Pub Date : 2019-03-01DOI: 10.1109/ICACCS.2019.8728389
Akshay Pillai, S. M, Lakshmy K V
As of today, most of the Internet of Things (IoT) devices work in a centralized environment. With IoT devices having to execute thousands of operations per second, it has become difficult for centralized systems to handle such platforms. Also, factors like operational and maintenance cost of these server machines and danger of DoS(Denial of Service) attack on such servers has threatened the practitioners to come up with a more distributed way of storing the contents. With its decentralized and privacy preserving features, blockchain technology fits well into the scheme of things. This mitigates the quintessential challenges faced in most of the centralized systems. In this paper, we are focusing on the new firmware update scheme to perform the update operations securely. We propose a blockchain based solution for managing firmware updates in IoT. Improper management of devices and distribution of firmware updates from the device vendor could sabotage the IoT ecosystem. The objective of this proposed scheme is to verify and distribute the firmware binaries securely to the IoT device deployed by the device vendor. The PUSH-based method is used for a firmware update in which verification of firmware is done by Hash Chain. It preserves the integrity of firmware by linking the latest version information by previous versions information with the help of a smart contract mechanism.
{"title":"Securing Firmware in Internet of Things using Blockchain","authors":"Akshay Pillai, S. M, Lakshmy K V","doi":"10.1109/ICACCS.2019.8728389","DOIUrl":"https://doi.org/10.1109/ICACCS.2019.8728389","url":null,"abstract":"As of today, most of the Internet of Things (IoT) devices work in a centralized environment. With IoT devices having to execute thousands of operations per second, it has become difficult for centralized systems to handle such platforms. Also, factors like operational and maintenance cost of these server machines and danger of DoS(Denial of Service) attack on such servers has threatened the practitioners to come up with a more distributed way of storing the contents. With its decentralized and privacy preserving features, blockchain technology fits well into the scheme of things. This mitigates the quintessential challenges faced in most of the centralized systems. In this paper, we are focusing on the new firmware update scheme to perform the update operations securely. We propose a blockchain based solution for managing firmware updates in IoT. Improper management of devices and distribution of firmware updates from the device vendor could sabotage the IoT ecosystem. The objective of this proposed scheme is to verify and distribute the firmware binaries securely to the IoT device deployed by the device vendor. The PUSH-based method is used for a firmware update in which verification of firmware is done by Hash Chain. It preserves the integrity of firmware by linking the latest version information by previous versions information with the help of a smart contract mechanism.","PeriodicalId":249139,"journal":{"name":"2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114031159","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 : 2019-03-01DOI: 10.1109/ICACCS.2019.8728553
A. Moin, Tanuja. Ch, N. Senthil Kumar, M. Nallakaruppan, U. Senthilkumaran
Global Effoets for reducing the accidents are growing faster but the accidents happened is growing are the fastest one. An analysis clealy shows around 30 percent of the accidents happening around the road is mainly because of the drunk and drive. Through survelliance camera and alcohol measuring meters we can monitor the drunk and drive incidents around the city. But cars are speedy at highways where deploying security person for checking drunken drivers is unimaginobly difficult. To solve this in the prescribed work we deploy the sensors in every tool booth to monitor the incoming vehicles and stop the drunken drivers to further drive on the highway. This device is built from existing data acquired from the drunken drivers which is analyzed with machine learning techniques and mathematical data analysis models.
{"title":"Sensing Drunken Drivers Using Data Science","authors":"A. Moin, Tanuja. Ch, N. Senthil Kumar, M. Nallakaruppan, U. Senthilkumaran","doi":"10.1109/ICACCS.2019.8728553","DOIUrl":"https://doi.org/10.1109/ICACCS.2019.8728553","url":null,"abstract":"Global Effoets for reducing the accidents are growing faster but the accidents happened is growing are the fastest one. An analysis clealy shows around 30 percent of the accidents happening around the road is mainly because of the drunk and drive. Through survelliance camera and alcohol measuring meters we can monitor the drunk and drive incidents around the city. But cars are speedy at highways where deploying security person for checking drunken drivers is unimaginobly difficult. To solve this in the prescribed work we deploy the sensors in every tool booth to monitor the incoming vehicles and stop the drunken drivers to further drive on the highway. This device is built from existing data acquired from the drunken drivers which is analyzed with machine learning techniques and mathematical data analysis models.","PeriodicalId":249139,"journal":{"name":"2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS)","volume":"135 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122906920","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 : 2019-03-01DOI: 10.1109/ICACCS.2019.8728305
P. P, Pulugurtha Niketha, SaanthaLakshmi K, Sharmila S, D. R
This paper advances in a vision based driver assistance system for effective lane detection Technique. First method involves image processing technique initially to convert the Red, green and blue (RGB) into grayscale images takes place by removing the effects of shades and immersion data of the images by maintaining the brightness of the images. Then to remove the sound available in the images and the obtained video is allowed to pass through the Gaussian filter in-order to remove sound from the images. The edges recognition is an important function to identify and detect the sharp break in an image by canny edge detection algorithm. Then Hough transform technique is applied to obtain the image pixels in the form of long straight line in the Hough space. So we can detect the lane if the vehicle tends to deviate from the lane in a complex situation and take corrective measures to change the lane.
{"title":"Advances in Vision based Lane Detection Algorithm Based on Reliable Lane Markings","authors":"P. P, Pulugurtha Niketha, SaanthaLakshmi K, Sharmila S, D. R","doi":"10.1109/ICACCS.2019.8728305","DOIUrl":"https://doi.org/10.1109/ICACCS.2019.8728305","url":null,"abstract":"This paper advances in a vision based driver assistance system for effective lane detection Technique. First method involves image processing technique initially to convert the Red, green and blue (RGB) into grayscale images takes place by removing the effects of shades and immersion data of the images by maintaining the brightness of the images. Then to remove the sound available in the images and the obtained video is allowed to pass through the Gaussian filter in-order to remove sound from the images. The edges recognition is an important function to identify and detect the sharp break in an image by canny edge detection algorithm. Then Hough transform technique is applied to obtain the image pixels in the form of long straight line in the Hough space. So we can detect the lane if the vehicle tends to deviate from the lane in a complex situation and take corrective measures to change the lane.","PeriodicalId":249139,"journal":{"name":"2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS)","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132753396","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 : 2019-03-01DOI: 10.1109/ICACCS.2019.8728480
P. Malini, G. Balaji, K. Boopathiraja, A. Gautami, P. Shanmugavadivu, S. Pandian
This paper presents an effective logical approach low power full adder, which reduces power consumption by implementing full adder using EXOR-EXNOR circuit. The advanced new hybrid FA modules are more efficient in terms of the energy and postponement, these are because of the low yield capability and low power consumption. These proposed circuits are planned dependent on the full-swing EXOR–EXNOR or EXOR/EXNOR gates. Every one of the new designs has their very own preferences regarding speed, energy consumption, delay product, capacity of driving, and soon. To examine the execution of the new structures, broad Tanner simulation tools are utilized. By utilizing the transistor measuring (W/L) technique, the optimization of the PDP gained for every hybrid adder circuit.
{"title":"Design of Swing Dependent XOR-XNOR Gates based Hybrid Full Adder","authors":"P. Malini, G. Balaji, K. Boopathiraja, A. Gautami, P. Shanmugavadivu, S. Pandian","doi":"10.1109/ICACCS.2019.8728480","DOIUrl":"https://doi.org/10.1109/ICACCS.2019.8728480","url":null,"abstract":"This paper presents an effective logical approach low power full adder, which reduces power consumption by implementing full adder using EXOR-EXNOR circuit. The advanced new hybrid FA modules are more efficient in terms of the energy and postponement, these are because of the low yield capability and low power consumption. These proposed circuits are planned dependent on the full-swing EXOR–EXNOR or EXOR/EXNOR gates. Every one of the new designs has their very own preferences regarding speed, energy consumption, delay product, capacity of driving, and soon. To examine the execution of the new structures, broad Tanner simulation tools are utilized. By utilizing the transistor measuring (W/L) technique, the optimization of the PDP gained for every hybrid adder circuit.","PeriodicalId":249139,"journal":{"name":"2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS)","volume":"605 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132788605","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 : 2019-03-01DOI: 10.1109/ICACCS.2019.8728327
S. Vani, T. Madhusudhana Rao, Ch. Kannam Naidu
Neural Networks, with their remarkable capacity to get significance from convoluted information can be utilized to remove patterns that are too composite to be in any way seen by humans. A prepared neural network can be thought of as a specialist in the classification of data which is given to analyze. There are different kinds of Neural Networks like Artificial Neural Network (ANN), Feedforward Neural Network, Recurrent Neural Network(RNN), Recursive Recurrent Neural Network (RRNN), Convolutional Neural Network(CNN), Modular Neural Network (MNN), Restricted Boltzmann Machine (RBM) etc. In this paper, we have discussed the performance of ANN, CNN, RNN, and RBM where CNN has outplayed the remaining with accuracy of 97.81%.
{"title":"Comparative Analysis on variants of Neural Networks: An Experimental Study","authors":"S. Vani, T. Madhusudhana Rao, Ch. Kannam Naidu","doi":"10.1109/ICACCS.2019.8728327","DOIUrl":"https://doi.org/10.1109/ICACCS.2019.8728327","url":null,"abstract":"Neural Networks, with their remarkable capacity to get significance from convoluted information can be utilized to remove patterns that are too composite to be in any way seen by humans. A prepared neural network can be thought of as a specialist in the classification of data which is given to analyze. There are different kinds of Neural Networks like Artificial Neural Network (ANN), Feedforward Neural Network, Recurrent Neural Network(RNN), Recursive Recurrent Neural Network (RRNN), Convolutional Neural Network(CNN), Modular Neural Network (MNN), Restricted Boltzmann Machine (RBM) etc. In this paper, we have discussed the performance of ANN, CNN, RNN, and RBM where CNN has outplayed the remaining with accuracy of 97.81%.","PeriodicalId":249139,"journal":{"name":"2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134347885","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 : 2019-03-01DOI: 10.1109/ICACCS.2019.8728395
N. Jayanthi, I. Kala, P. S. Sunantha, Sukra A
The important factor to calculate insurance is to inspect the damage of a vehicle for that the client has to migrate to the insurance company and have to wait for the arrival of the inspecting person. To make this ease for the client, he does not need to wait until the insurer calculates the amount of insurance to recover the damage happened. The core technique of this process is augmented reality. Once the dent images are uploaded then it produces the predicted cost. This predicted cost is produced as per the percentage of dent calculated using augmented reality image processing. Then as per the insurance claimed by the client, it is mapped with the amount calculated using augmented reality. This paper presents an innovative approach to detect vehicle’s body damage and cost estimation for the vehicle insurance with using 2D images
{"title":"Vehicle Insurance Calculator Using Augmented Reality","authors":"N. Jayanthi, I. Kala, P. S. Sunantha, Sukra A","doi":"10.1109/ICACCS.2019.8728395","DOIUrl":"https://doi.org/10.1109/ICACCS.2019.8728395","url":null,"abstract":"The important factor to calculate insurance is to inspect the damage of a vehicle for that the client has to migrate to the insurance company and have to wait for the arrival of the inspecting person. To make this ease for the client, he does not need to wait until the insurer calculates the amount of insurance to recover the damage happened. The core technique of this process is augmented reality. Once the dent images are uploaded then it produces the predicted cost. This predicted cost is produced as per the percentage of dent calculated using augmented reality image processing. Then as per the insurance claimed by the client, it is mapped with the amount calculated using augmented reality. This paper presents an innovative approach to detect vehicle’s body damage and cost estimation for the vehicle insurance with using 2D images","PeriodicalId":249139,"journal":{"name":"2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115742659","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 : 2019-03-01DOI: 10.1109/ICACCS.2019.8728350
R. Aarthi, R. B. Kumar, T. Ravichandran, S. Giridharan
Hydro power vitality is one of the most encouraging clean vitality technology. This vitality innovation has numerous difficulties when contrasted and other sustainable power sources for instance biomass, sun oriented and wind energies. It has high capital speculation cost. Hydro plant is an essential product in non-renewable energy sources. When we are going with a hydro plant, we have developed a piezoelectric generator that harvests mechanical vibrations energy for increasing generating electrical energy. Piezoelectric electrical device that is associate degree mechanical device undergoes mechanical vibrations thus turn out electricity. So here we have done an efficient turbine controller which can be sufficiently able to withstand stacking however not too much overwhelming in order to force superfluous on the drive. Nowadays control request is more. So this task has created to produce the electrical power so as to remunerate the electric power request and monitoring condition.
{"title":"A Smart Hydro Electric Generator in Home Based On IOT","authors":"R. Aarthi, R. B. Kumar, T. Ravichandran, S. Giridharan","doi":"10.1109/ICACCS.2019.8728350","DOIUrl":"https://doi.org/10.1109/ICACCS.2019.8728350","url":null,"abstract":"Hydro power vitality is one of the most encouraging clean vitality technology. This vitality innovation has numerous difficulties when contrasted and other sustainable power sources for instance biomass, sun oriented and wind energies. It has high capital speculation cost. Hydro plant is an essential product in non-renewable energy sources. When we are going with a hydro plant, we have developed a piezoelectric generator that harvests mechanical vibrations energy for increasing generating electrical energy. Piezoelectric electrical device that is associate degree mechanical device undergoes mechanical vibrations thus turn out electricity. So here we have done an efficient turbine controller which can be sufficiently able to withstand stacking however not too much overwhelming in order to force superfluous on the drive. Nowadays control request is more. So this task has created to produce the electrical power so as to remunerate the electric power request and monitoring condition.","PeriodicalId":249139,"journal":{"name":"2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124231286","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 : 2019-03-01DOI: 10.1109/ICACCS.2019.8728398
C. A. Kumar, B. Rajendra Naik
An encrypted image watermarking algorithm based on random pixel exchange and the alliance of SVD (singular value decomposition) and DTCWT (dual-tree complex wavelet transform) is proposed. Better directionality and shift invariance properties are motivated towards the selection of DTCWT. The invariance of SVD guarantees robustness and stability. The watermark image is preprocessed using random pixel exchange with a logistic key to get the encrypted version. Initially, the original image decomposed with DTCWT and selected the sub band based on the intensity invariance value. Applied the SVD on both selected sub band and encrypted watermark to generate the singular values. Next, the resultant singular values are combined with an appropriate scaling factor. To generate the watermarked image, performed the inverse DTCWT on modified sub bands. In the process of extraction, used the same scaling factor to generate the decrypted watermark image. With the correct logistic key, the watermark image is recovered. Further, transparency analysis and robustness analysis are carried out. High values of PSNR and normalized correlation (NC) indicates the better robustness and transparency of the proposed algorithm.
{"title":"A new encrypted image watermarking based on DTCWT and random pixel exchange","authors":"C. A. Kumar, B. Rajendra Naik","doi":"10.1109/ICACCS.2019.8728398","DOIUrl":"https://doi.org/10.1109/ICACCS.2019.8728398","url":null,"abstract":"An encrypted image watermarking algorithm based on random pixel exchange and the alliance of SVD (singular value decomposition) and DTCWT (dual-tree complex wavelet transform) is proposed. Better directionality and shift invariance properties are motivated towards the selection of DTCWT. The invariance of SVD guarantees robustness and stability. The watermark image is preprocessed using random pixel exchange with a logistic key to get the encrypted version. Initially, the original image decomposed with DTCWT and selected the sub band based on the intensity invariance value. Applied the SVD on both selected sub band and encrypted watermark to generate the singular values. Next, the resultant singular values are combined with an appropriate scaling factor. To generate the watermarked image, performed the inverse DTCWT on modified sub bands. In the process of extraction, used the same scaling factor to generate the decrypted watermark image. With the correct logistic key, the watermark image is recovered. Further, transparency analysis and robustness analysis are carried out. High values of PSNR and normalized correlation (NC) indicates the better robustness and transparency of the proposed algorithm.","PeriodicalId":249139,"journal":{"name":"2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129958455","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 : 2019-03-01DOI: 10.1109/ICACCS.2019.8728451
B. Sathish, Ganesan P, A. Ranganayakulu, D. S, S. Jagan Mohan Rao
In India rail transportation engage a major pose in endow with the essential transportation to maintain necessities of a hastily emergent financial system. At present, India possesses the fourth major railway net in the globe. The majority of the viable transportation conceded out by the railway system and consequently, any difficulty in the equal has the capacity to induce major damage to the financial system. A method for evade trains from devastating and crash with threat on railways is making known. According to the improvement, the techniques comprise a safety vehicle that travels along a railway a head of a train failure follow on in mishap generally get extensive means exposure still when the railway is not at fault and give to rail transport, among the unaware public, an unjustified image of inefficiency often fuelling calls for immediate reforms. This paper is intended at serving the railway control apprehensive to make stronger and expand the surveyor equipment vital through recent protection supervision.
{"title":"Advanced Automatic Detection of Cracks in Railway Tracks","authors":"B. Sathish, Ganesan P, A. Ranganayakulu, D. S, S. Jagan Mohan Rao","doi":"10.1109/ICACCS.2019.8728451","DOIUrl":"https://doi.org/10.1109/ICACCS.2019.8728451","url":null,"abstract":"In India rail transportation engage a major pose in endow with the essential transportation to maintain necessities of a hastily emergent financial system. At present, India possesses the fourth major railway net in the globe. The majority of the viable transportation conceded out by the railway system and consequently, any difficulty in the equal has the capacity to induce major damage to the financial system. A method for evade trains from devastating and crash with threat on railways is making known. According to the improvement, the techniques comprise a safety vehicle that travels along a railway a head of a train failure follow on in mishap generally get extensive means exposure still when the railway is not at fault and give to rail transport, among the unaware public, an unjustified image of inefficiency often fuelling calls for immediate reforms. This paper is intended at serving the railway control apprehensive to make stronger and expand the surveyor equipment vital through recent protection supervision.","PeriodicalId":249139,"journal":{"name":"2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS)","volume":"242 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131474390","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 : 2019-03-01DOI: 10.1109/ICACCS.2019.8728458
K. Priya, S. M. Mansoor Roomi, P. Shanmugavadivu, M. Sethuraman, P. Kalaivani
Automatic analysis and performance evaluation of interviewees is a largely unexplored and challenging problem. The proposed work provides a computational structure to enumerate the performance of the interviewee in the context of communication to give their performance feedback from the analysis of multimodal signals such as facial images and voice. A video captured during the interview is split into audio and visual frames. From the visual frames, the face is detected and their emotions are analyzed with the help of Histogram of Oriented Gradients. The facial expressions are classified by using Support Vector Machine. The classified facial expressions are happy, fear, sad, neutral, surprise, disgust and angry. From the audio cues,, the Mel Frequency Cepstral Coefficient features are extracted and this is categorized as fluent, non-fluent-pause and non-fluent-stammer. Both emotion and fluency of the candidate are fused to find performance score. This automated analysis provides the ratings for interview behavior such as poor, medium, high performance.
{"title":"An Automated System for the Assesment of Interview Performance through Audio & Emotion Cues","authors":"K. Priya, S. M. Mansoor Roomi, P. Shanmugavadivu, M. Sethuraman, P. Kalaivani","doi":"10.1109/ICACCS.2019.8728458","DOIUrl":"https://doi.org/10.1109/ICACCS.2019.8728458","url":null,"abstract":"Automatic analysis and performance evaluation of interviewees is a largely unexplored and challenging problem. The proposed work provides a computational structure to enumerate the performance of the interviewee in the context of communication to give their performance feedback from the analysis of multimodal signals such as facial images and voice. A video captured during the interview is split into audio and visual frames. From the visual frames, the face is detected and their emotions are analyzed with the help of Histogram of Oriented Gradients. The facial expressions are classified by using Support Vector Machine. The classified facial expressions are happy, fear, sad, neutral, surprise, disgust and angry. From the audio cues,, the Mel Frequency Cepstral Coefficient features are extracted and this is categorized as fluent, non-fluent-pause and non-fluent-stammer. Both emotion and fluency of the candidate are fused to find performance score. This automated analysis provides the ratings for interview behavior such as poor, medium, high performance.","PeriodicalId":249139,"journal":{"name":"2019 5th International Conference on Advanced Computing & Communication Systems (ICACCS)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116112066","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：