Search

White blood cells, WBCs for short, are an essential component of the human immune system. These cells are our body's first line of defense against infections and diseases caused by bacteria, viruses, and fungi, as well as abnormal and external substances that may enter the bloodstream. A wrong WBC count can signify dangerous viral infections, autoimmune disorders, cancer, sarcoidosis, aplastic anemia, leukemia, tuberculosis, etc. A lot of these diseases and disorders can be extremely painful and often result in death. Leukemia is among the more common types of blood cancer and when left undetected leads to death. An early diagnosis is necessary which is possible by looking at the shapes and determining the numbers of young and immature WBCs to see if they are normal or not. Performing this task manually is a cumbersome, expensive, and time-consuming process for hematologists, and therefore computer-aided systems have been developed to help with this problem. This paper proposes an improved method of classification of WBCs utilizing a combination of preprocessing, convolutional neural networks (CNNs), feature selection algorithms, and classifiers. In preprocessing, contrast-limited adaptive histogram equalization (CLAHE) is applied to the input images. A CNN is designed and trained to be used for feature extraction along with ResNet50 and EfficientNetB0 networks. Ant colony optimization is used to select the best features which are then serially fused and passed onto classifiers such as support vector machine (SVM) and quadratic discriminant analysis (QDA) for classification. The classification accuracy achieved on the Blood Cell Images dataset is 98.44%, which shows the robustness of the proposed work.

Automatic modulation classification (AMC) is a process of automatic detection of modulation format imposed on the received signal with no prior information (carrier, signal power, phase offset) of the signal, also known as blind classification. In this paper, we proposed a new AMC algorithm, by combining the synergy of the meta-heuristic technique with Gabor feature extraction mainly used in texture analysis. Gabor filters are used to extract the features that are further optimized using the cuckoo search algorithm to increase the efficiency of the classification procedure. The classification approach is applied on digitally modulated signals having phase-shift keying, frequency-shift keying, and quadrature amplitude modulation schemes of order 2-64 over the nonfading channel (AWGN) and fading channel (Rayleigh). Simulations and performance comparison with the existing literature validate that the proposed solution has better classification accuracy with lower sample size and lower signal-to-noise ratio.

The recent advancement in remote sensing technologies has resulted in the availability of different imaging modes and higher resolution satellite images. Accessibility of these remote sensing or satellite images, automatic ship detection and tracking has become an important research topic in the field of maritime surveillance. In this paper, a novel method for ship detection using satellite images is proposed. First the preprocessing is carried out to remove the noise from the images using Ship Detection and Tracking (SDT) filter. Then, the land masking (sea-land area separation) and cloud masking is carried out based on the gradient feature extraction using SDT edge detection, along with SDT segmentation. Finally, the ships are identified using the Machine Learning (ML) classifiers like Support Vector Machine (SVM), Random Forest Classifier (RFC), Linear Discriminant Analysis (LDA), Logistic Regression (LR), KNN, and Gaussian Naïve Bayes-based classifier based on the features extracted from Histogram of Oriented Gradients (HOG). The proposed work is cross validated using the Google earth data. Performance of our proposed method is evaluated using the recall and the precision values. Further, for tracking ships, an improved multiple hypothesis tracking (MHT) algorithm is proposed and tested using the Kaggle dataset.

Internet users and internet services are increasing day by day, which increases the internet traffic from zeta-bytes to petabytes with ultra-high-speed. Different types of architecture are implemented to handle high-speed data traffic. The two layers approach of the Software-Defined Network (SDN) architecture converts classical network architecture to consistent, centralized controllable network architecture with programming ability. On the other hand, network security is still the main concern for the network administrator and detection of malicious internet packets in ultra-high-speed traffic of the programmable network. Therefore, in this paper, we proposed a Statistical Analysis Based Intrusion Detection System (SABIDS) by using Machine Learning (ML) approach. The key idea is to implement the SABIDS inside the (RYU) controller that will statistically analyse the high-speed internet traffic flows and block the identified packet generator IP automatically. The SABIDS scheme consists of 3 modules, (1) fetch the runtime flow statistics, (2) Identify the nature of the flow by statistical and pattern match techniques, (3) Block the malicious flow’s source IP. Different types of ML classifiers are used to evaluate the performance of the scheme. This scheme enables the SDN controller to detect malicious traffic and avoid potential losses like system failure or risk of being an attack.

Dynamic opportunistic channel access with software-defined radio at a network layer in distributed cognitive IoT introduces a concurrent channel selection along with end-to-end route selection for application data transmission. State-of-the-art cognitive IoT big data-based routing protocols are not explored in terms of how the spectrum management is being coordinated with the network layer for concurrent channel route selection during end-to-end channel route discovery for data transmission of IoT and big data applications. In this paper, a reactive big data-based “cognitive dynamic source routing protocol” is proposed for cognitive-based IoT networks to concurrently select the channel route at the network layer from source to destination. Experimental results show that the proposed protocol cognitive DSR with concurrent channel route selection criteria is outperformed. This will happen when it is compared with the existing distributed cognitive DSR with independent channel route application data transmission.

In medical imaging, automated detection of stomach and gastrointestinal diseases using WCE (wireless capsule endoscopy) images is an emerging research domain. It includes numerous limitations and challenges such as variation in the contrast, texture variation, color and complexity in the background etc. To overcome these challenges, several computer-aided methods are proposed by the researchers. But there exist different limitations in these methods. In this work, a new method is proposed for computer-aided diagnosis of stomach disease classification. This hybrid approach is based on the amassed texture and deep CNN features. Initially, the contrast of image is improved by using power-law transformation. Texture features are extracted from the enhanced dataset by using LBP and SFTA features. Extracted texture features are then fused to obtain strong feature vectors. At the same time, two pre-trained deep learning models are utilized for CNN feature extraction namely VGG16 and InceptionV3. Extracted deep features are fused serially along with the obtained handcrafted feature vector to obtain an ensemble deep feature vector. A unique feature vector is obtained by serial fusion of both fused vectors to get an advantage of accumulated texture and CNN features. This feature vector is supplied to various classifiers and evaluated with existing methods. The promising recognition proficiency portrays the strength of proposed approach.

This letter presents a compact triple-band antenna composed of a spiral radiator with an open-ended slot at the ground for human head-implantable wireless communications. It operates simultaneously at a Medical Implant Communications Service (MICS) band (402–405 MHz), a Wireless Medical Telemetry Service (WMTS) band (1427–1432 MHz), and an Industrial, Scientific, and Medical (ISM) band (2400–2480 MHz). The proposed antenna has a thin profile of 0.5 mm with a volume of 197 mm3. Semisolid phantoms are used for the design and experimental validation, and detailed parameter studies are carried out to determine the working principles of the antenna. Based on simulations and measurements, it was found that the proposed antenna covers all the desired frequency bands with comparably high boresight gains given its compact dimensions.

The public sector, private firms, business community, and civil society are generating data that are high in volume, veracity, and velocity and come from a diversity of sources. This type of data is today known as big data. Public administrations pursue big data as “new oil” and implement data-centric policies to collect, generate, process, share, exploit, and protect data for promoting good governance, transparency, innovative digital services, and citizens’ engagement in public policy. All of the above constitute the Government Big Data Ecosystem (GBDE). Despite the great interest in this ecosystem, there is a lack of clear definitions, the various important types of government data remain vague, the different actors and their roles are not well defined, while the impact in key public administration sectors is not yet deeply understood and assessed. Such research and literature gaps impose a crucial obstacle for a better understanding of the prospects and nascent issues in exploiting GBDE. With this study, we aim to start filling the above-mentioned gaps by organizing our findings from an extended Systematic Literature Review into a framework to organise and address the above-mentioned challenges. Our goal is to contribute in this fast-evolving area by bringing some clarity and establishing common understanding around key elements of the emerging GBDE.

This research aimed to investigate the relationship between Facebook use and depression, also to test the role of social comparison as a moderator. The research employed Social Comparison theory. For quantitative research, social survey analysis was used to access the relationship between time spent on Facebook and level of depression. The population selected for the current study was based on the university students. A sampling frame was obtained of all the enrolled students of Foundation University Islamabad. Sample of 384 students was drawn through systematic random sampling. Data was analyzed using hierarchical multiple regression in SPSS 21. All the results were found significant. Findings of the study suggested that there is a significant relationship between time spent on Facebook and level of depression. Moreover, the results also indicated that the social comparison effectively moderate the relationship between time spent on Facebook and level of depression among university students.

Quasi-isotropic antennas are promising candidates due to their applications in modern communication systems, where full spatial coverage and/or uniform signal reception is required. In this work, an in-depth review of quasi-isotropic antennas is presented, with the aim of understanding the working principles of such antennas and presenting the recent advancements, challenges, and solutions offered by various researchers. First, different design techniques adopted to achieve quasi-isotropic patterns, such as the use of complementary dipoles, multiple monopoles or dipoles, and an array of discrete elements are discussed. Then, different types of quasi-isotropic antennas—for example, planar, electrically small, 3-D printed, dual-band/wideband, circularly polarized, metamaterial-inspired, and dielectric resonator-based quasi-isotropic antennas—are revisited. Their applications in various technologies, such as RFID, energy harvesting, wireless sensor networks, and the IoT, are briefly explained. Lastly, different key performance parameters, such as complexity of configuration, design approach, physical profile, far field and radiation characteristics, reflection coefficients, operating frequency and bandwidth, gain deviation, and fabrication process, are discussed and tabulated. This review not only provides a guideline but will also help antenna engineers in designing a quasi-isotropic antenna with desirable performance.

One of the attractive and practical techniques to transform the domain integrals to equivalent boundary integrals is the dual reciprocity method (DRM). The success of DRM relies on the proper treatment of the non-homogeneous term in the governing differential equation. For this purpose, radial basis functions (RBFs) interpolations are performed to approximate the non-homogeneous term accurately. Moreover, when the interpolation points are large, the global RBFs produced dense and ill-conditioned interpolation matrix, which poses severe stability and computational issues. Fortunately, there exist interpolation functions with local support known as compactly supported radial basis functions (CSRBFs). These functions produce a sparse and well-conditioned interpolation matrix, especially for large-scale problems. Therefore, this paper aims to apply DRM based on multiquadrics (MQ) RBFs and CSRBFs for evaluation of the Poisson equation, especially for large-scale problems. Furthermore, the convergence analysis of DRM with MQ and CSRBFs is performed, along with error estimate and stability analysis. Several experiments are performed to ensure the well-conditioned, efficient, and accurate behavior of the CSRBFs compared to the MQ-RBFs, especially for large-scale interpolation points.

The art of paper folding also known as Origami plays an important role in various research areas of different scientific fields. Origami structures possess many useful characteristics such as reconfigurability, flexibility, deployability, compactness, and multi-functionality. These attributes are inevitable for modern communication systems. Additionally, they provide antenna engineers an extra degree of freedom while blueprinting next-generation designs. One of the desirable features of origami is its folding capability. Using this property, it can be transformed into a two-Dimensional (2D) sheet from a three-Dimensional (3D) structure and vice versa through external stimulus. In recent years, researchers have proposed numerous smart materials to optimize folding behavior. These smart materials extend the functionality of origami technology for designing self-folding structures required in space systems, small scale devices, and self-assembly systems. Origami structures feature many useful characteristics pertinent to modern day design challenges of communication systems such as reconfiguration, flexibility, compactness, and multifunctionality. In this work, a state of the art review is presented on conceptualization, design challenges, and fabrication of light-weight and low-cost deployable origami antennas. Furthermore, to provide critical insights deployment challenges and possible solutions are also provided. It is believed that this work will not only help peers to understand the basic working principles of different origami structures but will also lay the foundation for future research in the evolving field of origami-based antennas. Moreover, the design methodology proposed in this paper will also provide pragmatic solutions for origami antennas suitable for the harsh and rigid environments.

In this letter, we demonstrate a novel strategy for designing a low complexity deep neural network (DNN) receiver. The compact-stacked Autoencoder (CSAE) receiver is designed based on the proposed neuron and layer numbers selection (NLNS) methodology. Compared with other DNN-based receiver, the CSAE receiver has low complexity but can achieve superior performance. Simulation results show that CSAE receiver can achieve or even outperform state of the art accuracy, and furthermore, the proposed receiver provides a robust performance against the phase offset, carrier frequency offset (CFO), and imperfect channel state information (ICSI).

Wireless Sensor Network (WSN) is composed of numerous tiny smart sensors nodes integrated with Internet of Things (IoT) play a crucial role in many applications. The IoT connects physical devices to form a network which consist of software, sensor for exchange of information. Clustering is most common technique for efficient energy utilization in WNS. Sensor nodes when they have data, forwards it to Cluster Head (CH) and CH transfers the received data from the sensor nodes to the sink. When the sink nodes are far away from CH, long-haul transmission consumes higher power. In this paper we propose efficient data transfer mechanism for clustered IoT network through the cooperation of member nodes. First, we use greedy algorithm to select cooperative sensor nodes to act as relay for long distance transmission. Then, to encourage sensor nodes in data forwarding, cluster head uses priority buffers to prioritize assisting sensor nodes data. Simulation results show that, the proposed approach conserves energy and increases the life-time of clustered IoT network.

Hazy image observation is a serious phenomenon occurred by random scattering of atmospheric elements. This reduces the scene prominence in terms of color contrast and makes the vision system poor. To overcome this issue, dehazing of digital images is dealt with much attention in the field of computer vision. Dense scattering in hazy image results in loss of original spectral information of the object. It is required to remove the unwanted artifacts of weather during image acquisition process of the given object to improve the visual insight of an acquired image. It is found that most of the existing methods fail to retrieve the sufficient information from hazy images. To address such problem, a robust single image dehazing method is introduced to recover the haze-free image. This is performed by calculating the atmospheric light of the given hazy images by decomposing and retaining the high frequency sub bands using wavelet domain. The dense haze elimination is performed on approximated low frequency sub band of the given hazy image. On reconstruction process, well-refined dehaze image is obtained. Moreover, transmission maps are also produced as a byproduct of this method.

Lung cancer is a fatal type of cancer and it causes of severe deaths of approximately 422 people every day, worldwide. However, an early diagnosis is an expedient requirement for increasing the chances of human survival. In this regard the existing techniques of tumor detection, CT scans are mostly utilized to recognize the infected regions, nevertheless, the major challenges of CT images are low visibility of tumor regions, negative rates, to name but a few. In this work, we propose a novel design of contrast stretching based classical features fusion process for localizing the of lungs cancer classification. The proposed method encompasses three significant steps: firstly, contrast of original CT images is improved by gamma correction max intensity weights approach. Secondly, multiple texture, point, and geometric features are extracted from contrast images, which are later subjected to a serial canonical correlation-based fusion. Thirdly, zero values and negative features are replaced by an entropy-based approach, followed by weighted NCA for selection. Most discriminate features are fed into ensemble classifier for final classification. The validation of the proposed method is conducted on publicly available dataset: Lungs Data Science Bowl 2017 to achieving maximum accuracy of 99.4%. The numerical results clearly show that the performance of our proposed method outperforms in comparison with several existing methods with greater accuracy.

In the context of Automatic Modulation Classification (AMC), some recent works have utilized multiple features to train the neural network. With an ultimate aim to develop a systematic approach to select the most diverse and unique features, we propose and demonstrate a novel method to select the most diverse $m\atopwithdelims ()2$ features from a larger feature set. Bhattacharyya distance metric for the dissimilarity between two probability distributions is utilized to select the features with the highest distance for all modulation pairs within a test pool. The proposed approach is analyzed for three different neural networks based classifiers, amidst AWGN and frequency-selective fading channels. A substantial reduction in computational complexity is achieved with an acceptable compromise on the classification performance.

The increasing demand of routing in the field of communication is the most important subject in ad hoc networks now a days. Flying Ad Hoc Network (FANET) is one of the emerging areas that evolved from Mobile Ad Hoc Networks. Selecting the best optimal path in any network is a real challenge for a routing protocol. Because the network performance like throughput, Quality of Service (QoS), user experience, response time and other key parameters depend upon the efficiency of the algorithm running inside the routing protocol. The complexity and diversity of the problem is augmented due to dynamic spatial and temporal mobility of FANET nodes. Due to these challenges the performance and efficiency of the routing protocol becomes very critical. This paper presents a novel routing protocol for FANET using modified AntHocNet. Ant colony optimization technique or metaheuristics in general has shown better dependability and performance as compared to other legacy best path selection techniques. Energy stabilizing parameter introduced in this study improves energy efficiency and overall network performance. Simulation results show that the proposed protocol is better than generic Ant Colony Optimization (ACO) and other traditional routing protocols utilized in FANET.

A low-complexity likelihood methodology is proposed for automatic modulation classification of orthogonal space-time block code (STBC) based multiple-input multiple-output (MIMO) systems. We exploit the zero-forcing equalization technique to modify the typical average likelihood ratio test (ALRT) function. The proposed ALRT function has a low computational complexity compared to existing ALRT functions for MIMO systems classification. The proposed approach is analyzed for blind channel scenarios when the receiver has imperfect channel state information (CSI). Performance analysis is carried out for scenarios with different numbers of antennas. Alamouti-STBC systems with 2 × 2 and 2 × 1 and space-time transmit diversity with a 4 × 4 transmit and receive antenna configuration are considered to verify the proposed approach. Some popular modulation schemes are used as the modulation test pool. Monte-Carlo simulations are performed to evaluate the proposed methodology, using the probability of correct classification as the criterion. Simulation results show that the proposed approach has high classification accuracy at low signal-to-noise ratios and exhibits robust behavior against high CSI estimation error variance.

BackgroundBreast cancer is one of the most prevalent cause of morbidity and mortality in women all over the world. Histopathological diagnosis is a vital component in the management of breast cancer. The application of artificial intelligence is yielding promising results for the better patient care.AimThe main aim of the present research project is to explore the potential of spatial supervised technique to develop scale invariant system for the histological diagnosis of breast cancer.Materials and MethodsThe anonymized images of hematoxylin and eosin stained section of the dataset, which has been acquired from the website. The slides were taken at different zoom (magnification) levels. Spatial supervised learning has been employed to make a scale invariant system. We used 400x and 40x to generate the results. For the 400x, we trained our network on a dataset of 200x,100x, and 40x images. The datasets were split into training and validation sets. The training set contained 80% digital slides of the respected dataset, and the validation set contained 20% digital slides of the respected dataset. The final result was generated by splitting the dataset of 400x into the training and test dataset. The training set contained 50% digital slides, and the test set also contained 50% digital slides. This unusual split is done to show how good spatial supervised learning works. Similarly, for 40x, we trained our networks on a dataset of 400x,200x, and 100x. The same steps were followed to obtain the 40x results.ResultsThe result analysis revealed that the ResNet 18 with spatial supervised learning on dataset of 40x yielded the F-1 score of 1.0, while ResNet 18 with supervised learning only, on dataset of 40x yielded F-1 score of 0.9823. ResNet 18 with spatial supervised learning on dataset of 400x revealed F-1 score of 0.9957, and ResNet 18 with supervised learning only, on dataset of 400x showed the F-1 score of 0.9591. For supervised learning dataset is spited into training (80%) and testing (20% of dataset).ConclusionThe analysis of digitized pathology images with the application of convolutional neural network Resnet -18 architecture with spatial supervised learning revealed excellent results, which is demonstrated by a very high F-1 score of 1.0.The development of scale invariant system with application of spatial supervised technique solved the problem of images with variable magnifications. The finding would further pave the pathway for application of deep learning for the histological diagnosis of pathological lesions.

An advancement in Hyperspectral Imaging (HI) technology is creating important attraction among the researchers to develop better classification techniques. This technology is well known for its high spatial and spectral information due to which the discrimination of materials is much more accurate and efficient. The useful information is extracted in Hyperspectral Imaging technology after applying it in agriculture, biomedical, and disaster management studies. A review comparison has been carried out for air borne images using hyperspectral acquisition hardware for classification as well as segmentation purpose. Numerous approaches that have been focused for implementation namely semi-supervised technique used for hyperspectral imaging using active learning and multinomial logistic regression, Generalized Composite Kernels (GCKs) classification framework, classification of spectral-spatial based data on loopy belief propagation (LBP), multiple feature learning of HI classification, and semi-supervised GCKs with classification accuracy on AVIRIS dataset (59.97%, 92.89%, 81.45%, 75.84%, and 95.50) and segmentation accuracies using α-expansion method as (73.27%, 93.57%, 92.86%, 91.73% and 98.31), respectively.

License plate localization is the process of finding the license plate area and drawing a bounding box around it, while recognition is the process of identifying the text within the bounding box. The current state-of-the-art license plate localization and recognition approaches require license plates of standard size, style, fonts, and colors. Unfortunately, in Pakistan, license plates are non-standard and vary in terms of the characteristics mentioned above. This paper presents a deep-learning-based approach to localize and recognize Pakistani license plates with non-uniform and non-standardized sizes, fonts, and styles. We developed a new Pakistani license plate dataset (PLPD) to train and evaluate the proposed model. We conducted extensive experiments to compare the accuracy of the proposed approach with existing techniques. The results show that the proposed method outperformed the other methods to localize and recognize non-standard license plates.

In decision-making problems reward function plays an important role in finding the best policy. Reinforcement Learning (RL) provides a solution for decision-making problems under uncertainty in an Intelligent Environment (IE). However, it is difficult to specify the reward function for RL agents in large and complex problems. To counter these problems an extension of RL problem named Inverse Reinforcement Learning (IRL) is introduced, where reward function is learned from expert demonstrations. IRL is appealing for its potential use to build autonomous agents, capable of modeling others, deprived of compromising in performance of the task. This approach of learning by demonstrations relies on the framework of Markov Decision Process (MDP). This article elaborates original IRL algorithms along with their close variants to mitigate challenges. The purpose of this paper is to highlight an overview and theoretical background of IRL in the field of Machine Learning (ML) and Artificial Intelligence (AI). We presented a brief comparison between different variants of IRL in this article.

The public sector, private firms, business community, and civil society are generating data that is high in volume, veracity, velocity and comes from a diversity of sources. This kind of data is known as big data. Public Administrations (PAs) pursue big data as “new oil” and implement data-centric policies to transform data into knowledge, to promote good governance, transparency, innovative digital services, and citizens’ engagement in public policy. From the above, the Government Big Data Ecosystem (GBDE) emerges. Managing big data throughout its lifecycle becomes a challenging task for governmental organizations. Despite the vast interest in this ecosystem, appropriate big data management is still a challenge. This study intends to fill the above-mentioned gap by proposing a data lifecycle framework for data-driven governments. Through a Systematic Literature Review, we identified and analysed 76 data lifecycles models to propose a data lifecycle framework for data-driven governments (DaliF). In this way, we contribute to the ongoing discussion around big data management, which attracts researchers’ and practitioners’ interest.

In aged people, the central vision is affected by Aged-Related Macular Degeneration (AMD). The purpose of this research is to make safe, non-contact and cost-effective platform that can be used for the localization of the macula and monitoring system for dry AMD. Firstly, the fundus image is pre-processed using Contrast-Limited Adaptive Histogram Equalization (CHALE) and bottom-hat transformation function. Secondly, the enhanced image is used to extract the vascular structure that is blood vessels by using Kirsch's Template Method and the OSTU thresholding is used to segment out dark regions because macula are dark in color. The extraction of the blob like structures, dark region and background, estimated image is subtracted from extraction blood vessels image. The shape features are removed in order to differentiate between blobs like structure from vessel segments and the eccentricity of the candidate region further differentiate between vessels like structures from blob-like structures. This system results were evaluated and compared with state-of-the-art techniques. The result is demonstrated that the proposed system is appropriate for localization of macula and early detection of dry AMD.

Due to the rapid growth in artificial intelligence (AI) and deep learning (DL) approaches, the security and robustness of the deployed algorithms need to be guaranteed. The security susceptibility of the DL algorithms to adversarial examples has been widely acknowledged. The artificially created examples will lead to different instances negatively identified by the DL models that are humanly considered benign. Practical application in actual physical scenarios with adversarial threats shows their features. Thus, adversarial attacks and defense, including machine learning and its reliability, have drawn growing interest and, in recent years, has been a hot topic of research. We introduce a framework that provides a defensive model against the adversarial speckle-noise attack, the adversarial training, and a feature fusion strategy, which preserves the classification with correct labelling. We evaluate and analyze the adversarial attacks and defenses on the retinal fundus images for the Diabetic Retinopathy recognition problem, which is considered a state-of-the-art endeavor. Results obtained on the retinal fundus images, which are prone to adversarial attacks, are 99% accurate and prove that the proposed defensive model is robust.

Person re-identification (ReID) is an imperative area of pedestrian analysis and has practical applications in visual surveillance. In the person ReID, the robust feature representation is a key issue because of inconsistent visual appearances of a person. Also, an exhaustive gallery search is required to find the target image against each probe image. To answer such issues, this manuscript presents a framework named features-based clustering and deep features in person ReID. The proposed framework initially extracts three types of handcrafted features on the input images including shape, color, and texture for feature representation. To acquire optimal features, a feature fusion and selection technique is applied to these handcrafted features. Afterward, to optimize the gallery search, features-based clustering is performed for splitting the whole gallery into $$k$$ consensus clusters. For relationship learning of gallery features and related labels of the chosen clusters, radial basis kernel is employed. Later on, cluster-wise, images are selected and provided to the deep convolution neural network model to obtain deep features. Then, a cluster-wise feature vector is obtained by fusing the deep and handcrafted features. It follows the feature matching process where multi-class support vector machine is applied to choose the related cluster. Finally, to find accurate matching pair from the classified cluster(s) instead of the whole gallery search, a cross-bin histogram-based distance similarity measure is used. The recognition rate at rank 1 is attained as 46.82%, 48.12%, and 40.67% on selected datasets VIPeR, CUHK01, and iLIDS-VID, respectively. It confirms the proposed framework outperforms the existing ReID approaches.

The most important intricacy when processing natural scene text images is the existence of fog, smoke or haze. These intrusion elements decrease the contrast and disrupt the color fidelity of the image for various computer vision applications. In this paper, such a challenging issue is addressed. The intended work presents a novel method, that is, single image dehazing, based on transmission map. The contributions are performed in the following ways: (1) text extraction from hazy image is not straightforward due to lack of haze-free images and hazy images. To address this limitation, we introduce synthetic natural scene text image composed of pairs of synthetic hazy and corresponding haze-free images using mainstream datasets. Different from existing dehazing datasets, text in hazy images is considered compulsory content, which needs to be separated from background using the recovered image. For doing this, based on transmission map the scenic depth is calculated using haze density and color attenuation to generate depth map. In the next step, raw transmission map is computed, which is further refined using bilateral filtering to preserve edges and avoid possible noise; (2) text region proposals are estimated on the restored images using novel low-level connected component technique and character bounding is employed to complete the process. Finally, the experimentations are carried out on the images selected from standard datasets including MSRA-TD500, SVT and KAIST. The experimental outcomes demonstrate that the intended method performs better when compared with benchmark standard techniques and publically available dehazing datasets.

Despite its significance, modulation classification of constant envelope modulations (CEM) has not gained worthy attention in AMC literature so far. Two neural network-based architectures, i.e., radial basis function network (RBFN) and sparse-autoencoder-based deep neural network (DNN) are proposed and analyzed for the classification of spectrally efficient CEM modulations. A blind classification method which does not require any a-priori information about the channel or CEM specifics is based on the effectiveness of proposed hybrid feature space (HFS), used to train the trending neural network classifiers. Classification performance of both networks is analyzed for the typical additive white Gaussian noise (AWGN) channel and less explored, unfriendly, frequency-selective fading environment under the impact of Doppler shift.

Electrocardiography is the primary diagnostic tool for measuring the malfunction of different heart activities in the form of various cardiac diseases. Some cardiac diseases require special attention due to the urgency and risk factors involved. Myocardial infarction (MI) is one of the cardiac diseases that require robust identification. Early prediction in MI cases without prior history remains to be an ongoing challenge. This article delivers a major novel contribution in the context of predictive classification of flattened T-wave MI cases. Therefore, a novel model-driven deep deterministic learning (MDDDL) approach is proposed. In MDDDL, two different data sets are used for the execution of operational activities in terms of flattened T-wave predictive classification. The first data set is the publicly available Physikalisch-Technische Bundesanstalt (PTB), and the second data set is exclusively obtained from the University of Malaya Medical Centre (UMMC). Firstly, the systematic behaviour of MDDDL is defined in terms of pattern recognition of extracted features between T-wave alternans and flattened T-wave subjects, and then both data sets are merged considering data fusion approach and pre-defined conditions. Afterwards, the empirical approach is adopted in MDDDL evaluation in relation to global acceptance and state-of-the-art comparison. Finally, some qualitative improvements, such as inclusion of a backtracking factor for rapid prediction of flattened anomalies and increasing the number of features along with enhancement of fusion processes to reduce complexity, are required by the MDDDL and should be covered in future works.

Technology has contributed in every aspect of society. Academics is not an exception. The management of educational technology has come up with exceptional results in the new paradigm of learning environment. In recent years, flipped learning approach has gained much popularity and has been more widely accepted and adopted as a driving force for enabling active learning. This paper defines the formulation of novel framework, inspired by flipped learning approach, leading to effective learning environment. It also describes a novel extension of student-centered learning by integrating educational technology, technology enhanced learning strategy, student questions generation and instant response system into the higher education. It also examines the impact of this extension on student learning engagement, motivation, attitude, and calculating the impact of acceptance for unconventional education on the overall system. The result indicated that effective learning environment has a significant positive effect on learning motivation and engagement. The result showed that the constructs of education technology, technology enhanced learning strategy, students question generation and instance response system in the presence of “impact of acceptance for unconventional education” has an effect on formulating effective learning environment. Research recommendations are given on the basis of results of the study.

Application of deep learning in the area of automatic modulation classification (AMC) is still evolving. An unsupervised sparse-autoencoder-based deep neural network (SAE-DNN) is proposed to deal with the problem of AMC for much neglected frequency selective fading scenarios with Doppler shift. The authors propose a set of low complexity spectral and cumulant based features for training SAE-DNN. The network is designed using forced dimensionality reduction and sparsity constraint to achieve a low complexity solution with improved ability to learn more refined and robust features from the input training data. A unique training method is presented in this study which incorporates a range of SNR values for the entire span of the training dataset, as compared to the conventional approach which only uses a single SNR value for all the training examples. A comprehensive performance analysis shows that the proposed method outperforms many conventional counterparts in the literature. Generalisation test verifies that network is feasible for all channel conditions. A robust classification behaviour is observed against phase-frequency impairments and Doppler shift for frequency selective fading scenarios.

Human action recognition from a video sequence has received much attention lately in the field of computer vision due to its range of applications in surveillance, healthcare, smart homes, tele-immersion, to name but a few. However, it is still facing several challenges such as human variations, occlusion, change in illumination, complex background. In this article, we consider the problems related to multiple human detection and classification using novel statistical weighted segmentation and rank correlation-based feature selection approach. Initially, preprocessing is performed on a set of frames to remove existing noise and to make the foreground maximal differentiable compared to the background. A novel weighted segmentation method is also introduced for human extraction prior to feature extraction. Ternary features are exploited including color, shape, and texture, which are later combined using serial-based features fusion method. To avoid redundancy, rank correlation-based feature selection technique is employed, which acts as a feature optimizer and leads to improved classification accuracy. The proposed method is validated on six datasets including Weizmann, KTH, Muhavi, WVU, UCF sports, and MSR action and validated based on seven performance measures. A fair comparison with existing work is also provided which proves the significance of proposed compared to other techniques.

This paper presents a novel hybrid extreme learning machine (ELM) with cuckoo search algorithm (CSA) for the classification purposes of the digitally modulated signals, such as phase shift keying (PSK), frequency shift keying (FSK), and quadrature amplitude modulation (QAM). Nine modulation schemes having different orders have been considered for this paper. First, the Gabor filter is used to extract the key features from the received signal which are then optimized by the CSA. Finally, the ELM is used to classify the modulation schemes using these optimized features. Our proposed CSA-ELM approach is not only fast convergent and robust but also manifests improved percentage classification accuracy at low SNRs and lower sample size for both AWGN and Rayleigh fading channels.

The automotive industry is growing day by day and personal vehicles have become a significant transportation resource now. With the rise in private transportation vehicles, getting a free space for parking one's car, especially in populated areas, has not only become difficult but also results in several issues, such as: (i) traffic congestion, (ii) wastage of time, (iii) environmental pollution, and most importantly (iv) unnecessary fuel consumption. On the other hand, car parking spaces in urban areas are not increasing at the same rate as the vehicles on roads. Therefore, smart car parking systems have become an essential need to address the issues mentioned above. Several researchers have attempted to automate the parking space allocation by utilizing state-of-the-art technologies. Significant work has been done in the domains of Wireless Sensor Networks (WSN), Cloud Computing, Fog Computing, and Internet of Things (IoT) to facilitate the advancements in smart parking services. Few researchers have proposed methods for smart car parking using the cloud computing infrastructures. However, latency is a significant concern in cloud-based applications, including intelligent transportation and especially in smart car parking systems. Fog computing, bringing the cloud computing resources in proximate vicinity to the network edge, overcomes not only the latency issue but also provides significant improvements, such as on-demand scaling, resource mobility, and security. The primary motivation to employ fog computing in the proposed approach is to minimize the latency as well as network usage in the overall smart car parking system. For demonstrating the effectiveness of the proposed approach for reducing the lag and network usage, simulations have been performed in iFogSim and the results have been compared with that of the cloud-based deployment of the smart car parking system. Experimental results exhibit that the proposed fog-based implementation of the efficient parking system minimizes latency significantly. It is also observed that the proposed fog-based implementation reduces the overall network usage in contrast to the cloud-based deployment of the smart car parking.

The use of Conversational agents (CAs) in healthcare is an emerging field. These CAs seem to be effective in accomplishing administrative tasks, e.g. providing locations of care facilities and scheduling appointments. Modern CAs use machine learning (ML) to recognize, understand and generate a response. Given the criticality of many healthcare settings, ML and other component errors may result in CA failures and may cause adverse effects on patients. Therefore, in-depth assurance is required before the deployment of ML in critical clinical applications, e.g. management of medication dose or medical diagnosis. CA safety issues could arise due to diverse causes, e.g. related to user interactions, environmental factors and ML errors. In this paper, we classify failures of perception (recognition and understanding) of CAs and their sources. We also present a case study of a CA used for calculating insulin dose for gestational diabetes mellitus (GDM) patients. We then correlate identified perception failures of CAs to potential scenarios that might compromise patient safety.

Switched reluctance motors (SRMs) are simple in structure, easy to manufacture, magnet-less, brushless, and highly robust compared to other AC motors which makes them a good option for applications that operate in harsh environment. However, the motor has non-linear magnetic characteristics, and it comes with various pole-phase combinations and circuit topologies that causes many difficulties in deciding on which type to choose. In this paper, the viability of SRM as a low-cost, rugged machine for vehicle radiator cooling fan is considered. First, necessary design considerations are presented, then three commonly use types of SRM are analyzed: A 3-phase 6/4, 3-phase 12/8, and a 4-phase 8/6 to find their static and dynamic characteristics so the most suitable type can be selected. Simulation results show that the 8/6 SRM produces the highest efficiency with less phase current which reduces the converter burden. However, with asymmetric half bridge converter, eight power switches are required for 8/6 SRM and thus put a burden on the overall drive cost. As a solution, the Miller converter with only six switches for four phase SRM. To verify the proposed idea, the 8/6 SRM was manufactured and tested. The results show that Miller converter can be used for the proposed SRM with slightly reduced efficiency at 80.4%.

Traffic Sign Recognition (TSR) is a crucial step for automated vehicles and driver assistance systems. Automated TSD in an extreme environment has always been challenging due to foggy, rainy, blurry, and cropping images. A real-time TSD model named improved Extreme Learning Machine Network (iELMNet) is proposed to tackle these challenges. Primary modules of iELMNet include: a) Custom DensNet; b) Accurate Anchor Prediction Model (A2PM); c) Scale Transformation (ST), and d) Extreme Learning Machine (ELM) classifier. Convolutional Neural Network (CNN) model improvises edges of traffic-signs using mapped images extracted from handcrafted features. A2PM removes the redundant features to improve efficiency. ST is utilized to allow the proposed technique for detecting these signs of variant sizes. ELM classifier tries to classify traffic signs robustly by minimizing the feature dimensions. The proposed model is evaluated over three publicly available datasets, i.e., CURE-TSR, TT100k, and GTSRB, and acquired 98.63%, 95.22%, and 99.45% precision, respectively. The output of proposed model demonstrates its competence and ability to implement it in a practical environment.

Video based Human Action Recognition (HAR) is an active research field of Machine Learning (ML) and human detection in videos is the most important step in action recognition. Recently, several techniques and algorithms have been proposed to increase the accuracy of HAR process, but margin of improvement still exists. Detection and classification of human actions is a challenging task due to random changes in human appearance, clothes, illumination, and background. In this article, an efficient technique to classify human actions by utilizing steps like removing redundant frames from videos, extracting Segments of Interest (SoIs), feature descriptor mining through Geodesic Distance (GD), 3D Cartesian-plane Features (3D-CF), Joints MOCAP (JMOCAP) and n-way Point Trajectory Generation (nPTG). A Neuro Fuzzy Classifier (NFC) is used at the end for the classification purpose. The proposed technique is tested on two publicly available datasets including HMDB-51 and Hollywood2, and achieved an accuracy of 82.55% and 91.99% respectively. These efficient results prove the validity of proposed model.

The outbreak of COVID-19 pandemic presents an unprecedented challenge for humanity. The historical data about the past pandemics indicates towards a high possibility of future pandemics. Moreover, current pandemic is expected to stay for longer time. In this situation, social robots hold a huge potential to assist in fighting against current and future pandemics by minimizing human-to-human interactions e.g., by providing digital help desk, and monitoring the compliance of people with required safety measures at public places. A huge number of robots are required to monitor large spaces like shopping malls, airports etc. Therefore, we present Multi-Agent System (MAS) to provide robot based mobile help desk and monitoring safety measure of wearing face mask, for large spaces in an efficient and cost-effective manner. Our proposed MAS is based on collaborative work of two agents: 1) CCTV Camera, and 2) Robot. Experimental results show efficiency and effectiveness of proposed MAS in navigation and control of robot based on visual information interpreted by CCTV camera to provide mobile help desk, and detecting face masks through robot by using state-of-the-art real-time computer vision algorithms in large spaces.

Superpixel segmentation, a preprocessing component, is widely used in computer vision tasks. Superpixel algorithm is supposed to generate superpixels with required boundary adherence, compactness as well as less computational complexity. However, most of the existing superpixel algorithms do not perform satisfactorily when it comes to compactness and boundary adherence, as they are a paradox in nature. In this paper, we propose a new superpixel segmentation method based on density peak (DP) clustering and modification of the original DP algorithm. The experimental results have been compared with state-of-the-art methods, both quantitatively and qualitatively, revealing the efficient outcomes that adhere to the object boundaries better than others.

Summary COVID‐19 is a quickly spreading over 10 million persons globally. The overall number of infected patients worldwide is estimated to be around 133,381,413 people. Infection rate is being increased on daily basis. It has also caused a devastating effect on the world economy and public health. Early stage detection of this disease is mandatory to reduce the mortality rate. Artificial intelligence performs a vital role for COVID‐19 detection at an initial stage using chest radiographs. The proposed methods comprise of the two phases. Deep features (DFs) are derived from its last fully connected layers of pre‐trained models like AlexNet and MobileNet in phase‐I. Later these feature vectors are fused serially. Best features are selected through feature selection method of PCA and passed to the SVM and KNN for classification. In phase‐II, quantum transfer learning model is utilized, in which a pre‐trained ResNet‐18 model is applied for DF collection and then these features are supplied as an input to the 4‐qubit quantum circuit for model training with the tuned hyperparameters. The proposed technique is evaluated on two publicly available x‐ray imaging datasets. The proposed methodology achieved an accuracy index of 99.0% with three classes including corona virus‐positive images, normal images, and pneumonia radiographs. In comparison to other recently published work, the experimental findings show that the proposed approach outperforms it.

The elderly population in need of long-term care is rising, adding to the workload of healthcare workers in nursing homes. Throughout a work day health workers often must perform the time consuming process of collecting various types of health data from the residents. A recent study has revealed that frontline nurses and caregivers spend over half of their time accessing and updating patient records instead of providing care. New technology could enhance these data-oriented operations, and free up time so that staff can care for patients in other ways. Intelligent human-computer interaction paradigms can enhance data retrieval, visualization, and communication processes efficiently in a way to improve the overall productivity during work. In this study, we present an intelligent holographic mixed reality (MR) system that leverages Microsoft Hololens for work practices of healthcare work in nursing homes. Supported by computer vision, this system provides automatic data retrieval, in addition to interactive data visualization and mid-air data entry mechanism. Using face recognition through the Hololens’ visual sensors, the system recognizes individual patients, and automatically retrieves relevant health data and supports data entry.