I've completed my graduation in Electrical and Electronic Engineering. Seeking to admit me into a renowned university for Higher studies. Research interest in Bioinformatics, Signal processing, Machine learning, Neural networks.
The Badminton Activity Recognition (BAR) Dataset was collected for the sport of Badminton for 12 ... more The Badminton Activity Recognition (BAR) Dataset was collected for the sport of Badminton for 12 commonly played strokes. Besides the strokes, the objective of the dataset is to capture the associated leg movements.
2019 IEEE 5th International Conference for Convergence in Technology (I2CT), 2019
With the massive expansion of image security for day to day purposes, image watermarking has beco... more With the massive expansion of image security for day to day purposes, image watermarking has become a critical factor regarding protection schemes. Here, we proposed a watermarking plan where we created a secondary image using directive contrast of the DWT (Discrete Wavelet Transform) subbands from the host image and used this secondary image for watermark embedding using DWT-SVD transformation. The horizontal subband was decomposed up to 2-levels during insertion of the watermark into the cover image to achieve better performance against noise attacks. The obtained results depict that our scheme can resist a number of signal processing attacks maintaining good perceptual quality with PSNR above 50 dB and NC more than 0.99. The evaluations of our process justify both of the imperceptibility to human visual system and robustness against noise attacks which are the prime aspects of image watermarking.
2017 3rd International Conference on Electrical Information and Communication Technology (EICT), 2017
The rapid acceleration in the growth of digitized media has made authentication and protection of... more The rapid acceleration in the growth of digitized media has made authentication and protection of digital data through watermarking vitally important. In this paper, we proposed a semi blind watermarking scheme utilizing both Discrete Wavelength Transform (DWT) and Singular Value Decomposition (SVD). To embed the watermark, we transformed the host image into wavelet domain and generated a secondary host image using directive contrast. By remodeling the SVD coefficients of the watermark with the SVD coefficients of secondary image we inserted the watermark into the secondary image. A genuine extraction scheme has also been developed to recover the watermark from the cover image. The scheme has been employed using horizontal sub band. In addition to, evaluations have been added in terms of vertical and diagonal sub bands to compare the performance of the algorithm on the basis of specific sub bands. Experimental evaluations in terms of Normalized Correlation (NC) and Peak Signal to Noise Ratio (PSNR) give proof that our procedure is durable and imperceptible under variety of attacks.
2021 IEEE International Conference on Smart Computing (SMARTCOMP), 2021
To deploy an intelligent transport system in urban environment, an effective and real-time accide... more To deploy an intelligent transport system in urban environment, an effective and real-time accident risk prediction method is required that can help maintain road safety, provide adequate level of medical assistance and transport in case of an emergency. Reducing traffic accidents is an important problem for increasing public safety, so accident analysis and prediction have been a subject of extensive research in recent time. Even if a traffic hazard occurs, a readily deployable structure with an accurate prediction of accident can contribute to better management of rescue resources. But the significant shortcomings of current studies are the use of small-scale datasets with minimal scope, being based on extensive data sets, and not being applicable for real-time purposes. To overcome these challenges, we propose ARIS: a system for real-time traffic accident prediction built on a traffic accident dataset named 'US-Accidents' which covers 49 states of United States, collected from February 2016 to June 2020. Our approach is based on a deep neural network model that utilizes a variety of data characteristics, such as time-sensitive weather data, textual information, and discerning factors. We have tested ARIS against multiple baselines through a comprehensive series of experiments across several major cities of USA, and we have noticed significant improvement during inference especially in detecting accident classes. Additionally, to make our model edge-implementable we have compressed our model using a joint technique of magnitude-based weight pruning and model quantization. We have also demonstrated the inference results along with power consumption profiling after deploying the model on a resource constrained environment that consists of Intel Neural Compute Stick 2 (NCS2) with Raspberry Pi 4B (RPi4). Our investigation and observations indicate major improvements to predict unusual traffic accident event even after model compression and deployment. We have managed to reduce the model size and inference time by ≈ 6x, and ≈ 70 % respectively with insignificant drop in performance. Furthermore, to better understand the importance of each individual type of variables used in our analysis, we have showcased a comprehensive ablation study.
2020 IEEE 20th International Conference on Bioinformatics and Bioengineering (BIBE), 2020
Stay at home order during the COVID-19 helps flatten the curve but ironically, instigate mental h... more Stay at home order during the COVID-19 helps flatten the curve but ironically, instigate mental health problems among the people who have Substance Use Disorders. Measuring the electrical activity signals in brain using off-the-shelf consumer wearable devices such as smart wristwatch and mapping them in real time to underlying mood, behavioral and emotional changes play striking roles in postulating mental health anomalies. In this work, we propose to implement a wearable, On-device Mental Anomaly Detection (OMAD) system to detect anomalous behaviors and activities that render to mental health problems and help clinicians to design effective intervention strategies. We propose an intrinsic artifact removal model on Electroencephalogram (EEG) signal to better correlate the fine-grained behavioral changes. We design model compression technique on the artifact removal and activity recognition (main) modules. We implement a magnitude-based weight pruning technique both on convolutional neural network and Multilayer Perceptron to employ the inference phase on Nvidia Jetson Nano; one of the tightest resourceconstrained devices for wearables. We experimented with three different combinations of feature extractions and artifact removal approaches. We evaluate the performance of OMAD in terms of accuracy, F1 score, memory usage and running time for both unpruned and compressed models using EEG data from both control and treatment (alcoholic) groups for different object recognition tasks. Our artifact removal model and main activity detection model achieved about ≈ 93% and 90% accuracy, respectively with significant reduction in model size (70%) and inference time (31%).
The rapid acceleration in the growth of digitized media has made authentication and protection o... more The rapid acceleration in the growth of digitized media has made authentication and protection of digital data through watermarking vitally important. In this paper, we proposed a semi blind watermarking scheme utilizing both Discrete Wavelength Transform (DWT) and Singular Value Decomposition (SVD). To embed the watermark, we transformed the host image into wavelet domain and generated a secondary host image using directive contrast. By remodeling the SVD coefficients of the watermark with the SVD coefficients of secondary image we inserted the watermark into the secondary image. A genuine extraction scheme has also been developed to recover the watermark from the cover image. The scheme has been employed using horizontal sub band. In addition to, evaluations have been added in terms of vertical and diagonal sub bands to compare the performance of the algorithm on the basis of specific sub bands. Experimental evaluations in terms of Normalized Correlation (NC) and Peak Signal to Noise Ratio (PSNR) give proof that our procedure is durable and imperceptible under variety of attacks. Keywords—discrete wavelet transform, human visual system, singular value decomposition, watermarking, directive contrast.
— The rapid acceleration in the growth of digitized media has made authentication and protection ... more — The rapid acceleration in the growth of digitized media has made authentication and protection of digital data through watermarking vitally important. In this paper, we proposed a semi blind watermarking scheme in the joint DWT-SVD domain. To embed the watermark, we transformed the host image into wavelet domain and generated a reference image using directive contrast. By remodeling the SVD coefficients of the watermark with the SVD coefficients of reference image we inserted the watermark into the reference image. A genuine extraction scheme has also been developed to recover the watermark from the cover image. The scheme has been employed using horizontal sub band. In addition to, evaluations have been added in terms of vertical and diagonal sub bands to compare the performance of the algorithm on the basis of specific sub bands. Experimental evaluations in terms NC and PSNR give proof that our procedure is durable and imperceptible under variety of attacks.
The Badminton Activity Recognition (BAR) Dataset was collected for the sport of Badminton for 12 ... more The Badminton Activity Recognition (BAR) Dataset was collected for the sport of Badminton for 12 commonly played strokes. Besides the strokes, the objective of the dataset is to capture the associated leg movements.
2019 IEEE 5th International Conference for Convergence in Technology (I2CT), 2019
With the massive expansion of image security for day to day purposes, image watermarking has beco... more With the massive expansion of image security for day to day purposes, image watermarking has become a critical factor regarding protection schemes. Here, we proposed a watermarking plan where we created a secondary image using directive contrast of the DWT (Discrete Wavelet Transform) subbands from the host image and used this secondary image for watermark embedding using DWT-SVD transformation. The horizontal subband was decomposed up to 2-levels during insertion of the watermark into the cover image to achieve better performance against noise attacks. The obtained results depict that our scheme can resist a number of signal processing attacks maintaining good perceptual quality with PSNR above 50 dB and NC more than 0.99. The evaluations of our process justify both of the imperceptibility to human visual system and robustness against noise attacks which are the prime aspects of image watermarking.
2017 3rd International Conference on Electrical Information and Communication Technology (EICT), 2017
The rapid acceleration in the growth of digitized media has made authentication and protection of... more The rapid acceleration in the growth of digitized media has made authentication and protection of digital data through watermarking vitally important. In this paper, we proposed a semi blind watermarking scheme utilizing both Discrete Wavelength Transform (DWT) and Singular Value Decomposition (SVD). To embed the watermark, we transformed the host image into wavelet domain and generated a secondary host image using directive contrast. By remodeling the SVD coefficients of the watermark with the SVD coefficients of secondary image we inserted the watermark into the secondary image. A genuine extraction scheme has also been developed to recover the watermark from the cover image. The scheme has been employed using horizontal sub band. In addition to, evaluations have been added in terms of vertical and diagonal sub bands to compare the performance of the algorithm on the basis of specific sub bands. Experimental evaluations in terms of Normalized Correlation (NC) and Peak Signal to Noise Ratio (PSNR) give proof that our procedure is durable and imperceptible under variety of attacks.
2021 IEEE International Conference on Smart Computing (SMARTCOMP), 2021
To deploy an intelligent transport system in urban environment, an effective and real-time accide... more To deploy an intelligent transport system in urban environment, an effective and real-time accident risk prediction method is required that can help maintain road safety, provide adequate level of medical assistance and transport in case of an emergency. Reducing traffic accidents is an important problem for increasing public safety, so accident analysis and prediction have been a subject of extensive research in recent time. Even if a traffic hazard occurs, a readily deployable structure with an accurate prediction of accident can contribute to better management of rescue resources. But the significant shortcomings of current studies are the use of small-scale datasets with minimal scope, being based on extensive data sets, and not being applicable for real-time purposes. To overcome these challenges, we propose ARIS: a system for real-time traffic accident prediction built on a traffic accident dataset named 'US-Accidents' which covers 49 states of United States, collected from February 2016 to June 2020. Our approach is based on a deep neural network model that utilizes a variety of data characteristics, such as time-sensitive weather data, textual information, and discerning factors. We have tested ARIS against multiple baselines through a comprehensive series of experiments across several major cities of USA, and we have noticed significant improvement during inference especially in detecting accident classes. Additionally, to make our model edge-implementable we have compressed our model using a joint technique of magnitude-based weight pruning and model quantization. We have also demonstrated the inference results along with power consumption profiling after deploying the model on a resource constrained environment that consists of Intel Neural Compute Stick 2 (NCS2) with Raspberry Pi 4B (RPi4). Our investigation and observations indicate major improvements to predict unusual traffic accident event even after model compression and deployment. We have managed to reduce the model size and inference time by ≈ 6x, and ≈ 70 % respectively with insignificant drop in performance. Furthermore, to better understand the importance of each individual type of variables used in our analysis, we have showcased a comprehensive ablation study.
2020 IEEE 20th International Conference on Bioinformatics and Bioengineering (BIBE), 2020
Stay at home order during the COVID-19 helps flatten the curve but ironically, instigate mental h... more Stay at home order during the COVID-19 helps flatten the curve but ironically, instigate mental health problems among the people who have Substance Use Disorders. Measuring the electrical activity signals in brain using off-the-shelf consumer wearable devices such as smart wristwatch and mapping them in real time to underlying mood, behavioral and emotional changes play striking roles in postulating mental health anomalies. In this work, we propose to implement a wearable, On-device Mental Anomaly Detection (OMAD) system to detect anomalous behaviors and activities that render to mental health problems and help clinicians to design effective intervention strategies. We propose an intrinsic artifact removal model on Electroencephalogram (EEG) signal to better correlate the fine-grained behavioral changes. We design model compression technique on the artifact removal and activity recognition (main) modules. We implement a magnitude-based weight pruning technique both on convolutional neural network and Multilayer Perceptron to employ the inference phase on Nvidia Jetson Nano; one of the tightest resourceconstrained devices for wearables. We experimented with three different combinations of feature extractions and artifact removal approaches. We evaluate the performance of OMAD in terms of accuracy, F1 score, memory usage and running time for both unpruned and compressed models using EEG data from both control and treatment (alcoholic) groups for different object recognition tasks. Our artifact removal model and main activity detection model achieved about ≈ 93% and 90% accuracy, respectively with significant reduction in model size (70%) and inference time (31%).
The rapid acceleration in the growth of digitized media has made authentication and protection o... more The rapid acceleration in the growth of digitized media has made authentication and protection of digital data through watermarking vitally important. In this paper, we proposed a semi blind watermarking scheme utilizing both Discrete Wavelength Transform (DWT) and Singular Value Decomposition (SVD). To embed the watermark, we transformed the host image into wavelet domain and generated a secondary host image using directive contrast. By remodeling the SVD coefficients of the watermark with the SVD coefficients of secondary image we inserted the watermark into the secondary image. A genuine extraction scheme has also been developed to recover the watermark from the cover image. The scheme has been employed using horizontal sub band. In addition to, evaluations have been added in terms of vertical and diagonal sub bands to compare the performance of the algorithm on the basis of specific sub bands. Experimental evaluations in terms of Normalized Correlation (NC) and Peak Signal to Noise Ratio (PSNR) give proof that our procedure is durable and imperceptible under variety of attacks. Keywords—discrete wavelet transform, human visual system, singular value decomposition, watermarking, directive contrast.
— The rapid acceleration in the growth of digitized media has made authentication and protection ... more — The rapid acceleration in the growth of digitized media has made authentication and protection of digital data through watermarking vitally important. In this paper, we proposed a semi blind watermarking scheme in the joint DWT-SVD domain. To embed the watermark, we transformed the host image into wavelet domain and generated a reference image using directive contrast. By remodeling the SVD coefficients of the watermark with the SVD coefficients of reference image we inserted the watermark into the reference image. A genuine extraction scheme has also been developed to recover the watermark from the cover image. The scheme has been employed using horizontal sub band. In addition to, evaluations have been added in terms of vertical and diagonal sub bands to compare the performance of the algorithm on the basis of specific sub bands. Experimental evaluations in terms NC and PSNR give proof that our procedure is durable and imperceptible under variety of attacks.
Uploads
Papers by Emon Dey
Drafts by Emon Dey