Syed Sohail Ahmed

Syed Sohail Ahmed

Auto-generated profile, based on publicly available information

Syed Sohail Ahmed

Department of Computer Engineering, College of Computer, Qassim University, Buraydah, Kingdom of Saudi Arabia

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 August 2025 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
KLKai Li
Kai Li
CLConggai Li
Conggai Li
XYXin Yuan
Xin Yuan
SLShenghong Li
Shenghong Li
SZSai Zou
Sai Zou
ÖAÖzgür B. Akan
Özgür B. Akan
This article focuses on zero-trust foundation models (ZTFMs), a novel paradigm that embeds zero-trust security principles into the lifecycle of foundation models (FMs) for Internet of Things (IoT) systems. By integrating core tenets, such as least privilege access, continuous verification, data confidentiality, and behavioral analytics into the design, training, and deployment of FMs, ZTFMs can enable secure, privacy-preserving artificial intelligence (AI) across distributed, heterogeneous, and potentially adversarial IoT environments. We present the first structured synthesis of ZTFMs, identifying their potential to transform conventional trust-based IoT architectures into resilient, self-defending ecosystems. Moreover, we propose a comprehensive technical framework, incorporating federated learning (FL), blockchain-based identity management, micro-segmentation, and trusted execution environments (TEEs) to support decentralized, verifiable intelligence at the network edge. In addition, we investigate emerging security threats unique to ZTFM-enabled systems and evaluate countermeasures, such as anomaly detection, adversarial training, and secure aggregation. Through this analysis, we highlight key open research challenges in terms of scalability, secure orchestration, interpretable threat attribution, and dynamic trust calibration. This survey lays a foundational roadmap for secure, intelligent, and trustworthy IoT infrastructures powered by FMs.

30 January 2023 in Journal of Sensors
Verified
Journal Article
Open access
PDF file
SASyed Sohail Ahmed
Syed Sohail Ahmed
ZMZahid Mehmood
Zahid Mehmood
IAImran Ahmad Awan
Imran Ahmad Awan
RYRehan Mehmood Yousaf
Rehan Mehmood Yousaf
Handwritten digit recognition (HDR) shows a significant application in the area of information processing. However, correct recognition of such characters from images is a complicated task due to immense variations in the writing style of people. Moreover, the occurrence of several image artifacts like the existence of intensity variations, blurring, and noise complicates this process. In the proposed method, we have tried to overcome the aforementioned limitations by introducing a deep learning‐ (DL‐) based technique, namely, EfficientDet‐D4, for numeral categorization. Initially, the input images are annotated to exactly show the region of interest (ROI). In the next phase, these images are used to train the EfficientNet‐B4‐based EfficientDet‐D4 model to detect and categorize the numerals into their respective classes from zero to nine. We have tested the proposed model over the MNIST dataset to demonstrate its efficacy and attained an average accuracy value of 99.83%. Furthermore, we have accomplished the cross‐dataset evaluation on the USPS database and achieved an accuracy value of 99.10%. Both the visual and reported experimental results show that our method can accurately classify the HDR from images even with the varying writing style and under the presence of various sample artifacts like noise, blurring, chrominance, position, and size variations of numerals. Moreover, the introduced approach is capable of generalizing well to unseen cases which confirms that the EfficientDet‐D4 model is an effective solution to numeral recognition.

26 July 2022 in BioMed Research International
Verified
Journal Article
Open access
PDF file
AAArshiya Sajid Ansari
Arshiya Sajid Ansari
Abu Sarwar ZamaniAbu Sarwar Zamani
Abu Sarwar Zamani
MMMohammad Sajid Mohammadi
Mohammad Sajid Mohammadi
MEMeenakshi
Meenakshi
MRMahyudin Ritonga
Mahyudin Ritonga
KKKarthikeyan Kaliyaperumal
Karthikeyan Kaliyaperumal
A diagnosis of pancreatic cancer is one of the worst cancers that may be received anywhere in the world; the five‐year survival rate is very less. The majority of cases of this condition may be traced back to pancreatic cancer. Due to medical image scans, a significant number of cancer patients are able to identify abnormalities at an earlier stage. The expensive cost of the necessary gear and infrastructure makes it difficult to disseminate the technology, putting it out of the reach of a lot of people. This article presents detection of pancreatic cancer in CT scan images using machine PSO SVM and image processing. The Gaussian elimination filter is utilized during the image preprocessing stage of the removal of noise from images. The K means algorithm uses a partitioning technique to separate the image into its component parts. The process of identifying objects in an image and determining the regions of interest is aided by image segmentation. The PCA method is used to extract important information from digital photographs. PSO SVM, naive Bayes, and AdaBoost are the algorithms that are used to perform the classification. Accuracy, sensitivity, and specificity of the PSO SVM algorithm are better.

23 July 2025 in SLAS Technology
Verified
Journal Article
Open access
MWMuhammad Waqar
Muhammad Waqar
ZKZeshan Aslam Khan
Zeshan Aslam Khan
SKShanzey Tariq Khawaja
Shanzey Tariq Khawaja
NCNaveed Ishtiaq Chaudhary
Naveed Ishtiaq Chaudhary
SKSaadia Khan
Saadia Khan
MRMuhammad Asif Zahoor Raja
Muhammad Asif Zahoor Raja
Deep learning (DL) has had an incredible influence on many different scientific areas over the past couple of decades. Particularly in the field of healthcare, DL strategies were able to outclass other existing methodologies in image processing. The rapid expansion of the monkeypox endemic to over 40 nations apart from Africa has prompted serious worries in the realm of public health. Given that monkeypox can have symptoms that are akin to both chickenpox and measles, early detection can be difficult. Fortunately, due to the developments in artificial intelligence approaches, it can be implemented to promptly and accurately identify monkeypox disease using visual data information. Many DL driven techniques have already been exploited in the literature for skin related issues, which have provided accurate results to some extent. These models were dependent on extensive computational and time resources due to which the real-time applicability is difficult. Rather of building and training CNNs from scratch, this study uses transfer learning (TL) technique to fine-tune pre-trained networks, particularly exploiting various versions of ConvNeXt, by substituting last layer with additional task specific ones. A number of pre-processing and data augmentation methods have also been assessed and adjusted with regard to computing time and performance. The proposed study performs the binary and multi class monkeypox disease classification task. Promising accurate results of 99.9 % on the benchmark MSLD (binary class) dataset and 94 % on the MSLD v2.0 (multi-class) dataset is obtained by fine-tuned TL-based ConvNeXtSmall and ConvNeXtBase architecture with Adafactor optimization technique, demonstrating the practicality of the suggested framework as a substitute for the current ones. The proposed model is assessed through both standard train-test split and k-fold cross validation techniques. Furthermore, performance of models is also assessed on several other metrics including recall, F1 score, precision and multiple statistical tests incorporated with explainable AI methods for better interpretability of results. The concerns regarding the real-time applicability are tackled by utilizing the less time consuming and computationally efficient networks through the exploitation of transfer learning capabilities. Moreover, the explainable findings of the proposed study will be highly valuable for the healthcare professionals to understand the decisive behavior of the model and make informed clinical decisions.

11 March 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
SHSyed Muddusir Hussain
Syed Muddusir Hussain
JRJawwad Assistant Professor Sami Ur Rahman
Jawwad Assistant Professor Sami Ur Rahman
TNTayaba Naz
Tayaba Naz
FAFaraz Akram
Faraz Akram
SASyed Sohail Ahmed
Syed Sohail Ahmed
SNSadam Hussain Noorani
Sadam Hussain Noorani
Background/Objectives: The human brain regulates physiological processes, cognitive functions, and emotional responses. Brain-related conditions, such as neurological disorders, strokes, and tumors, are complex and pose significant challenges to medical professionals. Among these, brain tumors are particularly critical due to their impact on essential functions and the difficulty in achieving accurate diagnosis and classification. This study aims to explore the application of deep learning models in brain tumor image classification, focusing on improving diagnostic accuracy through model optimization. Methods: This research conducts a comparative analysis of four deep learning architectures: CNN, VGG-19, Inception V3, and ResNet-10. Each model's performance is evaluated on validation accuracy over ten epochs, both with and without hyper parameter tuning. Key hyper parameters, such as learning rate and optimizer selection, are adjusted to enhance model performance. Results: The CNN achieved a baseline validation accuracy of 77.86%, which improved to 89.31% after hyper parameter tuning. VGG-19, with tuning, reached a validation accuracy of 70.23%. ResNet-10 performed the worst, maintaining an accuracy of 51.91%, even with tuning. Inception V3 showed moderate performance, achieving a validation accuracy of 55.73%. The results highlight the significant impact of hyper parameter optimization on model accuracy. Conclusions: Fine-tuning hyper parameters and selecting appropriate models are critical to improving the accuracy of brain tumor classification. These findings provide insights into developing practical and efficient deep learning models, paving the way for advancements in diagnostic imaging, early detection, and clinical neuroscience.

4 December 2025 in IEEE Sensors Journal
Verified
Journal Article
Closed access
ARAasim Raheel
Aasim Raheel
DKDaud Khalid
Daud Khalid
SASyed Sohail Ahmed
Syed Sohail Ahmed
Technologies such as virtual reality, augmented reality, haptics, and sensory feedback systems play crucial roles in creating and delivering multiple sensorial media experiences. Tactile-enhanced audio-visual experiences represent an exciting frontier in immersive technology. By integrating tactile feedback with audio-visual stimuli, this approach aims to provide a more holistic sensory experience, enhancing immersion and realism in virtual environments. Tactile-audio-visual stimuli were generated by synchronizing conventional multimedia with a fan and a heater, while EEG, PPG, and GSR signals were acquired simultaneously. The study highlights the statistically significant differences in valence, arousal, and dominance between audio-visual and tactile-enhanced audio-visual contents. To evaluate emotional states, early and late feature fusion strategies are employed for the classification of valence, arousal, and dominance in response to the enriched digital content. Classifier-dependent feature selection is also applied to test the efficacy of the late feature fusion strategy. The proposed scheme shows better performance compared to prior emotion recognition studies on enhanced multimedia content, achieving higher accuracy and improved F-scores.