Pub Date : 2020-11-06DOI: 10.1109/PDGC50313.2020.9315854
Shakti Arora, D. Verma, V. Athavale
Attendance management system is always an important entity for any of the organization, a number of attendance system like barcode, RFID, finger-print recognition system are already available in the market. While various companies are using different types of attendance management system according to their budget and convenience. Few of the designed and adopted systems have their own drawbacks like data handling, data security and privacy of the information. In this pape, we have proposed and designed a secured attendance management system with Secret sharing algorithm. The main objective is to automate the attendance system and provide the complete authentic and secure database of all the employees or users. Due to Covid-19 maximum of the organizations are trying to adopt the attendance management system without any physical connectivity or manual intervention. Our proposed solution is the best feasible solution to handle the stated problems. Attendance can be marked by scanning the QR code with a mobile phone at distant locations while secret sharing security algorithm is providing the security by distributing the complete code into number of secret shares which can be only recovered by authentic entities so integrity and privacy of the information is maintained properly.
{"title":"A secured automated Attendance Management System implemented with Secret Sharing Algorithm","authors":"Shakti Arora, D. Verma, V. Athavale","doi":"10.1109/PDGC50313.2020.9315854","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315854","url":null,"abstract":"Attendance management system is always an important entity for any of the organization, a number of attendance system like barcode, RFID, finger-print recognition system are already available in the market. While various companies are using different types of attendance management system according to their budget and convenience. Few of the designed and adopted systems have their own drawbacks like data handling, data security and privacy of the information. In this pape, we have proposed and designed a secured attendance management system with Secret sharing algorithm. The main objective is to automate the attendance system and provide the complete authentic and secure database of all the employees or users. Due to Covid-19 maximum of the organizations are trying to adopt the attendance management system without any physical connectivity or manual intervention. Our proposed solution is the best feasible solution to handle the stated problems. Attendance can be marked by scanning the QR code with a mobile phone at distant locations while secret sharing security algorithm is providing the security by distributing the complete code into number of secret shares which can be only recovered by authentic entities so integrity and privacy of the information is maintained properly.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130257967","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}
Wireless Sensor Networks comprise of various low-cost, low-energy sensor nodes that perform the data gathering task. In a network, data or packets are transferred from source to destination via sink node or other coordinating nodes. It can be outlined as a network of devices that communicate information collected from the sensor field. The information flow takes place with the help of wireless links. Sensors are normally qualified by limited interaction abilities because of power and bandwidth constraints. In this paper, the main focus is on network issues and their solution. We consider Machine Learning techniques implemented in this network to solve some network problems. Machine Learning is the process where we train the model or machine based on training data, the model is programmed in such a way so that it “learns” from the information that it holds. This paper contains details of publications spanning a period of 2015–2020 for Machine Learning techniques that describe the challenging issues of Wireless Sensor Network.
{"title":"Machine Learning Technique for Wireless Sensor Networks","authors":"Rajwinder Kaur, Jasminder Kaur Sandhu, Luxmi Sapra","doi":"10.1109/PDGC50313.2020.9315775","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315775","url":null,"abstract":"Wireless Sensor Networks comprise of various low-cost, low-energy sensor nodes that perform the data gathering task. In a network, data or packets are transferred from source to destination via sink node or other coordinating nodes. It can be outlined as a network of devices that communicate information collected from the sensor field. The information flow takes place with the help of wireless links. Sensors are normally qualified by limited interaction abilities because of power and bandwidth constraints. In this paper, the main focus is on network issues and their solution. We consider Machine Learning techniques implemented in this network to solve some network problems. Machine Learning is the process where we train the model or machine based on training data, the model is programmed in such a way so that it “learns” from the information that it holds. This paper contains details of publications spanning a period of 2015–2020 for Machine Learning techniques that describe the challenging issues of Wireless Sensor Network.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129001339","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 : 2020-11-06DOI: 10.1109/PDGC50313.2020.9315749
Sangeetha Annam, Anshu Singla
Digital image is one of the primary way of communication in the present digital world. During the acquiring process, the images may become noisy. Noise reduction is a demanding task during the image analysis process without dissimilating the important features. It is the procedure of restoring the original image by discarding unwanted noises and known as Image denoising. The main intention of any noise removal technique is to completely eradicate the noise from the image, such that the resulting image is better than the original image. In this digital era, remote sensing images are widely commercial for environmental monitoring. In this study, a correlative analysis of different noise removal methods using various filters in spectral images is performed. Spectral images are introduced with different types of noise and further filters are applied to denoise the image. The performances of the methods are evaluated using benchmarks: Signal-to-Noise Ratio (SNR) and Peak Signal-to-N oise Ratio (PSNR). Experimental results demonstrate that the SNR and PSNR measures were comparatively higher for all the filters when the image is introduced with Poisson noise.
{"title":"Correlative Analysis of Denoising Methods in Spectral Images Embedded with Different Noises","authors":"Sangeetha Annam, Anshu Singla","doi":"10.1109/PDGC50313.2020.9315749","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315749","url":null,"abstract":"Digital image is one of the primary way of communication in the present digital world. During the acquiring process, the images may become noisy. Noise reduction is a demanding task during the image analysis process without dissimilating the important features. It is the procedure of restoring the original image by discarding unwanted noises and known as Image denoising. The main intention of any noise removal technique is to completely eradicate the noise from the image, such that the resulting image is better than the original image. In this digital era, remote sensing images are widely commercial for environmental monitoring. In this study, a correlative analysis of different noise removal methods using various filters in spectral images is performed. Spectral images are introduced with different types of noise and further filters are applied to denoise the image. The performances of the methods are evaluated using benchmarks: Signal-to-Noise Ratio (SNR) and Peak Signal-to-N oise Ratio (PSNR). Experimental results demonstrate that the SNR and PSNR measures were comparatively higher for all the filters when the image is introduced with Poisson noise.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125422000","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 : 2020-11-06DOI: 10.1109/PDGC50313.2020.9315851
Naveen Kumar, S. Yadav, Divakar Yadav
In today's world with ever increasing amount of text assets overloaded on web with digitized libraries, sorting out these documents got developed into a feasible need. Document clustering is an important procedure which consequently sorts out huge number of articles into a modest number of balanced gatherings. Document clustering is making groups of similar documents into number of clusters such that documents within the same group with high similarity values among one another and dissimilar to documents from other clusters. Common applications of document Clustering includes grouping similar news articles, analysis of customer feedback, text mining, duplicate content detection, finding similar documents, search optimization and many more. This lead to utilization of these documents for finding required information in a competent and efficient manner. Document clustering required a measurement for evaluating how surprising two given information are. This dissimilarity is often estimated by using some distance measures, for example, Cosine Similarity, Euclidean distance, etc. In our work, we evaluated and analyzed how effective these measures are in partitioned clustering for text document datasets. In our experiments we have used standard K-means algorithm and our results details on six text documents datasets and five most commonly used distance or similarity measures in text clustering.
{"title":"Similarity Measure Approaches Applied in Text Document Clustering for Information Retrieval","authors":"Naveen Kumar, S. Yadav, Divakar Yadav","doi":"10.1109/PDGC50313.2020.9315851","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315851","url":null,"abstract":"In today's world with ever increasing amount of text assets overloaded on web with digitized libraries, sorting out these documents got developed into a feasible need. Document clustering is an important procedure which consequently sorts out huge number of articles into a modest number of balanced gatherings. Document clustering is making groups of similar documents into number of clusters such that documents within the same group with high similarity values among one another and dissimilar to documents from other clusters. Common applications of document Clustering includes grouping similar news articles, analysis of customer feedback, text mining, duplicate content detection, finding similar documents, search optimization and many more. This lead to utilization of these documents for finding required information in a competent and efficient manner. Document clustering required a measurement for evaluating how surprising two given information are. This dissimilarity is often estimated by using some distance measures, for example, Cosine Similarity, Euclidean distance, etc. In our work, we evaluated and analyzed how effective these measures are in partitioned clustering for text document datasets. In our experiments we have used standard K-means algorithm and our results details on six text documents datasets and five most commonly used distance or similarity measures in text clustering.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125540269","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 : 2020-11-06DOI: 10.1109/PDGC50313.2020.9315855
Uddalok Sen, M. Sarkar, N. Mukherjee
In order to propose an efficient scheduling policy in a large distributed heterogeneous environment, resource requirements of newly submitted jobs should be predicted prior to the execution of jobs. An execution history can be maintained to store the execution profile of all jobs executed earlier on a given set of resources. The execution history stores the actual CPU cycle consumed by the job as well as the resource details where it is executed. A feedback-guided job-modeling scheme can be used to detect similarity between the newly submitted jobs and previously executed jobs. It can also be used to predict resource requirements based on this similarity. However, efficient resource scheduling based on this knowledge has not been dealt with. In this paper, we propose a hybrid, scheduling policy of new jobs, which are independent of each other, based on their similarity with history jobs. Here we focus on exact clone jobs only i.e. its identical job is found in execution history and predicted resource consumption is same as exact resource consumption. We also endeavor to deal with two conflicting parameters i.e., execution cost and make span of jobs. A comparison with other existing algorithms is also presented in this paper.
{"title":"Hybrid Job Scheduling in Distributed Systems based on Clone Detection","authors":"Uddalok Sen, M. Sarkar, N. Mukherjee","doi":"10.1109/PDGC50313.2020.9315855","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315855","url":null,"abstract":"In order to propose an efficient scheduling policy in a large distributed heterogeneous environment, resource requirements of newly submitted jobs should be predicted prior to the execution of jobs. An execution history can be maintained to store the execution profile of all jobs executed earlier on a given set of resources. The execution history stores the actual CPU cycle consumed by the job as well as the resource details where it is executed. A feedback-guided job-modeling scheme can be used to detect similarity between the newly submitted jobs and previously executed jobs. It can also be used to predict resource requirements based on this similarity. However, efficient resource scheduling based on this knowledge has not been dealt with. In this paper, we propose a hybrid, scheduling policy of new jobs, which are independent of each other, based on their similarity with history jobs. Here we focus on exact clone jobs only i.e. its identical job is found in execution history and predicted resource consumption is same as exact resource consumption. We also endeavor to deal with two conflicting parameters i.e., execution cost and make span of jobs. A comparison with other existing algorithms is also presented in this paper.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122224835","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 : 2020-11-06DOI: 10.1109/PDGC50313.2020.9315777
Akansha Tyagi, Sandhya Bansal, Arjun Kashyap
Sign language recognition is a highly adaptive interface between the deaf-mute community and machines. In India, Indian Sign Language (ISL) plays a significant role in the deaf-mute society, breaking communication distancing. Extracting features from the input image is crucial in vision-based Indian Sign Language Recognition (ISLR). This paper addresses feature detection and extraction techniques used in the ISLR. This paper categorizes existing techniques into three broad groups: scale-based, intensity-based, and hybrid techniques. SIFT (Scale Invariant Feature Transform), SURF (Speeded up Robust Features), FAST (Features from Accelerated Segment Test), BRIEF (Binary Robust Independent Elementary Features), and ORB (Oriented FAST and rotated BRIEF) are the techniques that have been evaluated and compared for intensity scaling, occlusion, orientation, affine transformation, blurring, and illumination. Results were generated in terms of key point detected, time-taken, and the match rate. SIFT is consistent in most circumstances, though it is slow. FAST is the fastest with good performance like ORB, and BRIEF shows its advantages in affine transformation and intensity changes.
{"title":"Comparative Analysis of Feature Detection and Extraction Techniques for Vision-based ISLR system","authors":"Akansha Tyagi, Sandhya Bansal, Arjun Kashyap","doi":"10.1109/PDGC50313.2020.9315777","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315777","url":null,"abstract":"Sign language recognition is a highly adaptive interface between the deaf-mute community and machines. In India, Indian Sign Language (ISL) plays a significant role in the deaf-mute society, breaking communication distancing. Extracting features from the input image is crucial in vision-based Indian Sign Language Recognition (ISLR). This paper addresses feature detection and extraction techniques used in the ISLR. This paper categorizes existing techniques into three broad groups: scale-based, intensity-based, and hybrid techniques. SIFT (Scale Invariant Feature Transform), SURF (Speeded up Robust Features), FAST (Features from Accelerated Segment Test), BRIEF (Binary Robust Independent Elementary Features), and ORB (Oriented FAST and rotated BRIEF) are the techniques that have been evaluated and compared for intensity scaling, occlusion, orientation, affine transformation, blurring, and illumination. Results were generated in terms of key point detected, time-taken, and the match rate. SIFT is consistent in most circumstances, though it is slow. FAST is the fastest with good performance like ORB, and BRIEF shows its advantages in affine transformation and intensity changes.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126086633","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 : 2020-11-06DOI: 10.1109/PDGC50313.2020.9315850
Prateek Mishra, S. Yadav, S. Arora
An Internet of Things (IoT) architecture comprised of cloud, fog and resource constrained IoT end devices. The exponential development of IoT has increased the processing and footprint overhead in IoT end devices. All the components of IoT end devices that establish Chain of Trust (CoT) to ensure security are termed as Trusted Computing Base (TCB). The increased overhead in the IoT end device has increased the demand to increase the size of TCB surface area hence increases complexity of TCB surface area and also the increased the visibility of TCB surface area to the external world made the IoT end devices architecture over-architectured and unsecured. The TCB surface area minimization that has been remained unfocused reduces the complexity of TCB surface area and visibility of TCB components to the external un-trusted world hence ensures security in terms of confidentiality, integrity, authenticity (CIA) at the IoT end devices. The TCB minimization thus will convert the over-architectured IoT end device into lightweight and secured architecture highly desired for resource constrained IoT end devices. In this paper we review the IoT end device architectures proposed in the recent past and concluded that these architectures of resource constrained IoT end devices are over-architectured due to larger TCB and ignored bugs and vulnerabilities in TCB hence un-secured. We propose the Novel levelled architecture with TCB minimization by replacing oversized hypervisor with lightweight Micro(μ)-hypervisor i.e. μ-visor and transferring μ-hypervisor based virtualization over fog node for light weight and secured IoT End device architecture. The bug free TCB components confirm stable CoT for guaranteed CIA resulting into robust Trusted Execution Environment (TEE) hence secured IoT end device architecture. Thus the proposed resulting architecture is secured with minimized SRAM and flash memory combined footprint 39.05% of the total available memory per device. In this paper we review the IoT end device architectures proposed in the recent past and concluded that these architectures of resource constrained IoT end devices are over-architectured due to larger TCB and ignored bugs and vulnerabilities in TCB hence un-secured. We propose the Novel levelled architecture with TCB minimization by replacing oversized hypervisor with lightweight Micro(μ)-hypervisor i.e. μ-visor and transferring μ-hypervisor based virtualization over fog node for light weight and secured IoT End device architecture. The bug free TCB components confirm stable CoT for guaranteed CIA resulting into robust Trusted Execution Environment (TEE) hence secured IoT end device architecture. Thus the proposed resulting architecture is secured with minimized SRAM and flash memory combined footprint 39.05% of the total available memory per device.
{"title":"TCB Minimization towards Secured and Lightweight IoT End Device Architecture using Virtualization at Fog Node","authors":"Prateek Mishra, S. Yadav, S. Arora","doi":"10.1109/PDGC50313.2020.9315850","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315850","url":null,"abstract":"An Internet of Things (IoT) architecture comprised of cloud, fog and resource constrained IoT end devices. The exponential development of IoT has increased the processing and footprint overhead in IoT end devices. All the components of IoT end devices that establish Chain of Trust (CoT) to ensure security are termed as Trusted Computing Base (TCB). The increased overhead in the IoT end device has increased the demand to increase the size of TCB surface area hence increases complexity of TCB surface area and also the increased the visibility of TCB surface area to the external world made the IoT end devices architecture over-architectured and unsecured. The TCB surface area minimization that has been remained unfocused reduces the complexity of TCB surface area and visibility of TCB components to the external un-trusted world hence ensures security in terms of confidentiality, integrity, authenticity (CIA) at the IoT end devices. The TCB minimization thus will convert the over-architectured IoT end device into lightweight and secured architecture highly desired for resource constrained IoT end devices. In this paper we review the IoT end device architectures proposed in the recent past and concluded that these architectures of resource constrained IoT end devices are over-architectured due to larger TCB and ignored bugs and vulnerabilities in TCB hence un-secured. We propose the Novel levelled architecture with TCB minimization by replacing oversized hypervisor with lightweight Micro(μ)-hypervisor i.e. μ-visor and transferring μ-hypervisor based virtualization over fog node for light weight and secured IoT End device architecture. The bug free TCB components confirm stable CoT for guaranteed CIA resulting into robust Trusted Execution Environment (TEE) hence secured IoT end device architecture. Thus the proposed resulting architecture is secured with minimized SRAM and flash memory combined footprint 39.05% of the total available memory per device. In this paper we review the IoT end device architectures proposed in the recent past and concluded that these architectures of resource constrained IoT end devices are over-architectured due to larger TCB and ignored bugs and vulnerabilities in TCB hence un-secured. We propose the Novel levelled architecture with TCB minimization by replacing oversized hypervisor with lightweight Micro(μ)-hypervisor i.e. μ-visor and transferring μ-hypervisor based virtualization over fog node for light weight and secured IoT End device architecture. The bug free TCB components confirm stable CoT for guaranteed CIA resulting into robust Trusted Execution Environment (TEE) hence secured IoT end device architecture. Thus the proposed resulting architecture is secured with minimized SRAM and flash memory combined footprint 39.05% of the total available memory per device.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126107808","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 : 2020-11-06DOI: 10.1109/PDGC50313.2020.9315783
Garima Thakur, Harsh Sohal, Shruti Jain
Approximate computing provides the tradeoff between the accuracy, the speed as well as power consumption. Approximate adders and other logical circuits can reduce hardware overhead. In this paper non-speculative and speculative parallel prefix adder is proposed and makes it more reliable to be used in applications where high speed circuits are required. If there is misprediction of result in speculative adder then error-correction is activated in the next clock cycle. Speculation is a process in which approximation is done. Approximate computing is widely used in the current scenario. The speculative adder reduces the critical path and provides the trade-off between reliability and performance. Proposed speculative parallel prefix adder results in 8.204ns delay which shows 36.87%, 2.35%, 26.32 % improvement in comparison to conventional NSA, proposed NSA, and conventional SA. Architecture is implemented for 16-bit operand length and used is an FPGA-based processing application.
{"title":"FPGA-Based Parallel Prefix Speculative Adder for Fast Computation Application","authors":"Garima Thakur, Harsh Sohal, Shruti Jain","doi":"10.1109/PDGC50313.2020.9315783","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315783","url":null,"abstract":"Approximate computing provides the tradeoff between the accuracy, the speed as well as power consumption. Approximate adders and other logical circuits can reduce hardware overhead. In this paper non-speculative and speculative parallel prefix adder is proposed and makes it more reliable to be used in applications where high speed circuits are required. If there is misprediction of result in speculative adder then error-correction is activated in the next clock cycle. Speculation is a process in which approximation is done. Approximate computing is widely used in the current scenario. The speculative adder reduces the critical path and provides the trade-off between reliability and performance. Proposed speculative parallel prefix adder results in 8.204ns delay which shows 36.87%, 2.35%, 26.32 % improvement in comparison to conventional NSA, proposed NSA, and conventional SA. Architecture is implemented for 16-bit operand length and used is an FPGA-based processing application.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116553729","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 : 2020-11-06DOI: 10.1109/PDGC50313.2020.9315746
Megha Chhabra, M. Shukla, K. Ravulakollu
In this paper, a method for improving the efficiency of latent fingerprint segmentation and detection system is presented. Structural detection and precise segmentation of fingerprints otherwise not visible to the naked eye (called latents), provide the basis for automatic identification of latent fingerprints. The method is based on the assumption, that including detection of relevant structure of interest from latent fingerprint image into an effective segmentation model pipeline improves the effectiveness of the model and efficiency of the automated segmentation. The approach discards detections of poor-quality due to noise, inadequate data, misplaced structures of interests from multiple instances of fingermarks in the image etc. A collaborative detector-segmentation approach is proposed which establishes reproducibility and repeatability of the model, consequently increasing the efficiency of the frame of work. The results are obtained on IIIT -DCLF database. Performing saliency-based detection using color based visual distortion reducing the subsequent information processing cost through a stack of the convolutional autoencoder. The results obtained signify significant improvement over published results.
{"title":"Improving the Efficiency of Automated Latent Fingerprint Identification Using Stack of Convolutional Auto-encoder","authors":"Megha Chhabra, M. Shukla, K. Ravulakollu","doi":"10.1109/PDGC50313.2020.9315746","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315746","url":null,"abstract":"In this paper, a method for improving the efficiency of latent fingerprint segmentation and detection system is presented. Structural detection and precise segmentation of fingerprints otherwise not visible to the naked eye (called latents), provide the basis for automatic identification of latent fingerprints. The method is based on the assumption, that including detection of relevant structure of interest from latent fingerprint image into an effective segmentation model pipeline improves the effectiveness of the model and efficiency of the automated segmentation. The approach discards detections of poor-quality due to noise, inadequate data, misplaced structures of interests from multiple instances of fingermarks in the image etc. A collaborative detector-segmentation approach is proposed which establishes reproducibility and repeatability of the model, consequently increasing the efficiency of the frame of work. The results are obtained on IIIT -DCLF database. Performing saliency-based detection using color based visual distortion reducing the subsequent information processing cost through a stack of the convolutional autoencoder. The results obtained signify significant improvement over published results.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"28 6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131743913","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 : 2020-11-06DOI: 10.1109/PDGC50313.2020.9315845
Anant Kumar Jayswal
Cloud computing is the shared pool of heterogeneous computing, storage, and network resources across the globe. The resources are allocated to cloud users using a service level agreement. The resources are accessed by the end-users based on pricing models. In such scenario placement and management of resources over cloud datacenters is a critical issue. Task allocation in cloud places an important role in the performance of cloud and manage utilization of resource and performance of tasks. There exist various static and dynamic algorithm to solve this issue. In this work a Bat Algorithm inspired task allocation algorithm for cloud infrastructure is proposed to improve the performance of cloud in term of execution time and start time as compared to existing algorithms.
{"title":"Efficient Task Allocation for Cloud Using Bat Algorithm","authors":"Anant Kumar Jayswal","doi":"10.1109/PDGC50313.2020.9315845","DOIUrl":"https://doi.org/10.1109/PDGC50313.2020.9315845","url":null,"abstract":"Cloud computing is the shared pool of heterogeneous computing, storage, and network resources across the globe. The resources are allocated to cloud users using a service level agreement. The resources are accessed by the end-users based on pricing models. In such scenario placement and management of resources over cloud datacenters is a critical issue. Task allocation in cloud places an important role in the performance of cloud and manage utilization of resource and performance of tasks. There exist various static and dynamic algorithm to solve this issue. In this work a Bat Algorithm inspired task allocation algorithm for cloud infrastructure is proposed to improve the performance of cloud in term of execution time and start time as compared to existing algorithms.","PeriodicalId":347216,"journal":{"name":"2020 Sixth International Conference on Parallel, Distributed and Grid Computing (PDGC)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121272229","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：