sheeraz Arif - Profile on Academia.edu (original) (raw)

Papers by sheeraz Arif

Data Analysis of Network Parameters for Secure Implementations of SDN-Based Firewall

Computers, materials & continua, Dec 31, 2022

3-Dimensional Convolution Based Iterative Model for Efficient Motion Map Generation for Representing Video Discriminative Information

In this paper, we present a simple method to integrate the discriminative information of video fo... more In this paper, we present a simple method to integrate the discriminative information of video for the action recognition tasks. We introduce the concept of motion map to represent the prefix of video sequences by optimizing the recognition accuracy of original video. 3-dimensional convolution (3Dconv) based model is used to generate the new motion map by integrating current motion map and future video frame. This model is capable of increasing the length of training video in iterative manner and allow us to generate the final motion map. Experimental evaluation results on widely used datasets i.e HMDB51 and UCF101 have revealed effectiveness and flexibility of proposed method over other baseline schemes.

Research Square (Research Square), Feb 23, 2021

The smart agricultural robotic system can decrease the dependence on various traditional agricult... more The smart agricultural robotic system can decrease the dependence on various traditional agriculture crop spraying methods such as pesticides, herbicides, and fertilizer. To meet the world population food requirements, conventional schemes are not sufficient for spraying agrochemicals to control the weeds and increase crop production. Therefore, a smart and intelligent farming system is introduced to increase the production of crops and to reach crop production target. In this paper, Deep Learning (DL) based algorithms is applied for the identification and classification of weed plants using combination of Convolutional Neural Networks (CNN) and Long-Short-Term Memory (LSTM). Convolutional Neural Networks (CNN) has a unique structure to get discriminative features for the input images, and LSTM allows to jointly optimize the classification. To validate the proposed scheme, nine kinds of weeds are classified using the proposed method such as vine weeds, three-leaf weeds, spiky weeds, and invasive creeping weeds. We carried out several extensive experiments and 99.36% of average classification accuracy is achieved. The obtained results show that the combination of CCN-LSTM has significantly higher classification capabilities in comparison to other existing prominent approaches.

Since the birth of Synthetic Aperture Radar (SAR), it has been widely used in the military field ... more Since the birth of Synthetic Aperture Radar (SAR), it has been widely used in the military field and so on. However, the existence of speckle noise makes a good deal inconvenience for the subsequent image processing. The continuous development of sparse representation (SR) opens a new field for the speckle suppressing of SAR image. Although the SR de-noising may be effective, the over-smooth phenomenon still has bad influence on the integrity of the image information. In this paper, one novel SAR image de-noising method based on residual image fusion and sparse representation is proposed. Firstly we can get the similar block groups by the non-local similar block matching method (NLS-BM). Then SR de-noising based on the adaptive K-means singular value decomposition (K-SVD) is adopted to obtain the initial de-noised image and residual image. The residual image is processed by Shearlet transform (ST), and the corresponding de-noising methods are applied on it. Finally, in ST domain the low-frequency and high-frequency components of the initial de-noised and residual image are fused respectively by relevant fusion rules. The final de-noised image can be recovered by inverse ST. Experimental results show the proposed method can not only suppress the speckle effectively, but also save more details and other useful information of the original SAR image, which could provide more authentic and credible records for the follow-up image processing.

Application of a Wavelet based Krylov Subspace Algorithm on Digital Signal Convergence

In the World of Communication, digital transmission has its importance in sense of speed and accu... more In the World of Communication, digital transmission has its importance in sense of speed and accuracy which is the basic requirement of current time. Nowadays, successful as well as rapid communication is the main concern of the research. It can be achieved by using different technique and methods based on theories built upon the branches of applied sciences and engineering. In this research an algorithm is presented by sequentially combining two transforms, Wavelet and Krylov. The Algorithm was formerly developed by the same and was known as WK Algorithm. In this research the Algorithm is first studied for digital signal application and results are presented and concluded by applying also with other two methods in order to verify and validate the research.

Information, Nov 9, 2018

Recently, direction of arrival (DOA) estimation premised on the sparse arrays interpolation appro... more Recently, direction of arrival (DOA) estimation premised on the sparse arrays interpolation approaches, such as co-prime arrays (CPA) and nested array, have attained extensive attention because of the effectiveness and capability of providing higher degrees of freedom (DOFs). The co-prime array interpolation approach can detect O(MN) paths with O(M + N) sensors in the array. However, the presence of missing elements (holes) in the difference coarray has limited the number of DOFs. To implement co-prime coarray on subspace based DOA estimation algorithm namely multiple signal classification (MUSIC), a reshaping operation followed by the spatial smoothing technique have been presented in the literature. In this paper, an active coarray interpolation (ACI) is proposed to efficiently recovering the covariance matrix of the augmented coarray from the original covariance matrix of source signals with no vectorizing and spatial smoothing operation; thus, the computational complexity reduces significantly. Moreover, the numerical simulations of the proposed ACI approach offers better performance compared to its counterparts.

Future Internet, Mar 1, 2018

The overlay integration of low-power femtocells over macrocells in a heterogeneous network (HetNe... more The overlay integration of low-power femtocells over macrocells in a heterogeneous network (HetNet) plays an important role in dealing with the increasing demand of spectral efficiency, coverage and higher data rates, at a nominal cost to network operators. However, the downlink (DL) transmission power of an inadequately deployed femtocell causes inter-cell interference (ICI), which leads to severe degradation and sometimes link failure for nearby macrocell users. In this paper, we propose an adaptive network sensing (ANS) technique for downlink power control to obviate the ICI. The simulation results have shown that the ANS power control technique successfully decreases the cell-edge macro user's interference and enhances the throughput performance of macro users, while also optimizing the coverage and capacity of the femtocell. When compared with the Femto User Equipment (FUE)-assisted and Macro User Equipment (MUE)-assisted power control technique, the proposed technique offers a good tradeoff in reducing interference to macro users, while maintaining the quality of service (QoS) requirement of the femtocell users.

QoE-driven multi-service resource scheduling strategy in mobile network

As quality of experience (QoE) concerns more about users' end-to-end subjective experience th... more As quality of experience (QoE) concerns more about users' end-to-end subjective experience than quality of service (QoS), it becomes an important performance metric when designing a resource scheduling algorithm. In this paper, we propose a QoE-driven multi-service resource scheduling (QMRS) algorithm aiming at maximizing the QoE of the whole system. In QMRS, a specific utility model is adopted as a normalized QoE evaluation metric of end users, which is highly universalizable and extensible and of great importance for the newborn service evaluation. We use a greedy algorithm based on utility models for different services to optimize the wireless resource allocation in multi-users mobile network. Compared with the traditional proportional fair (PF) scheduling method, the end users' utility value increases from 0.82 to 0.92 in less users condition. In condition of 45 users, the utility value can increase to 0.56 with QMRS method from 0.26 with PF method. The results validate that the proposed QMRS can guarantee users' QoE in different services with limited wireless resource.

Wireless Communications and Mobile Computing, Sep 30, 2021

Existing attribute learning methods rely on predefined attributes, which require manual annotatio... more Existing attribute learning methods rely on predefined attributes, which require manual annotations. Due to the limitation of human experience, the predefined attributes are not capable enough of providing enough description. This paper proposes a self-supervised attribute learning (SAL) method, which automatically generates attribute descriptions by differentially occluding the object region to deal with the above problems. The relationship between attributes is formulated with triplet loss functions and is utilized to supervise the CNN. Attribute learning is used as an auxiliary task of a multitask image classification and segmentation network, in which self-supervision of attributes motivates the CNN to learn more discriminative features for the main semantic tasks. Experimental results on public benchmarks CUB-2011 and Pascal VOC show that the proposed SAL-Net can obtain more accurate classification and segmentation results without additional annotations. Moreover, the SAL-Net is embedded into a multiobject recognition and segmentation system, which realizes instance-aware semantic segmentation with the help of a region proposal algorithm and a fusion nonmaximum suppression algorithm.

Maǧallaẗ al-abḥāṯ al-handasiyyaẗ, Sep 2, 2021

Deep convolutional neural network (DCNN) and recurrent neural network (RNN) have been proved as a... more Deep convolutional neural network (DCNN) and recurrent neural network (RNN) have been proved as an imperious research area in multimedia understanding and obtained remarkable action recognition performance. However, videos contain rich motion information with varying dimensions. Existing recurrent based pipelines fail to capture long-term motion dynamics in videos with various motion scales and complex actions performed by multiple actors. Consideration of contextual and salient features is more important than mapping a video frame into a static video representation. This research work provides a novel pipeline by analyzing and processing the video information using a 3D convolution (C3D) network and newly introduced deep bidirectional LSTM. Like popular two-stream convent, we also introduce a two-stream framework with one modification; that is, we replace the optical flow stream by saliency-aware stream to avoid the computational complexity. First, we generate a saliency-aware video stream by applying the saliency-aware method. Secondly, a two-stream 3D-convolutional network (C3D) is utilized with two different types of streams, i.e., RGB stream and saliency-aware video stream, to collect both spatial and semantic temporal features. Next, a deep bidirectional LSTM network is used to learn sequential deep temporal dynamics. Finally, time-series-pooling-layer and softmax-layers classify human activity and behavior. The introduced system can learn long-term temporal dependencies and can predict complex human actions. Experimental results demonstrate the significant improvement in action recognition accuracy on different benchmark datasets.

arXiv (Cornell University), Jun 26, 2022

Breast cancer is one of the leading causes of death among women across the globe. It is difficult... more Breast cancer is one of the leading causes of death among women across the globe. It is difficult to treat if detected at advanced stages, however, early detection can significantly increase chances of survival and improves lives of millions of women. Given the widespread prevalence of breast cancer, it is of utmost importance for the research community to come up with the framework for early detection, classification and diagnosis. Artificial intelligence research community in coordination with medical practitioners are developing such frameworks to automate the task of detection. With the surge in research activities coupled with availability of large datasets and enhanced computational powers, it expected that AI framework results will help even more clinicians in making correct predictions. In this article, a novel framework for classification of breast cancer using mammograms is proposed. The proposed framework combines robust features extracted from novel Convolutional Neural Network (CNN) features with handcrafted features including HOG (Histogram of Oriented Gradients) and LBP (Local Binary Pattern). The obtained results on CBIS-DDSM dataset exceed state of the art.

Computers in Biology and Medicine, Mar 1, 2022

Breast cancer is one of leading cause of death among women. Early diagnosis of breast cancer can ... more Breast cancer is one of leading cause of death among women. Early diagnosis of breast cancer can significantly improve lives of millions of women across the globe. In the last decade, researchers working in the domain of computer vision and Artificial Intelligence (AI) have beefed up their efforts to come up with the automated framework that not only detects but also identifies stage of breast cancer. The reason for this surge in research activities in this direction are mainly due to advent of robust AI algorithms (deep learning), availability of hardware that can train those robust and complex AI algorithms and accessibility of large enough dataset required for training AI algorithms. Different imaging modalities that have been exploited by researchers to automate the task of breast cancer detection are mammograms, ultrasound, magnetic resonance imaging, histopathological images or any combination of them. This article analyzes these imaging modalities and presents their strengths, limitations and enlists resources from where their datasets can be accessed for research purpose. This article then summarizes AI and computer vision based state-of-the-art methods proposed in the last decade, to detect breast cancer using various imaging modalities. Generally, in this article we have focused on to review frameworks that have reported results using mammograms as it is most widely used breast imaging modality that serves as first test that medical practitioners usually prescribe for the detection of breast cancer. Second reason of focusing on mammogram imaging modalities is the availability of its labeled datasets. Datasets availability is one of the most important aspect for the development of AI based frameworks as such algorithms are data hungry and generally quality of dataset affects performance of AI based algorithms. In a nutshell, this research article will act as a primary resource for the research community working in the field of automated breast imaging analysis.

Survey Dataset on Mental Health in Tech Professionals from Open Sourcing Mental Health Surveys (2017-2021)

arXiv (Cornell University), Oct 3, 2021

Breast cancer is one of leading cause of death among women. Early diagnosis of breast cancer can ... more Breast cancer is one of leading cause of death among women. Early diagnosis of breast cancer can significantly improve lives of millions of women across the globe. In the last decade, researchers working in the domain of computer vision and Artificial Intelligence (AI) have beefed up their efforts to come up with the automated framework that not only detects but also identifies stage of breast cancer. The reason for this surge in research activities in this direction are mainly due to advent of robust AI algorithms (deep learning), availability of hardware that can train those robust and complex AI algorithms and accessibility of large enough dataset required for training AI algorithms. Different imaging modalities that have been exploited by researchers to automate the task of breast cancer detection are mammograms, ultrasound, magnetic resonance imaging, histopathological images or any combination of them. This article analyzes these imaging modalities and presents their strengths, limitations and enlists resources from where their datasets can be accessed for research purpose. This article then summarizes AI and computer vision based state-of-the-art methods proposed in the last decade, to detect breast cancer using various imaging modalities. Generally, in this article we have focused on to review frameworks that have reported results using mammograms as it is most widely used breast imaging modality that serves as first test that medical practitioners usually prescribe for the detection of breast cancer. Second reason of focusing on mammogram imaging modalities is the availability of its labeled datasets. Datasets availability is one of the most important aspect for the development of AI based frameworks as such algorithms are data hungry and generally quality of dataset affects performance of AI based algorithms. In a nutshell, this research article will act as a primary resource for the research community working in the field of automated breast imaging analysis.

Breast cancer classification using deep learned features boosted with handcrafted features

Biomedical Signal Processing and Control, Sep 1, 2023

Research in Agricultural Engineering

Weed identification and controlling systems are gaining great attention and are very effective fo... more Weed identification and controlling systems are gaining great attention and are very effective for large productivity in the agriculture sector. Currently, farmers are facing a weed control and management problem, and to tackle this challenge precision agriculture in the form of selective spraying is much-needed practice. In this article, we introduce a novel framework for a weed identification system that leverages (hybrid) the robust and relevant features of deep learning models, such as convolutional neural network (CNN) and handcrafted features. First, we apply the image preprocessing and augmentation techniques for image quality and dataset size enhancement. Then, we apply handcrafted feature extraction techniques, such as local binary pattern (LBP) and histogram of oriented gradients (HOG) to extract texture and shape features from the input. We also apply the deep learning model, such as CNN, to capture the relevant semantic features. Lastly, we concatenate the features extracted from a different domain and explore the performance using different classifiers. We achieved better performance and classification accuracy in the presence of the extreme gradient boosting (XGBoost) classifier. The achieved results witnessed the effectiveness and applicability of the given method and the importance of concatenated features.

Survey Dataset on Mental Health in Tech Professionals from Open Sourcing Mental Health Surveys (2017-2021)

Extreme Gradient Boosting-based Vulnerability Predictions for Wearable IoT Devices: With illustrated approach

2023 International Conference on Communication, Computing and Digital Systems (C-CODE)

Towards Secure Implementations Of SDN Based Firewall

JISR on Computing, Dec 16, 2022

KSII Transactions on Internet and Information Systems, 2019

Since the birth of Synthetic Aperture Radar (SAR), it has been widely used in the military field ... more Since the birth of Synthetic Aperture Radar (SAR), it has been widely used in the military field and so on. However, the existence of speckle noise makes a good deal inconvenience for the subsequent image processing. The continuous development of sparse representation (SR) opens a new field for the speckle suppressing of SAR image. Although the SR de-noising may be effective, the over-smooth phenomenon still has bad influence on the integrity of the image information. In this paper, one novel SAR image de-noising method based on residual image fusion and sparse representation is proposed. Firstly we can get the similar block groups by the non-local similar block matching method (NLS-BM). Then SR de-noising based on the adaptive K-means singular value decomposition (K-SVD) is adopted to obtain the initial de-noised image and residual image. The residual image is processed by Shearlet transform (ST), and the corresponding de-noising methods are applied on it. Finally, in ST domain the low-frequency and high-frequency components of the initial de-noised and residual image are fused respectively by relevant fusion rules. The final de-noised image can be recovered by inverse ST. Experimental results show the proposed method can not only suppress the speckle effectively, but also save more details and other useful information of the original SAR image, which could provide more authentic and credible records for the follow-up image processing.

Data Analysis of Network Parameters for Secure Implementations of SDN-Based Firewall

Computers, materials & continua, Dec 31, 2022

3-Dimensional Convolution Based Iterative Model for Efficient Motion Map Generation for Representing Video Discriminative Information

In this paper, we present a simple method to integrate the discriminative information of video fo... more In this paper, we present a simple method to integrate the discriminative information of video for the action recognition tasks. We introduce the concept of motion map to represent the prefix of video sequences by optimizing the recognition accuracy of original video. 3-dimensional convolution (3Dconv) based model is used to generate the new motion map by integrating current motion map and future video frame. This model is capable of increasing the length of training video in iterative manner and allow us to generate the final motion map. Experimental evaluation results on widely used datasets i.e HMDB51 and UCF101 have revealed effectiveness and flexibility of proposed method over other baseline schemes.

Research Square (Research Square), Feb 23, 2021

The smart agricultural robotic system can decrease the dependence on various traditional agricult... more The smart agricultural robotic system can decrease the dependence on various traditional agriculture crop spraying methods such as pesticides, herbicides, and fertilizer. To meet the world population food requirements, conventional schemes are not sufficient for spraying agrochemicals to control the weeds and increase crop production. Therefore, a smart and intelligent farming system is introduced to increase the production of crops and to reach crop production target. In this paper, Deep Learning (DL) based algorithms is applied for the identification and classification of weed plants using combination of Convolutional Neural Networks (CNN) and Long-Short-Term Memory (LSTM). Convolutional Neural Networks (CNN) has a unique structure to get discriminative features for the input images, and LSTM allows to jointly optimize the classification. To validate the proposed scheme, nine kinds of weeds are classified using the proposed method such as vine weeds, three-leaf weeds, spiky weeds, and invasive creeping weeds. We carried out several extensive experiments and 99.36% of average classification accuracy is achieved. The obtained results show that the combination of CCN-LSTM has significantly higher classification capabilities in comparison to other existing prominent approaches.

Since the birth of Synthetic Aperture Radar (SAR), it has been widely used in the military field ... more Since the birth of Synthetic Aperture Radar (SAR), it has been widely used in the military field and so on. However, the existence of speckle noise makes a good deal inconvenience for the subsequent image processing. The continuous development of sparse representation (SR) opens a new field for the speckle suppressing of SAR image. Although the SR de-noising may be effective, the over-smooth phenomenon still has bad influence on the integrity of the image information. In this paper, one novel SAR image de-noising method based on residual image fusion and sparse representation is proposed. Firstly we can get the similar block groups by the non-local similar block matching method (NLS-BM). Then SR de-noising based on the adaptive K-means singular value decomposition (K-SVD) is adopted to obtain the initial de-noised image and residual image. The residual image is processed by Shearlet transform (ST), and the corresponding de-noising methods are applied on it. Finally, in ST domain the low-frequency and high-frequency components of the initial de-noised and residual image are fused respectively by relevant fusion rules. The final de-noised image can be recovered by inverse ST. Experimental results show the proposed method can not only suppress the speckle effectively, but also save more details and other useful information of the original SAR image, which could provide more authentic and credible records for the follow-up image processing.

Application of a Wavelet based Krylov Subspace Algorithm on Digital Signal Convergence

In the World of Communication, digital transmission has its importance in sense of speed and accu... more In the World of Communication, digital transmission has its importance in sense of speed and accuracy which is the basic requirement of current time. Nowadays, successful as well as rapid communication is the main concern of the research. It can be achieved by using different technique and methods based on theories built upon the branches of applied sciences and engineering. In this research an algorithm is presented by sequentially combining two transforms, Wavelet and Krylov. The Algorithm was formerly developed by the same and was known as WK Algorithm. In this research the Algorithm is first studied for digital signal application and results are presented and concluded by applying also with other two methods in order to verify and validate the research.

Information, Nov 9, 2018

Recently, direction of arrival (DOA) estimation premised on the sparse arrays interpolation appro... more Recently, direction of arrival (DOA) estimation premised on the sparse arrays interpolation approaches, such as co-prime arrays (CPA) and nested array, have attained extensive attention because of the effectiveness and capability of providing higher degrees of freedom (DOFs). The co-prime array interpolation approach can detect O(MN) paths with O(M + N) sensors in the array. However, the presence of missing elements (holes) in the difference coarray has limited the number of DOFs. To implement co-prime coarray on subspace based DOA estimation algorithm namely multiple signal classification (MUSIC), a reshaping operation followed by the spatial smoothing technique have been presented in the literature. In this paper, an active coarray interpolation (ACI) is proposed to efficiently recovering the covariance matrix of the augmented coarray from the original covariance matrix of source signals with no vectorizing and spatial smoothing operation; thus, the computational complexity reduces significantly. Moreover, the numerical simulations of the proposed ACI approach offers better performance compared to its counterparts.

Future Internet, Mar 1, 2018

The overlay integration of low-power femtocells over macrocells in a heterogeneous network (HetNe... more The overlay integration of low-power femtocells over macrocells in a heterogeneous network (HetNet) plays an important role in dealing with the increasing demand of spectral efficiency, coverage and higher data rates, at a nominal cost to network operators. However, the downlink (DL) transmission power of an inadequately deployed femtocell causes inter-cell interference (ICI), which leads to severe degradation and sometimes link failure for nearby macrocell users. In this paper, we propose an adaptive network sensing (ANS) technique for downlink power control to obviate the ICI. The simulation results have shown that the ANS power control technique successfully decreases the cell-edge macro user's interference and enhances the throughput performance of macro users, while also optimizing the coverage and capacity of the femtocell. When compared with the Femto User Equipment (FUE)-assisted and Macro User Equipment (MUE)-assisted power control technique, the proposed technique offers a good tradeoff in reducing interference to macro users, while maintaining the quality of service (QoS) requirement of the femtocell users.

QoE-driven multi-service resource scheduling strategy in mobile network

As quality of experience (QoE) concerns more about users' end-to-end subjective experience th... more As quality of experience (QoE) concerns more about users' end-to-end subjective experience than quality of service (QoS), it becomes an important performance metric when designing a resource scheduling algorithm. In this paper, we propose a QoE-driven multi-service resource scheduling (QMRS) algorithm aiming at maximizing the QoE of the whole system. In QMRS, a specific utility model is adopted as a normalized QoE evaluation metric of end users, which is highly universalizable and extensible and of great importance for the newborn service evaluation. We use a greedy algorithm based on utility models for different services to optimize the wireless resource allocation in multi-users mobile network. Compared with the traditional proportional fair (PF) scheduling method, the end users' utility value increases from 0.82 to 0.92 in less users condition. In condition of 45 users, the utility value can increase to 0.56 with QMRS method from 0.26 with PF method. The results validate that the proposed QMRS can guarantee users' QoE in different services with limited wireless resource.

Wireless Communications and Mobile Computing, Sep 30, 2021

Existing attribute learning methods rely on predefined attributes, which require manual annotatio... more Existing attribute learning methods rely on predefined attributes, which require manual annotations. Due to the limitation of human experience, the predefined attributes are not capable enough of providing enough description. This paper proposes a self-supervised attribute learning (SAL) method, which automatically generates attribute descriptions by differentially occluding the object region to deal with the above problems. The relationship between attributes is formulated with triplet loss functions and is utilized to supervise the CNN. Attribute learning is used as an auxiliary task of a multitask image classification and segmentation network, in which self-supervision of attributes motivates the CNN to learn more discriminative features for the main semantic tasks. Experimental results on public benchmarks CUB-2011 and Pascal VOC show that the proposed SAL-Net can obtain more accurate classification and segmentation results without additional annotations. Moreover, the SAL-Net is embedded into a multiobject recognition and segmentation system, which realizes instance-aware semantic segmentation with the help of a region proposal algorithm and a fusion nonmaximum suppression algorithm.

Maǧallaẗ al-abḥāṯ al-handasiyyaẗ, Sep 2, 2021

Deep convolutional neural network (DCNN) and recurrent neural network (RNN) have been proved as a... more Deep convolutional neural network (DCNN) and recurrent neural network (RNN) have been proved as an imperious research area in multimedia understanding and obtained remarkable action recognition performance. However, videos contain rich motion information with varying dimensions. Existing recurrent based pipelines fail to capture long-term motion dynamics in videos with various motion scales and complex actions performed by multiple actors. Consideration of contextual and salient features is more important than mapping a video frame into a static video representation. This research work provides a novel pipeline by analyzing and processing the video information using a 3D convolution (C3D) network and newly introduced deep bidirectional LSTM. Like popular two-stream convent, we also introduce a two-stream framework with one modification; that is, we replace the optical flow stream by saliency-aware stream to avoid the computational complexity. First, we generate a saliency-aware video stream by applying the saliency-aware method. Secondly, a two-stream 3D-convolutional network (C3D) is utilized with two different types of streams, i.e., RGB stream and saliency-aware video stream, to collect both spatial and semantic temporal features. Next, a deep bidirectional LSTM network is used to learn sequential deep temporal dynamics. Finally, time-series-pooling-layer and softmax-layers classify human activity and behavior. The introduced system can learn long-term temporal dependencies and can predict complex human actions. Experimental results demonstrate the significant improvement in action recognition accuracy on different benchmark datasets.

arXiv (Cornell University), Jun 26, 2022

Breast cancer is one of the leading causes of death among women across the globe. It is difficult... more Breast cancer is one of the leading causes of death among women across the globe. It is difficult to treat if detected at advanced stages, however, early detection can significantly increase chances of survival and improves lives of millions of women. Given the widespread prevalence of breast cancer, it is of utmost importance for the research community to come up with the framework for early detection, classification and diagnosis. Artificial intelligence research community in coordination with medical practitioners are developing such frameworks to automate the task of detection. With the surge in research activities coupled with availability of large datasets and enhanced computational powers, it expected that AI framework results will help even more clinicians in making correct predictions. In this article, a novel framework for classification of breast cancer using mammograms is proposed. The proposed framework combines robust features extracted from novel Convolutional Neural Network (CNN) features with handcrafted features including HOG (Histogram of Oriented Gradients) and LBP (Local Binary Pattern). The obtained results on CBIS-DDSM dataset exceed state of the art.

Computers in Biology and Medicine, Mar 1, 2022

Breast cancer is one of leading cause of death among women. Early diagnosis of breast cancer can ... more Breast cancer is one of leading cause of death among women. Early diagnosis of breast cancer can significantly improve lives of millions of women across the globe. In the last decade, researchers working in the domain of computer vision and Artificial Intelligence (AI) have beefed up their efforts to come up with the automated framework that not only detects but also identifies stage of breast cancer. The reason for this surge in research activities in this direction are mainly due to advent of robust AI algorithms (deep learning), availability of hardware that can train those robust and complex AI algorithms and accessibility of large enough dataset required for training AI algorithms. Different imaging modalities that have been exploited by researchers to automate the task of breast cancer detection are mammograms, ultrasound, magnetic resonance imaging, histopathological images or any combination of them. This article analyzes these imaging modalities and presents their strengths, limitations and enlists resources from where their datasets can be accessed for research purpose. This article then summarizes AI and computer vision based state-of-the-art methods proposed in the last decade, to detect breast cancer using various imaging modalities. Generally, in this article we have focused on to review frameworks that have reported results using mammograms as it is most widely used breast imaging modality that serves as first test that medical practitioners usually prescribe for the detection of breast cancer. Second reason of focusing on mammogram imaging modalities is the availability of its labeled datasets. Datasets availability is one of the most important aspect for the development of AI based frameworks as such algorithms are data hungry and generally quality of dataset affects performance of AI based algorithms. In a nutshell, this research article will act as a primary resource for the research community working in the field of automated breast imaging analysis.

Survey Dataset on Mental Health in Tech Professionals from Open Sourcing Mental Health Surveys (2017-2021)

arXiv (Cornell University), Oct 3, 2021

Breast cancer is one of leading cause of death among women. Early diagnosis of breast cancer can ... more Breast cancer is one of leading cause of death among women. Early diagnosis of breast cancer can significantly improve lives of millions of women across the globe. In the last decade, researchers working in the domain of computer vision and Artificial Intelligence (AI) have beefed up their efforts to come up with the automated framework that not only detects but also identifies stage of breast cancer. The reason for this surge in research activities in this direction are mainly due to advent of robust AI algorithms (deep learning), availability of hardware that can train those robust and complex AI algorithms and accessibility of large enough dataset required for training AI algorithms. Different imaging modalities that have been exploited by researchers to automate the task of breast cancer detection are mammograms, ultrasound, magnetic resonance imaging, histopathological images or any combination of them. This article analyzes these imaging modalities and presents their strengths, limitations and enlists resources from where their datasets can be accessed for research purpose. This article then summarizes AI and computer vision based state-of-the-art methods proposed in the last decade, to detect breast cancer using various imaging modalities. Generally, in this article we have focused on to review frameworks that have reported results using mammograms as it is most widely used breast imaging modality that serves as first test that medical practitioners usually prescribe for the detection of breast cancer. Second reason of focusing on mammogram imaging modalities is the availability of its labeled datasets. Datasets availability is one of the most important aspect for the development of AI based frameworks as such algorithms are data hungry and generally quality of dataset affects performance of AI based algorithms. In a nutshell, this research article will act as a primary resource for the research community working in the field of automated breast imaging analysis.

Breast cancer classification using deep learned features boosted with handcrafted features

Biomedical Signal Processing and Control, Sep 1, 2023

Research in Agricultural Engineering

Weed identification and controlling systems are gaining great attention and are very effective fo... more Weed identification and controlling systems are gaining great attention and are very effective for large productivity in the agriculture sector. Currently, farmers are facing a weed control and management problem, and to tackle this challenge precision agriculture in the form of selective spraying is much-needed practice. In this article, we introduce a novel framework for a weed identification system that leverages (hybrid) the robust and relevant features of deep learning models, such as convolutional neural network (CNN) and handcrafted features. First, we apply the image preprocessing and augmentation techniques for image quality and dataset size enhancement. Then, we apply handcrafted feature extraction techniques, such as local binary pattern (LBP) and histogram of oriented gradients (HOG) to extract texture and shape features from the input. We also apply the deep learning model, such as CNN, to capture the relevant semantic features. Lastly, we concatenate the features extracted from a different domain and explore the performance using different classifiers. We achieved better performance and classification accuracy in the presence of the extreme gradient boosting (XGBoost) classifier. The achieved results witnessed the effectiveness and applicability of the given method and the importance of concatenated features.

Survey Dataset on Mental Health in Tech Professionals from Open Sourcing Mental Health Surveys (2017-2021)

Extreme Gradient Boosting-based Vulnerability Predictions for Wearable IoT Devices: With illustrated approach

2023 International Conference on Communication, Computing and Digital Systems (C-CODE)

Towards Secure Implementations Of SDN Based Firewall

JISR on Computing, Dec 16, 2022

KSII Transactions on Internet and Information Systems, 2019

Since the birth of Synthetic Aperture Radar (SAR), it has been widely used in the military field ... more Since the birth of Synthetic Aperture Radar (SAR), it has been widely used in the military field and so on. However, the existence of speckle noise makes a good deal inconvenience for the subsequent image processing. The continuous development of sparse representation (SR) opens a new field for the speckle suppressing of SAR image. Although the SR de-noising may be effective, the over-smooth phenomenon still has bad influence on the integrity of the image information. In this paper, one novel SAR image de-noising method based on residual image fusion and sparse representation is proposed. Firstly we can get the similar block groups by the non-local similar block matching method (NLS-BM). Then SR de-noising based on the adaptive K-means singular value decomposition (K-SVD) is adopted to obtain the initial de-noised image and residual image. The residual image is processed by Shearlet transform (ST), and the corresponding de-noising methods are applied on it. Finally, in ST domain the low-frequency and high-frequency components of the initial de-noised and residual image are fused respectively by relevant fusion rules. The final de-noised image can be recovered by inverse ST. Experimental results show the proposed method can not only suppress the speckle effectively, but also save more details and other useful information of the original SAR image, which could provide more authentic and credible records for the follow-up image processing.