Document Classification System Research Articles

Design of an Automatic Classification System for Educational Reform Documents Based on Naive Bayes Algorithm

With the continuous deepening of educational reform, a large number of educational policies, programs, and research reports have emerged, bringing a heavy burden of information processing and management to educators. Traditional manual classification and archiving methods are inefficient and susceptible to subjective factors. Therefore, an automated method is needed to quickly and accurately classify and archive documents into their respective categories. Based on this, this paper proposes a design of an automatic document classification system for educational reform based on the Naive Bayes algorithm to address the challenges of document management in the education field. Firstly, the relevant literature and document data in the field of educational reform are collected and organized to establish an annotated dataset for model detection. Secondly, the raw data are preprocessed by cleaning and transforming the original text data to make them more suitable for input into machine learning algorithms. Thirdly, various algorithms are trained and selected to determine the best algorithm for classifying educational reform documents. Finally, based on the determined algorithm, a corresponding classification software is designed to automatically classify and archive educational reform documents for analysis. Through experimental evaluation and result analysis, this research demonstrates the effectiveness and accuracy of the education reform document automatic classification system based on the Naive Bayes algorithm. This method can efficiently classify a large number of documents into their respective categories quickly and accurately, thereby improving the efficiency of educators and their information management capabilities. In the future, further exploration of feature extraction methods and machine learning algorithms can be conducted to optimize the classification performance and apply this method to practical management and decision-making in the education field.

The development of robotics courses for young children under vector space model.

Robotics education is important in training children's thinking, practical, and innovation abilities. It is significant to stimulate children's interest in learning and improve their learning quality. The existing research has not paid attention to the application of robotics education in children. It is necessary to stimulate children's interest in learning. This paper will take senior kindergarten students as the research object. It analyzes the application of the Vector Space Model (VSM) in robotics course development. The research and development of children's robotics courses incorporating Artificial Intelligence technology are based on the survey results of robotics courses offered by 38 kindergartens in Baoji City. An automatic document classification system based on VSM is designed to assist in compiling robotics teaching textbooks. Finally, the system performance is tested. The results show that about 24% of kindergartens offer robotics courses, and 76% do not. Besides, 70.14% of teachers support the establishment of children's robotics courses. The classification effect of the VSM system is better than that of Chinese documents. This system performs better than the automatic document classification system based on Term Frequency-Inverse Document Frequency. Its classification accuracy, recall, and F1 value are all above 85%. The development of the robotics course provides a better teaching environment for teaching young children about AI and robots. The robotics education discussed in this paper is a hot spot in the current curriculum reform and is of great significance to the development and innovation in early childhood education.

Quantum computing and machine learning for Arabic language sentiment classification in social media

With the increasing amount of digital data generated by Arabic speakers, the need for effective and efficient document classification techniques is more important than ever. In recent years, both quantum computing and machine learning have shown great promise in the field of document classification. However, there is a lack of research investigating the performance of these techniques on the Arabic language. This paper presents a comparative study of quantum computing and machine learning for two datasets of Arabic language document classification. In the first dataset of 213,465 Arabic tweets, both classic machine learning (ML) and quantum computing approaches achieve high accuracy in sentiment analysis, with quantum computing slightly outperforming classic ML. Quantum computing completes the task in approximately 59 min, slightly faster than classic ML, which takes around 1 h. The precision, recall, and F1 score metrics indicate the effectiveness of both approaches in predicting sentiment in Arabic tweets. Classic ML achieves precision, recall, and F1 score values of 0.8215, 0.8175, and 0.8121, respectively, while quantum computing achieves values of 0.8239, 0.8199, and 0.8147, respectively. In the second dataset of 44,000 tweets, both classic ML (using the Random Forest algorithm) and quantum computing demonstrate significantly reduced processing times compared to the first dataset, with no substantial difference between them. Classic ML completes the analysis in approximately 2 min, while quantum computing takes approximately 1 min and 53 s. The accuracy of classic ML is higher at 0.9241 compared to 0.9205 for quantum computing. However, both approaches achieve high precision, recall, and F1 scores, indicating their effectiveness in accurately predicting sentiment in the dataset. Classic ML achieves precision, recall, and F1 score values of 0.9286, 0.9241, and 0.9249, respectively, while quantum computing achieves values of 0.92456, 0.9205, and 0.9214, respectively. The analysis of the metrics indicates that quantum computing approaches are effective in identifying positive instances and capturing relevant sentiment information in large datasets. On the other hand, traditional machine learning techniques exhibit faster processing times when dealing with smaller dataset sizes. This study provides valuable insights into the strengths and limitations of quantum computing and machine learning for Arabic document classification, emphasizing the potential of quantum computing in achieving high accuracy, particularly in scenarios where traditional machine learning techniques may encounter difficulties. These findings contribute to the development of more accurate and efficient document classification systems for Arabic data.

The Implementation of Bantu Warga Apps and Metabase for Spatial Data Processing In Surabaya

Civil registration and vital statistics (CRVS) is known as an essential supporting system for effective policy-making and service delivery. Its primary purpose is establishing an individual's legal identity and vital events to ensure all citizens get their rights well. Furthermore, an advanced level of CRVS is equipped with a forecasting system to serve more useful data. This paper discusses the potential benefits and challenges of using Metabase and Bantu Warga as civil ministry support systems. The spatial data visualization system using open-source Metabase ran well and resulted in many visualization geospatial maps like birth, marriage and divorce, education, and employment. The forecasting autoregression model configuration and cumulative sum dataset reach the best error result in 1056618. The other aspects, like the self-isolation management system, civil documents classification system, and OCR system, have a good result.

Development of Legal Document Classification System Based on Support Vector Machine

This paper was prepared while developing text classification system for legal documents, especially those that issued by Legislative Assembly of Perm Krai. The problem in question is a lack of solutions that meet regional requirements, the main of which is the classification used in region. The research that evaluates applications of Natural Language Processing models is conveyed. The primary result of the study is the actual applicability of Support Vector Machine (SVM) to preprocessed legal document categorization. There were a server-side API constructed to perform the task, and a server-side models pre-trained of which SVM is favored.

Optimizing Sentiment Big Data Classification Using Multilayer Perceptron

Internet-based platforms such as social media have a great deal of big data that is available in the shape of text, audio, video, and image. Sentiment Analysis (SA) of this big data has become a field of computational studies. Therefore, SA is necessary in texts in the form of messages or posts to determine whether a sentiment is negative or positive. SA is also crucial for the development of opinion mining systems. SA combines techniques of Natural Language Processing (NLP) with data mining approaches for developing inelegant systems. Therefore, an approach that can classify sentiments into two classes, namely, positive sentiment and negative sentiment is proposed. A Multilayer Perceptron (MLP) classifier has been used in this document classification system. The present research aims to provide an effective approach to improving the accuracy of SA systems. The proposed approach is applied to and tested on two datasets, namely, a Twitter dataset and a movie review dataset; the accuracies achieved reach 85% and 99% respectively.

Automatic classification of document resources based on Naive Bayesian classification algorithm

World Wide Web has become big as the amount of documents collection is increasing rapidly. The automatic classification of document resources based on Naive Bayesian classification algorithm is detailed in this paper. Firstly, this paper introduces the relevant theories of naive Bayes classification and the automatic document classification system. Then, a massive network academic document automatic classification system is designed and implemented. The system uses modular design, including academic document automatic capture module, academic document word document matrix processing module, ontology integration module and semantic driven classification module. Finally, based on the Naive Bayesian classification algorithm, the training set of 12 categories preset is utilized in the professional classification directory of the Ministry of education.. Experiments show that the naive Bayesian classification algorithm can effectively complete the automatic capture, processing and classification of massive academic documents, which can not only improve the classification accuracy, but also reduce the running time of automatic classification. It solves the problems of the integration of two heterogeneous ontology libraries and also the problem that the traditional word vector space cannot meet people's needs for semantic classification.

RESEARCH OF THE TEXT PROCESSING METHODS IN ORGANIZATION OF ELECTRONIC STORAGES OF INFORMATION OBJECTS

The subject matter of the article is electronic storage of information objects (IO) ordered by specified rules at the stage of accumulation of qualification thesis and scientific work of the contributors of the offered knowledge exchange system provided to the system in different formats (text, graphic, audio). Classified works of contributors of the system are the ground for organization of thematic rooms for discussion to spread scientific achievements, to adopt new ideas, to exchange knowledge and to look for employers or mentors in different countries. The goal of the work is to study the libraries of text processing and analysis to speed-up and increase accuracy of the scanned text documents classification in the process of serialized electronic storage of information objects organization. The following tasks are: to study the text processing methods on the basis of the proposed generalized model of the system of classification of scanned documents with the specified location of the block of text processing and analysis; to investigate the statistics of change in the execution time of the developed parallel modification of the methods of the word processing module for the system with shared memory for collections of text documents of different sizes; analyze the results. The methods used are the following: parallel digital sorting methods, methods of mathematical statistics, linguistic methods of text analysis. The following results were obtained: in the course of the research fulfillment the generalized model of the scanned documents classification system that consist of image processing unit and text processing unit that include unit of the scanned image previous processing; text detection unit; previous text processing; compiling of the frequency dictionary; text proximity detection was offered. Conclusions: the proposed parallel modification of the previous text processing unit gives acceleration up to 3,998 times. But, at a very high computational load (collection of 18144 files, about 1100 MB), the resources of an ordinary multiprocessor-based computer with the shared memory obviously is not enough to solve such problems in the mode close to real time.

Identification of drug-related problems followed by clinical pharmacist interventions in an outpatient pharmacotherapy clinic.

Pharmacotherapy is an essential strategy for the treatment of many medical conditions especially chronic disease and often involves multiple medications being used simultaneously. Increasing the use of medications may pose some challenges to safe and effective drug therapy and if not identified and prevented by the pharmacists eventually can lead to drug-related problems (DRPs). The present study aimed to examine the incidence of DRPs in Iranian patients and to evaluate patients' adherence to the clinical pharmacist interventions as well as the physicians' acceptance of these recommendations. This study was conducted in a university-affiliated outpatient pharmacotherapy clinic over a 22-month period. Patients aged 18years and older with at least one chronic disease receiving at least four medications were included in the study. The patients were interviewed by a clinical pharmacist for comprehensive medication review. DRPs were identified using the DOCUMENT classification system. Recommendations were provided by the clinical pharmacist including interventions involving patient and/or physician to resolve DRPs. The patients were followed up after 2 weeks to evaluate their compliance and physician acceptance of clinical pharmacist recommendations. Two hundred patients were included in this study. Overall, 875 DRPs were identified with an average of 4.37 per patient. The most prevalent DRPs were related to patient education or information (22.8%), undertreated indications (17.4%) and patient compliance (17.2%). The most common drugs associated with DRPs were alimentary and metabolism (22.2% of DRPs) followed by the cardiovascular system (19.2%) and nervous system (9.6%) medications. The DRP incidence correlated with gender only and was higher in females (p=0.019). The clinical pharmacist provided 912 interventions with an average of 4.56 and 1.04 interventions per patient and per DRPs respectively. Patient education (41.3%), medication initiation or discontinuation (24.5%), and non-pharmacological interventions (12.9%) were the most common clinical pharmacist interventions. Out of 912 interventions, 665 were followed up, out of which 427 were patient dependent and 228 involved physicians. The patient's compliance with clinical pharmacist recommendations was 81.2%. The physician acceptance rate of the recommendations was 44.1%. The study shows that especially designed services such as pharmacotherapy clinics running by clinical pharmacists are necessary to detect and resolve DRPs in an effective way. The high compliance rate of the patients indicates patients' confidence in the clinical pharmacist services provided in the pharmacotherapy clinic. The low acceptance rate of the physicians highlights the need to improve interprofessional collaboration between clinical pharmacists and physicians in an outpatient setting.

An Automated Knowledge Mining and Document Classification System with Multi-model Transfer Learning

Service manual documents are crucial to the engineering company as they provide guidelines and knowledge to service engineers. However, it has become inconvenient and inefficient for service engineers to retrieve specific knowledge from documents due to the complexity of resources. In this research, we propose an automated knowledge mining and document classification system with novel multi-model transfer learning approaches. Particularly, the classification performance of the system has been improved with three effective techniques: fine-tuning, pruning, and multi-model method. The fine-tuning technique optimizes a pre-trained BERT model by adding a feed-forward neural network layer and the pruning technique is used to retrain the BERT model with new data. The multi-model method initializes and trains multiple BERT models to overcome the randomness of data ordering during the fine-tuning process. In the first iteration of the training process, multiple BERT models are being trained simultaneously. The best model is then selected for the next phase of the training process with another two iterations and the training processes for other BERT models will be terminated. The performance of the proposed system has been evaluated by comparing with two robust baseline methods, BERT and BERT-CNN. Experimental results on a widely used Corpus of Linguistic Acceptability (CoLA) dataset have shown that the proposed techniques perform better than these baseline methods in terms of accuracy and MCC score.

Analyzing Newspaper Articles for Text-Related Data for Finding Vulnerable Posts Over the Internet That Are Linked to Terrorist Activities

One of the most critical activities of revealing terrorism-related information is classifying online documents.The internet provides consumers with a variety of useful knowledge, and the volume of web material is increasingly growing. This makes finding potentially hazardous records incredibly difficult. To define the contents, merely extracting keywords from records is inadequate. Many methods have been studied so far to develop automatic document classification systems, they are mainly computational and knowledge-based approaches. due to the complexities of natural languages, these approaches do not provide sufficient results. To fix this shortcoming, we given approach of structure dependent on the WordNet hierarchy and the frequency of n-gram data that employs word similarity. Using four different queries terms from four different regions, this approach was checked for the NY Times articles that were sampled. Our suggested approach successfully removes background words and phrases from the document recognizes connected to terrorism texts, according to experimental findings.

Система классификации документов с маркшейдерскими данными

All enterprises engaged in exploration activities on the territory of the Russian Federation, are facing the need to formulate tasks for the mine surveyor service and control their execution. It affects enterprise’s workflow process. Due to it, a problem of organization of efficient document processing in electronic document management systems (timely identification of documents containing mine surveying data) takes place. The article presents possible solution of this problem – automated document classification system into EDMS in the form of optional add-on for 1C:Document Management. Within the classification system creation a preprocessing script for primary document texts, including cleaning, lemmatization, stop words removing, as well as preparation of input features for the classifier were developed and implemented. Applicability of different machine learning algorithms to solution of considering classification problem was studied, the values of hyperparameters providing the highest value of the ROC AUC metric were determined. The quality of all obtained models was assessed using metrics Precision, Recall and F-measures, the stability of the classification quality to changes in the input data was investigated. The identified problem of instability of classification results was solved by building and implementing a machine learning model in the form of ensemble of classifiers. Classification model (an ensemble of clusters) was tested on the set of real documents of Gazprom nedra Ltd; classiffication quality on the test sample by ROC AUC metric was 0,91. Except the classification module itself, developed system contains the storage database for learning outcomes, function library for organization of work with the database and API interfaces allowing to process classification requests, coming from external systems. These API interfaces, in particular, implement the ability to load saved trained models, validate data coming from external systems, preprocess input text documents, train new models and assess their quality, save both trained models and the results of their testing. Also the possibility of the additional training of the models on a new data was realized.

Bengali text document categorization based on very deep convolution neural network

In recent years, the amount of digital text contents or documents in the Bengali language has increased enormously on online platforms due to the effortless access of the Internet via electronic gadgets. As a result, an enormous amount of unstructured data is created that demands much time and effort to organize, search or manipulate. To manage such a massive number of documents effectively, an intelligent text document classification system is proposed in this paper. Intelligent classification of text document in a resource-constrained language (like Bengali) is challenging due to unavailability of linguistic resources, intelligent NLP tools, and larger text corpora. Moreover, Bengali texts are available in two morphological variants (i.e., Sadhu-bhasha and Cholito-bhasha) making the classification task more complicated. The proposed intelligent text classification model comprises GloVe embedding and Very Deep Convolution Neural Network (VDCNN) classifier. Due to the unavailability of standard corpus, this work develops a large Embedding Corpus (EC) containing 969,000 unlabelled texts and Bengali Text Classification Corpus (BDTC) containing 156,207 labelled documents arranged into 13 categories. Moreover, this work proposes the Embedding Parameters Identification (EPI) Algorithm, which selects the best embedding parameters for low-resource languages (including Bengali). Evaluation of 165 embedding models with intrinsic evaluators (semantic & syntactic similarity measures) shows that the GloVe model is more suitable (regarding Spearman & Pearson correlation) than other embeddings (Word2Vec, FastText, m-BERT) in Bengali text. Experimental results on the test dataset confirm that the proposed GloVe + VDCNN model outperformed (achieving the highest 96.96% accuracy) the other classification models and existing methods to perform the Bengali text classification task.

ICS Code Automatic Classification(ICAC) in Standard Documents Using Machine Learning Algorithms

4차 산업혁명 이후, 표준의 범위가 확대되어 가고 있다. 새로운 용어나 유사한 용어들이 표준의 제목에 사용됨에 따라, 표준문서의 분류 및 검색이 복잡해지고 있다. 현재, 표준문서들의 효율적인 검색 및 관리를 위해 국제표준화기구인 ISO에서 운영하는 국제표준분류체계(ICS) 코드가 있으나, 아직도 ISO와 IEC를 제외한 다른 표준 개발 기구들이 ICS 코드체계를 채택하지 않은 설정이다. 더욱이 ICS 코드가 필요에 따라 새로이 수정되면, 이에 따라 ICS코드를 할당받은 기존 표준들도 새로이 ICS 코드를 재할당 받아야 한다. 그러므로 수정되는 ICS 코드 체계에 따라 자동적으로 표준문서를 분류할 수 있는 시스템이 필요한 실정이다. 본 연구는 이러한 표준 문서 분류 시스템을 구축하기 위하여 연구단계를 두 단계로 나누었다. 첫 번째 단계로, 현재의 ICS가 있는 표준들을 가지고 ICS 할당 시스템을 만들어 정확도를 검증하는 것이고, 두 번째 단계로, ICS 코드를 채택하지 않은 표준문서들에 ICS 코드를 할당하도록 하는 것이다. 특별히, 본 논문은 위에서 언급한 첫 번째 단계에 해당하는ICS 분류 및 할당 시스템을 머신러닝 알고리즘을 이용한 구조를 제안하고 이를 구현한 것을 보이는 것이다. 최선의 알고리즘을 선택하여 표준문서들의 ICS 코드를 분류하기 위해 잘 알려진 GRU 알고리즘을 비롯한 여러 알고리즘을 가장 최적의 결과를 보이는 파라미터를 사용하여 시험하였다. 결과적으로 머신러닝 알고리즘 보다 단어의 종속성을 학습하여 분류를 진행하는 딥러닝 알고리즘이 높은 성능을 보였으며, 딥러닝 알고리즘 중 GRU 알고리즘이 가장 높은 성능을 보였다.Since the Fourth Industrial Revolution, the scope of standards has been expanding. Classification and retrieval of standard documents are becoming complicated as new terms or similar terms are used in the title of the standard. Currently, there is an International Classification for Standards (ICS) code operated by ISO, the International Organization for Standardization, for the efficient search and management of standard documents, but it is still not adopted by other standard development organizations except ISO and IEC. Furthermore, if the ICS code is newly modified as needed, existing standards will also be required to reallocate the new ICS code accordingly. Therefore, a system is needed to automatically classify standard documents according to the ICS code scheme being modified. This work has been divided into two steps to build this standard document classification system. The first step is to create an ICS allocation system with the current ICS standards to verify accuracy, and the second step is to assign ICS codes to standard documents that do not adopt ICS codes. Specifically, this paper proposes a structure using machine learning algorithms and performs ICS classification and allocation systems corresponding to the first step mentioned above. To classify the ICS code of standard documents by selecting the best algorithm, several algorithms, including the well-known GRU algorithm, were tested using parameters with the best results. As a result, deep learning algorithms that learn the dependencies of words to proceed with classification showed higher performance than machine learning algorithms, and GRU algorithms showed the highest performance among deep learning algorithms.

What is in those compact shelves? Auditing and quantifying a government documents collection

As academic libraries evolve, the complexity and breadth of federal government documents collections pose challenges to librarians. These materials are often shelved under the Superintendent of Documents classification system (SuDoc) and, depending on the library, may be only partially cataloged. The collection’s monolithic nature may complicate projects to catalog, promote, move, or deaccession materials. Using a collection inventory to define mini collections by SuDoc area helps quantify these large collections for academic librarians. The collection inventory system described in this article can be customized and applied beyond the scope of government information. Its approach informs how we assess and build collections, how we inherit collections, and how we work within established systems.

Advanced Applications on Bilingual Document Analysis and Processing Systems

Today, rapid digitization requires efficient bilingual non-image and image document classification systems. Although many bilingual NLP and image-based systems provide solutions for real-world problems, they primarily focus on text extraction, identification, and recognition tasks with limited document types. This article discusses a journey of these systems and provides an overview of their methods, feature extraction techniques, document sets, classifiers, and accuracy for English-Hindi and other language pairs. The gaps found lead toward the idea of a generic and integrated bilingual English-Hindi document classification system, which classifies heterogeneous documents using a dual class feeder and two character corpora. Its non-image and image modules include pre- and post-processing stages and pre-and post-segmentation stages to classify documents into predefined classes. This article discusses many real-life applications on societal and commercial issues. The analytical results show important findings of existing and proposed systems.

Characterization of drug-related problems and associated factors in ambulatory patients in China.

This study aimed to investigate the prevalence and the type of drug-related problems (DRPs) in ambulatory patients and identify factors that may be associated with risk of DRPs. Consecutive patients were enrolled from pharmacist outpatient clinics between January 2018 and June 2019. The pharmacists performed a comprehensive assessment of the patient's drug therapy. The DRPs and recommendations were evaluated using the DOCUMENT classification system. The study population consisted of 248 patients with a mean age of 72.55±6.29. The patients had a mean of 7.55±4.72 ongoing medications during patients' routine clinic visits. A total of 1188 DRPs were identified during the study period. An average of 4.79 DRPs per patient was detected. Sixty-two different traditional Chinese patent medicines (TCPMs) contributed to 102 DRPs. Drug selection (24.9%) was the most common DRP followed by under treated (24.2%) and monitoring needed (24.2%). The number of medications taken was the significant factor for DRPs. Pharmacists made 1092 recommendations to address the DRPs (an average 0.92 recommendations per DRP). A change in therapy was the most common recommendation (43.6%), followed by the category 'monitoring' (28.6%). The overall acceptance rate of clinical pharmacist recommendations was 88.7%. More than a half (51.6%) of all interventions were assigned a moderate level of clinical significance. Drug-related problems were commonly observed among ambulatory Chinese patients. Clinical pharmacists had a valuable role to play in identifying and solving the DRPs.

An Enhanced Document Referential, Classification And Retention System using Muiltinomial Naive Bayes Algorithm

An Enhanced Document Referential, Classification And Retention System using Muiltinomial Naive Bayes Algorithm - written by O.O. Anyiam , F.E. Onuodu , L.N. Onyejegbu published on 2020/01/21 download full article with reference data and citations

A New Similarity Measure for Document Classification and Text Mining

Accurate, efficient and fast processing of textual data and classification of electronic documents have become an important key factor in knowledge management and related businesses in today’s world. Text mining, information retrieval, and document classification systems have a strong positive impact on digital libraries and electronic content management, e-marketing, electronic archives, customer relationship management, decision support systems, copyright infringement, and plagiarism detection, which strictly affect economics, businesses, and organizations. In this study, we propose a new similarity measure that can be used with k-nearest neighbors (k-NN) and Rocchio algorithms, which are some of the well-known algorithms for document classification, information retrieval, and some other text mining purposes. We have tested our novel similarity measure with some structured textual data sets and we have compared the results with some other standard distance metrics and similarity measures such as Cosine similarity, Euclidean distance, and Pearson correlation coefficient. We have obtained some promising results, which show that this proposed similarity measure could be alternatively used within all suitable algorithms, methods, and models for text mining, document classification, and relevant knowledge management systems.
 Keywords: text mining, document classification, similarity measures, k-NN, Rocchio algorithm

A Hybrid Hindi Printed Document Classification System Using SVM and Fuzzy

This article introduces a new advanced tri-layered segmentation and bi-leveled-classifier-based Hindi printed document classification system, which categorizes imaged documents into pre-defined mutually exclusive categories by using SVM and Fuzzy matching at character and document classifications, respectively. During training, the improved and noise-free image is segmented into lines and words by profiling. Then it obtains Shirorekha Less (SL) isolated characters along with upper, left and right modifier components from the SL words. These components use their locations and inter character-modifier component distance to get associate with their corresponding characters only. Further, confidence values of all characters are calculated with SVM training and all characters are mapped into Romanized labels to generate the words. Finally, documents are classified by Fuzzy based matching of Romanized detected words and predefined classes. The average execution times of SL characters are 0.22675 sec. and 0.20375 sec. and classification accuracy are 74.61% and 80.73% for training and testing, respectively.