Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
360
result(s) for
"Mehmood, Abid"
Sort by:
The international handbook on social innovation : collective action, social learning and transdisciplinary research
This handbook provides an overview of theoretical perspectives, methodologies and instructive experiences from all continents, as well as implications for collective action and policy. It argues strongly for social innovation as a key to human development.
Book
LightAnomalyNet: A Lightweight Framework for Efficient Abnormal Behavior Detection
The continuous development of intelligent video surveillance systems has increased the demand for enhanced vision-based methods of automated detection of anomalies within various behaviors found in video scenes. Several methods have appeared in the literature that detect different anomalies by using the details of motion features associated with different actions. To enable the efficient detection of anomalies, alongside characterizing the specificities involved in features related to each behavior, the model complexity leading to computational expense must be reduced. This paper provides a lightweight framework (LightAnomalyNet) comprising a convolutional neural network (CNN) that is trained using input frames obtained by a computationally cost-effective method. The proposed framework effectively represents and differentiates between normal and abnormal events. In particular, this work defines human falls, some kinds of suspicious behavior, and violent acts as abnormal activities, and discriminates them from other (normal) activities in surveillance videos. Experiments on public datasets show that LightAnomalyNet yields better performance comparative to the existing methods in terms of classification accuracy and input frames generation.
Journal Article
Abnormal Behavior Detection in Uncrowded Videos with Two-Stream 3D Convolutional Neural Networks
The increasing demand for surveillance systems has resulted in an unprecedented rise in the volume of video data being generated daily. The volume and frequency of the generation of video streams make it both impractical as well as inefficient to manually monitor them to keep track of abnormal events as they occur infrequently. To alleviate these difficulties through intelligent surveillance systems, several vision-based methods have appeared in the literature to detect abnormal events or behaviors. In this area, convolutional neural networks (CNNs) have also been frequently applied due to their prevalence in the related domain of general action recognition and classification. Although the existing approaches have achieved high detection rates for specific abnormal behaviors, more inclusive methods are expected. This paper presents a CNN-based approach that efficiently detects and classifies if a video involves the abnormal human behaviors of falling, loitering, and violence within uncrowded scenes. The approach implements a two-stream architecture using two separate 3D CNNs to accept a video and an optical flow stream as input to enhance the prediction performance. After applying transfer learning, the model was trained on a specialized dataset corresponding to each abnormal behavior. The experiments have shown that the proposed approach can detect falling, loitering, and violence with an accuracy of up to 99%, 97%, and 98%, respectively. The model achieved state-of-the-art results and outperformed the existing approaches.
Journal Article
A Comprehensive Study of ChatGPT: Advancements, Limitations, and Ethical Considerations in Natural Language Processing and Cybersecurity
This paper presents an in-depth study of ChatGPT, a state-of-the-art language model that is revolutionizing generative text. We provide a comprehensive analysis of its architecture, training data, and evaluation metrics and explore its advancements and enhancements over time. Additionally, we examine the capabilities and limitations of ChatGPT in natural language processing (NLP) tasks, including language translation, text summarization, and dialogue generation. Furthermore, we compare ChatGPT to other language generation models and discuss its applicability in various tasks. Our study also addresses the ethical and privacy considerations associated with ChatGPT and provides insights into mitigation strategies. Moreover, we investigate the role of ChatGPT in cyberattacks, highlighting potential security risks. Lastly, we showcase the diverse applications of ChatGPT in different industries and evaluate its performance across languages and domains. This paper offers a comprehensive exploration of ChatGPT’s impact on the NLP field.
Journal Article
Co-created visual narratives and inclusive place branding: a socially responsible approach to residents’ participation and engagement
This paper discusses the importance of co-created visual narratives in developing participatory and inclusive place branding. We refer to the need for a socially responsible approach when considering place branding policies and practices. For this purpose, we develop and empirically apply a novel framework with four interconnected phases comprising place-based contextualization, re-appreciation, re-positioning, and consolidation of residents’ perceptions, experiences and aspirations to develop and initiate inclusive place branding processes. Using participatory research and collaborative visual methods, we worked with a group of residents in Carvalhal de Vermilhas, Portugal. This work stimulated the co-development of collective agency to consider narratives, values and identities to be articulated for creating and promoting more inclusive representation of place in a (hypothetical) branding exercise. The framework application as well as its challenges and limitations, particularly in co-creation processes, were critically deliberated at all phases. Collaborative visual techniques from our analysis emerge as valuable participatory tools for researchers towards improving residents’ participation in place branding, and therefore contributing towards a more inclusive form of this practice. However, we are also aware of the perils associated with communities’ opening up their pristine heritage to touristic ventures, and hence suggest considering the importance of sustainable place-shaping in all branding decisions.
Journal Article
A lightweight noise-tolerant encryption scheme for secure communication: An unmanned aerial vehicle application
In the modern era, researchers have focused a great deal of effort on multimedia security and fast processing to address computational processing time difficulties. Due to limited battery capacity and storage, Unmanned Aerial Vehicles (UAVs) must use energy-efficient processing. In order to overcome the vulnerability of time inefficiency and provide an appropriate degree of security for digital images, this paper proposes a new encryption system based on the bit-plane extraction method, chaos theory, and Discrete Wavelet Transform (DWT). Using confusion and diffusion processes, chaos theory is used to modify image pixels. In contrast, bit-plane extraction and DWT are employed to reduce the processing time required for encryption. Multiple cyberattack analysis, including noise and cropping attacks, are performed by adding random noise to the ciphertext image in order to determine the proposed encryption scheme’s resistance to such attacks. In addition, a variety of statistical security analyses, including entropy, contrast, energy, correlation, peak signal-to-noise ratio (PSNR), and mean square error (MSE), are performed to evaluate the security of the proposed encryption system. Moreover, a comparison is made between the statistical security analysis of the proposed encryption scheme and the existing work to demonstrate that the suggested encryption scheme is better to the existing ones.
Journal Article
Automated Estimation of Crop Yield Using Artificial Intelligence and Remote Sensing Technologies
Agriculture is the backbone of any country, and plays a viable role in the total gross domestic product (GDP). Healthy and fruitful crops are of immense importance for a government to fulfill the food requirements of its inhabitants. Because of land diversities, weather conditions, geographical locations, defensive measures against diseases, and natural disasters, monitoring crops with human intervention becomes quite challenging. Conventional crop classification and yield estimation methods are ineffective under unfavorable circumstances. This research exploits modern precision agriculture tools for enhanced remote crop yield estimation, and types classification by proposing a fuzzy hybrid ensembled classification and estimation method using remote sensory data. The architecture enhances the pooled images with fuzzy neighborhood spatial filtering, scaling, flipping, shearing, and zooming. The study identifies the optimal weights of the strongest candidate classifiers for the ensembled classification method adopting the bagging strategy. We augmented the imagery datasets to achieve an unbiased classification between different crop types, including jute, maize, rice, sugarcane, and wheat. Further, we considered flaxseed, lentils, rice, sugarcane, and wheat for yield estimation on publicly available datasets provided by the Food and Agriculture Organization (FAO) of the United Nations and the Word Bank DataBank. The ensemble method outperformed the individual classification methods for crop type classification on an average of 13% and 24% compared to the highest gradient boosting and lowest decision tree methods, respectively. Similarly, we observed that the gradient boosting predictor outperformed the multivariate regressor, random forest, and decision tree regressor, with a comparatively lower mean square error value on yield years 2017 to 2021. Further, the proposed architecture supports embedded devices, where remote devices can adopt a lightweight classification algorithm, such as MobilenetV2. This can significantly reduce the processing time and overhead of a large set of pooled images.
Journal Article
Automatic Diagnosis of Glaucoma from Retinal Images Using Deep Learning Approach
Glaucoma is characterized by increased intraocular pressure and damage to the optic nerve, which may result in irreversible blindness. The drastic effects of this disease can be avoided if it is detected at an early stage. However, the condition is frequently detected at an advanced stage in the elderly population. Therefore, early-stage detection may save patients from irreversible vision loss. The manual assessment of glaucoma by ophthalmologists includes various skill-oriented, costly, and time-consuming methods. Several techniques are in experimental stages to detect early-stage glaucoma, but a definite diagnostic technique remains elusive. We present an automatic method based on deep learning that can detect early-stage glaucoma with very high accuracy. The detection technique involves the identification of patterns from the retinal images that are often overlooked by clinicians. The proposed approach uses the gray channels of fundus images and applies the data augmentation technique to create a large dataset of versatile fundus images to train the convolutional neural network model. Using the ResNet-50 architecture, the proposed approach achieved excellent results for detecting glaucoma on the G1020, RIM-ONE, ORIGA, and DRISHTI-GS datasets. We obtained a detection accuracy of 98.48%, a sensitivity of 99.30%, a specificity of 96.52%, an AUC of 97%, and an F1-score of 98% by using the proposed model on the G1020 dataset. The proposed model may help clinicians to diagnose early-stage glaucoma with very high accuracy for timely interventions.
Journal Article
Advanced molecular tools for surveillance and management of tobamoviruses
Tobamoviruses are a group of plant viruses that can cause yield losses of up to 70% and reduce fruit quality by 30–50%. Historically, tobamoviruses were dominated by tobacco mosaic virus (TMV) and tomato mosaic virus (ToMV). However, the landscape is rapidly shifting with the emergence of economically significant viruses such as tomato mottle mosaic virus (ToMMV) and tomato brown rugose fruit virus (ToBRFV). Both can circumvent the previously durable Tm-2² resistance in tomato and spread across multiple continents. This shift coincides with dramatic leaps in diagnostic tools, which have enhanced surveillance capabilities. Sensitive detection of tobamoviruses in the field with minimal sample preparation can be achieved using latest technologies such as isothermal amplification, CRISPR/Cas-hybrid assays or next-generation sequencing. Virus-host interactions underscore that viral proteins, including replicase components, are potent suppressors of RNA silencing (VSRs). Small RNA profiling and network analyses of viral movement proteins reveal complex mechanisms of immune evasion and resistance breakdown. These findings are largely based on dominant NB-LRR genes such as L , Tm-1 , and Tm-2 2 . However, evidence indicates that ToBRFV can bypass this resistance via mutation in the movement protein, so supplementary methods should be considered. This review covers latest approaches, such as genome editing with CRISPR, targeting susceptibility genes, RNA interference (RNAi), and multi-omics approaches (transcriptomics, proteomics, metabolomics, ionomics), that can facilitate real-time surveillance and breeding for enhanced resilience. Moreover, the use of bio-formulations and nano-formulations as eco-friendly alternatives against tobamoviruses is discussed in detail. Climate change further complicates disease dynamics by undermining temperature-sensitive resistance, altering virus prevalence, and exacerbating yield losses. The rapid emergence of new tobamoviruses, which threatens the economy, necessitates a comprehensive approach. The integration of molecular diagnostics using CRISPR, omics technologies, designed protective systems, and climate-augmented disease prediction offers a detailed blueprint for the sustainable control of tobamoviruses and crop protection.
Journal Article
Exploring the potential of moringa leaf extract as bio stimulant for improving yield and quality of black cumin oil
The history of plants to be utilized as medicines is thousands of years old. Black cumin is one of the most widely examined plant possessing naturally occurring compounds with antimicrobial potential. Foliar application of growth stimulators is a successful strategy to enhance yield and quality in many crops. A field study was planned to apply growth stimulator like moringa leaf extract on black cumin crop grown under field conditions using RCB design with three replications. All other agronomic inputs and practices were uniform. The treatments were moringa leaf extract concentrations (10%, 20%), growth stages (40 days after sowing, 80 DAS, 120 DAS, 40 + 80 DAS, 40 + 120 DAS, 80 + 120 DAS, 40 + 80 + 120 days after sowing) and two controls unsprayed check (i.e. no moringa leaf extract, no water) and sprayed check (no moringa leaf extract + water). Application of 20% moringa leaf extract at stage-7 (40 + 80 + 120 days after sowing) had significantly increased plant height, branches plant
−1
, essential oil content, fixed oil content, peroxidase value and iodine value of black cumin oil over unsprayed control. Application of moringa leaf extract showed maximum results and improves growth and yield of black cumin when applied at 40 + 80 + 120 days after sowing. As this study was only conducted using moringa leaf extract, it is advisable to conduct an experiment with various bio stimulants along with fertilizer combinations and growth regulators to check their synergistic effects for more reliable and acceptable recommendations in future.
Journal Article