- Social Robot Interaction and HRI
- Mental Health Research Topics
- Cognitive Radio Networks and Spectrum Sensing
- Wireless Communication Networks Research
- Chaos-based Image/Signal Encryption
- Emotions and Moral Behavior
- Emotion and Mood Recognition
- Decision-Making and Behavioral Economics
- Opinion Dynamics and Social Influence
- AI in cancer detection
- Big Data and Business Intelligence
- Cryptographic Implementations and Security
- Complex Systems and Time Series Analysis
- COVID-19 epidemiological studies
- Digital Mental Health Interventions
- Advanced Steganography and Watermarking Techniques
- Coding theory and cryptography
- Mathematical and Theoretical Epidemiology and Ecology Models
- Data Quality and Management
- Advanced Malware Detection Techniques
- Sentiment Analysis and Opinion Mining
- Advanced Neural Network Applications
- Reinforcement Learning in Robotics
- AI in Service Interactions
- Digital Media Forensic Detection
Quaid-i-Azam University
2010-2022
Vrije Universiteit Amsterdam
2007-2012
Advanced Media Research (United States)
2010
Prostate cancer (PCa) is a severe type of and causes major deaths among men due to its poor diagnostic system. The images obtained from patients with carcinoma consist complex necessary features that cannot be extracted readily by traditional techniques. This research employed deep learning long short-term memory (LSTM) Residual Net (ResNet - 101), independent hand-crafted features, fine-tuned. results were compared such as texture, morphology, gray level co-occurrence matrix (GLCM) using...
The protection of digital content is increasingly becoming a significant issue for researchers and engineers.In this context, nonlinear dynamic systems play vital role in information security through their chaotic behavior susceptibility to initial conditions.This research presents 3D mapbased symmetric algorithm multiple images improve encryption efficiency encourage secure transmission.The proposed scheme comprises the following four modules: combination (the are combined into single image...
Massive advances in internet infrastructure are impacting e-healthcare services compared to conventional means. Therefore, extra care and protection is needed for extremely confidential patient medical records. With this intention, we have proposed an enhanced image steganography method, improve imperceptibility data hiding capacity of stego images. The Image Region Decomposition (IRD) embeds more secret information with better imperceptibility, patient's algorithm decomposes the grayscale...
Electronic devices are integral part of our life and modeling their lifetime is the most challenging interesting field in reliability analysis. To investigate failure behavior electronic analysis commonly used. In literature, however, it reported that one five device a result corrosion to save electricity predict future failures, important summarize data by some flexible probability models. This will not only help companies, but also users providing them information about maximum voltage...
With the growth of networks, Internet Things (IoT) and new cyber attacks pose threats to privacy security, secure communication is therefore becoming one most crucial concerns. For this purpose, symmetric algorithms namel; The Rijndael algorithm, Serpent TWOFISH algorithm pay equal attention. In paper, algorithm's mathematical complexity improved by using substitution boxes (S-boxes) drawn from a multiplicative group units chain ring Σ <sub xmlns:mml="http://www.w3.org/1998/Math/MathML"...
Social media is a vital source to produce textual data, further utilized in various research fields. It has been considered an essential foundation for organizations get valuable data assess the users’ thoughts and opinions on specific topic. Text classification procedure assign tags predefined classes automatically based their contents. The aspect-based sentiment analysis classify text challenging. Every work related approached this issue as current usually discusses document-level overall...
With dynamic changes in world's technology, an increasing growth and adoption observed the usage of social media, computer networks, internet things, cloud computing. Research experiments are also generating huge amount data which to be collected, managed analyzed. This is known as "Big Data". analysts have perceived increase that contains both useful useless entities. In extraction information, warehouse finds difficulties enduring with generated. shifts paradigm, big analytics emerged...
Emotions in speech provide a lot of information about the speaker’s emotional state. This paper presents classification emotions using support vector machine (SVM) with Mel Frequency Cepstrum Coefficient (MFCC) features extracted from voice signal. We have considered following five emotions, namely anger, happy, neutral, pleasant surprise and sadness, for purposes. The proposed methodology, including SVM-Gaussian SVM-Quadratic, is tested its performance on Toronto Emotion Speech Set (TESS)...
With dynamic changes in world's technology, an increasing growth and adoption observed the usage of social media, computer networks, internet things, cloud computing. Research experiments are also generating huge amount data which to be collected, managed analyzed. This is known as "Big Data". analysts have perceived increase that contains both useful useless entities. In extraction information, warehouse finds difficulties enduring with generated. shifts paradigm, big analytics emerged...
Artificially intelligent (AI) game software incorporates different algorithms to generate human-like responses the users playing them. Testing AI poses great difficulty because of complex possibilities that can result at a given point and analysis said is tedious task. Also during development there are resource constraints due which testing targets specific parts software. An Chess takes into consideration large amount possible outcomes any before deciding move. Therefore, it in its entirety...
To create a robot with mind of its own, we extended formalized version model that explains affect-driven interaction mechanisms for goal-directed behavior. We ran simulation experiments intelligent software agents and found preferred decision options to rational in situations where choices low expected utility are irrational. This behavior counters current models making, which generally have hedonic bias always select the option highest utility.
This paper addresses comparative evaluation of population-based simulation in comparison to agent-based for different numbers agents. Population-based simulation, such as example the classical approaches predator-prey modelling and epidemics, has computational advantages over with large Therefore latter can be considered useful only when results are expected deviate from more realistic. However, there is sometimes also a silent assumption that larger agents, simulations approximate...
The wireless networks face challenges in efficient utilization of bandwidth due to paucity resources and lack central management, which may result undesired congestion. cognitive radio (CR) paradigm can bring efficiency, better bandwidth, appropriate management limited resources. While the CR is an attractive choice, CRs selfishly compete acquire utilize available that ultimately inappropriate power levels, causing degradation network’s Quality Service (QoS). A cooperative game theoretic...
Being the only nonlinear component in many cryptosystems, an S-box is integral part of modern symmetric ciphering techniques that creates randomness and increases confidentiality at substitution stage encryption. The ability to construct a cryptographically strong solely depends on its construction scheme. primary purpose encryption standards establish confusion between <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math...
Affect modeling plays a vital role in faithfully simulating human emotion and emotionally evocative technology. Current affect models are still strong simplifications compared to affective complexity. To establish richer agent interaction, we integrated three affect-related models: CoMERG, IPEFiC ADM EMA. These partly overlap, where distinct, they complement one another. The model called Silicon Coppélia was implemented simulation experiments were performed test the behavior of model. show...