Prashant Shambharkar | Delhi Technological University, Delhi, India (original) (raw)

Uploads

Papers by Prashant Shambharkar

Research paper thumbnail of Artificial Intelligence driven Intrusion Detection Framework for the Internet of Medical Things

Research Square (Research Square), Mar 14, 2023

The fusion of the internet of things (IoT) in the healthcare discipline has appreciably improved ... more The fusion of the internet of things (IoT) in the healthcare discipline has appreciably improved the medical treatment and operations activities of patients. Using the Internet of Medical Things (IoMT) technology, a doctor may treat more patients and save lives by employing real-time patient monitoring (RPM) and outlying diagnostics. Despite the many advantages, cyber-attacks on linked healthcare equipment can jeopardize privacy and even endanger the patient's health. However, it is a signi cant problem to offer high-safety attributes that ensure the secrecy and accuracy of patient health data. Any modi cation to the data might impact how the patients are treated, resulting in human fatalities under emergency circumstances. To assure patients' data safety and privacy in the network, and to meet the enormous requirement for IoMT devices with e cient healthcare services for the huge population, a secured robust model is necessary. Arti cial Intelligence (AI) based approaches like Machine Learning (ML), and Deep Learning (DL) have the potential to be useful methodology for intrusion detection because of the high dynamicity and enormous dimensionality of the data used in such systems. In this paper, three DL models have been proposed to build an intrusion detection system (IDS) for IoMT network. With a 100% accuracy rate, our proposed AI models exceed the current existing methodology in detecting network intrusions by utilizing the patient's biometric data features with network tra c ow. Furthermore, a thorough examination of employing several ML and DL approaches has been discussed for detecting intrusion in the IoMT network.

Research paper thumbnail of Study on Optimizing Feature Selection in Hate Speech Using Evolutionary Algorithms

Research paper thumbnail of COVID-19 Diagnosis Using Machine Learning Techniques

2022 International Conference on Communication, Computing and Internet of Things (IC3IoT), Mar 10, 2022

Research paper thumbnail of Enhancing Spam Detection on SMS performance using several Machine Learning Classification Models

2022 6th International Conference on Trends in Electronics and Informatics (ICOEI), Apr 28, 2022

Research paper thumbnail of From video summarization to real time video summarization in smart cities and beyond: A survey

Frontiers in big data, Jan 9, 2023

Research paper thumbnail of AttnHAR: Human Activity Recognition using Data Collected from Wearable Sensors

Research paper thumbnail of Comparative Study on Handwritten Digit Recognition Classifier Using CNN and Machine Learning Algorithms

2022 6th International Conference on Computing Methodologies and Communication (ICCMC), Mar 29, 2022

Digit Recognition is essential for interpreting image processing and pattern recognition since a ... more Digit Recognition is essential for interpreting image processing and pattern recognition since a machine cannot classify handwritten digits. Many real-time applications include OCR (Optical Character Recognition), which recognizes characters and digitizes printed texts. Converting handwritten digits to digital characters has been a challenging problem since the past. The physical documents cannot be efficiently processed without converting them to digital copies and it requires a lot of time and efforts. To provide a solution to handwritten classification, several algorithms and techniques have been proposed over the years. The objective of this research is to use Convolutional Neural Networks (CNN), K-Nearest Neighbor, and Support Vector Machine to recognize isolated handwritten digits. After implementing and training the models on the same dataset and comparing the results obtained for three different models, the results show that CNN is the most optimal machine learning technique to classify handwritten digits with an accuracy of 99.59 percent.

Research paper thumbnail of Plant Disease Detection And Prevention Using Deep Learning

Research paper thumbnail of GenGen: Analysing the Performance of Transformer-based Encoder-Decoder in a General Natural Language Generation Paradigm

2022 International Conference on Applied Artificial Intelligence and Computing (ICAAIC), May 9, 2022

Research paper thumbnail of Applicability of ML-IoT in Smart Healthcare Systems: Challenges, Solutions & Future Direction

2022 International Conference on Computer Communication and Informatics (ICCCI), Jan 25, 2022

In today's world, as population is at high peak and due to changing life style of people, ind... more In today's world, as population is at high peak and due to changing life style of people, individuals are suffering from various chronic disease. With shift towards modern methodology, involvement of human efforts has decreased, as know a day's people need to finish particular amount of task within few hours and with less effort. No doubt technology has made less intervention of human but it has certain limitations too. Due to less physical involvement, humans are more prone to diseases. Internet of things (IoT) plays a very crucial role in health care sector. Using various sensors, it become possible to trace the medical health condition of the human, and a message can be forwarded to nearby hospitals which helps the patients with ease. In this paper, three different diseases like heart disease, diabetes and novel COVID-19 are discussed where different machine learning algorithms are reviewed with involvement of IoT sensors.

Research paper thumbnail of CNN based Deep Learning Approach for Brain Tumor Detection in MRI Images

2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)

Research paper thumbnail of Early Detection of Alzheimer's Disease: The Importance of Speech Analysis

2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)

Research paper thumbnail of Deep Learning Methods For COVID-19 Mitigation: Applications, Challenges and Future Implications

2022 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)

Research paper thumbnail of Security Threats & Attacks in IoV Environment: Open Research Issues and Challenges

2022 Third International Conference on Intelligent Computing Instrumentation and Control Technologies (ICICICT)

Research paper thumbnail of Crop Protection against Animals Based on Voice Recognition

NEW ARCH-INTERNATIONAL JOURNAL OF CONTEMPORARY ARCHITECTURE, Oct 6, 2021

Research paper thumbnail of Image Forgery Detection using Modified Adaptive Over-Segmentation and Feature Matching

NEW ARCH-INTERNATIONAL JOURNAL OF CONTEMPORARY ARCHITECTURE, Oct 6, 2021

Research paper thumbnail of Hit Song Prediction: Using Ant Colony Optimization for Feature Selection

NEW ARCH-INTERNATIONAL JOURNAL OF CONTEMPORARY ARCHITECTURE, Oct 6, 2021

Research paper thumbnail of A Novel Intrusion Detection System Using Deep Learning

Advances in Intelligent Systems and Computing, 2021

Research paper thumbnail of Multimodal KDK Classifier for Automatic Classification of Movie Trailers

International Journal of Recent Technology and Engineering (IJRTE), 2019

Movie trailer classification is a field of automation of analyzing the movie trailers and classif... more Movie trailer classification is a field of automation of analyzing the movie trailers and classify them into one of the various genres. In this paper, we proposed a classifier to identify the genre of a movie trailer by analyzing it's audio and visual features simultaneously. Our Approach decomposes a trailer video into frames and audio file and then analyze them based on certain specific features to categorize them into four genres. Our aim was to minimize the number of parameters involved in analyzing the trailer since other papers use many arguments which are impractical. The proposed classifier was trained on 4 audio, 2 broad visual features extracted from over 900 movie trailers distributed across 4 different genres, namely Drama, Horror, Romance, and Action. The Classifier Model has been trained using Neural Networks and Convolutional Neural Networks. Our Classifier Model can be used in Recommendation Systems and various websites like IMDB for automation of the genre class...

Research paper thumbnail of Automatic Annotation of Events and Highlights Generation of Cricket Match Videos

International Journal of Innovative Technology and Exploring Engineering, 2019

In this paper, we propose a novel method for automatic annotation of events and highlights genera... more In this paper, we propose a novel method for automatic annotation of events and highlights generation for cricket match videos. The videos are divided into time intervals representing one ball clip using a Convolutional Neural Network (CNN) and Optical Character Recognition (OCR). CNN detects the start frame of a ball. OCR is used to detect the end of the ball and to annotate it by recognizing the change in runs/wickets. The proposed framework is able to annotate events and generate sufficiently good highlights for four full length cricket matches.

Research paper thumbnail of Artificial Intelligence driven Intrusion Detection Framework for the Internet of Medical Things

Research Square (Research Square), Mar 14, 2023

The fusion of the internet of things (IoT) in the healthcare discipline has appreciably improved ... more The fusion of the internet of things (IoT) in the healthcare discipline has appreciably improved the medical treatment and operations activities of patients. Using the Internet of Medical Things (IoMT) technology, a doctor may treat more patients and save lives by employing real-time patient monitoring (RPM) and outlying diagnostics. Despite the many advantages, cyber-attacks on linked healthcare equipment can jeopardize privacy and even endanger the patient's health. However, it is a signi cant problem to offer high-safety attributes that ensure the secrecy and accuracy of patient health data. Any modi cation to the data might impact how the patients are treated, resulting in human fatalities under emergency circumstances. To assure patients' data safety and privacy in the network, and to meet the enormous requirement for IoMT devices with e cient healthcare services for the huge population, a secured robust model is necessary. Arti cial Intelligence (AI) based approaches like Machine Learning (ML), and Deep Learning (DL) have the potential to be useful methodology for intrusion detection because of the high dynamicity and enormous dimensionality of the data used in such systems. In this paper, three DL models have been proposed to build an intrusion detection system (IDS) for IoMT network. With a 100% accuracy rate, our proposed AI models exceed the current existing methodology in detecting network intrusions by utilizing the patient's biometric data features with network tra c ow. Furthermore, a thorough examination of employing several ML and DL approaches has been discussed for detecting intrusion in the IoMT network.

Research paper thumbnail of Study on Optimizing Feature Selection in Hate Speech Using Evolutionary Algorithms

Research paper thumbnail of COVID-19 Diagnosis Using Machine Learning Techniques

2022 International Conference on Communication, Computing and Internet of Things (IC3IoT), Mar 10, 2022

Research paper thumbnail of Enhancing Spam Detection on SMS performance using several Machine Learning Classification Models

2022 6th International Conference on Trends in Electronics and Informatics (ICOEI), Apr 28, 2022

Research paper thumbnail of From video summarization to real time video summarization in smart cities and beyond: A survey

Frontiers in big data, Jan 9, 2023

Research paper thumbnail of AttnHAR: Human Activity Recognition using Data Collected from Wearable Sensors

Research paper thumbnail of Comparative Study on Handwritten Digit Recognition Classifier Using CNN and Machine Learning Algorithms

2022 6th International Conference on Computing Methodologies and Communication (ICCMC), Mar 29, 2022

Digit Recognition is essential for interpreting image processing and pattern recognition since a ... more Digit Recognition is essential for interpreting image processing and pattern recognition since a machine cannot classify handwritten digits. Many real-time applications include OCR (Optical Character Recognition), which recognizes characters and digitizes printed texts. Converting handwritten digits to digital characters has been a challenging problem since the past. The physical documents cannot be efficiently processed without converting them to digital copies and it requires a lot of time and efforts. To provide a solution to handwritten classification, several algorithms and techniques have been proposed over the years. The objective of this research is to use Convolutional Neural Networks (CNN), K-Nearest Neighbor, and Support Vector Machine to recognize isolated handwritten digits. After implementing and training the models on the same dataset and comparing the results obtained for three different models, the results show that CNN is the most optimal machine learning technique to classify handwritten digits with an accuracy of 99.59 percent.

Research paper thumbnail of Plant Disease Detection And Prevention Using Deep Learning

Research paper thumbnail of GenGen: Analysing the Performance of Transformer-based Encoder-Decoder in a General Natural Language Generation Paradigm

2022 International Conference on Applied Artificial Intelligence and Computing (ICAAIC), May 9, 2022

Research paper thumbnail of Applicability of ML-IoT in Smart Healthcare Systems: Challenges, Solutions & Future Direction

2022 International Conference on Computer Communication and Informatics (ICCCI), Jan 25, 2022

In today's world, as population is at high peak and due to changing life style of people, ind... more In today's world, as population is at high peak and due to changing life style of people, individuals are suffering from various chronic disease. With shift towards modern methodology, involvement of human efforts has decreased, as know a day's people need to finish particular amount of task within few hours and with less effort. No doubt technology has made less intervention of human but it has certain limitations too. Due to less physical involvement, humans are more prone to diseases. Internet of things (IoT) plays a very crucial role in health care sector. Using various sensors, it become possible to trace the medical health condition of the human, and a message can be forwarded to nearby hospitals which helps the patients with ease. In this paper, three different diseases like heart disease, diabetes and novel COVID-19 are discussed where different machine learning algorithms are reviewed with involvement of IoT sensors.

Research paper thumbnail of CNN based Deep Learning Approach for Brain Tumor Detection in MRI Images

2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)

Research paper thumbnail of Early Detection of Alzheimer's Disease: The Importance of Speech Analysis

2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC)

Research paper thumbnail of Deep Learning Methods For COVID-19 Mitigation: Applications, Challenges and Future Implications

2022 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)

Research paper thumbnail of Security Threats & Attacks in IoV Environment: Open Research Issues and Challenges

2022 Third International Conference on Intelligent Computing Instrumentation and Control Technologies (ICICICT)

Research paper thumbnail of Crop Protection against Animals Based on Voice Recognition

NEW ARCH-INTERNATIONAL JOURNAL OF CONTEMPORARY ARCHITECTURE, Oct 6, 2021

Research paper thumbnail of Image Forgery Detection using Modified Adaptive Over-Segmentation and Feature Matching

NEW ARCH-INTERNATIONAL JOURNAL OF CONTEMPORARY ARCHITECTURE, Oct 6, 2021

Research paper thumbnail of Hit Song Prediction: Using Ant Colony Optimization for Feature Selection

NEW ARCH-INTERNATIONAL JOURNAL OF CONTEMPORARY ARCHITECTURE, Oct 6, 2021

Research paper thumbnail of A Novel Intrusion Detection System Using Deep Learning

Advances in Intelligent Systems and Computing, 2021

Research paper thumbnail of Multimodal KDK Classifier for Automatic Classification of Movie Trailers

International Journal of Recent Technology and Engineering (IJRTE), 2019

Movie trailer classification is a field of automation of analyzing the movie trailers and classif... more Movie trailer classification is a field of automation of analyzing the movie trailers and classify them into one of the various genres. In this paper, we proposed a classifier to identify the genre of a movie trailer by analyzing it's audio and visual features simultaneously. Our Approach decomposes a trailer video into frames and audio file and then analyze them based on certain specific features to categorize them into four genres. Our aim was to minimize the number of parameters involved in analyzing the trailer since other papers use many arguments which are impractical. The proposed classifier was trained on 4 audio, 2 broad visual features extracted from over 900 movie trailers distributed across 4 different genres, namely Drama, Horror, Romance, and Action. The Classifier Model has been trained using Neural Networks and Convolutional Neural Networks. Our Classifier Model can be used in Recommendation Systems and various websites like IMDB for automation of the genre class...

Research paper thumbnail of Automatic Annotation of Events and Highlights Generation of Cricket Match Videos

International Journal of Innovative Technology and Exploring Engineering, 2019

In this paper, we propose a novel method for automatic annotation of events and highlights genera... more In this paper, we propose a novel method for automatic annotation of events and highlights generation for cricket match videos. The videos are divided into time intervals representing one ball clip using a Convolutional Neural Network (CNN) and Optical Character Recognition (OCR). CNN detects the start frame of a ball. OCR is used to detect the end of the ball and to annotate it by recognizing the change in runs/wickets. The proposed framework is able to annotate events and generate sufficiently good highlights for four full length cricket matches.