and K-nearest algorithms.

E-governance to Smart-Governance in Developing Countries Creating a digital path for realizing SDGs using Cloud computing, Big Data and Data Mining Technologies

ABSTRACT The emerging technologies of today are contributing to the exponential amount of data all around us. This data characterized by Velocity, Volume, Value, Variety, and Veracity(5V) in literature. This has led to a phenomenon called the Data Revolution as a result of the value that can be gleaned from the data available. The area of government where ICT capabilities are harnessed to enable governments realize its goal of public service delivery is described as e-governance. The e-governance context cannot be left out in this revolution especially in decision making. However, the vast amount of data produced by government in the public sector has not been fully harnessed decision making and planning efforts as the politician’s knowledge is mostly preferred. This proposed PhD study seeks to investigate the use of emerging technologies like cloud computing, Big Data, Knowledge Discovery in Databases (KDD) process in Data mining to create a digital path for the realization of the Sustainable Development Goals(SDGs) especially in developing countries. Automating decision support system in the public services via smart technologies and algorithms is envisaged. Keywords: Cloud Computing, E-governance, Big Data, analytics, SDGs

Enabling intrusion detection systems with dueling double deep Q-learning

PurposeIn this research, the authors demonstrate the advantage of reinforcement learning (RL) based intrusion detection systems (IDS) to solve very complex problems (e.g. selecting input features, considering scarce resources and constrains) that cannot be solved by classical machine learning. The authors include a comparative study to build intrusion detection based on statistical machine learning and representational learning, using knowledge discovery in databases (KDD) Cup99 and Installation Support Center of Expertise (ISCX) 2012.Design/methodology/approachThe methodology applies a data analytics approach, consisting of data exploration and machine learning model training and evaluation. To build a network-based intrusion detection system, the authors apply dueling double deep Q-networks architecture enabled with costly features, k-nearest neighbors (K-NN), support-vector machines (SVM) and convolution neural networks (CNN).FindingsMachine learning-based intrusion detection are trained on historical datasets which lead to model drift and lack of generalization whereas RL is trained with data collected through interactions. RL is bound to learn from its interactions with a stochastic environment in the absence of a training dataset whereas supervised learning simply learns from collected data and require less computational resources.Research limitations/implicationsAll machine learning models have achieved high accuracy values and performance. One potential reason is that both datasets are simulated, and not realistic. It was not clear whether a validation was ever performed to show that data were collected from real network traffics.Practical implicationsThe study provides guidelines to implement IDS with classical supervised learning, deep learning and RL.Originality/valueThe research applied the dueling double deep Q-networks architecture enabled with costly features to build network-based intrusion detection from network traffics. This research presents a comparative study of reinforcement-based instruction detection with counterparts built with statistical and representational machine learning.

Recognition of Regional Traditional House in Indonesia Using Convolutional Neural Network (CNN) Method

Indonesia is a country that has a lot of cultural diversity. This cultural diversity needs to be preserved. If this is not done, the culture that is owned by Indonesia can slowly disappear. The reduction in cultural values can also reduce the sense of belonging to the culture. This lack of sense of ownership makes it easy for other nations to make claims on the culture that is owned by Indonesia. Indonesia will lose its characteristics as a country that has a lot of cultural diversity. One of the efforts to preserve culture is to recognize the characteristics of each culture and be able to recognize the differences between one culture and another. For example, recognizing traditional houses from various ethnic groups based on their image. In this research, the image classification of the characteristics of traditional houses from several ethnic groups in Indonesia was carried out. The classification used to identify an image. In this study, deep learning techniques are used with the Convolutional Neural Network (CNN) algorithm and Keras framework. This CNN use several layers namely convolutional, pooling, flatten, and dense layer. The development of deep learning models uses the Knowledge Discovery in Database (KDD) method. This method consists of nine stages. The built model is evaluated using k-fold cross validation with a k value of 5 and produces an average accuracy of 80%. This shows that the model built is capable of classifying well. The built model is evaluated with 3 different epoch values, namely 50, 75, and 100. The larger the epoch value used, the greater the accuracy value. The model built is also able to make predictions with an accuracy of 80%.

Set Representation for Rule Generation Algorithms

The task of mining the association rule has become one of the most widely used discovery pattern methods in Knowledge Discovery in Databases (KDD). One such task is to represent the itemset in the memory. The representation of the itemset largely depend on the type of data structure that is used for storing them. Computing the process of mining the association rule im- pacts the memory and time requirement of the itemset. With the increase in the dimensionality of data and datasets, mining such large volume of datasets will be difficult since all these itemsets cannot be placed in the main memory. As representation of an itemset greatly affects the efficiency of the rule mining association, a compact and compress representation of an itemset is needed. In this paper, a set representation is introduced which is more memory and cost efficient. Bitmap representation takes one byte for an element but the set representation uses one bit. The set representation is being incorporated in Apriori Algorithm. Set representation is also being tested for different rule generation algorithms. The complexities of these different rule generation algorithms using set representation are being compared in terms of memory and time execution.

Classification of Depressive and Schizophrenic Episodes Using Night-Time Motor Activity Signal.

Major depressive disorder (MDD) is the most recurrent mental illness globally, affecting approximately 5% of adults. Furthermore, according to the National Institute of Mental Health (NIMH) of the U.S., calculating an actual schizophrenia prevalence rate is challenging because of this illness’s underdiagnosis. Still, most current global metrics hover between 0.33% and 0.75%. Machine-learning scientists use data from diverse sources to analyze, classify, or predict to improve the psychiatric attention, diagnosis, and treatment of MDD, schizophrenia, and other psychiatric conditions. Motor activity data are gaining popularity in mental illness diagnosis assistance because they are a cost-effective and noninvasive method. In the knowledge discovery in databases (KDD) framework, a model to classify depressive and schizophrenic patients from healthy controls is constructed using accelerometer data. Taking advantage of the multiple sleep disorders caused by mental disorders, the main objective is to increase the model’s accuracy by employing only data from night-time activity. To compare the classification between the stages of the day and improve the accuracy of the classification, the total activity signal was cut into hourly time lapses and then grouped into subdatasets depending on the phases of the day: morning (06:00–11:59), afternoon (12:00–17:59), evening (18:00–23:59), and night (00:00–05:59). Random forest classifier (RFC) is the algorithm proposed for multiclass classification, and it uses accuracy, recall, precision, the Matthews correlation coefficient, and F1 score to measure its efficiency. The best model was night-featured data and RFC, with 98% accuracy for the classification of three classes. The effectiveness of this experiment leads to less monitoring time for patients, reducing stress and anxiety, producing more efficient models, using wearables, and increasing the amount of data.