Papers by Ankur Choudhary
A Comparison of Traditional and Ensemble Machine Learning Approaches for Parkinson’s Disease Classification
Lecture notes on data engineering and communications technologies, 2022
A Pilot Study for Devanagari Script Character Recognition Using Deep Learning Models
Lecture notes on data engineering and communications technologies, 2022
High intensity ultrasound (HIU)-induced functionalization of foxtail millet protein and its fractions
Food Hydrocolloids
A novel chaotic archimedes optimization algorithm and its application for efficient selection of regression test cases
International Journal of Information Technology
Advances in Environmental Engineering and Green Technologies
This chapter reports the details of the existing system of MSW management and characterization of... more This chapter reports the details of the existing system of MSW management and characterization of Muzaffarnagar City located in Western Uttar Pradesh (UP) state in India. The overall waste generated in the city is about 120-125 tons per day (TPD) with a per capita generation rate of 0.415 kg/person/day with a collection efficiency of 70-80%. Physico-chemical and geotechnical properties of the MSW were carried out to determine its overall characteristics. The characterization results showed about 46% of the waste generated in the city is organic nature (from HIG and MIG) and 52% for (LIG) with chemical characterization showing that the elemental carbon was in the highest proportion. Further, the chapter also recommends suitable remedial measures for proper management of the existing MSW management system and suitable treatment alternatives.
Forge News Detection: A Systematic Review
SSRN Electronic Journal
Test Case Optimization using Butterfly Optimization Algorithm
2020 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence)
Software cannot be release until unless it attains significant degree of confidence on quality pa... more Software cannot be release until unless it attains significant degree of confidence on quality parameters. In order to maintain the software quality, testing plays an important role. But this is a costly affair as it consumes almost 50 percent of the overall software development cost. The increasing competitiveness and ever updating technological change as well as customer requirements make regression testing a most important activity. So, regression testing is conducted before every release of the software which becomes expensive. Optimization of regression test suite is a way to reduce this higher cost. This paper proposes an efficient self adaptive butterfly optimization technique. The proposed approach is further utilized on regression test suite optimization problem to reduce the regression test suite size. Performance of proposed approach has been evaluated against Bat Search Optimization based approaches using fault detection as performance measures. Different tests are performed to analyze and validate the results. These results demonstrate the dominance of the proposed approach over the compared ones.
RFDCS: A reactive fault detection and classification scheme for clustered wsns
Peer-to-Peer Networking and Applications
An Effective Approach for Classification of Dental Caries using Convolutional Neural Networks
2021 10th International Conference on System Modeling & Advancement in Research Trends (SMART)
In 20th century, Dental Caries have become a major health issue globally. According to WHO, 2.3 b... more In 20th century, Dental Caries have become a major health issue globally. According to WHO, 2.3 billion adults and 530 million children are suffering from dental caries-related issues. This problem can be controlled by early accurate detection and treatments. There exist many approaches in the literature to classify dental caries. But accuracy of these approaches is still a challenge. This paper proposes an effective approach using convolutional neural networks by adopting VGG16 and VGG19 models. The patient’s X-Ray images have been collected and labeled. The proposed models have been compared on the collected datasets. The results over this dataset indicate the superiority of VGG19 based model with 95% accuracy as compared to VGG16 based model with 91% accuracy.
Managing sewage sludge and pine needles through anaerobic co-digestion in a hilly terrain: a lost cost approach
International Journal of Environment and Waste Management, 2021
The pine needles (PNs) and sewage sludge (SS) have a significant amount of biodegradables. Due to... more The pine needles (PNs) and sewage sludge (SS) have a significant amount of biodegradables. Due to this they are highly susceptible to pollute the environment. Both the wastes can be managed via anaerobic digestion. However, the low ambient temperature in hilly areas can affect the digestion process. Therefore, to determine their anaerobic digestibility in a hilly terrain two digesters were examined: one with mono-anaerobic digestion of SS and another one with co-digestion of SS with PNs. It was found that co-digestion yielded 40.93% more biogas than that mono-digestion of SS. Cumulative methane yield of 158.6 mL g−1 VSadded and 268.45 mL g−1 VSadded was obtained from SS and co-digestion of SS-PNs, respectively. During the experiment, a reduction of 26.7% and 35% COD and VS for SS and 30 and 34% COD and VS for SS-PNs were reported, respectively. To study the anaerobic digestibility various mathematical models and one kinetic model were also used. This study concludes that PN and SS can be managed through anaerobic digestion however their co-digestion is highly recommended.
Springfield has many new initiatives and projects that are revitalizing the city. These neighborh... more Springfield has many new initiatives and projects that are revitalizing the city. These neighborhoods have had a few large infrastructure changes on going in the area. Some including large street realignments like the new connection between Central Street and Hickory Street and the new rotary in the Northern portion of the focus area. As well as these large projects, smaller projects like Educare, the New Elias Brookings school, and the Old Elias Brooking apartments are set to have lasting affects on the neighborhood.
Automobiles remained conceived to save the required time and hard work of people, but that showed... more Automobiles remained conceived to save the required time and hard work of people, but that showed to be deadly as the number of vehicles increased on road. Driver faces many problem like parking issues, accident and traffic. Therefore it required to solve matters of mishaps caused by automobiles. There is a need to generate a clever device that is employer friendly that purposes to provide information like, humidity, temperature, and way, trip travelled, and other things to employers. Smart Cars can help to reduce the number of accident which occur due to many problems like communication, careless driving, poor visibility, etc. To enable message among 2 automobiles to avoid uncommon decelerating began by 2 automobiles in vicinity and to prevent mishaps, smart cars can be helpful. Intelligent Car is coming generation automatic car that provide user relaxed, luxurious and safe travelling with comfort. In this paper, reviews of different methods of making smart car are covered.
Hetrogenous Computing Task Scheduling Using Improved Harmony Search Optimization
2018 International Conference on Advances in Computing, Communication Control and Networking (ICACCCN), 2018
Cloud computing is one of the enormously growing and challenging area in the modern era. There is... more Cloud computing is one of the enormously growing and challenging area in the modern era. There is a rapid technological advancement in virtualization technology to achieve most effective features of cloud services like reliability, cost-effective scalable services, availability and on-demand services. Tasks scheduling is one of the most challenging NP-hard problems in cloud systems. In past few decades, various solutions have been proposed to handle task scheduling problem, but the scope of optimization still persists. In this paper, we have proposed an improved harmony search algorithm based approach to solve task scheduling problem to minimize the total completion time measured as makespan and maximize the resource utilization of virtual machine, assuming that tasks are non-preemptive and independent. The proposed algorithm also ensures that no virtual machine is overloaded and its resources are utilized to the maximum level by minimizing makespan. An extensive experiment is designed and simulation is done on heterogeneous computing dataset available from open source. Results indicate the superiority of proposed approach over existing approaches.
Research on Teaching and Learning Quantum Mechanics Proposal for a Poster Session at the 1999 NARST Meeting
"I believe that any lover of nature should study quantum mechanics-- not its mathematics... more "I believe that any lover of nature should study quantum mechanics-- not its mathematics but its ideas."--Douglas Hofstadter Until recently the main purpose for students other than physicists and chemists to study quantum mechanics was for a better appreciation of its influence on modern thought. Now people who will be making decisions about business and technology need an understanding of modern physics. Recent developments in miniaturization of electronics and nanotechnology bring into the business and engineering world devices that can be appreciated only through the principles of quantum mechanics. Likewise, in the past few years experiments have directly analyzed some of the fundamental paradoxes in quantum mechanics. Thus, an understanding of quantum physics beyond the level of a coffee table book is needed for the well-informed citizens and all types of professional in the 21st Century. As the need for students to understand quantum phenomena increases, so does our need to understand the learning process for these abstract and counterintuitive concepts. In recent years research in student understanding of quantum science has increased greatly.
Mobile Robot Path Planning Based Upon Updated Whale Optimization Algorithm
2020 10th International Conference on Cloud Computing, Data Science & Engineering (Confluence), 2020
Automated navigation is an important feature of any mobile robot and is a challenge for a robot t... more Automated navigation is an important feature of any mobile robot and is a challenge for a robot to plan the path in an unknown environment. We can categorize the path planning strategy of robots in two methods, first is the Classical Methods and second is Heuristic Methods. In this paper, a modified whale optimization algorithm is proposed that ensures an optimal collision-free path. In whale optimization algorithm (WOA) the fitness of any whale will be calculated by taking in consideration the target location and the obstacles in the search space. Many simulations were run in different search spaces to find the optimal path at the end of the iterations when the individual reaches the final destination (target location). The simulation and results show, the proposed modified WOA is feasible for mobile robot path selection problems.
Image Watermarking Using LTP and DCT
2018 8th International Conference on Cloud Computing, Data Science & Engineering (Confluence), 2018
When an image enters into the digital world, the probability that the image will get tempered als... more When an image enters into the digital world, the probability that the image will get tempered also increases. Hence there exists a higher threat to such content (image, audio, and video) to be copied, modified and distributed. In this thesis, LTP (Local Ternary Pattern) along with DCT (Discrete Cosine Transform) have been employed. By using the DCT technique on the JPEG image we are able to provide lossy compression to the image. In this way, the image is compressed such that size of the image reduced enough for storage of content, in this case, a watermark image. Once this has been done, LTP technique is applied to it. The use of LTP will help to embed a watermark even if it is of a heavier size. The original image will be obtained with lesser impacts to it. To show the effectiveness of LTP watermarking, certain attacks like cropping, noise, and compression are applied. As a result, the extracted watermark is tempered. DCT ensures robustness by compressing the image while LTP allows watermark embedding and extraction. DWT and LBP both provide compression and watermarking respectively. But, this paper has briefly compared DCT and DWT techniques to conclude as to why DCT has been chosen. Also, this paper shows reasons as to why LTP is chosen over LBP. Index Terms-Image Compression, Image Watermarking, Discrete Cosine Transform (DCT), Discrete Wavelet Transform (DWT). Local Ternary Pattern (LTP), Local Binary Pattern (LBP).
Conceptualizing BCI and AI in Video Games
2019 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS), 2019
Video Games are the most common and popular ways of entertainment mainly amongst the younger gene... more Video Games are the most common and popular ways of entertainment mainly amongst the younger generation of world. Due to the advent of Virtual Reality (VR) and Brain Computer Interface (BCI), the gaming experience has increased exponentially amongst the users and the use of Artificial Intelligence (AI) in video games makes it less predictive and more tough and exciting to play. With Virtual Reality now looking distinctly normal, Brain Computer Interface is all set to become the futuristic technology in the gaming horizon. The researchers discover where the technology is at present and how it could transform the way users play in the future. Through this paper, we propose a method to make the video games more exciting and challenging for the users to experience ultimate gaming by combining the trending topics in the world of computer science i.e. BCI and AI.
Effect of solvents on extraction of polycyclic aromatic hydrocarbons from Coffee, Chicken and Kitchen exhaust depositions
Polycyclic aromatic hydrocarbons are carcinogenic compounds which are formed and accumulated in d... more Polycyclic aromatic hydrocarbons are carcinogenic compounds which are formed and accumulated in different food products at preand post-harvest stages. Extraction is an important step performed prior to PAHs determination and is governed by various factors. Type of solvent used for extraction is one such factor affecting the quantification and profiling of PAHs based on its interaction with food matrix. The present study focused on selection of solvent for the higher extraction efficiency of PAHs from matrices such as chicken, coffee and kitchen exhaust depositions. The different solvents such as cyclohexane, hexane, toluene, acetonitrile and DCM:Hexane were targeted. The highest concentration of total PAHs extracted from food matrix varied greatly with solvent used. Highest PAHs concentration (36.30 mg/kg) was obtained in kitchen exhaust depositions followed by coffee (28.96mg/kg) and chicken (19.39mg/kg) when the solvents of extraction were in cyclohexane, acetonitrile and toluene,...
Rules Mining for the Diagnosis of Breast Adenocarcinoma Using Rough Set Theory
In this paper a Rough Set Theory based approach is used to mine concise rules from a huge dataset... more In this paper a Rough Set Theory based approach is used to mine concise rules from a huge dataset of patients treated for Breast Adenocarcinoma, one of the prominent type of Adenocarcinoma among women. This paper works on a sample dataset containing data of six different classes, organized as objects and attributes. The dataset contains lot of uninformative attributes which has to be filtered out. Various algorithms are applied based on Rough Set Theory to first eliminate noise and redundancy from the dataset and then generate rules .Different set of rules are generated for different reducts obtained by the application of different algorithms. These rules are studied thoroughly to understand the behavior of the patients’ genes diagnosed with Breast Adenocarcinoma. Most important rules are singled out, using metric values, to get a good knowledge about the reasons behind the decision classes.
A Hybrid Metaheuristic to Solve Capacitated Vehicle Routing Problem
Uploads
Papers by Ankur Choudhary