Pub Date : 2019-05-01DOI: 10.1109/ICASERT.2019.8934467
Sifat Ahmed, Faisal Muhammad
When it comes down to buying products from online shops, one of the key factor that influences a buyer are the reviews associated with a product. While buying people try to understand the quality and authenticity of the product by reading the previous user feedback. And sellers have started taking advantage of it. Putting fake and spam reviews to deceive the buyers is a common strategy mostly used by newcomers. But these reviews are important when it comes to deciding whether to buy a product or not. We propose a method to detect these fake reviews from Amazon Review Dataset. Rather than using traditional machine learning classifiers we have used boosting algorithms to improve the accuracy of the traditional approach. In this approach, a significant increase in accuracy has been achieved by boosting weak learners. Up to 93% accuracy has been achieved when tried to detect fake reviews where traditional machine learning algorithms achieve an accuracy of up to 89%.
{"title":"Using Boosting Approaches to Detect Spam Reviews","authors":"Sifat Ahmed, Faisal Muhammad","doi":"10.1109/ICASERT.2019.8934467","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934467","url":null,"abstract":"When it comes down to buying products from online shops, one of the key factor that influences a buyer are the reviews associated with a product. While buying people try to understand the quality and authenticity of the product by reading the previous user feedback. And sellers have started taking advantage of it. Putting fake and spam reviews to deceive the buyers is a common strategy mostly used by newcomers. But these reviews are important when it comes to deciding whether to buy a product or not. We propose a method to detect these fake reviews from Amazon Review Dataset. Rather than using traditional machine learning classifiers we have used boosting algorithms to improve the accuracy of the traditional approach. In this approach, a significant increase in accuracy has been achieved by boosting weak learners. Up to 93% accuracy has been achieved when tried to detect fake reviews where traditional machine learning algorithms achieve an accuracy of up to 89%.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"17 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":"90509788","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.2019.8934915
Navila Rahman Nadi, F. Bingöl, Merete Badger
The objective of this paper is to obtain appropriate offshore location in the Bay of Bengal, Bangladesh for further development of wind energy. Through analyzing the previous published works, no offshore wind energy estimation has been found related to the Bay of Bengal. Therefore, this study can be claimed as the first footstep towards offshore wind energy analysis for this region. Generally, it is difficult to find offshore wind data relative to the wind turbine hub heights, thus a starting point is necessary to identify the possible wind power density of the region. In such scenario, Synthetic Aperture radars (SAR) have proven useful in previous studies. In this study, SAR based dataset- ENVISAT ASAR has been used for Wind Atlas generation of the Bay of Bengal. Furthermore, a comparative study has been performed with Global Wind Atlas (GWA) to determine a potential offshore wind farm production in a reasonable location at the bay. The annual energy production of that offshore windfarm has been analyzed by combining SAR, GWA and ASCAT datasets. Through ASAR based Wind Atlas and GWA comparison, some differences have been found where there are less samples from the ASAR datasets. Thus, Weibull statistical analysis are performed to have a better Weibull fitting and accurate estimation of Annual Energy production (AEP). The study summarizes that, satellite datasets can be a very useful method to detect potential zone if compared with any long time statistical result and bathymetry data together.
{"title":"Offshore Wind Energy Estimation in the Bay of Bengal with Satellite Wind Measurement","authors":"Navila Rahman Nadi, F. Bingöl, Merete Badger","doi":"10.1109/ICASERT.2019.8934915","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934915","url":null,"abstract":"The objective of this paper is to obtain appropriate offshore location in the Bay of Bengal, Bangladesh for further development of wind energy. Through analyzing the previous published works, no offshore wind energy estimation has been found related to the Bay of Bengal. Therefore, this study can be claimed as the first footstep towards offshore wind energy analysis for this region. Generally, it is difficult to find offshore wind data relative to the wind turbine hub heights, thus a starting point is necessary to identify the possible wind power density of the region. In such scenario, Synthetic Aperture radars (SAR) have proven useful in previous studies. In this study, SAR based dataset- ENVISAT ASAR has been used for Wind Atlas generation of the Bay of Bengal. Furthermore, a comparative study has been performed with Global Wind Atlas (GWA) to determine a potential offshore wind farm production in a reasonable location at the bay. The annual energy production of that offshore windfarm has been analyzed by combining SAR, GWA and ASCAT datasets. Through ASAR based Wind Atlas and GWA comparison, some differences have been found where there are less samples from the ASAR datasets. Thus, Weibull statistical analysis are performed to have a better Weibull fitting and accurate estimation of Annual Energy production (AEP). The study summarizes that, satellite datasets can be a very useful method to detect potential zone if compared with any long time statistical result and bathymetry data together.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"15 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89414813","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.2019.8934449
Md. Raihan Mia, A. S. M. Latiful Hoque
Problem Based e-learning(PBeL) in bangla language is one of the most progressing areas of the use of ICT in education. Question Bank(QB) is the main component of any PBeL system. Searching similarity in the complex structure of QB is a challenging task in the development of PBeL system. We have been developed an efficient Question Bank Similarity Searching System(QB3S) to find similar questions, handle duplicate question and rank search result of a query input based on NLP and Information Retrieval techniques. QB3S has four modules: bangla documents processing, question structure analysis and clustered indexing by B+ tree , word-net construction and Information retrieval module. Lexical analysis, stemming by finite automata rules and stopwords removing have been used for bangla document processing. The most challenging procedures of QB3S were Analyzing the structure of data for clustered indexing in the sorted sequential file of the QB database with a B+ tree data structure and improved TF-IDF algorithm with weighted functionality. A Word-net has been used for handling synonyms. Vector Space Model(VSM) has been designed from the value of TF-IDF weighted matrix. By using cosine similarity product rule, we have been Calculated the similarity value between the query input and all mcq of DB from VSM. QB3S has been evaluated in some experimental dataset to find results by imposing different test cases. The accuracy of searching performance which has found to be satisfactory.
{"title":"Question Bank Similarity Searching System (QB3S) Using NLP and Information Retrieval Technique","authors":"Md. Raihan Mia, A. S. M. Latiful Hoque","doi":"10.1109/ICASERT.2019.8934449","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934449","url":null,"abstract":"Problem Based e-learning(PBeL) in bangla language is one of the most progressing areas of the use of ICT in education. Question Bank(QB) is the main component of any PBeL system. Searching similarity in the complex structure of QB is a challenging task in the development of PBeL system. We have been developed an efficient Question Bank Similarity Searching System(QB3S) to find similar questions, handle duplicate question and rank search result of a query input based on NLP and Information Retrieval techniques. QB3S has four modules: bangla documents processing, question structure analysis and clustered indexing by B+ tree , word-net construction and Information retrieval module. Lexical analysis, stemming by finite automata rules and stopwords removing have been used for bangla document processing. The most challenging procedures of QB3S were Analyzing the structure of data for clustered indexing in the sorted sequential file of the QB database with a B+ tree data structure and improved TF-IDF algorithm with weighted functionality. A Word-net has been used for handling synonyms. Vector Space Model(VSM) has been designed from the value of TF-IDF weighted matrix. By using cosine similarity product rule, we have been Calculated the similarity value between the query input and all mcq of DB from VSM. QB3S has been evaluated in some experimental dataset to find results by imposing different test cases. The accuracy of searching performance which has found to be satisfactory.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"25 1","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89439561","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.2019.8934602
Mohammad Hasibul Hasan Hasib, Jannati Nabiha Nur, Kamrun Nahar Shushama, I. Rahaman, M. Rana, M. A. Al Mahfuz
In this paper, we demonstrate a highly sensitive Kretschmann configuration based surface plasmon resonance (SPR) biosensor with high detection accuracy (DA) and quality factor (QF). Five layers of biosensor model is proposed using numerical simulation and graphical analysis. In this model, graphene and heterostructures of black phosphorus improve the sensitivity of biosensor. Silver (Ag) is coupled with prism CaF2 for better reflectivity, since CaF2 has the less refractive index (RI). The mentioned model gives the highest sensitivity for 633 nm wavelength p-polarized light is 263.51 º/RIU with higher detection accuracy (DA) 2.14 and quality factor (QF) 57.915 RIU-1.
{"title":"Enhancement of Sensitivity for Surface Plasmon Resonance Biosensor with Higher Detection Accuracy and Quality Factor","authors":"Mohammad Hasibul Hasan Hasib, Jannati Nabiha Nur, Kamrun Nahar Shushama, I. Rahaman, M. Rana, M. A. Al Mahfuz","doi":"10.1109/ICASERT.2019.8934602","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934602","url":null,"abstract":"In this paper, we demonstrate a highly sensitive Kretschmann configuration based surface plasmon resonance (SPR) biosensor with high detection accuracy (DA) and quality factor (QF). Five layers of biosensor model is proposed using numerical simulation and graphical analysis. In this model, graphene and heterostructures of black phosphorus improve the sensitivity of biosensor. Silver (Ag) is coupled with prism CaF2 for better reflectivity, since CaF2 has the less refractive index (RI). The mentioned model gives the highest sensitivity for 633 nm wavelength p-polarized light is 263.51 º/RIU with higher detection accuracy (DA) 2.14 and quality factor (QF) 57.915 RIU-1.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"100 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":"87983969","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.2019.8934653
Abu Sayeed, Md. Ali Hossain, Md. Rabiul Islam
In remote sensing image classification, really it is an intimidating when kernel supervised learning approaches stands in need of adequate amount of training samples. Often there is a vital problem for definition and acquisition of reference data. For Hyperspectral image classification, improved spectral information is required to make it suitable for ground object identification. In this paper, Support Vector Machine with RBF kernel (KSVM) and the spectral angle mapper (SAM) are used for performance comparison in terms of classification accuracy in Hyperspectral image classification. Kernel support vector machine is more preferable for the mastery to generalize better hyperplane when limited availability of training samples and separate the classes competently in a new dimension feature space. Experiments are performed on NASA Airborne Visible Infrared Spectrometer (AVIRIS) image and it shows KSVM outperforms SAM and obtains the highest accuracy. Due to more well-conditioned against the outliers, KSVM significantly reduced the classification complexities than SAM.
{"title":"Feature Selection and Comparative Analysis of the Supervised Learning Model for Hyperspectral Image Classification","authors":"Abu Sayeed, Md. Ali Hossain, Md. Rabiul Islam","doi":"10.1109/ICASERT.2019.8934653","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934653","url":null,"abstract":"In remote sensing image classification, really it is an intimidating when kernel supervised learning approaches stands in need of adequate amount of training samples. Often there is a vital problem for definition and acquisition of reference data. For Hyperspectral image classification, improved spectral information is required to make it suitable for ground object identification. In this paper, Support Vector Machine with RBF kernel (KSVM) and the spectral angle mapper (SAM) are used for performance comparison in terms of classification accuracy in Hyperspectral image classification. Kernel support vector machine is more preferable for the mastery to generalize better hyperplane when limited availability of training samples and separate the classes competently in a new dimension feature space. Experiments are performed on NASA Airborne Visible Infrared Spectrometer (AVIRIS) image and it shows KSVM outperforms SAM and obtains the highest accuracy. Due to more well-conditioned against the outliers, KSVM significantly reduced the classification complexities than SAM.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"93 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":"85851751","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.2019.8934478
Sania Zahan, M. Islam
Epilepsy is a neurological disorder originating from brain cells that can affect harshly on patients’ life. Imbalance in electrical signals in the neuron cells results in involuntary partial or full body movements or other physiological symptoms. Seizure attack is unpredictable and during its occurrence patient may lose control which can cause serious injury even death. Medical facilities like medication or surgery can be done to improve living condition and life expectancy of patients. For these measures to be beneficial early and correct detection of epilepsy is crucial. However detection from scalp EEG is tough due to the presence of artifacts, the state of the brain and the frequency of seizure occurrence. Hence this study proposes a reliable model of detection system. A zero phase bandpass butterworth filter is used to extract only the EEG signal eliminating all physiological and device artifacts. Frequency distribution of brain signal in both interictal and ictal state differs from that in normal person. So statistical measurements that correctly maps these changes are used to classify the dataset. For classification, a nonlinear support vector machine is used on two sets of dataset combination. Performance of detecting epileptic signal even in the interictal state is promising for use in medical applications.
{"title":"Epileptic Seizure Detection and Classification using Support Vector Machine from Scalp EEG Signal","authors":"Sania Zahan, M. Islam","doi":"10.1109/ICASERT.2019.8934478","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934478","url":null,"abstract":"Epilepsy is a neurological disorder originating from brain cells that can affect harshly on patients’ life. Imbalance in electrical signals in the neuron cells results in involuntary partial or full body movements or other physiological symptoms. Seizure attack is unpredictable and during its occurrence patient may lose control which can cause serious injury even death. Medical facilities like medication or surgery can be done to improve living condition and life expectancy of patients. For these measures to be beneficial early and correct detection of epilepsy is crucial. However detection from scalp EEG is tough due to the presence of artifacts, the state of the brain and the frequency of seizure occurrence. Hence this study proposes a reliable model of detection system. A zero phase bandpass butterworth filter is used to extract only the EEG signal eliminating all physiological and device artifacts. Frequency distribution of brain signal in both interictal and ictal state differs from that in normal person. So statistical measurements that correctly maps these changes are used to classify the dataset. For classification, a nonlinear support vector machine is used on two sets of dataset combination. Performance of detecting epileptic signal even in the interictal state is promising for use in medical applications.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"1 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":"78627725","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.2019.8934542
Kazi Shahrukh Omar, F. Rabbi, Afia Anjum, Tahrima Oannahary, Rezaul Karim Rizvi, Diana Shahrin, Tasmiah Tamzid Anannya, Sanjida Nasreen Tumpa, MMahboob Karim, Muhammad Nazrul Islam
Alzheimer’s Disease (AD) is a chronic neurodegenerative disease that causes to develop dementia. Alzheimer’s patients find it hard to remember recent events, reason and even to recognize people they know. As the disease advances, symptoms can include difficulty with language, disorientation including getting lost, mood swings, loss of motivation, lack of self-awareness and overall behavior. Though a limited number of IT based solutions exist to provide support for Alzheimer’s patients, but most of these provide very isolated services either for the patients or for the caregivers. The objective of this research is to propose an assistive tool for Alzheimer’s patients and their caregivers to provide support like health monitoring, assist to find lost items, provide reminder to take medicine and assist to monitor patient’s location. A light-weighted evaluation study was carried out with 15 participants. The evaluation study showed that the proposed system was effective and usable for the patients and their caregivers.
{"title":"An Intelligent Assistive Tool for Alzheimer’s Patient","authors":"Kazi Shahrukh Omar, F. Rabbi, Afia Anjum, Tahrima Oannahary, Rezaul Karim Rizvi, Diana Shahrin, Tasmiah Tamzid Anannya, Sanjida Nasreen Tumpa, MMahboob Karim, Muhammad Nazrul Islam","doi":"10.1109/ICASERT.2019.8934542","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934542","url":null,"abstract":"Alzheimer’s Disease (AD) is a chronic neurodegenerative disease that causes to develop dementia. Alzheimer’s patients find it hard to remember recent events, reason and even to recognize people they know. As the disease advances, symptoms can include difficulty with language, disorientation including getting lost, mood swings, loss of motivation, lack of self-awareness and overall behavior. Though a limited number of IT based solutions exist to provide support for Alzheimer’s patients, but most of these provide very isolated services either for the patients or for the caregivers. The objective of this research is to propose an assistive tool for Alzheimer’s patients and their caregivers to provide support like health monitoring, assist to find lost items, provide reminder to take medicine and assist to monitor patient’s location. A light-weighted evaluation study was carried out with 15 participants. The evaluation study showed that the proposed system was effective and usable for the patients and their caregivers.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"28 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":"80122294","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.2019.8934479
Sujoy Barua, Anik Nath, Fahim Shahriyar, N. Mohammad
An analysis is presented to show time series data of electricity generation mix and forecasting by 2030 in Bangladesh. The comparative studies have been analyzed using spatiotemporal data of Germany, Australia and Bangladesh. The spatiotemporal data has been taken out from World Bank data bank for analysis. A Linear regression technique is applied for forecasting electricity generation mix from 2015 to 2030. The result shows the rise of renewable energy sources, coal and oil, and the diminution of natural gas gradually.
{"title":"A Spatiotemporal Analysis and Forecasting of Electricity Generation-Mix in Bangladesh","authors":"Sujoy Barua, Anik Nath, Fahim Shahriyar, N. Mohammad","doi":"10.1109/ICASERT.2019.8934479","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934479","url":null,"abstract":"An analysis is presented to show time series data of electricity generation mix and forecasting by 2030 in Bangladesh. The comparative studies have been analyzed using spatiotemporal data of Germany, Australia and Bangladesh. The spatiotemporal data has been taken out from World Bank data bank for analysis. A Linear regression technique is applied for forecasting electricity generation mix from 2015 to 2030. The result shows the rise of renewable energy sources, coal and oil, and the diminution of natural gas gradually.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"13 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":"91345819","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.2019.8934583
Fariya Tabassum, M. S. Rana
The performance of an automatic voltage regulator (AVR) system controlled by an optimal linear-quadratic-Gaussian (LQG) controller augmented with an integral action is investigated in this article for maintaining constant output voltage. The aim of this controller is to keep stable terminal voltage of a power system during sudden load variation. To verify its efficacy, a comparison is conducted with some existing controllers for instance the rate feedback stabilizer, proportional-integral-derivative (PID) controller, and linear quadratic regulator (LQR). The comparison is done on the basis of some important transient response characteristics and the proposed control scheme shows strong robustness against voltage variation due to load change.
{"title":"Robust Control of Terminal Voltage of an Isolated Electric Power Generating Unit","authors":"Fariya Tabassum, M. S. Rana","doi":"10.1109/ICASERT.2019.8934583","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934583","url":null,"abstract":"The performance of an automatic voltage regulator (AVR) system controlled by an optimal linear-quadratic-Gaussian (LQG) controller augmented with an integral action is investigated in this article for maintaining constant output voltage. The aim of this controller is to keep stable terminal voltage of a power system during sudden load variation. To verify its efficacy, a comparison is conducted with some existing controllers for instance the rate feedback stabilizer, proportional-integral-derivative (PID) controller, and linear quadratic regulator (LQR). The comparison is done on the basis of some important transient response characteristics and the proposed control scheme shows strong robustness against voltage variation due to load change.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"54 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":"90674501","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.2019.8934514
Shuvendu Roy, Md. Ijaj Sayim, M. Akhand
Voice classification task deals with sequential data. This is well known that this type of data is well processed by a recurrent neural network. In this work, we showed that in case of longer sequence convolutional neural network can give better accuracy. Whereas the recurrent network suffers from vanishing gradient problem even with a complex model like Long Short-Term Memory(LSTM). To illustrate the method we used pathological voice detection task. It is a type of problem in human voice caused by the internal defect in the throat and very hard to detect. In this work, we experimented with low dimension feature to compare both models rather than focusing on improving the overall accuracy.
{"title":"Pathological Voice Classification Using Deep Learning","authors":"Shuvendu Roy, Md. Ijaj Sayim, M. Akhand","doi":"10.1109/ICASERT.2019.8934514","DOIUrl":"https://doi.org/10.1109/ICASERT.2019.8934514","url":null,"abstract":"Voice classification task deals with sequential data. This is well known that this type of data is well processed by a recurrent neural network. In this work, we showed that in case of longer sequence convolutional neural network can give better accuracy. Whereas the recurrent network suffers from vanishing gradient problem even with a complex model like Long Short-Term Memory(LSTM). To illustrate the method we used pathological voice detection task. It is a type of problem in human voice caused by the internal defect in the throat and very hard to detect. In this work, we experimented with low dimension feature to compare both models rather than focusing on improving the overall accuracy.","PeriodicalId":6613,"journal":{"name":"2019 1st International Conference on Advances in Science, Engineering and Robotics Technology (ICASERT)","volume":"123 2 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":"91038900","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：