Pub Date : 2021-12-01DOI: 10.1109/ComPE53109.2021.9752457
Md Sadik Tasrif Anubhove, Sayeed Hasan, Dewan Mahnaaz Mahmud, Eftakhar Hossain, Mohammad Zeyad, S. Ahmed, Sanjid Islam
Bangladesh's power generation is wholly reliant on non-renewable resources. Modern life is reliant on technology, and in order to keep up with the world's population and increase living standards, electricity production is crucial. Electricity outages disrupt the regular flow of life. Due to a higher demand than generation, impoverished people in countries like Bangladesh are subjected to load shedding. Utilization of renewable energy and effective power conservation are critical in meeting people's needs. Low income people, in particular, suffer greatly during daily load shedding of more than five hours. This manuscript offers an environment friendly, independent, cost-effective design of a system that provides power not only during daylight hours but also during load-shedding in the Bangladeshi sub-district of Parbatipur. With the right use of renewable energy, the suggested system sends energy directly to low-powered DC loads and charges the battery when sunlight is available, minimizing the inverter's cost and the unit cost of the electricity bill. To charge a 12 V DC battery, a photovoltaic (PV) panel is employed, and an Arduino is used to monitor the battery and manage the charging process. Through analysis, the suggested system is shown to be effective in reducing the trend of emissions toward greenhouse gases.
{"title":"Solar Energy Home Systems for Rural Areas Communities in Bangladesh","authors":"Md Sadik Tasrif Anubhove, Sayeed Hasan, Dewan Mahnaaz Mahmud, Eftakhar Hossain, Mohammad Zeyad, S. Ahmed, Sanjid Islam","doi":"10.1109/ComPE53109.2021.9752457","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9752457","url":null,"abstract":"Bangladesh's power generation is wholly reliant on non-renewable resources. Modern life is reliant on technology, and in order to keep up with the world's population and increase living standards, electricity production is crucial. Electricity outages disrupt the regular flow of life. Due to a higher demand than generation, impoverished people in countries like Bangladesh are subjected to load shedding. Utilization of renewable energy and effective power conservation are critical in meeting people's needs. Low income people, in particular, suffer greatly during daily load shedding of more than five hours. This manuscript offers an environment friendly, independent, cost-effective design of a system that provides power not only during daylight hours but also during load-shedding in the Bangladeshi sub-district of Parbatipur. With the right use of renewable energy, the suggested system sends energy directly to low-powered DC loads and charges the battery when sunlight is available, minimizing the inverter's cost and the unit cost of the electricity bill. To charge a 12 V DC battery, a photovoltaic (PV) panel is employed, and an Arduino is used to monitor the battery and manage the charging process. Through analysis, the suggested system is shown to be effective in reducing the trend of emissions toward greenhouse gases.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"143 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131618767","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 : 2021-12-01DOI: 10.1109/ComPE53109.2021.9752437
S. Karad, Ritula Thakur
Modelling and control of complex non-linear systems is always important area of investigation in different fields of engineering applications. Since last decade fractional order control emerge as an efficient strategy for modelling and control of complex non-linear systems and shown the efficiency. Also, recently intelligent control strategies based on various AI techniques shown their efficiency in various fields such as process control, power system, renewable energy, etc. This paper applies Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) tuned intelligent fractional order pitch regulator for doubly fed induction generator (DFIG) based wind turbine (WT) system. Proposed scheme is modelled and simulated using Matlab/Simulink to analyze its time domain performance for a step input as well as tracking response with ITAE and IAE index.
{"title":"Genetic Algorithm and Particle Swarm Optimization tuned Fractional Order Pitch Angle Control","authors":"S. Karad, Ritula Thakur","doi":"10.1109/ComPE53109.2021.9752437","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9752437","url":null,"abstract":"Modelling and control of complex non-linear systems is always important area of investigation in different fields of engineering applications. Since last decade fractional order control emerge as an efficient strategy for modelling and control of complex non-linear systems and shown the efficiency. Also, recently intelligent control strategies based on various AI techniques shown their efficiency in various fields such as process control, power system, renewable energy, etc. This paper applies Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) tuned intelligent fractional order pitch regulator for doubly fed induction generator (DFIG) based wind turbine (WT) system. Proposed scheme is modelled and simulated using Matlab/Simulink to analyze its time domain performance for a step input as well as tracking response with ITAE and IAE index.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126466313","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 : 2021-12-01DOI: 10.1109/ComPE53109.2021.9751995
Mamta Dhaka, D. Sharma, Suresh Kumar Sharma, A. Dixit
The dynamic information & communication (ICT) sector is cloud computing, which creates new environmental protection issues. Cloud Computing technologies have many uses since they are scalable, reliable and confidence-based and cost-effective, relatively cheap. The Cloud computing revolution restructures current networking and provides potential environmental, economic, and technical benefits. In this paper, we have discussed and reviewed several aspects of secure and energy-efficient resource utilization using green cloud services in healthcare services. Checklists, alerts, and tools use the EHR systems to improve quality and the patient's safety and to promote standardized, evidence-based practice with embedded clinical guiding principles, electronic prescribing and testing methods that reduce errors and redundancies, and discrete data areas which encourage the use of efficiency dashboards & compliance reports. Quicker, higher precise interaction and simplified procedures have resulted in higher patient flows, less duplicate testing, more rapid patient survey response, redistribution of transcribing and demand workers, more comprehensive collection of fees and government incentives. Their survey aims to provide up-to-date advice for green cloud computing research.
{"title":"An Analysis of Electronic Health Record System in Healthcare Services in Cloud: A Review Perspective","authors":"Mamta Dhaka, D. Sharma, Suresh Kumar Sharma, A. Dixit","doi":"10.1109/ComPE53109.2021.9751995","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9751995","url":null,"abstract":"The dynamic information & communication (ICT) sector is cloud computing, which creates new environmental protection issues. Cloud Computing technologies have many uses since they are scalable, reliable and confidence-based and cost-effective, relatively cheap. The Cloud computing revolution restructures current networking and provides potential environmental, economic, and technical benefits. In this paper, we have discussed and reviewed several aspects of secure and energy-efficient resource utilization using green cloud services in healthcare services. Checklists, alerts, and tools use the EHR systems to improve quality and the patient's safety and to promote standardized, evidence-based practice with embedded clinical guiding principles, electronic prescribing and testing methods that reduce errors and redundancies, and discrete data areas which encourage the use of efficiency dashboards & compliance reports. Quicker, higher precise interaction and simplified procedures have resulted in higher patient flows, less duplicate testing, more rapid patient survey response, redistribution of transcribing and demand workers, more comprehensive collection of fees and government incentives. Their survey aims to provide up-to-date advice for green cloud computing research.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131832012","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 : 2021-12-01DOI: 10.1109/ComPE53109.2021.9752294
Jyotsnamayee Ram
Data from SCATSAT-1 is widely used in a variety of terrestrial and oceanographic applications. SCATSAT – 1's payload is a scatterometer. The scatterometer measures the backscatter coefficient over the globe. The backscattering coefficient is used to compute parameters such as Sigma0, Wind Vectors (over ocean), and Brightness temperature, and related HDF products are generated. It provides data products in four Levels (1-4) in the form of various parameters. This project is being carried out with the help of data products of Level 2 and 3. (Sigma0, Wind vectors & Brightness Temperature). The objectives covered in this project are: a) To generate CF (Climate and Forecast Metadata Conventions) - compliant SCATSAT-1 data products: One method for making the data platform independent and accessible through visualization packages is to make it CF compliant. b) Additionally, to visualize data through http-based access: Data visualization is a key necessity for the scientific data community's study and research. CF provides a standardized mechanism for creating metadata construct. The goal is to require conforming datasets to have adequate self-describing information (metadata). CF-compliant data products can be created by including extra attributes and datasets as defined in the conventions. In addition, a web application is also developed to visualize these datasets over geospatial platform.
{"title":"SCATSAT – 1 Data Products Visualization","authors":"Jyotsnamayee Ram","doi":"10.1109/ComPE53109.2021.9752294","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9752294","url":null,"abstract":"Data from SCATSAT-1 is widely used in a variety of terrestrial and oceanographic applications. SCATSAT – 1's payload is a scatterometer. The scatterometer measures the backscatter coefficient over the globe. The backscattering coefficient is used to compute parameters such as Sigma0, Wind Vectors (over ocean), and Brightness temperature, and related HDF products are generated. It provides data products in four Levels (1-4) in the form of various parameters. This project is being carried out with the help of data products of Level 2 and 3. (Sigma0, Wind vectors & Brightness Temperature). The objectives covered in this project are: a) To generate CF (Climate and Forecast Metadata Conventions) - compliant SCATSAT-1 data products: One method for making the data platform independent and accessible through visualization packages is to make it CF compliant. b) Additionally, to visualize data through http-based access: Data visualization is a key necessity for the scientific data community's study and research. CF provides a standardized mechanism for creating metadata construct. The goal is to require conforming datasets to have adequate self-describing information (metadata). CF-compliant data products can be created by including extra attributes and datasets as defined in the conventions. In addition, a web application is also developed to visualize these datasets over geospatial platform.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124644736","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 : 2021-12-01DOI: 10.1109/ComPE53109.2021.9751727
K. C., Mandalapu Durga Pradeep, Kopparapu Sasidhar, Chitta Aditya, K. Sankaran, V. Kiruthika
Electrocardiogram (ECG) refers to the test performed on the heart with a view to detect abnormalities in the cardiovascular system if any. The careful analysis of the components of ECG enables the medical experts to detect the minor abnormalities of the heart and suggest effective treatment. This paper proposes an effective method of analyzing the ECG to detect the various abnormalities. After the collection and analysis of the ECG signal, behavioral and dynamic features can be obtained from the signal followed by two methods of classification by factor and feature testing. The proposed work for this paper has been implemented using MATLAB. The proposed methodology proved effective in analyzing and classifying the ECG signals with 97% accuracy.
{"title":"A Low Cost and Portable Electrocardiogram (ECG) for Predicting Arrhythmia","authors":"K. C., Mandalapu Durga Pradeep, Kopparapu Sasidhar, Chitta Aditya, K. Sankaran, V. Kiruthika","doi":"10.1109/ComPE53109.2021.9751727","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9751727","url":null,"abstract":"Electrocardiogram (ECG) refers to the test performed on the heart with a view to detect abnormalities in the cardiovascular system if any. The careful analysis of the components of ECG enables the medical experts to detect the minor abnormalities of the heart and suggest effective treatment. This paper proposes an effective method of analyzing the ECG to detect the various abnormalities. After the collection and analysis of the ECG signal, behavioral and dynamic features can be obtained from the signal followed by two methods of classification by factor and feature testing. The proposed work for this paper has been implemented using MATLAB. The proposed methodology proved effective in analyzing and classifying the ECG signals with 97% accuracy.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"2016 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121339581","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 : 2021-12-01DOI: 10.1109/ComPE53109.2021.9752235
Ms. Aishwarya Gowda A G, Hui-Kai Su, W. Kuo
In the growing requirement of healthcare needs the healthcare devices and instruments are used in every level of treatments. All of these devices are not just used once in their lifetime. Most of the devices are very expensive and are reused on different patients depending on their requirements. As the reusing increases, the history of usage and disinfecting with proper cleaning plays a major role in maintaining hygiene. This process of maintaining the required hygiene will stop the spread of diseases and infections to other patients. Hence, knowing the complete whereabouts of medical instruments will ensure the safety and provide complete information about the devices at a single tap before using the device. This gives a clear understanding of the devices for doctors or health care workers before the use of any reusable medical instruments. The process of recording the whereabouts of these instruments is accomplished with the latest striving technology like Artificial Intelligence. This will not just help in knowing the history but also provides clarity of information and trust on the devices before being used. LSTM is a model based on artificial intelligence which adds on in detecting the device and the purpose of usage automatically. The whereabouts are identified and carried out with a well-trained AI model and additive real-time data updates.
{"title":"Medical Instruments Whereabouts Using Artificial Intelligence","authors":"Ms. Aishwarya Gowda A G, Hui-Kai Su, W. Kuo","doi":"10.1109/ComPE53109.2021.9752235","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9752235","url":null,"abstract":"In the growing requirement of healthcare needs the healthcare devices and instruments are used in every level of treatments. All of these devices are not just used once in their lifetime. Most of the devices are very expensive and are reused on different patients depending on their requirements. As the reusing increases, the history of usage and disinfecting with proper cleaning plays a major role in maintaining hygiene. This process of maintaining the required hygiene will stop the spread of diseases and infections to other patients. Hence, knowing the complete whereabouts of medical instruments will ensure the safety and provide complete information about the devices at a single tap before using the device. This gives a clear understanding of the devices for doctors or health care workers before the use of any reusable medical instruments. The process of recording the whereabouts of these instruments is accomplished with the latest striving technology like Artificial Intelligence. This will not just help in knowing the history but also provides clarity of information and trust on the devices before being used. LSTM is a model based on artificial intelligence which adds on in detecting the device and the purpose of usage automatically. The whereabouts are identified and carried out with a well-trained AI model and additive real-time data updates.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130645370","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 : 2021-12-01DOI: 10.1109/ComPE53109.2021.9752014
Deeksha Naithani, M. Chaturvedi, P. Juneja, Prabhat Kumar, S. Kapoor
The idea of fractional order controller in combination with Nelder Mead algorithm is proposed in this paper for controlling a multivariable industrial scale polymerization reactor. The concept of decentralization is also applied to identify the pairing and decentralization of loops for better performance of the controller. PID controller is tuned using Cohen-Coon (CC) tuning technique. CC tuning technique is more flexible and suitable in comparison to conventional Ziegler-Nichols tuning technique. Using Nelder-Mead optimization technique, the Fractional Order-PID (FO-PID) controller parameters including the special parametric values are calculated which plays a very important role in tuning of FO-PID controllers finely and for optimal performance of these controllers. Simulation results are obtained and dynamic characteristics and performance indices are calculated and analyzed.
{"title":"Design and Implementation of Fractional Order Controllers Using Nelder-Mead Algorithm","authors":"Deeksha Naithani, M. Chaturvedi, P. Juneja, Prabhat Kumar, S. Kapoor","doi":"10.1109/ComPE53109.2021.9752014","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9752014","url":null,"abstract":"The idea of fractional order controller in combination with Nelder Mead algorithm is proposed in this paper for controlling a multivariable industrial scale polymerization reactor. The concept of decentralization is also applied to identify the pairing and decentralization of loops for better performance of the controller. PID controller is tuned using Cohen-Coon (CC) tuning technique. CC tuning technique is more flexible and suitable in comparison to conventional Ziegler-Nichols tuning technique. Using Nelder-Mead optimization technique, the Fractional Order-PID (FO-PID) controller parameters including the special parametric values are calculated which plays a very important role in tuning of FO-PID controllers finely and for optimal performance of these controllers. Simulation results are obtained and dynamic characteristics and performance indices are calculated and analyzed.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134176252","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 : 2021-12-01DOI: 10.1109/ComPE53109.2021.9751921
V. Baskar, Ikben Ghosh, S. Karthikeyan, R. Hemalatha, T. Thamizhvani
In 2014, the World Health Organization estimated that 285 million people were visually impaired in the world, 39 million are blind and 246 million have low vision. With the development of technologies, various techniques evolved for assisting the visually impaired people. These people need to have such supportive system which will make the things much easier and they don’t have to rely on others every now and then. For which various devices has already been invented. But most of them are GPS based which unfortunately prevent them to be effectively and efficiently used in the indoor environment. Our motive is to bring up an idea which can help these people in the indoor environment and make their life much simpler. In our project both the obstacle detection and navigation together are done using the Raspberry Pi 3 camera, the PIR sensor, ultrasonic sensors, so that the obstacles can be detected in real time. For the navigation purpose the ultrasonic sensor has been used and the output is provided by speakers and the vibrator motors and buzzer. For the testing of the system, obstacles are placed in front of the system and it was able to detect the obstacles successfully and without any errors. The Camera was able to detect the predefined objects successfully. The speaker and buzzer motors were able to warn the user about the obstacles. The device includes two vibrator motors that are placed in both the hands that will be navigating the user which way the obstacle is there and which way the user has to move. The vibrators were successfully able to navigate the user.
{"title":"An Indoor Obstacle Detector to Assist the Visually Impaired Person on Real-Time with a Navigator","authors":"V. Baskar, Ikben Ghosh, S. Karthikeyan, R. Hemalatha, T. Thamizhvani","doi":"10.1109/ComPE53109.2021.9751921","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9751921","url":null,"abstract":"In 2014, the World Health Organization estimated that 285 million people were visually impaired in the world, 39 million are blind and 246 million have low vision. With the development of technologies, various techniques evolved for assisting the visually impaired people. These people need to have such supportive system which will make the things much easier and they don’t have to rely on others every now and then. For which various devices has already been invented. But most of them are GPS based which unfortunately prevent them to be effectively and efficiently used in the indoor environment. Our motive is to bring up an idea which can help these people in the indoor environment and make their life much simpler. In our project both the obstacle detection and navigation together are done using the Raspberry Pi 3 camera, the PIR sensor, ultrasonic sensors, so that the obstacles can be detected in real time. For the navigation purpose the ultrasonic sensor has been used and the output is provided by speakers and the vibrator motors and buzzer. For the testing of the system, obstacles are placed in front of the system and it was able to detect the obstacles successfully and without any errors. The Camera was able to detect the predefined objects successfully. The speaker and buzzer motors were able to warn the user about the obstacles. The device includes two vibrator motors that are placed in both the hands that will be navigating the user which way the obstacle is there and which way the user has to move. The vibrators were successfully able to navigate the user.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134200502","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 : 2021-12-01DOI: 10.1109/ComPE53109.2021.9751919
Pranjali Deshpande, Sunita Jahirabadkar
Language is the basic and unique tool of communication for humans. More than 7000 languages exist on our planet. Among these, the languages which lack in linguistic resources for building statistical NLP applications are known as low resource languages (LRL). Written communication is the most popular medium for humans to express and preserve their thoughts. Advancements in technology are bringing the world closer by facilitating remote communication access. Due to increase in the use of internet, with every second new textual information is getting generated. Not all this textual information is useful. With this context the task of summarization is gaining importance. Summary can be generated by two ways: Extractive and Abstractive. In Extractive summarization the key phrases and key sentences in the source document are retained, whereas Abstractive summary is generated by rewriting the key sentences. The task of summarization becomes more challenging in case of LRL documents. The paper focuses on the experiments carried out for extractive summarization of LRL documents using two approaches: Lexical chain and BERT.
{"title":"Study of Low Resource Language Document Extractive Summarization using Lexical chain and Bidirectional Encoder Representations from Transformers (BERT)","authors":"Pranjali Deshpande, Sunita Jahirabadkar","doi":"10.1109/ComPE53109.2021.9751919","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9751919","url":null,"abstract":"Language is the basic and unique tool of communication for humans. More than 7000 languages exist on our planet. Among these, the languages which lack in linguistic resources for building statistical NLP applications are known as low resource languages (LRL). Written communication is the most popular medium for humans to express and preserve their thoughts. Advancements in technology are bringing the world closer by facilitating remote communication access. Due to increase in the use of internet, with every second new textual information is getting generated. Not all this textual information is useful. With this context the task of summarization is gaining importance. Summary can be generated by two ways: Extractive and Abstractive. In Extractive summarization the key phrases and key sentences in the source document are retained, whereas Abstractive summary is generated by rewriting the key sentences. The task of summarization becomes more challenging in case of LRL documents. The paper focuses on the experiments carried out for extractive summarization of LRL documents using two approaches: Lexical chain and BERT.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130844520","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 : 2021-12-01DOI: 10.1109/ComPE53109.2021.9751835
Deepak Kumar, Alpana Kakkar, A. Dubey
The technological era has changed drastically from whatit used to be few decades ago. Each person at this time may have more than one device which produces data, and being in this era, data is neither limited nor it is resistible. In decade like this every device produces data, each click produces data; this data could be structured, semistructured and unstructured containing location data to logs of sensors. The amount of data being produced every day is just increasing and there is no near future that this will slow down. This has come as a blessing to almost all sectors as this data can be used to make their future decision, thus decreasing the changes of failure. This paper aims to give pattern analysis in academic for mentor systems. We have analyzeda case study of an academic dataset of mentor systems and analyzed this to give the behavior and pattern included in the data to make better decision.
{"title":"Pattern Analysis in Academics for Mentor Systems","authors":"Deepak Kumar, Alpana Kakkar, A. Dubey","doi":"10.1109/ComPE53109.2021.9751835","DOIUrl":"https://doi.org/10.1109/ComPE53109.2021.9751835","url":null,"abstract":"The technological era has changed drastically from whatit used to be few decades ago. Each person at this time may have more than one device which produces data, and being in this era, data is neither limited nor it is resistible. In decade like this every device produces data, each click produces data; this data could be structured, semistructured and unstructured containing location data to logs of sensors. The amount of data being produced every day is just increasing and there is no near future that this will slow down. This has come as a blessing to almost all sectors as this data can be used to make their future decision, thus decreasing the changes of failure. This paper aims to give pattern analysis in academic for mentor systems. We have analyzeda case study of an academic dataset of mentor systems and analyzed this to give the behavior and pattern included in the data to make better decision.","PeriodicalId":211704,"journal":{"name":"2021 International Conference on Computational Performance Evaluation (ComPE)","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129787204","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：