sonain jamil - Academia.edu (original) (raw)

Papers by sonain jamil

Sensors

The usage of media such as images and videos has been extensively increased in recent years. It h... more The usage of media such as images and videos has been extensively increased in recent years. It has become impractical to store images and videos acquired by camera sensors in their raw form due to their huge storage size. Generally, image data is compressed with a compression algorithm and then stored or transmitted to another platform. Thus, image compression helps to reduce the storage size and transmission cost of the images and videos. However, image compression might cause visual artifacts, depending on the compression level. In this regard, performance evaluation of the compression algorithms is an essential task needed to reconstruct images with visually or near-visually lossless quality in case of lossy compression. The performance of the compression algorithms is assessed by both subjective and objective image quality assessment (IQA) methodologies. In this paper, subjective and objective IQA methods are integrated to evaluate the range of the image quality metrics (IQMs) ...

Sensors

Image processing on smartphones, which are resource-limited devices, is challenging. Panorama gen... more Image processing on smartphones, which are resource-limited devices, is challenging. Panorama generation on modern mobile phones is a requirement of most mobile phone users. This paper presents an automatic sequential image stitching algorithm with high-resolution panorama generation and addresses the issue of stitching failure on smartphone devices. A robust method is used to automatically control the events involved in panorama generation from image capture to image stitching on Android operating systems. The image frames are taken in a firm spatial interval using the orientation sensor included in smartphone devices. The features-based stitching algorithm is used for panorama generation, with a novel modification to address the issue of stitching failure (inability to find local features causes this issue) when performing sequential stitching over mobile devices. We also address the issue of distortion in sequential stitching. Ultimately, in this study, we built an Android applic...

IEEE Access

Most people watch short-form content, especially when viewing it on their smartphones. While shor... more Most people watch short-form content, especially when viewing it on their smartphones. While short-form content is widely used for entertainment, it is also for essential information sharing with broad audiences. The importance of short-form content is self-evident, as Facebook and YouTube have introduced Facebook Reels and YouTube Shorts, respectively. The rapid, widespread adoption of short-form content indicates the need for a new international standard to ensure the interoperability of broad content and content creation tools. This article overviews a new international standard development effort in the Joint Photographic Experts Group (JPEG) in ISO/IEC JTC1/WG1 to create JPEG Snack (ISO/IEC 19566-8) to enable image-rich content creation and sharing. JPEG Snack images, audio, videos, and captions are embedded in the standard JPEG-1 (ISO/IEC 10918-1) image file. The JPEG Snack file comprises two components: i) a default JPEG-1 image and ii) an ISO base media file format (ISOMBFF (ISO/IEC 14496-12)) box-based file extension. The JPEG-1 image portion makes the file compatible with existing JPEG viewers for preview and user navigation, while enhanced JPEG Snack viewers can display the rich image/audio/video/caption short-form content. The article presents essential features of the JPEG Snack and its comparison with JPEG-linked media format (JLINK (ISO/IEC 19566-7)) and JPEG 360 (ISO/IEC 19566-6). It also presents the pros and cons of JPEG Snack over high-efficiency image file format (HEIF (ISO/IEC 23008-12)).

Cornell University - arXiv, Nov 11, 2022

As a special type of transformer, Vision Transformers (ViTs) are used to various computer vision ... more As a special type of transformer, Vision Transformers (ViTs) are used to various computer vision applications (CV), such as image recognition. There are several potential problems with convolutional neural networks (CNNs) that can be solved with ViTs. For image coding tasks like compression, super-resolution, segmentation, and denoising, different variants of the ViTs are used. The purpose of this survey is to present the first application of ViTs in CV. The survey is the first of its kind on ViTs for CVs to the best of our knowledge. In the first step, we classify different CV applications where ViTs are applicable. CV applications include image classification, object detection, image segmentation, image compression, image super-resolution, image denoising, and anomaly detection. Our next step is to review the state-of-the-art in each category and list the available models. Following that, we present a detailed analysis and comparison of each model and list its pros and cons. After that, we present our insights and lessons learned for each category. Moreover, we discuss several open research challenges and future research directions.

IEEE Access

Applied System Innovation

As a result of the advancement in the fourth industrial revolution and communication technology, ... more As a result of the advancement in the fourth industrial revolution and communication technology, the use of digital twins (DT) and federated learning (FL) in the industrial Internet of Things (IIoT), the Internet of Vehicles (IoV), and the Internet of Drones (IoD) is increasing. However, the deployment of DT and FL for IoV is challenging. In this survey, we focus on DT and FL for IIoT, IoV, and IoD. Initially, we analyzed the existing surveys. In this paper, we present the applications of DT and FL in IIoT, IoV, and IoD. We also present the open research issues and future directions.

AI, 2022

Drones are commonly used in numerous applications, such as surveillance, navigation, spraying pes... more Drones are commonly used in numerous applications, such as surveillance, navigation, spraying pesticides in autonomous agricultural systems, various military services, etc., due to their variable sizes and workloads. However, malicious drones that carry harmful objects are often adversely used to intrude restricted areas and attack critical public places. Thus, the timely detection of malicious drones can prevent potential harm. This article proposes a vision transformer (ViT) based framework to distinguish between drones and malicious drones. In the proposed ViT based model, drone images are split into fixed-size patches; then, linearly embeddings and position embeddings are applied, and the resulting sequence of vectors is finally fed to a standard ViT encoder. During classification, an additional learnable classification token associated to the sequence is used. The proposed framework is compared with several handcrafted and deep convolutional neural networks (D-CNN), which revea...

ArXiv, 2022

In the realm of image processing and computer vision (CV), machine learning (ML) architectures ar... more In the realm of image processing and computer vision (CV), machine learning (ML) architectures are widely applied. Convolutional neural networks (CNNs) solve a wide range of image processing issues and can solve image compression problem. Compression of images is necessary due to bandwidth and memory constraints. Helpful, redundant, and irrelevant information are three different forms of information found in images. This paper aims to survey recent techniques utilizing mostly lossy image compression using ML architectures including different auto-encoders (AEs) such as convolutional auto-encoders (CAEs), variational auto-encoders (VAEs), and AEs with hyper-prior models, recurrent neural networks (RNNs), CNNs, generative adversarial networks (GANs), principal component analysis (PCA) and fuzzy means clustering. We divide all of the algorithms into several groups based on architecture. We cover still image compression in this survey. Various discoveries for the researchers are emphasi...

Telecom

Mobile communication networks evolved from first-generation (1G) to sixth-generation (6G) and the... more Mobile communication networks evolved from first-generation (1G) to sixth-generation (6G) and the requirement for quality of services (QoS) and higher bandwidth increased. The evolvement of 6G can be deployed in industry 5.0 to fulfill the future industry requirement. However, deploying 6G in industry 6.0 is very challenging, and installing a reconfigurable intelligent surface (RIS) is an efficient solution. RIS contains the passive elements which are programmed for the tuning of a wireless channel. We formulate an optimization problem to allocate resources in the RIS-supported network. This article presents a mixed-integer non-linear programable problem (MINLP) considering the industry 5.0 scenario and proposes a novel algorithm to solve the optimization problem. We obtain the ϵ optimal solution using the proposed algorithm. The proposed algorithm is evaluated in energy efficiency (EE), throughput, latency, and channel allocation. We compare the performance of several algorithms, a...

Electronics

The deployment of millimeter waves can fulfil the stringent requirements of high bandwidth and hi... more The deployment of millimeter waves can fulfil the stringent requirements of high bandwidth and high energy efficiency in fifth generation (5G) networks. Still, millimeter waves communication is challenging because it requires line of sight (LOS). The heterogeneous network (HetNet) of millimeter waves and microwaves solves this problem. This paper proposes a millimeter -microwaves heterogeneous HetNet deployed in an indoor factory (InF). In InF, the manufacturing and production are performed inside big and small halls. We consider non standalone dual-mode base stations (DMBS) working on millimeter waves and microwaves. We analyze the network in terms of throughput and energy efficiency (EE). We formulate mixed-integer-non-linear-programming (MINLP) to maximize the throughput and EE of the network. The formulated problem is a complex optimization problem and hard to solve with exhaustive search. We propose a novel outer approximation algorithm (OAA) to solve this problem, and the prop...

Journal of Imaging

Cardiovascular diseases (CVDs) are the primary cause of death. Every year, many people die due to... more Cardiovascular diseases (CVDs) are the primary cause of death. Every year, many people die due to heart attacks. The electrocardiogram (ECG) signal plays a vital role in diagnosing CVDs. ECG signals provide us with information about the heartbeat. ECGs can detect cardiac arrhythmia. In this article, a novel deep-learning-based approach is proposed to classify ECG signals as normal and into sixteen arrhythmia classes. The ECG signal is preprocessed and converted into a 2D signal using continuous wavelet transform (CWT). The time–frequency domain representation of the CWT is given to the deep convolutional neural network (D-CNN) with an attention block to extract the spatial features vector (SFV). The attention block is proposed to capture global features. For dimensionality reduction in SFV, a novel clump of features (CoF) framework is proposed. The k-fold cross-validation is applied to obtain the reduced feature vector (RFV), and the RFV is given to the classifier to classify the ar...

2021 15th International Conference on Open Source Systems and Technologies (ICOSST)

2021 International Conference on Computing, Electronic and Electrical Engineering (ICE Cube)

2020 International Conference on Information Science and Communication Technology (ICISCT), 2020

Wildlife plays a vital role in balancing the environment. It also provides stability to different... more Wildlife plays a vital role in balancing the environment. It also provides stability to different natural processes of nature. In recent year, there are many animals which are facing the danger of extinction. The reason for animal extinction is natural occurrences such as climatic heating, cooling, or changes in sea levels. In literate, many techniques are proposed to detect and classify animals, but each technique has a limitation. In this paper, we propose a novel framework using deep convolutional neural networks (D-CNN) and k Nearest Neighbors (kNN) to detect animals. The dataset contains four class snow leopard, Marco polo sheep, Himalayan bear, and other animals. Many D-CNN like AlexNet, ResNet-50, VGG-19, and inception v3 are used to extract features. The experimental results verify that inception v3 integrated with kNN outperforms other D-CNNs. It also has more accuracy of 98.3% with a classification error of 2%, which is quite negligible.

2020 IEEE 23rd International Multitopic Conference (INMIC), 2020

Millimetre waves (mmwave) with enormous bandwidth and spectrum availability can fulfil the string... more Millimetre waves (mmwave) with enormous bandwidth and spectrum availability can fulfil the stringent requirement of future 5G networks. But there are many challenges to deploy mmWave. One of the biggest challenges is the line-of-sight (LOS). Heterogeneous networks (HetNets) supported by mmwave and microwave can resolve the problem of LOS. In this paper, we consider a HetNet supported with mmwaves and microwaves to achieve the challenging goals of 5G in a smart indoor factory. We formulate an optimization problem in terms of resource allocation and mode selection for HetNets, where the objective is to maximize the network energy efficiency and throughput. The formulated problem is the non-linear fractional programming problem. We propose the outer approximation algorithm (OAA) to solve the optimization problem. OAA is examined by extensive simulation work. The performance of beta\betabeta-optimal solution obtained by the OAA method is shown for different network parameters, such as the num...

2021 International Conference on Digital Futures and Transformative Technologies (ICoDT2), 2021

Pneumonia is an infectious and deadly disease. According to the World Health Organization (WHO), ... more Pneumonia is an infectious and deadly disease. According to the World Health Organization (WHO), every third person dies due to this disease. It can be cured if detected accurately and on time. Chest X-rays are used to diagnose this disease, but it requires expert radiotherapists and a very time-consuming process. So, it is the need of the hour to develop an automatic system to detect pneumonia that could perform better and produce faster results. However, traditional handcrafted machine learning techniques show low accuracy and are expensive in terms of complexity. Deep convolutional neural networks (D-CNNs) show better performance in this regard and are simple and easy to use as compared to machine learning algorithms. In this paper, a novel algorithm based on AlexNet and SVM is proposed to detect pneumonia. We also compared the results of AlexNet with other D-CNNs to check which one is performing better. Experimental results prove that AlexNet integrated with SVM outperforms all ...

Applied Sciences

Novel coronavirus, known as COVID-19, is a very dangerous virus. Initially detected in China, it ... more Novel coronavirus, known as COVID-19, is a very dangerous virus. Initially detected in China, it has since spread all over the world causing many deaths. There are several variants of COVID-19, which have been categorized into two major groups. These groups are variants of concern and variants of interest. Variants of concern are more dangerous, and there is a need to develop a system that can detect and classify COVID-19 and its variants without touching an infected person. In this paper, we propose a dual-stage-based deep learning framework to detect and classify COVID-19 and its variants. CT scans and chest X-ray images are used. Initially, the detection is done through a convolutional neural network, and then spatial features are extracted with deep convolutional models, while handcrafted features are extracted from several handcrafted descriptors. Both spatial and handcrafted features are combined to make a feature vector. This feature vector is called the vocabulary of feature...

In recent years, breast cancer is causing the death of many women. The major reasons for breast c... more In recent years, breast cancer is causing the death of many women. The major reasons for breast cancer are an increase in age, dense breast tissue, alcoholism, body weight, and radiation exposure. If it is detected at an early stage, then the chances of survival increase. Machine Learning and deep learning can help us to detect breast cancer at initial stage. In this paper, we propose a novel deep neural network CanNet to detect cancer with high accuracy. CanNet has accuracy of 99% with 98.8% specmcity and 99.1% sensitivity. We also compared our experimental results with other state-of-the-art methods. The comparison shows that CanNet is more efficient than all other methods.

Sensors

IEEE Access

Cornell University - arXiv, Nov 11, 2022

IEEE Access

Applied System Innovation

AI, 2022

ArXiv, 2022

Telecom

Electronics

Journal of Imaging

2021 15th International Conference on Open Source Systems and Technologies (ICOSST)

2021 International Conference on Computing, Electronic and Electrical Engineering (ICE Cube)

2020 International Conference on Information Science and Communication Technology (ICISCT), 2020

2020 IEEE 23rd International Multitopic Conference (INMIC), 2020

2021 International Conference on Digital Futures and Transformative Technologies (ICoDT2), 2021

Applied Sciences