Search

Mango pulp weevil (MPW) behavior has been long studied but frequency characterization of the said pest in different adult activities was not yet explored. This study focused on the comparative classification of the mating activity of the MPW. Data was collected on a controlled environment with an acoustic chamber built, and the frequency was acquired using a MEMS (Micro Electro-Mechanical Systems) microphone, connected through a microcontroller. Two different algorithms namely the Decision Tree Learning algorithm and Naive Bayes Classifier algorithm, were tested and compared. Performance in the filtering and optimization of the two algorithms were evaluated in three different stages of mating, the pre-mating, mating and post-mating stage. Comparison of the results of the two algorithms for the premating stage, the Decision tree algorithm reached 75% accuracy while Naive Bayes algorithm had 95% accuracy, for the mating stage, it was 55% as compared to 70% and in post mating stage, 45% accuracy for the Decision Tree Learning algorithm and 85% for the Naive Bayes algorithm. These results showed that Naive Bayes classifier is more accurate in classifying the different stages of MPW activity.

A natural disaster is a natural event that can occur suddenly and cannot avoid. Natural disasters can result in property loss and loss of life. After the occurrence of a natural disaster, the evacuation process by the SAR team (search and rescue) must carry out immediately to increase the chances of victim evacuation safely or alive. However, finding victims after natural disasters is not an easy task. It is because the victims are challenging to see with the naked eye by the SAR team. This study aims to produce a prototype device capable of detecting victims of natural disasters and providing information on the location of victims to the base station. The prototype of this device uses thermal sensors as parameters to see the victim. The sensor that focuses on finding good victims is by detecting body temperature. This device is also equipped with a GPS receiver. In decision making, this device prototype uses the Naive Bayes algorithm. The decision result is determined by the Naive Bayes method. The victim’s location from the GPS receiver will be sent to the base station via the LoRa communication system. This study shows that the classification output of the naive Bayes algorithm detects humans up to a distance of 100 cm. On the GPS receiver used, the difference between the distance with the GPS on the smartphone is about 5 meters. In sending and receiving data at a distance of 20 meters, the average delay is 0.935 seconds. This system is still not optimal for actual application because the detection range is still very close.

A deep understanding of customer's needs and efficient analysis of customer behavior is such a measurement tool on which the paramount success of each enterprise relies upon. The customer retention ability is being focused on effective studies of potential customers, better decision-making, and enhanced business processes. Naive Bayes (NB) classifier, a simple classifier can be used for anticipating customer behavior. Through an excellent understanding of customers and their consuming behavior, a firm can retain loyal customers, improve its online footprint, forecast how customers will react to the company's marketing strategies, enhance business policy to discover new consuming areas, and boost profits income. The goal of this study is to look into the purchasing habits of telecom firm customers to help them be one of the leading brands in terms of implementing services in the telecoms sector. We conducted our data analysis on a customer records dataset from a telecommunication company, composed of various service usage records of its customers from various states across the United States of America.

Currently, the world's attention was focused on the disease outbreak, namely the corona virus (COVID19). World Health Organization (WHO) declare that this virus was a global pandemic in all countries. The various impacts that arise due to this virus cover various fields, namely health, social, political, religious, economic to resilience and security. Some of the services currently used were still focused on the health sector, namely in the form of treatment and information services related to the development of the spread of the virus. This research will develop a service that was used to identify social impacts in the community through observing community activities on social media, namely Twitter, in the form of an analysis of the public's reaction to COVID19. Through this Twitter, a data acquisition process will be carried out to obtain data related to COVID19 which will then be carried out a sentiment analysis using the Naive Bayes method so that the results of the public reaction sentiment will be obtained. The experimental result shows that prediction accuracy was 0,86. Furthermore, the results of the Recall was 0,687, the precision was 0,827 and the F-Score was 0.749

Rice is a staple cuisine for people in Asia, particularly in Indonesia. Rice reserves that are optimal provide sufficient dietary needs. The fundamental issue is that rice quality has deteriorated in recent years, resulting in losses. The traditional method for determining rice quality is to utilize human senses to detect the aroma of rice and examine the texture of the rice. In this paper, we use electronic nose dataser to predict rice quality using the Naive Bayes classifier methods; Gaussian, Bernoulli, Multinomial, and Complement. Among these four methods, Multinomial obtains an accuracy of 97%, Complement obtains an accuracy of 98%, and Gaussian obtains an accuracy of 82%, these methods showed a high ROC value of 1.00, indicating perfect classification. With a ROC value of 0.54, the Bernoulli method exhibited the least performance in classifying the rice quality by obtaining an accuracy of 52%• The managerial implications of these findings are discussed.

The abundance of event data in current software configuration management systems makes it possible to discover software process models automatically by using actual observed behavior. However, traditional process mining algorithms cannot be applied to event logs recorded in software configuration management (SCM) systems, such as SVN, because of missing activity attributes. To address this problem, a software process activity classifier is proposed to build event-activity mapping relationships from software development event streams, revealing activity attributes and associating the activity to the original SVN log. The proposed approach extracts activity from the SVN log based on semantic features and introduces a novel technique based on a naive Bayes approach to associate event activities dynamically. The approach has been applied to two real-world software development process logs, ArgoUML and jEdit , consisting of more than 80,000 events, covering development information from 1998 to 2015. With the application of our approach to such data, activities can be extracted from event logs and a classifier can be constructed for adding activity attributes to new events. The results of the classification are evaluated in terms of precision rate , recall rate, and the F-measure . Overall, two real-world software development process logs are used to validate the method, and the experimental results show that the approach can mine software process activities from SVN log events automatically and in real-time.

Epilepsy is one of the serious neurological disorder that affects about 50 million individuals globally at all ages and that can be detected from electroencephalogram (EEG) signals. This paper discusses the implementation of the Naive Bayes' classifier for the classification of epileptic events into seizure or non-seizure class. The design is carried out in Simulink environment where as it's implementation is performed on qkintex-7 FPGA hardware using HDL coder. The fixed point tool of the MATLAB is used for the conversion of floating point data into fixed point to make the hardware implementation possible. This classification is performed in real time with approximately 95 % to 100% classification accuracy.

One of the most significant techniques for improving the lifetime of Wireless sensor networks (WSN), is clustering, and the appropriate Cluster Head Selection Technique. The inefficiency in choosing an appropriate clustering approach for The Wireless Sensor Network provided may lead to a significant loss of time and energy. Data mining approaches have always been useful in solving a variety of data-based problems, but in some areas, these methods aren’t actively used, such as WSNs, so in this paper, we use one of the techniques called as Naive Bayes Classifier for the optimal cluster head selection and it is seen that this method is quite promising in improving the lifetime of nodes over the slice of time. Also, it lays the foundation that other techniques must also give promising results in improving the WSN lifetime.

These days, the healthcare enterprises procure huge amount of healthcare data that most of the times is not processed to find out the hidden facts and patterns. Data mining along with machine learning performs a prominent role in predicting the diseases. Nowadays, COVID – 19 has become a pandemic for the mankind. It is a communicable disease and it takes 12 – 24 hours in receiving the reports of diagnose. In various remote and high altitude areas and due to the exponential growth of COVID – 19 in various parts of the world, it is not feasible to perform the test on mass population. This research article describes a novel technique to diagnose coronavirus using naive bayes classifier and we hope that this technique would be useful and fruitful for the humanity and will be a great step to predict the COVID – 19.

Twitter is the well liked social media platform that has over 300 million monthly users which post 500 million tweets per day. This is the main reason why spammers use Twitter for their spiteful doings such as spreading malignant software that steals the user personal information and tweets containing fake or faulty URLs, assertively follow or un-follow users and trending fake tweets to get users attention, spread pornography advertisements. In recent years twitter has reportedly collected the data of active users and analyzed their actions, the report clearly shows that over 32 million users have interacted with server for casual information in daily basis. Hence, identifying and filtering the malicious tweets or trends that are harmful or unwanted for users is very important in current social world. This paper discusses about the ways to analyze the tweets and classify them into spam and ham based on the words involved in tweets. Although there are various machine learning and deep learning methods to classify and detect spam tweets like SVM, clustering methods and binary detection models that are used Naive Bayes classifier. Recently, twitter users are experiencing data stealing malware by accessing or visiting unnecessary spam messages or tweets. It has to be considered seriously since many people are losing money or personal information. Besides data stealing malware, fake trends also been a threat. It has to be controlled. Spammers are likely to interact with more people because of the auto-follow option.

The world is filled with information and getting the right information is a challenging task for internet users and online buyers. Recommender system helps internet users to get their information in a short span of time. It acts as an information extraction system that works behind users to perform their search easier. The recommender system comes under user’s content or item based search, similar users browsing behavior called collaborative and combination of both known as a hybrid. Here collaborative-based approach is adopted which recommends items to their users based on their past browsing behavior. In this article, the User-Item-Rating matrix is formulated concerning user personal profile, rating of the product, and reviews given by the users during their previous browsing history. In this research, user location is considered as an important attribute to group similar users. It also attempts to suppress the scalability and sparsity problems of the traditional collaborative filtering approach. So, the User-Item-Rating (UIR) matrix has considered the location, ratings and reviews for future recommendation. The Navie Bayes classifier algorithm is used to provide accurate topmost recommendations to internet users. The data set is taken from the MovieLens and IMDb database. The accuracy of the recommender system is measured based on the main metric f-measure. The experimental result has proven the improvement of the recommender system with the mentioned added attributes.

Twitter is one of the most commonly used social media, especially in Indonesia. People use Twitter social media to express their opinions every day. This allows the DISC method to be applied to find out Twitter user's character. By knowing their characters using the DISC method and Twitter, this can help parties like the HRD without spending more effort in selecting employees. Three main processes are performed in this study, data acquisition, pre-processing, and calculation process. Classification methods, namely Text Naive Bayes Classifier algorithm and K - Nearest Neighbor, are used to classified and mapping tweet data to the DISC method. As a result, the accuracy of the Naive Bayes Classifier algorithm is 34.16%, while the K – Nearest Neighbor is 28.33%. So it can be concluded that the Naive Bayes Classifier algorithm has a higher accuracy of 5.83% compared to K – Nearest Neighbor in classifying a Twitter account with TF-IDF Weighting into DISC method.

Spam or unsolicited emails that are used by spammers can cause huge loss to both the email users and the email server. Therefore, in order to detect spam emails not to enter into our mailbox, a developed email spam classification system is required. This paper proposes two popular machine learning methods, Naive Bayes Classifier and Support Vector Machine, to classify the emails into spam or ham based on the body or content of the emails. In Naive Bayes Classifier, independent words are considered as features. Support Vector Machine can be used to represent an email in vector space in which each feature means one dimension. Finally, two methods are compared in terms of precision, recall, F-measure performance metrics with the aim of finding the best method.

This study aims to analyze the Naive Bayes classifier (NBC) method and feature extraction of Local Binary Pattern (LBP) for the classification of skin diseases. NBC was chosen because it is reliable for small datasets. Whereas LBP is suitable for feature extraction because every skin disease has a distinctive texture. The combination of these two algorithms is proven to produce good accuracy in small datasets. Based on four experiments with a total of images used are 225, 180, 135 and 90 images on nine types of skin diseases, with a composition of 80% for training data and 20% for testing data resulted in an accuracy of 82.20%, 91.67%, 85.18%, and 94.44%. The best accuracy obtained with the total image used is 90, this proves that the Naive Bayes classifier has good performance for classifying images in small datasets and with a small number of datasets can save time to do the training process.

Mango Pulp Weevil (MPW) is a highly quarantined pest that is an immense problem to most countries in Asia because of its destructive nature to mango harvest. Investigation of the frequency characteristic of this pest of is an untouched area of research. This study introduces the idea of frequency detection and classification of the mating activities of MPW using acoustic sensors and a machine learning algorithm, specifically the Naive Bayes Algorithm. Soundproof chamber was built, and specimen monitoring is done during the night. Frequency acquisition was done using MEMS (Micro Electro Mechanical Systems) microphone as the acoustic sensor. The frequency is filtered and optimized by the trained Naive Bayes Algorithm. The optimal pre-mating frequency ranges from 1450Hz to 2000Hz, while the optimal mating frequency ranges from 800Hz to 950Hz, and lastly, the optimal post-mating frequency ranges from 1000Hz to 1250Hz.

Movie reviews are vital in telling the viewer whether a movie is worth watching or not. They can be classified into textual and non-textual movie reviews. While non-textual movie reviews (stars) give the user information as to how the movie fairs, textual movie reviews give the user a more detailed picture on the positive and negative aspects of the movie. Sentiment Analysis is the use of natural language processing, text analysis, biometrics and computational linguistics to identify, quantify, extract and effectively study states and subjective information given in textual format. This paper aims to conduct sentiment analysis of reviews of movies by using the Naive-Bayes algorithm and compare the results to that of a Rule-Based Approach using the AFINN-111 sentiment dictionary.

The defect is an error state, which is not according to the requirement of the given software. The error in the software system can affect the efficiency and reliability of the software therefore, early prediction of software defects can save the companies from a bigger loss. For this purpose, multiple algorithms have been proposed in the past decade. Still, the accuracy achieved is not suitable for the market demand which means that a lot of improvement needs to be done. In this paper, we have proposed an efficient and reliable framework for the prediction of the software defects. The framework is divided into three main steps which involves data preprocessing steps that includes: removal of noise and normalization. After that, feature extraction is done using correlation-based analysis and relevant features are selected, and finally applies machine learning models including naive Bayes and linear regression. Results show that the proposed method can reach an accuracy of 98.7% using Naive Bayes algorithm. Consequently, the significance of the proposed technique is that it will lower the cost of maintenance and reduce the code complexity by predicting the defects earlier in the software systems that will help the developers to remove those defects and ultimately improves the software quality before the deployment phase.

Papaya is one of the tropical fruits that is grown in Indonesia. The weather condition in Indonesia cause it to be attacked by pest and disease. The farmers have difficulty identifying them due to a lack of knowledge and obtaining information from experts. In this study, an expert system was developed to detect papaya disease. Expert knowledge is applied to the system so the farmer can use it to identify the condition without an expert. It is usually represented in the linguistic form, was converted into numbers using fuzzy reasoning, Triangular Fuzzy Number (TFN) membership function. Then the expert knowledge was processed using the Naive Bayes Classifier to obtain the results of the disease classification. The test was also performed using forward chaining search methods. The accuracy was 88% for FNBC and 90% for forward chaining compared to expert knowledge.

The presence of retrieval information and sentiment analysis may quicken the evaluation of the lecturers and the result of an ongoing issue during the course can be known directly and accurately. This evaluation is conducted every semester by completing the questionnaire. The results of the sentiment analysis are used as the evaluation for lecturer teaching improvement based on the required search results. Currently, the lecturer's assessment is still done manually (with hardcopy) by the LPMI department. Information retrieval is the process of taking users' search requests (queries) according to the likelihood of relevance to the input query. The generalized Vector Space Model (GVSM) uses vector space concepts in determining the relevance of the user input (query) to the document set. Sentiment analysis is the process of document classification. In this research, the sentiment analysis was divided into positive, negative, and neutral classes using the Naive Bayes Classifier (NBC) method. The classification process begins by dividing the document into training data and test data. The search results using the 43 most commented on lecturers rated with 5 keywords using the GVSM had a precision rate of 100% and the recall of 100%, while NBC's sentiment analysis had a precision or truth rate of 72% and an error rate of 28% with a long time of searching and sentiment analysis averaged 21.8 seconds. Based on that data, it can be concluded that the search and sentiment analysis applications can run properly and appropriately.