Pub Date : 2019-05-01DOI: 10.1109/ICASERT.2019.8934519
Sujoy Barua, Zainal Abedin, Anik Nath, C. Biswas
solar radiation (SR) is a significant parameter for producing solar power for the electric energy mix. Sun radiation data is hard to be accumulated at particular geographical location of a country due to measurement instruments is limited especially in developing country like Bangladesh. Hence, estimation of SR for a meteorological location is an important research to learn solar energy potentiality. In this regards, this paper presents a statistical inference model for the estimation of bright sunshine hour which is important metric for solar irradiance. Normal distribution model is inferred from the historical data of some important locations of Bangladesh. Mean and standard deviation are the parameters at 95% confidence interval which control the behavior of such distribution. In this statistical model, bright sunshine hour is estimated that expedite to find the potential of solar energy at particular location. The estimation model can be used as a decision making support to design photovoltaic power system for deployment of energy mix policy.
{"title":"A Statistical Estimation of Solar Power for Energy Mix in Bangladesh","authors":"Sujoy Barua, Zainal Abedin, Anik Nath, C. Biswas","doi":"10.1109/ICASERT.2019.8934519","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934519","url":null,"abstract":"solar radiation (SR) is a significant parameter for producing solar power for the electric energy mix. Sun radiation data is hard to be accumulated at particular geographical location of a country due to measurement instruments is limited especially in developing country like Bangladesh. Hence, estimation of SR for a meteorological location is an important research to learn solar energy potentiality. In this regards, this paper presents a statistical inference model for the estimation of bright sunshine hour which is important metric for solar irradiance. Normal distribution model is inferred from the historical data of some important locations of Bangladesh. Mean and standard deviation are the parameters at 95% confidence interval which control the behavior of such distribution. In this statistical model, bright sunshine hour is estimated that expedite to find the potential of solar energy at particular location. The estimation model can be used as a decision making support to design photovoltaic power system for deployment of energy mix policy.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"23 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85430030","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 : 2019-05-01DOI: 10.1109/ICASERT.2019.8934524
Kanij Ahmad, N. Mohammad, M. Quamruzzaman
Frequency adjustment and protection of a wind turbine due to wind gust is a salient aspect of the grid-tied wind farm. Both of them require conserving system stability. This paper presents an investigation of the converter based frequency adjusting method and wind turbine protection. A grid-tied wind power system model using the Doubly Fed Induction Generator in MATLAB is used. To regulate the active power output, synchronization between wind velocity and wind turbine speed is adjusted. Thus, wind farm operated at grid frequency and maximize turbine output. The control strategy of the converter based frequency synchronization of a grid-tied wind farm also includes protection subsystem. The protection system executed by receiving information from the logical block implemented in the wind farm model. It provides wind turbine protection by terminating wind turbine from a grid in abnormal wind conditions. The Simulation result validates the results and control methods.
{"title":"Converter based Frequency Adjustment and Protection of Grid-tied Wind Farm","authors":"Kanij Ahmad, N. Mohammad, M. Quamruzzaman","doi":"10.1109/ICASERT.2019.8934524","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934524","url":null,"abstract":"Frequency adjustment and protection of a wind turbine due to wind gust is a salient aspect of the grid-tied wind farm. Both of them require conserving system stability. This paper presents an investigation of the converter based frequency adjusting method and wind turbine protection. A grid-tied wind power system model using the Doubly Fed Induction Generator in MATLAB is used. To regulate the active power output, synchronization between wind velocity and wind turbine speed is adjusted. Thus, wind farm operated at grid frequency and maximize turbine output. The control strategy of the converter based frequency synchronization of a grid-tied wind farm also includes protection subsystem. The protection system executed by receiving information from the logical block implemented in the wind farm model. It provides wind turbine protection by terminating wind turbine from a grid in abnormal wind conditions. The Simulation result validates the results and control methods.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"26 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81654589","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 : 2019-05-01DOI: 10.1109/ICASERT.2019.8934665
Akash Bosu, Chaity Basak, S. Sharmin, K. M. A. Hossain, Sharmina Zaman Urmi, M. A. Mahfuz
In this paper, Zeonex based hexagonal photonic crystal fiber (PCF) is proposed to obtain low confinement loss and moderate effective material loss (EML) at terahertz frequency. We use the finite element method (FEM) with a perfectly matched layer (PML) boundary condition to investigate the modal properties of the PCF. Simulated results demonstrate that this structure transfers signal in single mode condition. Besides, excessive low confinement loss of 6.73×10-11 dB/cm, and EML of 0.1491 dB/cm have obtained at an operating frequency of 0.55 THz. In this paper, other crucial guiding parameters such as air-core power fraction, effective area, bending loss, and dispersion of the fiber have also discussed. This terahertz fiber can be a good candidate for several applications in the terahertz regime.
{"title":"Design and Characterization of low loss Single Mode Fiber for Terahertz Signal Transmission","authors":"Akash Bosu, Chaity Basak, S. Sharmin, K. M. A. Hossain, Sharmina Zaman Urmi, M. A. Mahfuz","doi":"10.1109/ICASERT.2019.8934665","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934665","url":null,"abstract":"In this paper, Zeonex based hexagonal photonic crystal fiber (PCF) is proposed to obtain low confinement loss and moderate effective material loss (EML) at terahertz frequency. We use the finite element method (FEM) with a perfectly matched layer (PML) boundary condition to investigate the modal properties of the PCF. Simulated results demonstrate that this structure transfers signal in single mode condition. Besides, excessive low confinement loss of 6.73×10-11 dB/cm, and EML of 0.1491 dB/cm have obtained at an operating frequency of 0.55 THz. In this paper, other crucial guiding parameters such as air-core power fraction, effective area, bending loss, and dispersion of the fiber have also discussed. This terahertz fiber can be a good candidate for several applications in the terahertz regime.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"3 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79748283","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 : 2019-05-01DOI: 10.1109/ICASERT.2019.8934902
Shuvendu Roy
Rule-based spelling correction system focused on finding the most matched word with the misspelled word. But this approach does not work well inside a sentence with multiple errors that has a combination of possible correct words to replace but only one current sentence. Replacing each word individually will result in errors. So, the spelling corrector system must understand the context of the sentence including the tense and gender of the subject and so on. The most popular example of typing mistake correction is the one Google provides in their search engine. It was introduced quite a while ago but no such good performing system is developed by anyone else. In this work, we have proposed a spelling correction system using deep learning. The basic intuition of our approach is taken from denoising autoencoder. Here we have trained the model with noisy input generated by changing, removing or adding extra character at random position inside the sequence. The job of the model is to model this noisy input to output the original errorless sequence. We have experimented with large English dataset and reported the performance in terms of character level accuracy. The proposed model has shown impressive results in correcting the spelling mistakes.
{"title":"Denoising Sequence-to-Sequence Modeling for Removing Spelling Mistakes","authors":"Shuvendu Roy","doi":"10.1109/ICASERT.2019.8934902","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934902","url":null,"abstract":"Rule-based spelling correction system focused on finding the most matched word with the misspelled word. But this approach does not work well inside a sentence with multiple errors that has a combination of possible correct words to replace but only one current sentence. Replacing each word individually will result in errors. So, the spelling corrector system must understand the context of the sentence including the tense and gender of the subject and so on. The most popular example of typing mistake correction is the one Google provides in their search engine. It was introduced quite a while ago but no such good performing system is developed by anyone else. In this work, we have proposed a spelling correction system using deep learning. The basic intuition of our approach is taken from denoising autoencoder. Here we have trained the model with noisy input generated by changing, removing or adding extra character at random position inside the sequence. The job of the model is to model this noisy input to output the original errorless sequence. We have experimented with large English dataset and reported the performance in terms of character level accuracy. The proposed model has shown impressive results in correcting the spelling mistakes.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"58 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84891356","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 : 2019-05-01DOI: 10.1109/ICASERT.2019.8934455
A. H. Uddin, Durjoy Bapery, Abu Shamim Mohammad Arif
Nowadays, micro-blogging sites like Twitter, Facebook, YouTube, etc., have become much popular for social interactions. People are expressing their depression over social media, which can be analyzed to identify causes behind their depression. Most of the researches on emotion and depression analysis are based on questionnaires and academic interviews in non-Bengali languages, especially English. These traditional methods are not always suitable for detecting human depression. In this paper, we introduced Gated Recurrent Neural Network based depression analysis approach on Bangla social media data. We collected Bangla data from Twitter, Facebook and other sources. We selected four hyper-parameters, namely, number of Gated Recurrent Unit (GRU) layers, layer size, batch size and number of epochs, and presented step by step tuning for these Hyper-parameters. The results show the effects of these tuning steps and how the steps can be beneficial in configuring GRU models for gaining high accuracy on a significantly smaller data set. This will help psychologists and concerned authorities of society detect depression among Bangla speaking social media users. It will also help researchers to implement Natural Language Processing tasks with Deep Learning methods.
{"title":"Depression Analysis of Bangla Social Media Data using Gated Recurrent Neural Network","authors":"A. H. Uddin, Durjoy Bapery, Abu Shamim Mohammad Arif","doi":"10.1109/ICASERT.2019.8934455","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934455","url":null,"abstract":"Nowadays, micro-blogging sites like Twitter, Facebook, YouTube, etc., have become much popular for social interactions. People are expressing their depression over social media, which can be analyzed to identify causes behind their depression. Most of the researches on emotion and depression analysis are based on questionnaires and academic interviews in non-Bengali languages, especially English. These traditional methods are not always suitable for detecting human depression. In this paper, we introduced Gated Recurrent Neural Network based depression analysis approach on Bangla social media data. We collected Bangla data from Twitter, Facebook and other sources. We selected four hyper-parameters, namely, number of Gated Recurrent Unit (GRU) layers, layer size, batch size and number of epochs, and presented step by step tuning for these Hyper-parameters. The results show the effects of these tuning steps and how the steps can be beneficial in configuring GRU models for gaining high accuracy on a significantly smaller data set. This will help psychologists and concerned authorities of society detect depression among Bangla speaking social media users. It will also help researchers to implement Natural Language Processing tasks with Deep Learning methods.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"1 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83749027","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 : 2019-05-01DOI: 10.1109/ICASERT.2019.8934719
A. Baki, Md. Nurur Rahman, Shawon Kumar Mondal
Microstrip patch antenna (MSA) has numerous applications such as aircraft, biomedical engineering, connected vehicles, cellular phones, satellites, smart grid, and spacecraft. Single MSA or MSA Array (MSAA) require low-cost materials with simple and inexpensive fabrication techniques. With the help of modern and highly precise printed-circuit technology it is possible to fabricate inexpensive and robust MSA/MSAA, which are compatible with microwave monolithic integrated circuit (MMIC) designs. Rectangular patch, one of the most popular patches, has different feeding techniques for impedance matching. Inset fed rectangular patch does not require any additional complex microwave circuit. Inset feeding mechanism can easily be optimized with the help of 3D simulation software. Very few investigations are made on inset fed MSAA, though several research papers can be found on inset fed rectangular MSA. In this paper a comparative analysis of edge fed and inset fed MSA/MSAA at 2.45 GHz frequency band is done using FR-4 and air substrates. It was found that the inset fed MSA with air substrate performs better when the directivities, gains, bandwidths and return losses are considered. Though FR4 substrate is cheap and miniaturization of MSAA is better with FR-4 substrate.
{"title":"Analysis of Performance-Improvement of Microstrip Antenna at 2.45 GHz Through Inset Feed Method","authors":"A. Baki, Md. Nurur Rahman, Shawon Kumar Mondal","doi":"10.1109/ICASERT.2019.8934719","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934719","url":null,"abstract":"Microstrip patch antenna (MSA) has numerous applications such as aircraft, biomedical engineering, connected vehicles, cellular phones, satellites, smart grid, and spacecraft. Single MSA or MSA Array (MSAA) require low-cost materials with simple and inexpensive fabrication techniques. With the help of modern and highly precise printed-circuit technology it is possible to fabricate inexpensive and robust MSA/MSAA, which are compatible with microwave monolithic integrated circuit (MMIC) designs. Rectangular patch, one of the most popular patches, has different feeding techniques for impedance matching. Inset fed rectangular patch does not require any additional complex microwave circuit. Inset feeding mechanism can easily be optimized with the help of 3D simulation software. Very few investigations are made on inset fed MSAA, though several research papers can be found on inset fed rectangular MSA. In this paper a comparative analysis of edge fed and inset fed MSA/MSAA at 2.45 GHz frequency band is done using FR-4 and air substrates. It was found that the inset fed MSA with air substrate performs better when the directivities, gains, bandwidths and return losses are considered. Though FR4 substrate is cheap and miniaturization of MSAA is better with FR-4 substrate.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"61 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80783801","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}
The distinguishing characteristics belong to a person are personality traits, which is predicted from person’s behavioral pattern. As most of the people provide lots of information knowingly or unknowingly into their writings, it is possible to extract personality traits from those texts. Individual personality traits detection from texts, yields enormous possibilities toward various applications named as forensic department, mental health diagnosis, etc. Meanwhile, deep learning algorithm performs fairly well in text based personality detection; however, its performance may vary with activation functions. Hence, this paper proposed an empirical approach to find the best personality detection performance by comparing several activation functions named as sigmoid, tanh, and leaky ReLU. Here, text documents were pre-processed and vectorized for input in convolutional neural network. The input size was multiple to length of word, sentence, documents, and feature vectors. Five personality traits named as EXT, NEU, AGR, CON, and OPN have been used for experimental analysis. The result showed that tanh and leaky ReLU performs over sigmoid in all datasets. The average F1-score of sigmoid, tanh and leaky ReLU showed 33.11%, 47.25%, and 49.07% respectively. However, Fl-score of leaky ReLU was high only for CON, tanh showed better result for others datasets. The overall performance showed by tanh is better than sigmoid and leaky ReLU for personality detection from text.
{"title":"Personality Detection from Text using Convolutional Neural Network","authors":"Md. Abdur Rahman, Asif Al Faisal, Tayeba Khanam, Mahfida Amjad, Md. Saeed Siddik","doi":"10.1109/ICASERT.2019.8934548","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934548","url":null,"abstract":"The distinguishing characteristics belong to a person are personality traits, which is predicted from person’s behavioral pattern. As most of the people provide lots of information knowingly or unknowingly into their writings, it is possible to extract personality traits from those texts. Individual personality traits detection from texts, yields enormous possibilities toward various applications named as forensic department, mental health diagnosis, etc. Meanwhile, deep learning algorithm performs fairly well in text based personality detection; however, its performance may vary with activation functions. Hence, this paper proposed an empirical approach to find the best personality detection performance by comparing several activation functions named as sigmoid, tanh, and leaky ReLU. Here, text documents were pre-processed and vectorized for input in convolutional neural network. The input size was multiple to length of word, sentence, documents, and feature vectors. Five personality traits named as EXT, NEU, AGR, CON, and OPN have been used for experimental analysis. The result showed that tanh and leaky ReLU performs over sigmoid in all datasets. The average F1-score of sigmoid, tanh and leaky ReLU showed 33.11%, 47.25%, and 49.07% respectively. However, Fl-score of leaky ReLU was high only for CON, tanh showed better result for others datasets. The overall performance showed by tanh is better than sigmoid and leaky ReLU for personality detection from text.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"23 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83151886","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 : 2019-05-01DOI: 10.1109/ICASERT.2019.8934470
A. Hossain, M. K. Hosain
An UWB Vivaldi antenna is proposed for cancer detection and treatment. The antenna operates at the resonant frequency of 4.76 GHz within the bandwidth of 4.63 GHz (3.13 GHz-7.76 GHz) in free space. In addition, the antenna possesses a high radiation efficiency of 81.34% and a gain of 5.81 dB in free space condition. The overall dimension of the proposed antenna is 110.46 x 96.77 x 1.67 mm3. The antenna is simulated with 1.6 mm thick FR-4 dielectric substrate since it is cost-effective and easily available. Furthermore, a six-layer biological tissue model comprising of skin, fat, outer cortical bone, cancellous bone, inner cortical bone, and muscle with a tumor of 10 mm radius is modeled to assess antenna performance for cancer detection and treatment. In simulation, a specific gap of 2.5 mm is maintained between the proposed antenna and the proposed phantom model in order to avoid skin burn and other side-effects. Cancerous cells in tumor are detected and killed because of higher SAR value of the cancerous tissue than the normal healthy tissue.
提出了一种用于癌症检测和治疗的超宽带维瓦尔第天线。该天线在自由空间4.63 GHz (3.13 GHz-7.76 GHz)带宽范围内工作在4.76 GHz的谐振频率。此外，该天线在自由空间条件下具有高达81.34%的辐射效率和5.81 dB的增益。天线的整体尺寸为110.46 x 96.77 x 1.67 mm3。该天线采用1.6 mm厚的FR-4介电基片进行模拟，因为它具有成本效益且易于获得。此外，建立了一个六层生物组织模型，包括皮肤、脂肪、外皮质骨、松质骨、内皮质骨和肌肉，肿瘤半径为10mm，以评估天线在癌症检测和治疗中的性能。在仿真中，为了避免皮肤烧伤和其他副作用，所提出的天线和所提出的幻影模型之间保持2.5 mm的特定间隙。由于肿瘤组织的SAR值高于正常健康组织，因此肿瘤细胞被发现并被杀死。
{"title":"Design and Simulation of an UWB Vivaldi Antenna for Cancer Detection and Treatment","authors":"A. Hossain, M. K. Hosain","doi":"10.1109/ICASERT.2019.8934470","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934470","url":null,"abstract":"An UWB Vivaldi antenna is proposed for cancer detection and treatment. The antenna operates at the resonant frequency of 4.76 GHz within the bandwidth of 4.63 GHz (3.13 GHz-7.76 GHz) in free space. In addition, the antenna possesses a high radiation efficiency of 81.34% and a gain of 5.81 dB in free space condition. The overall dimension of the proposed antenna is 110.46 x 96.77 x 1.67 mm3. The antenna is simulated with 1.6 mm thick FR-4 dielectric substrate since it is cost-effective and easily available. Furthermore, a six-layer biological tissue model comprising of skin, fat, outer cortical bone, cancellous bone, inner cortical bone, and muscle with a tumor of 10 mm radius is modeled to assess antenna performance for cancer detection and treatment. In simulation, a specific gap of 2.5 mm is maintained between the proposed antenna and the proposed phantom model in order to avoid skin burn and other side-effects. Cancerous cells in tumor are detected and killed because of higher SAR value of the cancerous tissue than the normal healthy tissue.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"2 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83234398","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 : 2019-05-01DOI: 10.1109/ICASERT.2019.8934888
K. M. AzharulHasan, M. Omar, Rahat Haider, S. M. M. Ahsan
In recent years managing Big Data is a big challenge. Big data has huge volume, variety of format and its volume increases at a very high velocity. Traditional data structures fail to handle these types of data. Moreover Big Data storage scheme is very expensive. So some efficient scheme is needed. In this paper we show the application of dynamic Extendible Array for Big data storage. It is an efficient scheme which has better performance over other approaches. We used MapReduce concept to distribute the data in heterogeneous environment. The data that belongs to different dimensions are distributed to different machines to do the operations efficiently. The basic operations including insertion, deletion, update and retrieval of various types namely point key query, single key query and range key query are performed. Moreover the dynamic extension of the structure without reorganizing the existing data is performed. Experimental results are well studied. We used cheap commodity machines for our implementation.
{"title":"Efficient Implementation of Dynamic Array SystemUsing MapReduce Framework","authors":"K. M. AzharulHasan, M. Omar, Rahat Haider, S. M. M. Ahsan","doi":"10.1109/ICASERT.2019.8934888","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934888","url":null,"abstract":"In recent years managing Big Data is a big challenge. Big data has huge volume, variety of format and its volume increases at a very high velocity. Traditional data structures fail to handle these types of data. Moreover Big Data storage scheme is very expensive. So some efficient scheme is needed. In this paper we show the application of dynamic Extendible Array for Big data storage. It is an efficient scheme which has better performance over other approaches. We used MapReduce concept to distribute the data in heterogeneous environment. The data that belongs to different dimensions are distributed to different machines to do the operations efficiently. The basic operations including insertion, deletion, update and retrieval of various types namely point key query, single key query and range key query are performed. Moreover the dynamic extension of the structure without reorganizing the existing data is performed. Experimental results are well studied. We used cheap commodity machines for our implementation.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"19 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81480812","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 : 2019-05-01DOI: 10.1109/ICASERT.2019.8934655
Omar Sharif, M. M. Hoque, E. Hossain
Recently, determining the customer impression is considered one of the prominent factors on the success of the restaurant businesses. Due to the rapid growth of digital contents related to restaurant or foods in the web, people are more inclined on reviews before going to any restaurant so the significance of customer review is inevitable. In order to selects a restaurant customer needs to check thousands of feedback’s to understand the restaurant quality or services. Therefore, classification of a significant amount of reviews into a sentimental category is required to attain meaningful insights so that the customer can choose restaurants based on their preferences. This classification can be done by sentiment analysis. This paper proposes a system that can classify customer reviews into positive and negative classes based on their sentimental feedback. We have tested the proposed system with 1000 restaurant reviews text written in Bengali. The experimental result shows that the proposed the system can classify restaurant reviews with 80.48% accuracy using multinomial Naïve Bayes.
{"title":"Sentiment Analysis of Bengali Texts on Online Restaurant Reviews Using Multinomial Naïve Bayes","authors":"Omar Sharif, M. M. Hoque, E. Hossain","doi":"10.1109/ICASERT.2019.8934655","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934655","url":null,"abstract":"Recently, determining the customer impression is considered one of the prominent factors on the success of the restaurant businesses. Due to the rapid growth of digital contents related to restaurant or foods in the web, people are more inclined on reviews before going to any restaurant so the significance of customer review is inevitable. In order to selects a restaurant customer needs to check thousands of feedback’s to understand the restaurant quality or services. Therefore, classification of a significant amount of reviews into a sentimental category is required to attain meaningful insights so that the customer can choose restaurants based on their preferences. This classification can be done by sentiment analysis. This paper proposes a system that can classify customer reviews into positive and negative classes based on their sentimental feedback. We have tested the proposed system with 1000 restaurant reviews text written in Bengali. The experimental result shows that the proposed the system can classify restaurant reviews with 80.48% accuracy using multinomial Naïve Bayes.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"24 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81597414","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：