Pub Date : 2019-05-01DOI: 10.1109/RTEICT46194.2019.9016894
Suchismita Batabyal, A. A. Bazil Rai
Hardware security is of utmost importance nowadays, with the increased number of threats like modelling attacks, reverse engineering and extracting secret information from the IC's. A physical unclonable function (PUF) is a promising solution to many security related problems and can be used to produce devices or IC's that are unique and resistant to cloning attempts. A PUF is like a fingerprint for a particular physical object, it is based on many manufacturing mismatches that occur during IC fabrication or the propagation delays that are present in the wires and interconnects. Various kinds of PUF designs are possible like ring oscillator, SRAM and arbiter PUF's etc. A Ring oscillator based PUF is designed based on the delays present in the wires that leads to different frequency of oscillation and can form the basis for key generation. They are also easily implemented in field programmable gate array (FPGA).In this paper we propose a ring oscillator based design with enhanced challenge response pair (CRP) with improved reliability. Our design has more number of challenge response pair since all the possible frequency comparisons of the Ro are done. Also it provides better reliability because our approach relies on relative values and not absolute value, it incorporates the difference between the highest frequency in the present comparison and the maximum of all the measured frequencies, under varying environmental conditions even if the absolute value changes, the relative value will never change.
{"title":"Design of A Ring Oscillator Based PUF with Enhanced Challenge Response pair and Improved Reliability","authors":"Suchismita Batabyal, A. A. Bazil Rai","doi":"10.1109/RTEICT46194.2019.9016894","DOIUrl":"https://doi.org/10.1109/RTEICT46194.2019.9016894","url":null,"abstract":"Hardware security is of utmost importance nowadays, with the increased number of threats like modelling attacks, reverse engineering and extracting secret information from the IC's. A physical unclonable function (PUF) is a promising solution to many security related problems and can be used to produce devices or IC's that are unique and resistant to cloning attempts. A PUF is like a fingerprint for a particular physical object, it is based on many manufacturing mismatches that occur during IC fabrication or the propagation delays that are present in the wires and interconnects. Various kinds of PUF designs are possible like ring oscillator, SRAM and arbiter PUF's etc. A Ring oscillator based PUF is designed based on the delays present in the wires that leads to different frequency of oscillation and can form the basis for key generation. They are also easily implemented in field programmable gate array (FPGA).In this paper we propose a ring oscillator based design with enhanced challenge response pair (CRP) with improved reliability. Our design has more number of challenge response pair since all the possible frequency comparisons of the Ro are done. Also it provides better reliability because our approach relies on relative values and not absolute value, it incorporates the difference between the highest frequency in the present comparison and the maximum of all the measured frequencies, under varying environmental conditions even if the absolute value changes, the relative value will never change.","PeriodicalId":269385,"journal":{"name":"2019 4th International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134074796","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/RTEICT46194.2019.9016745
B. Pallavi, Keshvamurthy
Among the generally occurring common skin cancer, Melanoma is said to be the most dangerous type of cancer. Many of the Computer vision techniques have adapted to detect the disease early days. In the similar way this paper proposes an image pattern classification to identify skin disease in images with a combination of texture and color feature extraction. The main aim of this paper is to find appropriate features that can identify skin disease. Initially, normal and diseased images are collected and pre-processed by converting the images into Grayscale by PCA and multilevel Otsu thresholding. In addition the post processing includes dilation and erosion techniques and canny edge detection for quantization. Then features of shape, color and texture are extracted from the images and these images are classified by support vector machine classifier. A combination of several features is used to evaluate the appropriate features to find distinctive features for identification of disease. When a single feature is used, shape feature has the lowest accuracy of and texture feature has the highest accuracy. A combination of texture and color feature extraction results highest classification accuracy.
{"title":"A Hybrid Diagnosis System for Malignant Melanoma Detection in Dermoscopic Images","authors":"B. Pallavi, Keshvamurthy","doi":"10.1109/RTEICT46194.2019.9016745","DOIUrl":"https://doi.org/10.1109/RTEICT46194.2019.9016745","url":null,"abstract":"Among the generally occurring common skin cancer, Melanoma is said to be the most dangerous type of cancer. Many of the Computer vision techniques have adapted to detect the disease early days. In the similar way this paper proposes an image pattern classification to identify skin disease in images with a combination of texture and color feature extraction. The main aim of this paper is to find appropriate features that can identify skin disease. Initially, normal and diseased images are collected and pre-processed by converting the images into Grayscale by PCA and multilevel Otsu thresholding. In addition the post processing includes dilation and erosion techniques and canny edge detection for quantization. Then features of shape, color and texture are extracted from the images and these images are classified by support vector machine classifier. A combination of several features is used to evaluate the appropriate features to find distinctive features for identification of disease. When a single feature is used, shape feature has the lowest accuracy of and texture feature has the highest accuracy. A combination of texture and color feature extraction results highest classification accuracy.","PeriodicalId":269385,"journal":{"name":"2019 4th International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114429252","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/RTEICT46194.2019.9016768
Nandita Bangera, K. N.
Analytics plays vital role in Data Science. It involves finding trends and patterns from the huge repository of data. Scanning huge amount of data consumes lot of time, which can be reduced by sampling. In this paper we have demonstrated effectiveness of Progressive sampling wherein the sample size is gradually increased till it reaches a desired accuracy. By applying an algorithm based on Rademacher average to mine frequent datasets using Progressive sampling, we have shown that the runtime and the sampling time is considerably reduced as compared with static sampling.
{"title":"A Progressive Sampling based Approach to Reduce Sampling Time","authors":"Nandita Bangera, K. N.","doi":"10.1109/RTEICT46194.2019.9016768","DOIUrl":"https://doi.org/10.1109/RTEICT46194.2019.9016768","url":null,"abstract":"Analytics plays vital role in Data Science. It involves finding trends and patterns from the huge repository of data. Scanning huge amount of data consumes lot of time, which can be reduced by sampling. In this paper we have demonstrated effectiveness of Progressive sampling wherein the sample size is gradually increased till it reaches a desired accuracy. By applying an algorithm based on Rademacher average to mine frequent datasets using Progressive sampling, we have shown that the runtime and the sampling time is considerably reduced as compared with static sampling.","PeriodicalId":269385,"journal":{"name":"2019 4th International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114768213","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/RTEICT46194.2019.9016781
Shridhar Patil, P. Deepika
Bayer Colour Filter Array is a matrix of photosensors covered with red, green, and blue colour filters. This setup is advantageous in smartphones as only a third of the required data is captured by the sensor in the camera. The rest of the components based on the colour format can be interpolated using a suitable algorithm to arrive at a full-colour image. Increasing the resolution of the camera sensor will translate to increased bandwidth in the image signal processing pipeline, and consequently power consumption. In addition to that, the bit depth is also on the rise to enhance the colours. These two factors will create a huge impact on the data to be handled in the pertinent processor. Hence, compression of the Bayer data is of immense significance. The existing standard compression schemes can be adapted to suit the Bayer format. Also, several compression schemes, specific to Bayer format have been proposed. Two compression methods, viz. JPEG-LS and Hierarchical Prediction based compression have been tested and the corresponding results are presented in this paper. The former is a standard while the latter has been proposed keeping the Bayer format in mind. Modelling of the algorithms shows that JPEG-LS is best suited in the use cases where lossless compression is desirable, and Hierarchical Prediction based compression is the better option where some amount of loss is acceptable.
{"title":"Compression of Bayer Colour Filter Array Images","authors":"Shridhar Patil, P. Deepika","doi":"10.1109/RTEICT46194.2019.9016781","DOIUrl":"https://doi.org/10.1109/RTEICT46194.2019.9016781","url":null,"abstract":"Bayer Colour Filter Array is a matrix of photosensors covered with red, green, and blue colour filters. This setup is advantageous in smartphones as only a third of the required data is captured by the sensor in the camera. The rest of the components based on the colour format can be interpolated using a suitable algorithm to arrive at a full-colour image. Increasing the resolution of the camera sensor will translate to increased bandwidth in the image signal processing pipeline, and consequently power consumption. In addition to that, the bit depth is also on the rise to enhance the colours. These two factors will create a huge impact on the data to be handled in the pertinent processor. Hence, compression of the Bayer data is of immense significance. The existing standard compression schemes can be adapted to suit the Bayer format. Also, several compression schemes, specific to Bayer format have been proposed. Two compression methods, viz. JPEG-LS and Hierarchical Prediction based compression have been tested and the corresponding results are presented in this paper. The former is a standard while the latter has been proposed keeping the Bayer format in mind. Modelling of the algorithms shows that JPEG-LS is best suited in the use cases where lossless compression is desirable, and Hierarchical Prediction based compression is the better option where some amount of loss is acceptable.","PeriodicalId":269385,"journal":{"name":"2019 4th International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123664450","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/RTEICT46194.2019.9016771
P. Naveen, Praveen Kumar N, K. Sriganesh, T. Rajesh, K. Sushmitha
One of the most common faults experienced by the permanent magnet synchronous motor (PMSM) is stator interturn fault which account for 35-40% of the machine failure. This paper focuses on the stator inter-turn fault analysis in the stator winding of Permanent Magnet Synchronous Motor (PMSM) using Finite Element Method. The analysis is carried out for 12.5% and 25% inter-turn short in stator winding of PMSM. The analytical parameters of the motor which includes torque, winding current, induced voltage, speed and electromagnetic parameters like flux density, flux lines and radial flux density were obtained for the faulty machine and compared with the healthy machine. The simulation is done using the ANSYS Maxwell finite element analysis tool.
{"title":"Stator Fault Analysis of Permanent Magnet Synchronous Motor using Finite Element Method","authors":"P. Naveen, Praveen Kumar N, K. Sriganesh, T. Rajesh, K. Sushmitha","doi":"10.1109/RTEICT46194.2019.9016771","DOIUrl":"https://doi.org/10.1109/RTEICT46194.2019.9016771","url":null,"abstract":"One of the most common faults experienced by the permanent magnet synchronous motor (PMSM) is stator interturn fault which account for 35-40% of the machine failure. This paper focuses on the stator inter-turn fault analysis in the stator winding of Permanent Magnet Synchronous Motor (PMSM) using Finite Element Method. The analysis is carried out for 12.5% and 25% inter-turn short in stator winding of PMSM. The analytical parameters of the motor which includes torque, winding current, induced voltage, speed and electromagnetic parameters like flux density, flux lines and radial flux density were obtained for the faulty machine and compared with the healthy machine. The simulation is done using the ANSYS Maxwell finite element analysis tool.","PeriodicalId":269385,"journal":{"name":"2019 4th International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122734686","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/RTEICT46194.2019.9016753
P. Saikishan Bharadwaj, R. Kannan, H. Sridevi
The integration of renewable energy into the grid has become a challenge and faces two fundamental technological problems, namely variability and location. As renewable resources are focused far from the customers, it requires extra-long length, high-capacity transmission to coordinate the supply with the demand. It is essential to recognize the fluctuation and the vulnerability when examining and anticipating the tasks of the power grid. The test of the changeability can be met by exchanging conventional generation goal in or out in response to the possible estimates of weather by forecast and schedule deviation settlement mechanism (DSM). The deviation settlement mechanism is a penalty to the generator who under injects or over injects power into or outside the state with a buffer limit to bring awareness to the generator so that the forecast generation almost meets the actual generation taking the accuracy & AvC into account, in this paper the DSM calculations for inter and intra state has been shown and the comparison between less and more deviation pattern is shown for both solar and wind substations.
{"title":"DSM in Forecasting and Scheduling for Improving Integration of Renewable Energy Generation to the Grid","authors":"P. Saikishan Bharadwaj, R. Kannan, H. Sridevi","doi":"10.1109/RTEICT46194.2019.9016753","DOIUrl":"https://doi.org/10.1109/RTEICT46194.2019.9016753","url":null,"abstract":"The integration of renewable energy into the grid has become a challenge and faces two fundamental technological problems, namely variability and location. As renewable resources are focused far from the customers, it requires extra-long length, high-capacity transmission to coordinate the supply with the demand. It is essential to recognize the fluctuation and the vulnerability when examining and anticipating the tasks of the power grid. The test of the changeability can be met by exchanging conventional generation goal in or out in response to the possible estimates of weather by forecast and schedule deviation settlement mechanism (DSM). The deviation settlement mechanism is a penalty to the generator who under injects or over injects power into or outside the state with a buffer limit to bring awareness to the generator so that the forecast generation almost meets the actual generation taking the accuracy & AvC into account, in this paper the DSM calculations for inter and intra state has been shown and the comparison between less and more deviation pattern is shown for both solar and wind substations.","PeriodicalId":269385,"journal":{"name":"2019 4th International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125136295","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/RTEICT46194.2019.9016914
P M Anand, S. Thiruppathirajan, E. S. Shajahan, S. Sreekumar, P. Vinod, M. Narayanan Namboodiripad
Electrocardiogram (ECG) is a vital signal which represents the state of health of astronauts in a manned spaceflight mission and hence must be continuously acquired and transmitted throughout the mission. Telemetry bandwidth is a premium resource in such applications. Traditional method of sampling at Nyquist rate is highly bandwidth inefficient. Hence it is advantageous to use Compressive sensing (CS) technique to optimize data at measurement point itself. Conventional CS techniques employ computationally intensive measurement matrices which are not hardware efficient for both acquisition as well as recovery. In this work, a hardware efficient scheme with use of a sparse binary measurement matrix is proposed. The signal is recovered from the compressive measurement using a constraint function based on inverted Laplace distribution function. Gradient decent method is used to recursively recover the original ECG signal from the compressive measurements in an efficient manner. Apart from this, a projection scheme is also proposed to minimize the recovery error. The proposed scheme was extensively evaluated with different ECG samples with different compression ratios. Finally, the proposed scheme was benchmarked with Approximated L0 norm based method and it is found to perform more efficiently in compressively sensing and recovery of ECG signals.
{"title":"Compressive Sampling and Reconstruction of ECG Signal for Manned Spaceflight Applications","authors":"P M Anand, S. Thiruppathirajan, E. S. Shajahan, S. Sreekumar, P. Vinod, M. Narayanan Namboodiripad","doi":"10.1109/RTEICT46194.2019.9016914","DOIUrl":"https://doi.org/10.1109/RTEICT46194.2019.9016914","url":null,"abstract":"Electrocardiogram (ECG) is a vital signal which represents the state of health of astronauts in a manned spaceflight mission and hence must be continuously acquired and transmitted throughout the mission. Telemetry bandwidth is a premium resource in such applications. Traditional method of sampling at Nyquist rate is highly bandwidth inefficient. Hence it is advantageous to use Compressive sensing (CS) technique to optimize data at measurement point itself. Conventional CS techniques employ computationally intensive measurement matrices which are not hardware efficient for both acquisition as well as recovery. In this work, a hardware efficient scheme with use of a sparse binary measurement matrix is proposed. The signal is recovered from the compressive measurement using a constraint function based on inverted Laplace distribution function. Gradient decent method is used to recursively recover the original ECG signal from the compressive measurements in an efficient manner. Apart from this, a projection scheme is also proposed to minimize the recovery error. The proposed scheme was extensively evaluated with different ECG samples with different compression ratios. Finally, the proposed scheme was benchmarked with Approximated L0 norm based method and it is found to perform more efficiently in compressively sensing and recovery of ECG signals.","PeriodicalId":269385,"journal":{"name":"2019 4th International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125542803","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/RTEICT46194.2019.9016709
S. N. Prajwalasimha, S. Kavya, C. Navyakanth
This paper intends a fast and efficient cryptosystem based on confusion and Henon chaotic diffusion. The algorithm encrypts an image in two stages. In the first stage, the original images is transformed using Pseudo Hadamard transformation (PHT) along with substitution image. The key length used in the algorithm is 128 bits. These secrete key digits are used as initial conditions for Henon chaotic generator. A substitution box (S-box) is constructed using random sequences generated by chaotic generator. The cipher image from confusion stage is then subjected for diffusion using S-box. Based on the results obtained from differential and analytical tests, the proposed algorithm can withstand such security attacks compared to existing systems.
{"title":"Digital Image Encryption based on Transformation and Henon Chaotic Substitution","authors":"S. N. Prajwalasimha, S. Kavya, C. Navyakanth","doi":"10.1109/RTEICT46194.2019.9016709","DOIUrl":"https://doi.org/10.1109/RTEICT46194.2019.9016709","url":null,"abstract":"This paper intends a fast and efficient cryptosystem based on confusion and Henon chaotic diffusion. The algorithm encrypts an image in two stages. In the first stage, the original images is transformed using Pseudo Hadamard transformation (PHT) along with substitution image. The key length used in the algorithm is 128 bits. These secrete key digits are used as initial conditions for Henon chaotic generator. A substitution box (S-box) is constructed using random sequences generated by chaotic generator. The cipher image from confusion stage is then subjected for diffusion using S-box. Based on the results obtained from differential and analytical tests, the proposed algorithm can withstand such security attacks compared to existing systems.","PeriodicalId":269385,"journal":{"name":"2019 4th International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129501166","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/RTEICT46194.2019.9016786
Karthik Iyer, Girish Ewoorkar, Abhishek Patil, Hareesha Gummani, A. Parkavi
Udemy and Nptel are online learning platform where learners get access to wide variety of courses. These platforms have 2 issues which we aim to solve. First, Currently in Udemy the questions asked in discussion forum are not divided based on course videos, i.e. there is common discussion forum where question with respect to any content in the course can be asked. This is problem because, when a new question is asked all the question in the discussion forum have to be compared with the new question for similarity. This can take up significant amount of computational time. To avoid this we have applied Random Forest classifier to find out the category of a newly asked question (with respect to Udemy it would mean finding which video the question relates to), if category is found only previously asked questions in the particular category are compared for similarity rather than the previously asked questions in the whole database. Second, Currently NPTEL is not course coordinator friendly. This is because lots of times there is redundancy in the questions asked, this is burden on the course coordinator because he/she has to answer to each and every version of the same question. This has been tackled by using techniques like GBDT, SVM to detect semantic similarity of questions. The Random Forest classifier achieved accuracy of nearly 73% and GBDT achieved accuracy of nearly 64%.
{"title":"Efficient Model for Searching and Detecting Semantically Similar Question in Discussion Forums of e-learning Platforms","authors":"Karthik Iyer, Girish Ewoorkar, Abhishek Patil, Hareesha Gummani, A. Parkavi","doi":"10.1109/RTEICT46194.2019.9016786","DOIUrl":"https://doi.org/10.1109/RTEICT46194.2019.9016786","url":null,"abstract":"Udemy and Nptel are online learning platform where learners get access to wide variety of courses. These platforms have 2 issues which we aim to solve. First, Currently in Udemy the questions asked in discussion forum are not divided based on course videos, i.e. there is common discussion forum where question with respect to any content in the course can be asked. This is problem because, when a new question is asked all the question in the discussion forum have to be compared with the new question for similarity. This can take up significant amount of computational time. To avoid this we have applied Random Forest classifier to find out the category of a newly asked question (with respect to Udemy it would mean finding which video the question relates to), if category is found only previously asked questions in the particular category are compared for similarity rather than the previously asked questions in the whole database. Second, Currently NPTEL is not course coordinator friendly. This is because lots of times there is redundancy in the questions asked, this is burden on the course coordinator because he/she has to answer to each and every version of the same question. This has been tackled by using techniques like GBDT, SVM to detect semantic similarity of questions. The Random Forest classifier achieved accuracy of nearly 73% and GBDT achieved accuracy of nearly 64%.","PeriodicalId":269385,"journal":{"name":"2019 4th International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129512333","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/RTEICT46194.2019.9016906
N. Ashwini, N. Swathi, L. Prem, B. Nithin, A. N. Prajwal, G. A. S. Raghavendra
The present technology in the defence for the surveillance system is not effective. The different ways in which intruders invading to an unauthorized territory has increased over a year and thus causing a massive destruction and other violence which in turn results in life losses and, disturbs the peace of a country. There is no much advanced technology which can control the trespassers from invading, navigating on any terrain condition and on water with full time surveillance. In this paper, we have proposed a counter-foe night vision eyed robot, for monitoring and recognizing the foe activities along with authorized and unauthorized persons discernation within the premises using advanced Haar transformation and face recognition system with weapon detection capability. If robot recognizes any unusual activities, will automatically captures the scene and send the processed image to the base station. It can also transmit live video if necessary, at certain condition. Unlike recent technologies robot has also got the capability for detecting the invisible foe activities that takes place beneath the terra-firm with terrain switching mechanism.
{"title":"Integrated Secure Columnist Hexpod All- Terrain Full Time Counter-Foe Master","authors":"N. Ashwini, N. Swathi, L. Prem, B. Nithin, A. N. Prajwal, G. A. S. Raghavendra","doi":"10.1109/RTEICT46194.2019.9016906","DOIUrl":"https://doi.org/10.1109/RTEICT46194.2019.9016906","url":null,"abstract":"The present technology in the defence for the surveillance system is not effective. The different ways in which intruders invading to an unauthorized territory has increased over a year and thus causing a massive destruction and other violence which in turn results in life losses and, disturbs the peace of a country. There is no much advanced technology which can control the trespassers from invading, navigating on any terrain condition and on water with full time surveillance. In this paper, we have proposed a counter-foe night vision eyed robot, for monitoring and recognizing the foe activities along with authorized and unauthorized persons discernation within the premises using advanced Haar transformation and face recognition system with weapon detection capability. If robot recognizes any unusual activities, will automatically captures the scene and send the processed image to the base station. It can also transmit live video if necessary, at certain condition. Unlike recent technologies robot has also got the capability for detecting the invisible foe activities that takes place beneath the terra-firm with terrain switching mechanism.","PeriodicalId":269385,"journal":{"name":"2019 4th International Conference on Recent Trends on Electronics, Information, Communication & Technology (RTEICT)","volume":"48 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128229769","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：