ORCID Profile
0000-0002-9032-1320
Current Organisations
Nirma University of Science and Technology
,
University of Oxford
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: MDPI AG
Date: 24-02-2022
DOI: 10.3390/S22051780
Abstract: The object recognition concept is being widely used a result of increasing CCTV surveillance and the need for automatic object or activity detection from images or video. Increases in the use of various sensor networks have also raised the need of lightweight process frameworks. Much research has been carried out in this area, but the research scope is colossal as it deals with open-ended problems such as being able to achieve high accuracy in little time using lightweight process frameworks. Convolution Neural Networks and their variants are widely used in various computer vision activities, but most of the architectures of CNN are application-specific. There is always a need for generic architectures with better performance. This paper introduces the Dimension-Based Generic Convolution Block (DBGC), which can be used with any CNN to make the architecture generic and provide a dimension-wise selection of various height, width, and depth kernels. This single unit which uses the separable convolution concept provides multiple combinations using various dimension-based kernels. This single unit can be used for height-based, width-based, or depth-based dimensions the same unit can even be used for height and width, width and depth, and depth and height dimensions. It can also be used for combinations involving all three dimensions of height, width, and depth. The main novelty of DBGC lies in the dimension selector block included in the proposed architecture. Proposed unoptimized kernel dimensions reduce FLOPs by around one third and also reduce the accuracy by around one half semi-optimized kernel dimensions yield almost the same or higher accuracy with half the FLOPs of the original architecture, while optimized kernel dimensions provide 5 to 6% higher accuracy with around a 10 M reduction in FLOPs.
Publisher: MDPI AG
Date: 18-12-2020
DOI: 10.3390/S20247299
Abstract: Human Action Recognition (HAR) is the classification of an action performed by a human. The goal of this study was to recognize human actions in action video sequences. We present a novel feature descriptor for HAR that involves multiple features and combining them using fusion technique. The major focus of the feature descriptor is to exploits the action dissimilarities. The key contribution of the proposed approach is to built robust features descriptor that can work for underlying video sequences and various classification models. To achieve the objective of the proposed work, HAR has been performed in the following manner. First, moving object detection and segmentation are performed from the background. The features are calculated using the histogram of oriented gradient (HOG) from a segmented moving object. To reduce the feature descriptor size, we take an averaging of the HOG features across non-overlapping video frames. For the frequency domain information we have calculated regional features from the Fourier hog. Moreover, we have also included the velocity and displacement of moving object. Finally, we use fusion technique to combine these features in the proposed work. After a feature descriptor is prepared, it is provided to the classifier. Here, we have used well-known classifiers such as artificial neural networks (ANNs), support vector machine (SVM), multiple kernel learning (MKL), Meta-cognitive Neural Network (McNN), and the late fusion methods. The main objective of the proposed approach is to prepare a robust feature descriptor and to show the ersity of our feature descriptor. Though we are using five different classifiers, our feature descriptor performs relatively well across the various classifiers. The proposed approach is performed and compared with the state-of-the-art methods for action recognition on two publicly available benchmark datasets (KTH and Weizmann) and for cross-validation on the UCF11 dataset, HMDB51 dataset, and UCF101 dataset. Results of the control experiments, such as a change in the SVM classifier and the effects of the second hidden layer in ANN, are also reported. The results demonstrate that the proposed method performs reasonably compared with the majority of existing state-of-the-art methods, including the convolutional neural network-based feature extractors.
Publisher: MDPI AG
Date: 23-04-2020
DOI: 10.3390/MIN10040379
Abstract: The stanniferous granites of the Zaaiplaats Tin Field are part of the A-Type Lebowa Granite Suite, within the greater Bushveld Igneous Complex of northeast South Africa. The tin field comprises three granites: (1) the Nebo, a leucocratic, equigranular biotite granite (2) The brick-red hypidiomorphic Bobbejaankop granite, which is extensively microclinized with chloritized biotite and characteristic synneusis-textured quartz and (3) The variably altered roof facies of the Bobbejaankop granite known as the Lease microgranite. The Bobbejaankop and Lease granites were both extensively mined for cassiterite until 1989. The cassiterite is hosted in disseminations, miarolitic cavities, and within large hydrothermal, tourmalinized, and greisenized pipes and lenticular ore-bodies. An extensive petrological and whole-rock XRF and ICP-MS geochemical study, has provided new insight into the magmatic and magmatic-hydrothermal mineralization processes in these granites. Trace elements and Rayleigh Fractionation modelling suggest the sequential fractionation of the Nebo granite magma to be the origin of the Bobbejaankop granite. Incompatible elemental ratios, such as Zr/Hf and Nb/Ta, record the influence of internally derived, F-rich, hydrothermal fluid accumulation within the roof of the Bobbejaankop granite. Thus, the Lease granite resulted from alteration of the partially crystallized Bobbejaankop granite, subsequent to fluid saturation, and the accumulation of a magmatic-hydrothermal, volatile-rich fluid in the granite cupola. The ratio of Nb/Ta, proved effective in distinguishing the magmatic and magmatic-hydrothermal transition within the Bobbejaankop granite. Elemental ratios reveal the differences between pre- and post-fluid saturation in the mineralizing regimes within the same pluton. Thus highlighting the effect that the location and degree of hydrothermal alteration have had on the distribution of endogranitic tin mineralization.
Publisher: MDPI AG
Date: 02-12-2021
DOI: 10.3390/S21238071
Abstract: Distributed denial-of-service (DDoS) attacks are significant threats to the cyber world because of their potential to quickly bring down victims. Memcached vulnerabilities have been targeted by attackers using DDoS lification attacks. GitHub and Arbor Networks were the victims of Memcached DDoS attacks with 1.3 Tbps and 1.8 Tbps attack strengths, respectively. The bandwidth lification factor of nearly 50,000 makes Memcached the deadliest DDoS attack vector to date. In recent times, fellow researchers have made specific efforts to analyze and evaluate Memcached vulnerabilities however, the solutions provided for security are based on best practices by users and service providers. This study is the first attempt at modifying the architecture of Memcached servers in the context of improving security against DDoS attacks. This study discusses the Memcached protocol, the vulnerabilities associated with it, the future challenges for different IoT applications associated with caches, and the solutions for detecting Memcached DDoS attacks. The proposed solution is a novel identification-pattern mechanism using a threshold scheme for detecting volume-based DDoS attacks. In the undertaken study, the solution acts as a pre-emptive measure for detecting DDoS attacks while maintaining low latency and high throughput.
Publisher: Geological Society of South Africa
Date: 03-2022
Abstract: The Zaaiplaats tin field is host to two of the historically most significant tin mines in South Africa. The geological maps of Zaaiplaats and Groenfontein have not been updated since the 1980s and 1950s respectively and warrant a renewed investigation. Cassiterite is hosted in the Bobbejaankop and Lease granites, of the Zaaiplaats and Groenfontein tin mines, which are part of the Lebowa Granite Suite of the Bushveld Complex. Tin mineralisation is primarily hosted as low-grade disseminations and within networks of high-grade hydrothermal pipes and lenticular ore-bodies. One difficulty in mapping such formations arises from the limited lithological variability between mineralised and unmineralised granitic facies. In order to map the granitic lithologies and discriminate alteration zones, an integrated approach is applied by combining remote sensing and in situ portable X-ray fluorescence (pXRF) mapping. The pXRF large ion lithophile (LIL) element distribution mapping, specifically correlating Rb, Sr and Ba with Sn, points to the concentration of late-stage magmatic-hydrothermal fluids, which are associated with endogranitic mineralisation. The use of the Rb/Ba ratio highlights regions of late-stage magmatic-hydrothermal alteration, effectively delineates granitic facies and identifies zones of potential tin mineralisation. Spectral image processing techniques were used as tools to support the mapping of these granites, their variable degrees of magmatic-hydrothermal alteration and regions of endogranitic disseminated mineralisation. We thus exemplify that an expert-based and synergic approach, combining inexpensive in situ pXRF and freely available satellite remote sensing data, supports the mapping and identification of endogranitic mineralisation in early exploration stages. Furthermore, due to its versatility, this approach can easily be applied to other styles of plutonic mineralisation.
Publisher: MDPI AG
Date: 11-10-2021
DOI: 10.3390/ELECTRONICS10202470
Abstract: Computer vision is becoming an increasingly trendy word in the area of image processing. With the emergence of computer vision applications, there is a significant demand to recognize objects automatically. Deep CNN (convolution neural network) has benefited the computer vision community by producing excellent results in video processing, object recognition, picture classification and segmentation, natural language processing, speech recognition, and many other fields. Furthermore, the introduction of large amounts of data and readily available hardware has opened new avenues for CNN study. Several inspirational concepts for the progress of CNN have been investigated, including alternative activation functions, regularization, parameter optimization, and architectural advances. Furthermore, achieving innovations in architecture results in a tremendous enhancement in the capacity of the deep CNN. Significant emphasis has been given to leveraging channel and spatial information, with a depth of architecture and information processing via multi-path. This survey paper focuses mainly on the primary taxonomy and newly released deep CNN architectures, and it ides numerous recent developments in CNN architectures into eight groups. Spatial exploitation, multi-path, depth, breadth, dimension, channel boosting, feature-map exploitation, and attention-based CNN are the eight categories. The main contribution of this manuscript is in comparing various architectural evolutions in CNN by its architectural change, strengths, and weaknesses. Besides, it also includes an explanation of the CNN’s components, the strengths and weaknesses of various CNN variants, research gap or open challenges, CNN applications, and the future research direction.
Publisher: MDPI AG
Date: 23-09-2023
DOI: 10.3390/S21237786
Abstract: The human immune system is very complex. Understanding it traditionally required specialized knowledge and expertise along with years of study. However, in recent times, the introduction of technologies such as AIoMT (Artificial Intelligence of Medical Things), genetic intelligence algorithms, smart immunological methodologies, etc., has made this process easier. These technologies can observe relations and patterns that humans do and recognize patterns that are unobservable by humans. Furthermore, these technologies have also enabled us to understand better the different types of cells in the immune system, their structures, their importance, and their impact on our immunity, particularly in the case of debilitating diseases such as cancer. The undertaken study explores the AI methodologies currently in the field of immunology. The initial part of this study explains the integration of AI in healthcare and how it has changed the face of the medical industry. It also details the current applications of AI in the different healthcare domains and the key challenges faced when trying to integrate AI with healthcare, along with the recent developments and contributions in this field by other researchers. The core part of this study is focused on exploring the most common classifications of health diseases, immunology, and its key subdomains. The later part of the study presents a statistical analysis of the contributions in AI in the different domains of immunology and an in-depth review of the machine learning and deep learning methodologies and algorithms that can and have been applied in the field of immunology. We have also analyzed a list of machine learning and deep learning datasets about the different subdomains of immunology. Finally, in the end, the presented study discusses the future research directions in the field of AI in immunology and provides some possible solutions for the same.
Publisher: Elsevier BV
Date: 09-2021
Publisher: Springer Science and Business Media LLC
Date: 13-04-2021
DOI: 10.1038/S41467-021-22349-Z
Abstract: Most known porphyry Cu deposits formed in the Phanerozoic and are exclusively associated with moderately oxidized, sulfur-rich, hydrous arc-related magmas derived from partial melting of the asthenospheric mantle metasomatized by slab-derived fluids. Yet, whether similar metallogenic processes also operated in the Precambrian remains obscure. Here we address the issue by investigating the origin, f O 2 , and S contents of calc-alkaline plutonic rocks associated with the Haib porphyry Cu deposit in the Paleoproterozoic Richtersveld Magmatic Arc (southern Namibia), an interpreted mature island-arc setting. We show that the ca. 1886–1881 Ma ore-forming magmas, originated from a mantle-dominated source with minor crustal contributions, were relatively oxidized (1‒2 log units above the fayalite-magnetite-quartz redox buffer) and sulfur-rich. These results indicate that moderately oxidized, sulfur-rich arc magma associated with porphyry Cu mineralization already existed in the late Paleoproterozoic, probably as a result of recycling of sulfate-rich seawater or sediments from the subducted oceanic lithosphere at that time.
Location: United Kingdom of Great Britain and Northern Ireland
No related grants have been discovered for Laurence Robb.