International Journal of Advanced Research in Science, Communication and Technology
In this method, the Automatic fake Currency Recognition System is used to identify fake paper mon... more In this method, the Automatic fake Currency Recognition System is used to identify fake paper money and determine if it is genuine or not. The current counterfeit issue brought on by demonetization has an impact on the financial system as well as other sectors. This strategy, which is comparatively superior to earlier image processing methods, examines a novel Convolution Neural Network approach for the identification of fake money notes through their images. This approach is based on Deep Learning, which has recently shown outstanding results in image categorization problems. Through the use of an image of the fake money note, this approach can assist both humans and machines in instantly recognizing the note. In this system original and fake notes images are used to perform training and classification operation. The proposed system achieved an accuracy of 99.46% and loss of 0.0033 using CNN algorithm.
Today cloud companies offer fully managed Spark services. This has made it easy to onboard new cu... more Today cloud companies offer fully managed Spark services. This has made it easy to onboard new customers but has also increased the volume of users and their workload sizes. However, both cloud providers and users lack the tools and time to optimize these massive workloads. To solve this problem, we designed SparkCruise that can help understand and optimize workload instances by adding a workload-driven feedback loop to the Spark query optimizer. In this paper, we present our approach to collecting and representing Spark query workloads and use it to improve the overall performance on the workload, all without requiring any access to user data. These methods scale with the number of workloads and apply learned feedback in an online fashion. We explain one specific workload optimization developed for computation reuse. We also share the detailed analysis of production Spark workloads and contrast them with the corresponding analysis of TPC-DS benchmark. To the best of our knowledge, ...
There has been a a significant increase in the popularity of using Unmanned Aerial Vehicles (UAVs... more There has been a a significant increase in the popularity of using Unmanned Aerial Vehicles (UAVs), popularly known as drones, in several applications. In many application scenarios, UAVs are deployed in missions where sensitive data is collected, such as monitoring critical infrastructure, industrial facilities, crops, and public safety. Due to the sensitive and/or safety critical nature of the data collected in these applications, it is imperative to consider the security and privacy aspects of the UAVs used in these scenarios. In this article, we propose an efficient privacy aware authenticated key agreement scheme for edge-assisted UAVs (Internet of Drones). Unlike the existing security solutions for UAVs, the proposed scheme does not need to store any secret keys in the devices but still can provide the desired security features. To the best of our knowledge, this is the first work where physical security of the UAV has been taken into account. The proposed system allows third-party communication and mobile edge computing service providers to authenticate the UAVs without any loss of provacy and outperforms existing methods in terms of computational complexity.
International Journal of Advanced Research in Science, Communication and Technology
In this method, the Automatic fake Currency Recognition System is used to identify fake paper mon... more In this method, the Automatic fake Currency Recognition System is used to identify fake paper money and determine if it is genuine or not. The current counterfeit issue brought on by demonetization has an impact on the financial system as well as other sectors. This strategy, which is comparatively superior to earlier image processing methods, examines a novel Convolution Neural Network approach for the identification of fake money notes through their images. This approach is based on Deep Learning, which has recently shown outstanding results in image categorization problems. Through the use of an image of the fake money note, this approach can assist both humans and machines in instantly recognizing the note. In this system original and fake notes images are used to perform training and classification operation. The proposed system achieved an accuracy of 99.46% and loss of 0.0033 using CNN algorithm.
Today cloud companies offer fully managed Spark services. This has made it easy to onboard new cu... more Today cloud companies offer fully managed Spark services. This has made it easy to onboard new customers but has also increased the volume of users and their workload sizes. However, both cloud providers and users lack the tools and time to optimize these massive workloads. To solve this problem, we designed SparkCruise that can help understand and optimize workload instances by adding a workload-driven feedback loop to the Spark query optimizer. In this paper, we present our approach to collecting and representing Spark query workloads and use it to improve the overall performance on the workload, all without requiring any access to user data. These methods scale with the number of workloads and apply learned feedback in an online fashion. We explain one specific workload optimization developed for computation reuse. We also share the detailed analysis of production Spark workloads and contrast them with the corresponding analysis of TPC-DS benchmark. To the best of our knowledge, ...
There has been a a significant increase in the popularity of using Unmanned Aerial Vehicles (UAVs... more There has been a a significant increase in the popularity of using Unmanned Aerial Vehicles (UAVs), popularly known as drones, in several applications. In many application scenarios, UAVs are deployed in missions where sensitive data is collected, such as monitoring critical infrastructure, industrial facilities, crops, and public safety. Due to the sensitive and/or safety critical nature of the data collected in these applications, it is imperative to consider the security and privacy aspects of the UAVs used in these scenarios. In this article, we propose an efficient privacy aware authenticated key agreement scheme for edge-assisted UAVs (Internet of Drones). Unlike the existing security solutions for UAVs, the proposed scheme does not need to store any secret keys in the devices but still can provide the desired security features. To the best of our knowledge, this is the first work where physical security of the UAV has been taken into account. The proposed system allows third-party communication and mobile edge computing service providers to authenticate the UAVs without any loss of provacy and outperforms existing methods in terms of computational complexity.
Uploads
Papers by Sahil Das