Proceedings of the AAAI Conference on Artificial Intelligence
The ability to leverage the advances in precision agriculture, computer vision, and edge devices ... more The ability to leverage the advances in precision agriculture, computer vision, and edge devices can immensely benefit sustainable agriculture yield. Utilizing the available resources to their maximum requires reliable and intelligent real-time insights to optimize and automate the current agriculture infrastructure. In some countries with low internet penetration rates, such systems need offline and extremely efficient edge deployments. We propose a framework that attends to the trifecta of (i) predicting crop water requirements and irrigating the land appropriately, (ii) providing intelligent insights from aerial images and sensor data for crop management that is fully offline, and (iii) effective post-training quantization and model pruning that leverage the lottery ticket hypothesis - an arbitrarily instantiated network containing a subnetwork that when trained independently will perform as well as the original full network, trained for a similar number of cycles for shrinking t...
A very popular saying in the Machine Learning community is "70% of Machine Learning is data ... more A very popular saying in the Machine Learning community is "70% of Machine Learning is data processing" and going by the structure of this book, the quote seems quite apt. In the preceding chapters, you saw how you can extract, process, and transform data to convert it to a form suitable for learning using Machine Learning algorithms. This chapter deals with the most important part of using that processed data, to learn a model that you can then use to solve real-world problems. You also learned about the CRISP-DM methodology for developing data solutions and projects—the step involving building and tuning these models is the final step in the iterative cycle of Machine Learning.
Code smells indicate the presence of quality issues in a software system. For a thorough large sc... more Code smells indicate the presence of quality issues in a software system. For a thorough large scale smell mining study, researchers require tools that not only allow them to detect a wide range of smells in a large number of repositories automatically but also offer mechanisms to customize the analysis. In this paper, we present a tool Designite that detects 19 design and 11 implementation smells for source code written in C# programming language. Designite provides a command line tool, in addition to an interactive user interface, to support automation required for a large scale mining study. Furthermore, the tool allows customization of quality analysis parameters, such as metric thresholds, to serve a wider range of users.
Journal of Evolution of medical and Dental Sciences, 2015
OBJECTIVE: To Calculate the incidence of mandibular fractures in faciomaxillary trauma and to stu... more OBJECTIVE: To Calculate the incidence of mandibular fractures in faciomaxillary trauma and to study the pattern of fracture and the commonest site of fractures in population in kumaon region between the periods of October 2012 to October 2014. MATERIALS AND METHODS: This is a descriptive study of the patients with alleged isolated maxillofacial injury presenting in the Emergency, ENT &HNS OPD and Dentistry OPD of Dr. Susheela Tiwari Memorial Hospital, Haldwani. RESULTS: Out of 78 patients with faciomaxillary trauma, 24 patients had mandibular fractures; highest percentage was found in 21–30 years of age with male predominance. Road traffic accidents were the most common cause of fracture with body being commonest site. CONCLUSIONS: The incidence and causes of mandibular fracture reflect trauma patterns within the community and can provide a guide to the design of programs geared toward prevention and treatment.
The software development community has been using code quality metrics for the last five decades.... more The software development community has been using code quality metrics for the last five decades. Despite their wide adoption, code quality metrics have attracted a fair share of criticism. In this paper, first, we carry out a qualitative exploration by surveying software developers to gauge their opinions about current practices and potential gaps with the present set of metrics. We identify deficiencies including lack of soundness, i.e., the ability of a metric to capture a notion accurately as promised by the metric, lack of support for assessing software architecture quality, and insufficient support for assessing software testing and infrastructure. In the second part of the paper, we focus on one specific code quality metric— LCOM as a case study to explore opportunities towards improved metrics. We evaluate existing LCOM algorithms qualitatively and quantitatively to observe how closely they represent the concept of cohesion. In this pursuit, we first create eight diverse cas...
A social network can be viewed as a complex interconnection of social entities. Mining a communit... more A social network can be viewed as a complex interconnection of social entities. Mining a community is the task of grouping these social entities together on the basis of their linked pattern. A lot of research has been done on this subject but most of them were only concerned with the unsigned graph. Our work is primarily for the networks having both positive and negative relations; these networks are known as signed social network. In this work, we propose CRA (Clustering re-clustering algorithm) which works in two phases. The first phase is based on Breadth First Search algorithm which forms clusters on the basis of the positive links only. The second phase takes the output of first phase as its input and produces clusters on the basis of a robust criteria termed as participation level. Our algorithm can mine the signed social networks where the negative inter-community links and the positive intra-community links are dense. The algorithm is also useful in mining the communities f...
We attempt to classify the cognitive thought process of human subjects based on their brain activ... more We attempt to classify the cognitive thought process of human subjects based on their brain activity observed through functional Magnetic Resonance Imaging(fMRI) using convolutional neural networks. This project has a huge potential in clinical and health applications. The viability of this project has been shown in previous related work. The primary goal of moving this approach forward is to gauge if, with reasonable probability, it is possible to train classifiers across many subjects. The main reason of using CNNs is that most other classifiers require feature engineering and pre-processing. With the use of neural networks, we avoid this and attempt to show, via comparison with a baseline SVM classifier (which has feature extraction done), that CNNs can perform better even with raw data input. We show our different approaches to model these classifiers and report our results which encapsulate the degree of success achieved over 9 different subjects’ fMRI data.
Abstract The article discusses experimental investigation of a polymeric nanocomposite composed o... more Abstract The article discusses experimental investigation of a polymeric nanocomposite composed of HPAM/GO-SiO2. The DLS, zeta potential, scanning electron microscopy, and infrared spectroscopy are utilized to analyze the resulting composite. As the interfacial tension of a nanopolymeric solution is dependent on a few critical variables, the research simulated interfacial tension using response surface methodology. The results indicate that interfacial tension is not equally critical for all parameters. There was no evidence presented to demonstrate the model's inadequacy. The central composite design had an R2 of 86.81%, indicating that it was the optimal choice for evaluating the impact of hybrid polymeric nanofluids.
Proceedings of the AAAI Conference on Artificial Intelligence
The ability to leverage the advances in precision agriculture, computer vision, and edge devices ... more The ability to leverage the advances in precision agriculture, computer vision, and edge devices can immensely benefit sustainable agriculture yield. Utilizing the available resources to their maximum requires reliable and intelligent real-time insights to optimize and automate the current agriculture infrastructure. In some countries with low internet penetration rates, such systems need offline and extremely efficient edge deployments. We propose a framework that attends to the trifecta of (i) predicting crop water requirements and irrigating the land appropriately, (ii) providing intelligent insights from aerial images and sensor data for crop management that is fully offline, and (iii) effective post-training quantization and model pruning that leverage the lottery ticket hypothesis - an arbitrarily instantiated network containing a subnetwork that when trained independently will perform as well as the original full network, trained for a similar number of cycles for shrinking t...
A very popular saying in the Machine Learning community is "70% of Machine Learning is data ... more A very popular saying in the Machine Learning community is "70% of Machine Learning is data processing" and going by the structure of this book, the quote seems quite apt. In the preceding chapters, you saw how you can extract, process, and transform data to convert it to a form suitable for learning using Machine Learning algorithms. This chapter deals with the most important part of using that processed data, to learn a model that you can then use to solve real-world problems. You also learned about the CRISP-DM methodology for developing data solutions and projects—the step involving building and tuning these models is the final step in the iterative cycle of Machine Learning.
Code smells indicate the presence of quality issues in a software system. For a thorough large sc... more Code smells indicate the presence of quality issues in a software system. For a thorough large scale smell mining study, researchers require tools that not only allow them to detect a wide range of smells in a large number of repositories automatically but also offer mechanisms to customize the analysis. In this paper, we present a tool Designite that detects 19 design and 11 implementation smells for source code written in C# programming language. Designite provides a command line tool, in addition to an interactive user interface, to support automation required for a large scale mining study. Furthermore, the tool allows customization of quality analysis parameters, such as metric thresholds, to serve a wider range of users.
Journal of Evolution of medical and Dental Sciences, 2015
OBJECTIVE: To Calculate the incidence of mandibular fractures in faciomaxillary trauma and to stu... more OBJECTIVE: To Calculate the incidence of mandibular fractures in faciomaxillary trauma and to study the pattern of fracture and the commonest site of fractures in population in kumaon region between the periods of October 2012 to October 2014. MATERIALS AND METHODS: This is a descriptive study of the patients with alleged isolated maxillofacial injury presenting in the Emergency, ENT &HNS OPD and Dentistry OPD of Dr. Susheela Tiwari Memorial Hospital, Haldwani. RESULTS: Out of 78 patients with faciomaxillary trauma, 24 patients had mandibular fractures; highest percentage was found in 21–30 years of age with male predominance. Road traffic accidents were the most common cause of fracture with body being commonest site. CONCLUSIONS: The incidence and causes of mandibular fracture reflect trauma patterns within the community and can provide a guide to the design of programs geared toward prevention and treatment.
The software development community has been using code quality metrics for the last five decades.... more The software development community has been using code quality metrics for the last five decades. Despite their wide adoption, code quality metrics have attracted a fair share of criticism. In this paper, first, we carry out a qualitative exploration by surveying software developers to gauge their opinions about current practices and potential gaps with the present set of metrics. We identify deficiencies including lack of soundness, i.e., the ability of a metric to capture a notion accurately as promised by the metric, lack of support for assessing software architecture quality, and insufficient support for assessing software testing and infrastructure. In the second part of the paper, we focus on one specific code quality metric— LCOM as a case study to explore opportunities towards improved metrics. We evaluate existing LCOM algorithms qualitatively and quantitatively to observe how closely they represent the concept of cohesion. In this pursuit, we first create eight diverse cas...
A social network can be viewed as a complex interconnection of social entities. Mining a communit... more A social network can be viewed as a complex interconnection of social entities. Mining a community is the task of grouping these social entities together on the basis of their linked pattern. A lot of research has been done on this subject but most of them were only concerned with the unsigned graph. Our work is primarily for the networks having both positive and negative relations; these networks are known as signed social network. In this work, we propose CRA (Clustering re-clustering algorithm) which works in two phases. The first phase is based on Breadth First Search algorithm which forms clusters on the basis of the positive links only. The second phase takes the output of first phase as its input and produces clusters on the basis of a robust criteria termed as participation level. Our algorithm can mine the signed social networks where the negative inter-community links and the positive intra-community links are dense. The algorithm is also useful in mining the communities f...
We attempt to classify the cognitive thought process of human subjects based on their brain activ... more We attempt to classify the cognitive thought process of human subjects based on their brain activity observed through functional Magnetic Resonance Imaging(fMRI) using convolutional neural networks. This project has a huge potential in clinical and health applications. The viability of this project has been shown in previous related work. The primary goal of moving this approach forward is to gauge if, with reasonable probability, it is possible to train classifiers across many subjects. The main reason of using CNNs is that most other classifiers require feature engineering and pre-processing. With the use of neural networks, we avoid this and attempt to show, via comparison with a baseline SVM classifier (which has feature extraction done), that CNNs can perform better even with raw data input. We show our different approaches to model these classifiers and report our results which encapsulate the degree of success achieved over 9 different subjects’ fMRI data.
Abstract The article discusses experimental investigation of a polymeric nanocomposite composed o... more Abstract The article discusses experimental investigation of a polymeric nanocomposite composed of HPAM/GO-SiO2. The DLS, zeta potential, scanning electron microscopy, and infrared spectroscopy are utilized to analyze the resulting composite. As the interfacial tension of a nanopolymeric solution is dependent on a few critical variables, the research simulated interfacial tension using response surface methodology. The results indicate that interfacial tension is not equally critical for all parameters. There was no evidence presented to demonstrate the model's inadequacy. The central composite design had an R2 of 86.81%, indicating that it was the optimal choice for evaluating the impact of hybrid polymeric nanofluids.
Uploads
Papers by Tushar Sharma