Naive Bayes Classifier Method Research Articles

KLASIFIKASI KATEGORI BUKU PADA PERPUSTAKAAN TEKNIK INFORMATIKA UNIVERSITAS ISLAM LAMONGAN

The large number of library materials in the form of new book available in the library every year cause officer have difficulty in classification process book. Similarly, faced by librarian of Islamic University of Lamongan became the object of this research, determining the type or category of book at first the usual system. The process is made a lot of errors because it is based on the knowledge of officers from reading the title or the appropriate category so that makes it difficult for library users to find the materials needed. Application applied in the research is a data classification application that is done automatically using the application developed by Naive Bayes Classifier method with the application of client software web-based. Web-based server application function to input book by administrator and to classify data book based on the title. Based on the experience, and then in this research built an Classification Of Books Category At The Islamic University Of Lamongan Engineering Library

Sentiment analysis system for movie review in Bahasa Indonesia using naive bayes classifier method

There are many ways of implementing the use of sentiments often found in documents; one of which is the sentiments found on the product or service reviews. It is so important to be able to process and extract textual data from the documents. Therefore, we propose a system that is able to classify sentiments from review documents into two classes: positive sentiment and negative sentiment. We use Naive Bayes Classifier method in this document classification system that we build. We choose Movienthusiast, a movie reviews in Bahasa Indonesia website as the source of our review documents. From there, we were able to collect 1201 movie reviews: 783 positive reviews and 418 negative reviews that we use as the dataset for this machine learning classifier. The classifying accuracy yields an average of 88.37% from five times of accuracy measuring attempts using aforementioned dataset.

RANCANG BANGUN SISTEM PAKAR SEBAGAI ALAT BANTU DIAGNOSA DINI NYERI KEPALA PRIMER

Background. Headache is the top ranked with 42% percentage of all complaints neurology’s patients. Focused and systematic approach is needed in making a diagnosis of primary headache type because management of headache is different for each type. Objective. Enabling users to identify the type of headache. Methods. The experiment was conducted using Naive Bayes classifier method which is the principle is multiplying the percentage likelihood of each variable for each parameter for each class. Results. The percentage value of each parameter obtained from the data of headache patients at neurology polyclinic poly of Dr. Soetomo Hospital within 1 year from the year 2014 to 2015. The percentage value of each class likelihood sought highest value which is the output or decision-diagnosis program. Analysis of each of the input parameters, gender, age, location of head pain, headache characteristics, appeared least autonomous signs, and scale of headache may indicate that each of the options selected by the user influence the decision of the diagnosis program. Conclusion. The design of early detection of primary headaches with the input parameters as mentioned before derived from the raw data as electronic medical records to be analyzed based on methods Naive Bayes classifier resulted in the decision diagnosis of migraine, cluster and TTH have accuracy values by 92 %.

A feature dependent Naive Bayes approach and its application to the software defect prediction problem

Naive Bayes is one of the most widely used algorithms in classification problems because of its simplicity, effectiveness, and robustness. It is suitable for many learning scenarios, such as image classification, fraud detection, web mining, and text classification. Naive Bayes is a probabilistic approach based on assumptions that features are independent of each other and that their weights are equally important. However, in practice, features may be interrelated. In that case, such assumptions may cause a dramatic decrease in performance. In this study, by following preprocessing steps, a Feature Dependent Naive Bayes (FDNB) classification method is proposed. Features are included for calculation as pairs to create dependence between one another. This method was applied to the software defect prediction problem and experiments were carried out using widely recognized NASA PROMISE data sets. The obtained results show that this new method is more successful than the standard Naive Bayes approach and that it has a competitive performance with other feature-weighting techniques. A further aim of this study is to demonstrate that to be reliable, a learning model must be constructed by using only training data, as otherwise misleading results arise from the use of the entire data set.

Radius based domain clustering for WiFi indoor positioning

PurposeNowadays, WiFi indoor positioning based on received signal strength (RSS) becomes a research hotspot due to its low cost and ease of deployment characteristics. To further improve the performance of WiFi indoor positioning based on RSS, this paper aims to propose a novel position estimation strategy which is called radius-based domain clustering (RDC). This domain clustering technology aims to avoid the issue of access point (AP) selection.Design/methodology/approachThe proposed positioning approach uses each individual AP of all available APs to estimate the position of target point. Then, according to circular error probable, the authors search the decision domain which has the 50 per cent of the intermediate position estimates and minimize the radius of a circle via a RDC algorithm. The final estimate of the position of target point is obtained by averaging intermediate position estimates in the decision domain.FindingsExperiments are conducted, and comparison between the different position estimation strategies demonstrates that the new method has a better location estimation accuracy and reliability.Research limitations/implicationsWeighted k nearest neighbor approach and Naive Bayes Classifier method are two classic position estimation strategies for location determination using WiFi fingerprinting. Both of the two strategies are affected by AP selection strategies and inappropriate selection of APs may degrade positioning performance considerably.Practical implicationsThe RDC positioning approach can improve the performance of WiFi indoor positioning, and the issue of AP selection and related drawbacks is avoided.Social implicationsThe RSS-based effective WiFi indoor positioning system can makes up for the indoor positioning weaknesses of global navigation satellite system. Many indoor location-based services can be encouraged with the effective and low-cost positioning technology.Originality/valueA novel position estimation strategy is introduced to avoid the AP selection problem in RSS-based WiFi indoor positioning technology, and the domain clustering technology is proposed to obtain a better accuracy and reliability.

Core recovery criterion – a new optimization method of geological information quality in the geological conditions of the Grodziec Syncline Area

Abstract The increasing requirements for the quality and amount of geological information induce the development of new technological solutions. The authors present the optimization of the coring method for a newly defined criterion of maximum geological information quality. It enables the efficiency of works to be improved without investing in new specialist and expensive equipment. The statistical classification methods commonly used in medicine and the economy were used for analyzing the homogeneity of the drilled rocks. The quadratic discriminant analysis (QDA) and the Naive Bayes classifier method turned out to be most efficient, therefore they were selected from among other methods differing in the way the classification rules are built. The newly defined criterion of maximum geological information quality and the mathematical model of maximum core recovery allowed the amount and the quality of recovered rock material in the geologic conditions of the Grodziec Syncline to be incresed. The control of the process relied on detecting phenomena responsible for core damaging, i.e. erosiveness of drilling mud, mechanical damaging due to jamming in the core barrel and unstable operation of the core bit downhole. The analysis revealed that the main factor influencing the lower recovery of cores is mechanical damaging due to jamming in the core barrel. For the sake of controlling the core recovery, the authors defined and used the jamming index which defines the effect of weight on bit on momentary rate of penetration. The efficiency of this method was proved by a test performed in industrial conditions while drilling a successive wellbore in the Grodziec Syncline. This paper was written on the basis of own experience and analyses performed by the authors while conducting works in the Grodziec Syncline in the South West Poland.

Instant Message Classification in Finnish Cyber Security Themed Free-Form Discussion

Instant messaging enables rapid collaboration between professionals during cyber security incidents. However, monitoring discussion manually becomes challenging as the number of communication channels increases. Failure to identify relevant information from the free-form instant messages may lead to reduced situational awareness. In this paper, the problem was approached by developing a framework for classification of instant message topics of cyber security-themed discussion in Finnish. The program utilizes open source software components in morphological analysis, and subsequently converts the messages into Bag-of-Words representations before classifying them into predetermined incident categories. We compared support vector machines (SVM), multinomial naive Bayes, and complement naive Bayes (CNB) classification methods with five-fold cross-validation. A combination of SVM and CNB achieved classification accuracy of over 85 %, while multiclass SVM achieved 87 % accuracy. The implemented program recognizes cyber security-related messages in IRC chat rooms and categorizes them accordingly.

Computer Vision-Based Real-Time 3D Gesture Recognition Using Depth Image

Gesture is one of the fundamental ways of human machine natural interaction. To understand gesture, the system should be able to interpret 3D movements of human. This paper presents a computer vision-based real-time 3D gesture recognition system using depth image which tracks 3D joint position of head, neck, shoulder, arms, hands and legs. This tracking is done by Kinect motion sensor with OpenNI API and 3D motion gesture is recognized using the movement trajectory of those joints. User to Kinect sensor distance is adapted using proposed center of gravity (COG) correction method and 3D joint position is normalized using proposed joint position normalization method. For gesture learning and recognition, data mining classification algorithms such as Naive Bayes and neural network is used. The system is trained to recognize 12 gestures used by umpires in a cricket match. It is trained and tested using about 2000 training instances for 12 gesture of 15 persons. The system is tested using 5-fold cross validation method and achieved 98.11% accuracy with neural network and 88.84% accuracy with Naive Bayes classification method.

Tool wear monitoring using naïve Bayes classifiers

A naive Bayes classifier method for tool condition monitoring is described. End-milling tests were performed at different spindle speeds and the cutting force was measured using a table-mounted dynamometer. The effect of tool wear on force features in the time and frequency domains was evaluated and used for training the classifier. The amount of tool wear was predicted using the naive Bayes classifier method. Two cases are presented. First, the tool wear is divided into discrete states based on the amount of flank wear and the probability of the tool wear being in any state is updated using force data. Second, a continuous case is considered and the probability density function of the tool flank wear width is updated. The results are discussed.

Classification of in-tube boiling R134a data belonging to the smooth and corrugated tubes

Different types of tubes have been used to improve cooling systems regarding the performance, cost and compactness. Corrugated tubes are tubes with their inner surface enhanced in these systems. One of the applications of machine learning, named as pattern classification, is often used to separate the human faces, voices, finger prints etc. In this study, it is used to separate the R134a data taken in-tube boiling process in smooth and enhanced tubes automatically. In other words, the developed numerical algorithms enabled artificial intelligence to predict the type of tubes having equivalent diameters used in the experiments. Systematical experiments, including saturation temperatures of 10, 15 and 20°C, mass fluxes of 200, 300 and 400kgm−2s−1 and heat fluxes of 20, 25 and 30Wm−2, are carried out for the comparisons using smooth and 5 different types of corrugated tubes having various corrugation depths and helix angles. The boiling process in the test tubes has been measured with 300 data points, having 30 individual parameters (inputs) for varying tube types for the reduction process by the Linear Discriminant Analysis (LDA) and Principle Component Analysis (PCA). The classification success rates of the methods of Linear Discriminant Classifier (LDC), Quadratic Discriminant Classifier (QDC), Naive Bayes Classifier (NBC) and Minimum Mahalanobis Distance Classifier (MMDC) by each dimensional reduction and the total area occupying under receiver operating characteristic (ROC) curves are determined according to 3-fold cross validation method. NBC method has the highest classification success with the accuracy of 98.33% as a result of the reduction to 3 dimensions by LDA method. In addition to this, QDC method has the highest area under curve (AUC) with the value of 0.9994 according to the reduction to 3 dimensions by LDA method. Dependency analyses showed that the use of 8 dimensional experimental parameters as the most important input is enough to determine the type of test tubes with a high accuracy.

Modeling of Reusability of Procedure based Software Components using Naive Bayes Classifier Approach

We have developed a highly flexible module to evaluate and access the reusability of software components. The purpose of this model is to do pattern recognition by discovering supervised features which can help us to measure the intangible aspects of software components in terms of reusability. There were several function based applications which were given due diligence for identifying their various degrees of reusability of their components. Once these projects were analyzed their software components were measured in terms of software metrics including (Volume, Coupling, Complexity, Reuse frequency, Regularity and Reusability). These measured metrics were carefully allocated a particular set of label which was based on the principals of software engineering and objectives to be achieved for doing the due research. Therefore, in this research work we are studying the degree of reusability by using six classes Naive Bayes Classification method which was able to give high precision value as compare to previous methods.

A balanced solution of a fuzzy soft set based decision making problem in medical science

The purpose of this paper is two folded. Firstly, the concept of mean potentiality approach (MPA) has been developed and an algorithm based on this new approach has been proposed to get a balanced solution of a fuzzy soft set based decision making problem. Secondly, a parameter reduction procedure based on relational algebra with the help of the balanced algorithm of mean potentiality approach has been used to reduce the choice parameter set in the parlance of fuzzy soft set theory and it is justified to the problems of diagnosis of a disease from the myriad of symptoms from medical science. Moreover the feasibility of this proposed method is demonstrated by comparing with Analytical Hierarchy Process (AHP), Naive Bayes classification method and Feng's method.

Implementation of a bio-inspired two-mode structural health monitoring system

A bio-inspired two-mode structural health monitoring (SHM) system based on the Naive Bayes(NB) classification method is discussed in this paper. To implement the molecular biology based Deoxyribonucleic acid (DNA) array concept in structural health monitoring, which has been demonstrated to be superior in disease detection, two types of array expression data have been proposed for the development of the SHM algorithm. For the micro-vibration mode, a two-tier auto-regression with exogenous (AR-ARX) process is used to extract the expression array from the recorded structural time history while an ARX process is applied for the analysis of the earthquake mode. The health condition of the structure is then determined using the NB classification method. In addition, the union concept in probability is used to improve the accuracy of the system. To verify the performance and reliability of the SHM algorithm, a downscaled eight-storey steel building located at the shaking table of the National Center for Research on Earthquake Engineering (NCREE) was used as the benchmark structure. The structural response from different damage levels and locations was collected and incorporated in the database to aid the structural health monitoring process. Preliminary verification has demonstrated that the structure health condition can be precisely detected by the proposed algorithm. To implement the developed SHM system in a practical application, a SHM prototype consisting of the input sensing module, the transmission module, and the SHM platform was developed. The vibration data were first measured by the deployed sensor, and subsequently the SHM mode corresponding to the desired excitation is chosen automatically to quickly evaluate the health condition of the structure. Test results from the ambient vibration and shaking table test showed that the condition and location of the benchmark structure damage can be successfully detected by the proposed SHM prototype system, and the information is instantaneously transmitted to a remote server to facilitate real-time monitoring. Implementing the bio-inspired two-mode SHM practically has been successfully demonstrated.