Papers by Sumit Srivastava
Explainable Artificial Intelligence (XAI) focuses on research and technology that can explain an ... more Explainable Artificial Intelligence (XAI) focuses on research and technology that can explain an AI system's functioning and its underlying methods, and also on making these explanations better through personalization. Our research study investigates a natural language personalization method called lexical alignment in understanding an explanation provided by a conversational agent. The study setup was online and navigated the participants through an interaction with a conversational agent. Participants faced either an agent designed to align its responses to those of the participants, a misaligned agent, or a control condition that did not involve any dialogue. The dialogue delivered an explanation based on a predefined set of causes and effects. The recall and understanding of the explanations was evaluated using a combination of Yes-No questions, a Cloze test (fill-in-the-blanks), and What-style questions. The analysis of the test scores revealed a significant advantage in information recall for those who interacted with an aligning agent against the participants who either interacted with a nonaligning agent or did not go through any dialogue. The Yes-No type questions that included probes on higher-order inferences (understanding) also reflected an advantage for the participants who had an aligned dialogue against both non-aligned and no dialogue conditions. The results overall suggest a positive effect of lexical alignment on understanding of explanations.
ECTI Transactions on Computer and Information Technology, Aug 19, 2022
In this manuscript, a hybridizing visual cryptography with Optimal Elliptic Curve Cryptography is... more In this manuscript, a hybridizing visual cryptography with Optimal Elliptic Curve Cryptography is proposed for medical image security in Internet of Things (IoT). The visual cryptography is generally used to send the secure and condential medical image to the receiver. Here, the medical image is transmitted as shares and all shares of the medical image are collectively loaded to retrieve the original medical image. Moreover, the multiple shares are created interms of pixel values of medical image and this share is extracted and partioned in blocks. The blocks of every share are encrypted with elliptic curve cryptography (ECC) mechanisms and encrypted image is decrypted using ECC decrypts. In hybridizing visual crypto with optimal elliptic curve crypto, the optimal key will be generated using an imperialist competitive algorithm. Finally, the decrypted output image compares to the original image. The proposed system is executed on MATLAB platform and performance is evaluated with existing method like Score-based Key Enumeration Algorithm (SKEA). The proposed ESEA approach reduces the le size as 45.76%, 24.97%, 15.86%, 33% and 33.86%.And higher PSNR as 29.08%, 25.86%, 23.98%, 25.86% and 42.75%. The proposed ESEA approach achieves 6.89% higher security than existing SKEA method. Furthermore, the simulation outcome demonstrates that the proposed technique can be able to nd the optimal global solutions eciently and accurately than the existing techniques.
Multi-class analysis, as the term suggest is the classification of the data in more than two clas... more Multi-class analysis, as the term suggest is the classification of the data in more than two classes. However not much studies were focused on such analysis and researchers often confined themselves to the binary sentiment classifiers. In this paper, we proposed machine learning algorithm as an approach to predict the sentiment classification. The experiments are conducted on public data sets combined with ensemble method named BAGGING, an abbreviation for Bootstrap aggregation with 10-cross fold validation technique is used to obtain the classification accuracy. The result accuracy suggested the exploring further improvement using the combination of the multi-class sentiment classifiers.
Proceedings of the 28th International Conference on Intelligent User Interfaces
Explainable Artificial Intelligence (XAI) focuses on research and technology that can explain an ... more Explainable Artificial Intelligence (XAI) focuses on research and technology that can explain an AI system's functioning and its underlying methods, and also on making these explanations better through personalization. Our research study investigates a natural language personalization method called lexical alignment in understanding an explanation provided by a conversational agent. The study setup was online and navigated the participants through an interaction with a conversational agent. Participants faced either an agent designed to align its responses to those of the participants, a misaligned agent, or a control condition that did not involve any dialogue. The dialogue delivered an explanation based on a predefined set of causes and effects. The recall and understanding of the explanations was evaluated using a combination of Yes-No questions, a Cloze test (fill-in-the-blanks), and What-style questions. The analysis of the test scores revealed a significant advantage in information recall for those who interacted with an aligning agent against the participants who either interacted with a nonaligning agent or did not go through any dialogue. The Yes-No type questions that included probes on higher-order inferences (understanding) also reflected an advantage for the participants who had an aligned dialogue against both non-aligned and no dialogue conditions. The results overall suggest a positive effect of lexical alignment on understanding of explanations.
ECTI Transactions on Computer and Information Technology (ECTI-CIT)
In this manuscript, a hybridizing visual cryptography with Optimal Elliptic Curve Cryptography is... more In this manuscript, a hybridizing visual cryptography with Optimal Elliptic Curve Cryptography is proposed for medical image security in Internet of Things (IoT). The visual cryptography is generally used to send the secure and confidential medical image to the receiver. Here, the medical image is transmitted as shares and all shares of the medical image are collectively loaded to retrieve the original medical image. Moreover, the multiple shares are created interms of pixel values of medical image and this share is extracted and partioned in blocks. The blocks of every share are encrypted with elliptic curve cryptography (ECC) mechanisms and encrypted image is decrypted using ECC decrypts. In hybridizing visual crypto with optimal elliptic curve crypto, the optimal key will be generated using an imperialist competitive algorithm. Finally, the decrypted output image compares to the original image. The proposed system is executed on MATLAB platform and performance is evaluated with e...
Algorithms for Intelligent Systems, 2020
Increasing environment concerns have resulted in efforts for companies to recycle, repair, remanu... more Increasing environment concerns have resulted in efforts for companies to recycle, repair, remanufacture, or reuse their products collected from the end user. This study deals with recycling (material recovery) system where recycled material is used as raw material for an EPQ-type production system. It is assumed that the recycled material arrives at the system with a constant rate and deteriorates continuously in accordance with a general probability distribution. We develop mathematical expression of the inventory level of the recycled material under Last- In-First- Out (LIFO) issuing policy. As spec ial cases, we study the exponential and Weibull distribution for the time to deterioration of an item. An approximate formula is derived using perturbation techniques for the case of Weibull distribution. An example problem is carried out to demonstrate the model.
Journal of Statistics and Management Systems, 2018
The web is being used more and more by users of mobile devices. In addition, it is increasingly p... more The web is being used more and more by users of mobile devices. In addition, it is increasingly possible to track the user's location, which provides immense opportunities in geospatial data and its management. Due to the use of location information in services for each mobile device, a large size of spatial data makes it difficult to process spatial queries efficiently and, therefore, we need a lightweight and scalable approach to process large amounts of stored data in distributed file systems. For the most part, all SNSs (social network services) focus on connecting the user account with their location information, such as check-in services, which helps them collect information about user activities and ratings. Of location, but also increases the load of data on their servers. . In this article we propose an indexing technique in combination with efficient processing of Boolean top-k spatial queries where location data is compressed to save space and the Boolean query helps filter results so that unrelated data is not processed, what helps to save space and faster processing of queries.
2012 Second International Conference on Advanced Computing & Communication Technologies, 2012
TEM (Transmission Electron Microscopy) is an important morphological characterization tool for Na... more TEM (Transmission Electron Microscopy) is an important morphological characterization tool for Nano-materials. Quite often a microscopy image gets corrupted by noise, which may arise in the process of acquiring the image, or during its transmission, or even during reproduction of the image. Removal of noise from an image is one of the most important tasks in image processing. Depending on
International Journal of Computer …
High-performance computing has created a new approach to science. Modeling is now a viable and re... more High-performance computing has created a new approach to science. Modeling is now a viable and respected alternative to the more traditional experiential and theoretical approaches. High performance is a key issue in data mining or in image rendering. Traditional high performance clusters have proved their worth in a variety of uses from predicting the weather to industrial design, from molecular dynamics to astronomical modeling. A multicomputer configuration, or cluster, is a group of computers that work together. A cluster has three basic elements-a collection of individual computers, a network connecting those computers, and software that enables a computer to share work among the other computers via the network. Clusters are also playing a greater role in business. Advances in clustering technology have led to high-availability and load-balancing clusters. Clustering is now used for missioncritical applications such as web and FTP servers. For permanent clusters there are, for lack of a better name, cluster kits Traditional high-performance clusters have proved their worth in a variety of uses-from predicting the weather to industrial design, from molecular dynamics to astronomical modeling. High-performance computing (HPC) has created a new approach to science-modeling is now a viable and respected alternative to the more traditional experiential and theoretical approaches. High performance is a key issue in data mining or in image rendering. Advances in clustering technology have led to high-availability and load-balancing clusters. Develop the algorithms for the Sorting that are faster and more accurate than they were ever before. The problem with the huge data sorting is that it takes a lot of time and as a result a large amount of money is required. This huge money is just wasted in the sorting of data and not in any useful work so, it is highly required that this time be as less as possible. So we came up with the some new methods to lower that Complexity. The approach we followed was High Performance Computing. , software packages that automate the installation process. A cluster kit provides all the software you are likely to need in a single distribution. Cluster kits tend to be very complete. For example, the OSCAR distribution. Open Source Cluster Application Resources is a software package that is designed to simplify cluster installation. A collection of open source cluster software, OSCAR includes everything that you are likely to need for a dedicated, high-performance cluster. OSCAR takes you completely through the installation of your cluster. In this Paper with the help of Open Source Cluster Application Resource (OSCAR) cluster kit, attempt to setup a high performance computational cluster with special concern to applications like Integration and Sorting. The ease use of cluster is possible globally and transparently managing cluster resources. Cluster computing approach nowadays is an ordinary configuration found in many organizations to target requirements of high performance computing.
Genetic Algorithms are used to create a version of biological evolution on computers. They operat... more Genetic Algorithms are used to create a version of biological evolution on computers. They operate on small computer program that, just like organisms undergoing natural evolution, are subject to mutation, sexual reproduction, and selection of the most fit. It provides several important mathematical analyses as to why simulating evolution on a computer might be a high optimal way of solving the hard problem. The paper try to work on the Genetic algorithm in broad sense of simulated evolutionary system because it is best-known term -although we recognize that the pure usage of genetic algorithm is generally more focused on optimization and search.
Genetic Algorithms are used to create a version of biological evolution on computers. They operat... more Genetic Algorithms are used to create a version of biological evolution on computers. They operate on small computer program that, just like organisms undergoing natural evolution, are subject to mutation, sexual reproduction, and selection of the most fit. It provides several important mathematical analyses as to why simulating evolution on a computer might be a high optimal way of solving
Procedia Computer Science, 2020
Today in every industry weather, it is ISP, IT products, social network or mobile services there ... more Today in every industry weather, it is ISP, IT products, social network or mobile services there is the problem of customer churn (Customers changing their services from one service provider to another). However, in telecommunication the customers churning very frequently. As the market in telecom is fiercely competitive, in that case, companies proactively have to determine the customers churn by analyzing their behavior and try to put effort and money in retaining the customers. In this proposed model, two machine-learning techniques were used for predicting customer churn Logistic regression and Logit Boost. Experiment was carried out in the WEKA Machine-learning tool, along with a real database from an American company Orange. The result were shown in different evaluation measures.
The web is being used more and more by users of mobile devices. In addition, it is increasingly p... more The web is being used more and more by users of mobile devices. In addition, it is increasingly possible to track the user's location, which provides immense opportunities in geospatial data and its management. Due to the use of location information in services for each mobile device, a large size of spatial data makes it difficult to process spatial queries efficiently and, therefore, we need a lightweight and scalable approach to process large amounts of stored data in distributed file systems. For the most part, all SNSs (social network services) focus on connecting the user account with their location information, such as check-in services, which helps them collect information about user activities and ratings. Of location, but also increases the load of data on their servers. . In this article we propose an indexing technique in combination with efficient processing of Boolean top-k spatial queries where location data is compressed to save space and the Boolean query helps filter results so that unrelated data is not processed, what helps to save space and faster processing of queries.
Journal of Statistics and Management Systems , 2018
The web is being used more and more by users of mobile devices. In addition, it is increasingly p... more The web is being used more and more by users of mobile devices. In addition, it is increasingly possible to track the user’s location, which provides immense opportunities in geospatial data and its management. Due to the use of location information in services for each mobile device, a large size of spatial data makes it difficult to process spatial
queries efficiently and, therefore, we need a lightweight and scalable approach to process large amounts of stored data in distributed file systems. For the most part, all SNSs (social network services) focus on connecting the user account with their location information, such as check-in services, which helps them collect information about user activities and ratings of location, but also increases the load of data on their servers. . In this article we propose an indexing technique in combination with efficient processing of Boolean top-k spatial queries
where location data is compressed to save space and the Boolean query helps filter results so that unrelated data is not processed, what helps to save space and faster processing of queries.
The problem that has occurred as a result of the increased connection between the device and the ... more The problem that has occurred as a result of the increased connection between the device and the system is creating information at an exponential rate that it is becoming increasingly difficult for a possible solution for processing. Therefore, creating a platform for such advanced level data processing, such as the need to increase the level of hardware and software with bright data. To improve the efficiency of the Hadoop Cluster in extensive data collection and analysis, we have proposed an algorithm system that meets the needs of protected discrimination data in Hadoop Clusters and improves performance and efficiency. The proposed paper aims to find out the effectiveness of the new algorithm, compare, consultation, and find out the best solution for improving the big data scenario is a competitive approach. The map reduction techniques from Hadoop will help maintain a close watch on the underlying or discriminatory Hadoop clusters with insights of results as expected from the luminosity.
The grassy landscape as a mosaic of grassland patches presented 287 species in the sampled quadra... more The grassy landscape as a mosaic of grassland patches presented 287 species in the sampled quadrats which represented 177 genera under 53 families. The species composition of different sites varied significantly and the species richness increased with the heterogeneity of communities. Some communities were found to be homogenous possibly due to similar ecological conditions. The highly disturbed communities showed reduced dominance and sprouting of many exclusive species in the communities. A few species, common to most of the concrete communities were Aneilema nudiflora, Cynodon dactylon, Evolvulus nummularis, Desmodium triflorum, Lindernia decussata, L. ciliata and Rungia repens. These species also showed high presence and constance values indicating their wide ecological amplitude to cover various microhabitats. The cluster analysis also showed distinct patterns of presence for various grassland communities. Few communities showed more similarity among themselves, suggesting quit...
The education system in India & across the world has shown a horizontal shift instead of vertical... more The education system in India & across the world has shown a horizontal shift instead of vertical development in one specific domain. The Engineering student in current scenario try to accumulate knowledge from various interdisciplinary course’s and develop application in respective area of study [2]–[4]. This interdisciplinary growth can also be supported and compared using various data mining techniques for future prediction and provide a mathematical foundation for the current selection of the course. This paper emphasis on one such study done for opting the open elective course at leading private university. The data mining process review, apply and compare the classification algorithms like K-NN, Support Vector machine with radial basis kernel. The paper also aims at adopting the data mining techniques as the mathematical foundation for the heuristic process being used till date.
Uploads
Papers by Sumit Srivastava
queries efficiently and, therefore, we need a lightweight and scalable approach to process large amounts of stored data in distributed file systems. For the most part, all SNSs (social network services) focus on connecting the user account with their location information, such as check-in services, which helps them collect information about user activities and ratings of location, but also increases the load of data on their servers. . In this article we propose an indexing technique in combination with efficient processing of Boolean top-k spatial queries
where location data is compressed to save space and the Boolean query helps filter results so that unrelated data is not processed, what helps to save space and faster processing of queries.
queries efficiently and, therefore, we need a lightweight and scalable approach to process large amounts of stored data in distributed file systems. For the most part, all SNSs (social network services) focus on connecting the user account with their location information, such as check-in services, which helps them collect information about user activities and ratings of location, but also increases the load of data on their servers. . In this article we propose an indexing technique in combination with efficient processing of Boolean top-k spatial queries
where location data is compressed to save space and the Boolean query helps filter results so that unrelated data is not processed, what helps to save space and faster processing of queries.