Pub Date : 2018-12-01DOI: 10.1109/ICCITECHN.2018.8631911
Orvila Sarker, Mehedi Hasan, N. M. Istiak Chowdhury
The main challenge in any online banking system is to secure information that stored in web server, also providing extra degree of privacy to individual bank client during every transaction. Unfortunately, traditional systems do not provide the scope to hide an individual client's transaction information in the server. As a result, there is a chance of being cheated by any bank employee or the authority who are responsible behind running the system. In this work we propose a method to design a secure web server using RC4 algorithm for online banking system. In this system, we have introduced a secure money transaction process by introducing a secrete key during each transaction made by the client or user. Only the valid client or authorized user can able to access his information. For this he has to make a registration to the system by providing some basic information about himself. But it'a really important to memorize the encryption key which provides both the encryption & decryption. If a user forgets this key, he will not be able to make any transaction.
{"title":"A Secure Web Server for E- Banking","authors":"Orvila Sarker, Mehedi Hasan, N. M. Istiak Chowdhury","doi":"10.1109/ICCITECHN.2018.8631911","DOIUrl":"https://doi.org/10.1109/ICCITECHN.2018.8631911","url":null,"abstract":"The main challenge in any online banking system is to secure information that stored in web server, also providing extra degree of privacy to individual bank client during every transaction. Unfortunately, traditional systems do not provide the scope to hide an individual client's transaction information in the server. As a result, there is a chance of being cheated by any bank employee or the authority who are responsible behind running the system. In this work we propose a method to design a secure web server using RC4 algorithm for online banking system. In this system, we have introduced a secure money transaction process by introducing a secrete key during each transaction made by the client or user. Only the valid client or authorized user can able to access his information. For this he has to make a registration to the system by providing some basic information about himself. But it'a really important to memorize the encryption key which provides both the encryption & decryption. If a user forgets this key, he will not be able to make any transaction.","PeriodicalId":355984,"journal":{"name":"2018 21st International Conference of Computer and Information Technology (ICCIT)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131755422","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-12-01DOI: 10.1109/ICCITECHN.2018.8631970
S. A. Shahriyar, Kazi Md. Rokibul Alam, S. Roy, Y. Morimoto
Single label image classification has been promisingly demonstrated using Convolutional Neural Network (CNN). However, how this CNN will fit for multi-label images is still difficult to solve. It is mainly difficult due to lack of multi-label training image data and high complexity of latent obj ect layouts. This paper proposes an approach for classifying multi-label image by a trained single label classifier using CNN with objectness measure and selective search. We have taken two established image segmentation techniques for segmenting a multi-label image into some segmented images. Then we have forwarded the images to our trained CNN and predicted the labels of the segmented images by generalizing the result. Our single-label image classifier gives 87% accuracy on CIFAR-10 dataset. Using objectness measure with CNN gives us 51 % accuracy on a multi-label dataset and gives up to 57% accuracy using selective search both considering top-4 labels that is significantly good for a simple approach rather than a complex approach for multi-label classification using CNN.
{"title":"An Approach for Multi Label Image Classification Using Single Label Convolutional Neural Network","authors":"S. A. Shahriyar, Kazi Md. Rokibul Alam, S. Roy, Y. Morimoto","doi":"10.1109/ICCITECHN.2018.8631970","DOIUrl":"https://doi.org/10.1109/ICCITECHN.2018.8631970","url":null,"abstract":"Single label image classification has been promisingly demonstrated using Convolutional Neural Network (CNN). However, how this CNN will fit for multi-label images is still difficult to solve. It is mainly difficult due to lack of multi-label training image data and high complexity of latent obj ect layouts. This paper proposes an approach for classifying multi-label image by a trained single label classifier using CNN with objectness measure and selective search. We have taken two established image segmentation techniques for segmenting a multi-label image into some segmented images. Then we have forwarded the images to our trained CNN and predicted the labels of the segmented images by generalizing the result. Our single-label image classifier gives 87% accuracy on CIFAR-10 dataset. Using objectness measure with CNN gives us 51 % accuracy on a multi-label dataset and gives up to 57% accuracy using selective search both considering top-4 labels that is significantly good for a simple approach rather than a complex approach for multi-label classification using CNN.","PeriodicalId":355984,"journal":{"name":"2018 21st International Conference of Computer and Information Technology (ICCIT)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132946812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-12-01DOI: 10.1109/ICCITECHN.2018.8631969
Ashraful Hossain Howlader, M. S. Islam, A. Islam
A systematic computer simulation has been carried out to find out the exclusive phonon properties of both pristine and vacancy defected (10,0) semiconductor zigzag silicon nanotube for the first time. It is found that phonons are scattered into other phonon states due to vacancy. Vacancy generates degenerate phonon branches. The simulated phonon density of states shows softening of high-frequency phonons. Quite significant reduction in the phonon transmission is observed over the whole frequency spectrum with the introduction of vacancy. Quasi ballistic phonon conduction is noticed instead of the presence of vacancy for low-frequency region. Again, high-frequency phonon localization is found in vacancy defected nanotube. The thermal conductivity decreases in a large amount with only 1 % vacancy. Moreover, entropy of the vacancy defected system is examined.
{"title":"A Study on Phonon Transmission of (10,0) Silicon Nanotube with Atomic Vacancies","authors":"Ashraful Hossain Howlader, M. S. Islam, A. Islam","doi":"10.1109/ICCITECHN.2018.8631969","DOIUrl":"https://doi.org/10.1109/ICCITECHN.2018.8631969","url":null,"abstract":"A systematic computer simulation has been carried out to find out the exclusive phonon properties of both pristine and vacancy defected (10,0) semiconductor zigzag silicon nanotube for the first time. It is found that phonons are scattered into other phonon states due to vacancy. Vacancy generates degenerate phonon branches. The simulated phonon density of states shows softening of high-frequency phonons. Quite significant reduction in the phonon transmission is observed over the whole frequency spectrum with the introduction of vacancy. Quasi ballistic phonon conduction is noticed instead of the presence of vacancy for low-frequency region. Again, high-frequency phonon localization is found in vacancy defected nanotube. The thermal conductivity decreases in a large amount with only 1 % vacancy. Moreover, entropy of the vacancy defected system is examined.","PeriodicalId":355984,"journal":{"name":"2018 21st International Conference of Computer and Information Technology (ICCIT)","volume":"140 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116421302","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-12-01DOI: 10.1109/ICCITECHN.2018.8631956
Kazi Masudul Alam, Md. Masum Moral, Kazi Shah Nawaz Ripon, Binayak Ray, A. Akther
Notice delivery is an essential activity to distribute important information at different levels of academic institutions of Bangladesh. Most of the academic institutions in Bangladesh use central notice board or mail man to distribute paper based notice to different levels of stakeholders. Due to the lack of synchronization, many a time, stakeholders are not well informed about several activities and events that are planned in an institute. As a result, participation in non-academic activities does not demonstrate good development. In order to improve this issue, we propose an online based publisher-subscriber network to deliver notice to academic stakeholders of any institute. This application improves the usual model by introducing hierarchy based group wise notice dissemination as well as supports multimedia (i.e. text, pdf, image, video, audio, etc.) content delivery. We have developed the proposed system and applied it in a University setup to demonstrate the efficacy of the proposed model.
{"title":"Applying Online-Based Publisher-Subscriber Network to Distribute Notice in Academic Institutions of Bangladesh","authors":"Kazi Masudul Alam, Md. Masum Moral, Kazi Shah Nawaz Ripon, Binayak Ray, A. Akther","doi":"10.1109/ICCITECHN.2018.8631956","DOIUrl":"https://doi.org/10.1109/ICCITECHN.2018.8631956","url":null,"abstract":"Notice delivery is an essential activity to distribute important information at different levels of academic institutions of Bangladesh. Most of the academic institutions in Bangladesh use central notice board or mail man to distribute paper based notice to different levels of stakeholders. Due to the lack of synchronization, many a time, stakeholders are not well informed about several activities and events that are planned in an institute. As a result, participation in non-academic activities does not demonstrate good development. In order to improve this issue, we propose an online based publisher-subscriber network to deliver notice to academic stakeholders of any institute. This application improves the usual model by introducing hierarchy based group wise notice dissemination as well as supports multimedia (i.e. text, pdf, image, video, audio, etc.) content delivery. We have developed the proposed system and applied it in a University setup to demonstrate the efficacy of the proposed model.","PeriodicalId":355984,"journal":{"name":"2018 21st International Conference of Computer and Information Technology (ICCIT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125485977","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-12-01DOI: 10.1109/ICCITECHN.2018.8631906
M. Ali, Al Maruf Hassan
The education sector has a vital role in the development of a country. Therefore, new technologies are introducing in this sector to make robust teaching and learning paradigms. Internet of Things (IoT)- a new technology becoming popular in the teaching method and it helps to make the classroom more interactive which is most important to establish robust learning and teaching process. In this paper, we develop applications for voice-enabled IoT device which can interact with teachers and students on textbook contexts. Our proposed model uses Artificial Intelligence (AI) to know users voice phrases and Machine Learning (ML) technology to learn new voice phrases. We present two case studies followed by National Textbook and Curriculum of Bangladesh to verify our proposed model. We simulate our applications with real voice data to verify it. In the last section, we discuss that how to improve current IoT model in the future with other databases for sensible results.
{"title":"Developing Applications for Voice Enabled IoT Devices to Improve Classroom Activities","authors":"M. Ali, Al Maruf Hassan","doi":"10.1109/ICCITECHN.2018.8631906","DOIUrl":"https://doi.org/10.1109/ICCITECHN.2018.8631906","url":null,"abstract":"The education sector has a vital role in the development of a country. Therefore, new technologies are introducing in this sector to make robust teaching and learning paradigms. Internet of Things (IoT)- a new technology becoming popular in the teaching method and it helps to make the classroom more interactive which is most important to establish robust learning and teaching process. In this paper, we develop applications for voice-enabled IoT device which can interact with teachers and students on textbook contexts. Our proposed model uses Artificial Intelligence (AI) to know users voice phrases and Machine Learning (ML) technology to learn new voice phrases. We present two case studies followed by National Textbook and Curriculum of Bangladesh to verify our proposed model. We simulate our applications with real voice data to verify it. In the last section, we discuss that how to improve current IoT model in the future with other databases for sensible results.","PeriodicalId":355984,"journal":{"name":"2018 21st International Conference of Computer and Information Technology (ICCIT)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115231432","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-12-01DOI: 10.1109/ICCITECHN.2018.8631968
Samrat Kumar Dey, A. Hossain, M. Rahman
Diabetes is caused due to the excessive amount of sugar condensed into the blood. Currently, it is considered as one of the lethal diseases in the world. People all around the globe are affected by this severe disease knowingly or unknowingly. Other diseases like heart attack, paralyzed, kidney disease, blindness etc. are also caused by diabetes. Numerous computer-based detection systems were designed and outlined for anticipating and analyzing diabetes. Usual identifying process for diabetic patients needs more time and money. But with the rise of machine learning, we have that ability to develop a solution to this intense issue. Therefore we have developed an architecture which has the capability to predict where the patient has diabetes or not. Our main aim of this exploration is to build a web application based on the higher prediction accuracy of some powerful machine learning algorithm. We have used a benchmark dataset namely Pima Indian which is capable of predicting the onset of diabetes based on diagnostics manner. With an accuracy of 82.35% prediction rate Artificial Neural Network (ANN) shows a significant improvement of accuracy which drives us to develop an Interactive Web Application for Diabetes Prediction.
{"title":"Implementation of a Web Application to Predict Diabetes Disease: An Approach Using Machine Learning Algorithm","authors":"Samrat Kumar Dey, A. Hossain, M. Rahman","doi":"10.1109/ICCITECHN.2018.8631968","DOIUrl":"https://doi.org/10.1109/ICCITECHN.2018.8631968","url":null,"abstract":"Diabetes is caused due to the excessive amount of sugar condensed into the blood. Currently, it is considered as one of the lethal diseases in the world. People all around the globe are affected by this severe disease knowingly or unknowingly. Other diseases like heart attack, paralyzed, kidney disease, blindness etc. are also caused by diabetes. Numerous computer-based detection systems were designed and outlined for anticipating and analyzing diabetes. Usual identifying process for diabetic patients needs more time and money. But with the rise of machine learning, we have that ability to develop a solution to this intense issue. Therefore we have developed an architecture which has the capability to predict where the patient has diabetes or not. Our main aim of this exploration is to build a web application based on the higher prediction accuracy of some powerful machine learning algorithm. We have used a benchmark dataset namely Pima Indian which is capable of predicting the onset of diabetes based on diagnostics manner. With an accuracy of 82.35% prediction rate Artificial Neural Network (ANN) shows a significant improvement of accuracy which drives us to develop an Interactive Web Application for Diabetes Prediction.","PeriodicalId":355984,"journal":{"name":"2018 21st International Conference of Computer and Information Technology (ICCIT)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126328480","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-12-01DOI: 10.1109/ICCITECHN.2018.8631961
Nahid Hossein, Mohammad Nurul Huda
This paper constructs a method for corroborating Bengali sentences whether they are equitable syntactically, semantically and pragmatically; then a method is devised for detecting parts of speech (POS) from the valid sentences. In our approach, we have analyzed several techniques to check whether construction of inputted Bengali sentence is valid, and finally, we have chosen the best technique among them. Moreover, after analyzing the construction of several Bengali sentences we have designed a rule-based algorithm for detecting POS with a significant accuracy. The idea of ignoring sentences with grammatical mistakes helped significantly to achieve higher accuracy and to reduce execution time. Moreover, our projected method achieved an accuracy of 91.45% which is the highest among similar POS tagger.
{"title":"A Comprehensive Parts of Speech Tagger for Automatically Checked Valid Bengali Sentences","authors":"Nahid Hossein, Mohammad Nurul Huda","doi":"10.1109/ICCITECHN.2018.8631961","DOIUrl":"https://doi.org/10.1109/ICCITECHN.2018.8631961","url":null,"abstract":"This paper constructs a method for corroborating Bengali sentences whether they are equitable syntactically, semantically and pragmatically; then a method is devised for detecting parts of speech (POS) from the valid sentences. In our approach, we have analyzed several techniques to check whether construction of inputted Bengali sentence is valid, and finally, we have chosen the best technique among them. Moreover, after analyzing the construction of several Bengali sentences we have designed a rule-based algorithm for detecting POS with a significant accuracy. The idea of ignoring sentences with grammatical mistakes helped significantly to achieve higher accuracy and to reduce execution time. Moreover, our projected method achieved an accuracy of 91.45% which is the highest among similar POS tagger.","PeriodicalId":355984,"journal":{"name":"2018 21st International Conference of Computer and Information Technology (ICCIT)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121989510","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-12-01DOI: 10.1109/ICCITECHN.2018.8631967
Arif-ul-Islam, S. Akhter
Hand sign recognition is an essential part in robot control, human computer interaction, communication with deaf or speech impaired people etc. where performance and time complexity are very important factors. Numerous researches are conducted to offer solutions for sign language classification. Among them, orientation based hashcode (OBH) model recognizes sign images at a lower time but with A lower accuracy. In this paper, we propose a system which consists of OBH, additional feature extraction and machine learning method. It is able to classify sign language finger spelling alphabets efficiently within a short time. Feature vector using Gabor filter and number of fingertips are used as attributes alongside orientation based hashcode for classification through Artificial Neural Network (ANN). Before feeding features into ANN model, Principle Component Analysis (PCA) is used to omit the redundant features. The dataset contains 576 American Sign Language (ASL) alphabet sign images (both RGB and depth images) of 24 different categories which are captured by Microsoft Kinect sensor. The proposed methodology is proved to be 95.8% accurate against randomly selected test dataset and 93.85% accurate using 9-fold validation.
{"title":"Orientation Hashcode and Articial Neural Network Based Combined Approach to Recognize Sign Language","authors":"Arif-ul-Islam, S. Akhter","doi":"10.1109/ICCITECHN.2018.8631967","DOIUrl":"https://doi.org/10.1109/ICCITECHN.2018.8631967","url":null,"abstract":"Hand sign recognition is an essential part in robot control, human computer interaction, communication with deaf or speech impaired people etc. where performance and time complexity are very important factors. Numerous researches are conducted to offer solutions for sign language classification. Among them, orientation based hashcode (OBH) model recognizes sign images at a lower time but with A lower accuracy. In this paper, we propose a system which consists of OBH, additional feature extraction and machine learning method. It is able to classify sign language finger spelling alphabets efficiently within a short time. Feature vector using Gabor filter and number of fingertips are used as attributes alongside orientation based hashcode for classification through Artificial Neural Network (ANN). Before feeding features into ANN model, Principle Component Analysis (PCA) is used to omit the redundant features. The dataset contains 576 American Sign Language (ASL) alphabet sign images (both RGB and depth images) of 24 different categories which are captured by Microsoft Kinect sensor. The proposed methodology is proved to be 95.8% accurate against randomly selected test dataset and 93.85% accurate using 9-fold validation.","PeriodicalId":355984,"journal":{"name":"2018 21st International Conference of Computer and Information Technology (ICCIT)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128133439","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2018-12-01DOI: 10.1109/ICCITECHN.2018.8631948
Sourin Dey, Md. Ashraful Alam
In the emerging field of speech processing and Automatic Speech Recognition (ASR), vowel perceptual space classification has a vital role for speech intelligibility. In this paper, formant based vowel perceptual space classification is implemented for Bangla vowels. A dataset of vowel signals for 50 speakers has been prepared. The first and second formants of vowels have been extracted from segmented recorded data of different speakers. These two formants have been employed to classify the Bangla vowels perceptual space. Two algorithms namely Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) are used to classify the vowels perceptual space using formants. SVM linear kernel has turned up to be efficient with 84.3% classification accuracy and SVM radial basis function (rbf) kernel has shown to be 100% accurate. KNN has exhibited maximum of 95% classification accuracy.
{"title":"Formant Based Bangla Vowel Perceptual Space Classification Using Support Vector Machine and K-Nearest Neighbor Method","authors":"Sourin Dey, Md. Ashraful Alam","doi":"10.1109/ICCITECHN.2018.8631948","DOIUrl":"https://doi.org/10.1109/ICCITECHN.2018.8631948","url":null,"abstract":"In the emerging field of speech processing and Automatic Speech Recognition (ASR), vowel perceptual space classification has a vital role for speech intelligibility. In this paper, formant based vowel perceptual space classification is implemented for Bangla vowels. A dataset of vowel signals for 50 speakers has been prepared. The first and second formants of vowels have been extracted from segmented recorded data of different speakers. These two formants have been employed to classify the Bangla vowels perceptual space. Two algorithms namely Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) are used to classify the vowels perceptual space using formants. SVM linear kernel has turned up to be efficient with 84.3% classification accuracy and SVM radial basis function (rbf) kernel has shown to be 100% accurate. KNN has exhibited maximum of 95% classification accuracy.","PeriodicalId":355984,"journal":{"name":"2018 21st International Conference of Computer and Information Technology (ICCIT)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128632508","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Bengali documents are increasing on the World Wide Web and it is becoming a overwhelming problem for the increasing large number of web users to reviewing and reduce the information. Many researches have been conducted in the field of Natural Language Processing for English documents and in order to serve with satisfactory accuracy. This research work proposed a simple and powerful extraction based method for summarizing of the Bengali text documents. The system could summarize a single document at a time. The ultimate objective of the proposed methodology helps readers to get summary and insight of the Bengali documents without reading revealing the in-depth details. In the proposed Bengali documents summary generation method there are four features: Preprocessing, Sentence Ranking and Summarization, Combining Parameters for Sentence Ranking, Summary Generator. The results of performance evaluation show that the average scores of Precision, Recall and final scores are 0.80, 0.67, and 0.72 respectively.
{"title":"Automated Bengali Document Summarization by Collaborating Individual Word & Sentence Scoring","authors":"Porimol Chandro, Md. Faizul Huq Arif, Md. Mahbubur Rahman, Md. Saeed Siddik, Mohammad Sayeedur Rahman, Md. Abdur Rahman","doi":"10.1109/ICCITECHN.2018.8631926","DOIUrl":"https://doi.org/10.1109/ICCITECHN.2018.8631926","url":null,"abstract":"Bengali documents are increasing on the World Wide Web and it is becoming a overwhelming problem for the increasing large number of web users to reviewing and reduce the information. Many researches have been conducted in the field of Natural Language Processing for English documents and in order to serve with satisfactory accuracy. This research work proposed a simple and powerful extraction based method for summarizing of the Bengali text documents. The system could summarize a single document at a time. The ultimate objective of the proposed methodology helps readers to get summary and insight of the Bengali documents without reading revealing the in-depth details. In the proposed Bengali documents summary generation method there are four features: Preprocessing, Sentence Ranking and Summarization, Combining Parameters for Sentence Ranking, Summary Generator. The results of performance evaluation show that the average scores of Precision, Recall and final scores are 0.80, 0.67, and 0.72 respectively.","PeriodicalId":355984,"journal":{"name":"2018 21st International Conference of Computer and Information Technology (ICCIT)","volume":"66 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132616210","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：