A5008903140- Advanced Image and Video Retrieval Techniques
- Image Retrieval and Classification Techniques
- Advanced Wireless Communication Techniques
- Wireless Communication Networks Research
- Neural Networks and Applications
- Advanced Steganography and Watermarking Techniques
- Chaos-based Image/Signal Encryption
- Digital Media Forensic Detection
- Machine Fault Diagnosis Techniques
- Video Analysis and Summarization
- Video Surveillance and Tracking Methods
- Image and Signal Denoising Methods
- PAPR reduction in OFDM
- Handwritten Text Recognition Techniques
- Anomaly Detection Techniques and Applications
- Smart Agriculture and AI
- Speech and Audio Processing
- Multi-Criteria Decision Making
- Face and Expression Recognition
- Human Pose and Action Recognition
- Emotion and Mood Recognition
- Speech Recognition and Synthesis
- Biometric Identification and Security
- Advanced Adaptive Filtering Techniques
- COVID-19 diagnosis using AI
United Arab Emirates University
2025
Italian Institute of Technology
2024-2025
Mohamed bin Zayed University of Artificial Intelligence
2023-2024
University of Stavanger
2024
Lady Reading Hospital
2024
University of Genoa
2024
Behman Hospital
2023
Islamia College University
2015-2023
National University of Sciences and Technology
2005-2022
Kohat University of Science and Technology
2017-2022
Recurrent neural network (RNN) and long short-term memory (LSTM) have achieved great success in processing sequential multimedia data yielded the state-of-the-art results speech recognition, digital signal processing, video text analysis. In this paper, we propose a novel action recognition method by using convolutional (CNN) deep bidirectional LSTM (DB-LSTM) network. First, features are extracted from every sixth frame of videos, which helps reduce redundancy complexity. Next, information...
The recent advances in embedded processing have enabled the vision based systems to detect fire during surveillance using convolutional neural networks (CNNs). However, such methods generally need more computational time and memory, restricting its implementation networks. In this research paper, we propose a cost-effective detection CNN architecture for videos. model is inspired from GoogleNet architecture, considering reasonable complexity suitability intended problem compared other...
Convolutional neural networks (CNNs) have yielded state-of-the-art performance in image classification and other computer vision tasks. Their application fire detection systems will substantially improve accuracy, which eventually minimize disasters reduce the ecological social ramifications. However, major concern with CNN-based is their implementation real-world surveillance networks, due to high memory computational requirements for inference. In this paper, we propose an original,...
This paper presents a method for speech emotion recognition using spectrograms and deep convolutional neural network (CNN). Spectrograms generated from the signals are input to CNN. The proposed model consisting of three layers fully connected extract discriminative features spectrogram images outputs predictions seven emotions. In this study, we trained on obtained Berlin emotions dataset. Furthermore, also investigated effectiveness transfer learning pre-trained AlexNet model. Preliminary...
This paper proposes a secure surveillance framework for Internet of things (IoT) systems by intelligent integration video summarization and image encryption. First, an efficient method is used to extract the informative frames using processing capabilities visual sensors. When event detected from keyframes, alert sent concerned authority autonomously. As final decision about mainly depends on extracted their modification during transmission attackers can result in severe losses. To tackle...
Security of information during transmission is a major issue in this modern era.All the communicating bodies want confidentiality, integrity, and authenticity their secret information.Researchers have presented various schemes to cope with these Internet security issues.In context, both steganography cryptography can be used effectively.However, limitation existing steganographic methods lowquality output stego images, which consequently results lack security.To issues, we present an...
The agriculture sector faces crop losses every year due to diseases around the globe, which adversely affect food productivity and quality. Detecting identifying plant at an early stage is still a challenge for farmers, particularly in developing countries. Widespread use of mobile computing devices advancements artificial intelligence have created opportunities technologies assist farmers disease detection treatment. To this end, deep learning has been widely used plants with highly...
Vehicular Adhoc Networks (VANETs) enable vehicle-infrastructure communication, enhancing Intelligent Transportation Systems (ITS). Vehicles interconnect wirelessly to share information. Still, this communication is vulnerable various attacks, particularly in Vehicle-to-Vehicle (V2V) scenarios. This study proposes an Artificial Intelligence-based Intrusion Detection System (IDS) edge-envisioned environment, combining edge computing and deep learning. The approach uses the Technique for Order...
One of the primary cause blindness is Glaucoma. Although disease incurable but its symptoms can be minimized therefore early detection essential. Elevated intraocular pressure, gradual vision loss which a step towards blindness, structural damage to retina are marked Manually. It diagnosed by examination size, structure, shape optic disc and cup. In patient glaucoma Cup size increases while area remains same hence cup ratio (CDR) in patient. CDR area, provides basis for diagnosis glaucoma....
Wireless Sensor Networks (WSNs) are becoming ubiquitous in everyday life due to their applications weather forecasting, surveillance, implantable sensors for health monitoring and other plethora of applications. WSN is equipped with hundreds thousands small sensor nodes. As the size a node decreases, critical issues such as limited energy, computation time memory become even more highlighted. In case, network lifetime mainly depends on efficient use available resources. Organizing nearby...