Mir Sajjad Hussain TALPUR

Dr. Mir Sajjad Hussain TALPUR


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
5 March 2024 in Sensors
Verified
Journal Article
Open access
PDF file
FTFauzia Talpur
Fauzia Talpur
IKImtiaz Ali ALi KOREJO
Imtiaz Ali ALi KOREJO
ACAftab A. Chandio
Aftab A. Chandio
AGAli Ghulam
Ali Ghulam
MTMir Sajjad Hussain TALPUR
Mir Sajjad Hussain TALPUR
The escalating reliance of modern society on information and communication technology has rendered it vulnerable to an array of cyber-attacks, with distributed denial-of-service (DDoS) attacks emerging as one of the most prevalent threats. This paper delves into the intricacies of DDoS attacks, which exploit compromised machines numbering in the thousands to disrupt data services and online commercial platforms, resulting in significant downtime and financial losses. Recognizing the gravity of this issue, various detection techniques have been explored, yet the quantity and prior detection of DDoS attacks has seen a decline in recent methods. This research introduces an innovative approach by integrating evolutionary optimization algorithms and machine learning techniques. Specifically, the study proposes XGB-GA Optimization, RF-GA Optimization, and SVM-GA Optimization methods, employing Evolutionary Algorithms (EAs) Optimization with Tree-based Pipelines Optimization Tool (TPOT)-Genetic Programming. Datasets pertaining to DDoS attacks were utilized to train machine learning models based on XGB, RF, and SVM algorithms, and 10-fold cross-validation was employed. The models were further optimized using EAs, achieving remarkable accuracy scores: 99.99% with the XGB-GA method, 99.50% with RF-GA, and 99.99% with SVM-GA. Furthermore, the study employed TPOT to identify the optimal algorithm for constructing a machine learning model, with the genetic algorithm pinpointing XGB-GA as the most effective choice. This research significantly advances the field of DDoS attack detection by presenting a robust and accurate methodology, thereby enhancing the cybersecurity landscape and fortifying digital infrastructures against these pervasive threats.

1 January 2025 in Social Science Review Archives
Verified
Journal Article
Open access
PDF file
SBSantosh Kumar Banbhrani
Santosh Kumar Banbhrani
MAMuhammad Naeem Akhter
Muhammad Naeem Akhter
FNFozia Noureen
Fozia Noureen
MTMir Sajjad Hussain TALPUR
Mir Sajjad Hussain TALPUR
The paper aims at assessing the role of Artificial Intelligence in healthcare innovation through considering its roles in individualized treatment, diagnosing systems, and drug discovery as well as surgical robots. In this context, the analyzed AI technologies provide progressive developments which answer the traditional global problems of the healthcare industry, such as the increasing need for personalized therapies and the complex medical care organization. Machine learning and other AI techniques provide the ability to interpret large amounts of patient-specific data, including genetic makeup and lifestyle, to assist in arriving at treatment regimens that will enhance outcomes in treatment resistant diseases such as cancer. Diagnostic tools have progressed tremendously in recent years due to Machine learning and deep learning advancement in algorithms such as Convolutional neural networks (CNNs) for medical imaging and disease diagnosis and detection have significantly been enhanced. Moreover, it continues working on drug discovery by pointing out probable therapeutic applications and optimizing clinical trials. AI is beneficial to robotic surgery; machines used in operating rooms come with advanced AI ability, thus improving their performance. This research highlights the wonderful possibilities of AI to transform the healthcare systems and provide a better chance for improvement in the medical services delivery and to use the resources effectively.

30 August 2022 in Molecules
Verified
Journal Article
Open access
PDF file
HTHira Sajjad Talpur
Hira Sajjad Talpur
ZRZia ur Rehman
Zia ur Rehman
Mostafa GoudaMostafa Gouda
Mostafa Gouda
ALAixin Liang
Aixin Liang
IBIqra Bano
Iqra Bano
Liguo YangLiguo Yang
Liguo Yang
Inhibin is a molecule that belongs to peptide hormones and is excreted through pituitary gonadotropins stimulation action on the granulosa cells of the ovaries. However, the differential regulation of inhibin and follicle-stimulating hormone (FSH) on granulosa cell tumor growth in mice inhibin-deficient females is not yet well understood. The objective of this study was to evaluate the role of inhibin and FSH on the granulosa cells of ovarian follicles at the premature antral stage. This study stimulated immature wild-type (WT) and Inhibin-α knockout (Inha−/−) female mice with human chorionic gonadotropin (hCG) and examined hCG-induced gene expression changes in granulosa cells. Also, screening of differentially expressed genes (DEGs) was performed in the two groups under study. In addition, related modules to external traits and key gene drivers were determined through Weighted Gene Co-Expression Network Analysis (WGCNA) algorithm. The results identified a number of 1074 and 931 DEGs and 343 overlapping DEGs (ODEGs) were shared in the two groups. Some 341 ODEGs had high relevance and consistent expression direction, with a significant correlation coefficient (r2 = 0.9145). Additionally, the gene co-expression network of selected 153 genes showed 122 nodes enriched to 21 GO biological processes (BP) and reproduction and 3 genes related to genomic pathways. By using principal component analysis (PCA), the 14 genes in the regulatory network were fixed and the cumulative proportion of fitted top three principal components was 94.64%. In conclusion, this study revealed the novelty of using ODEGs for investigating the inhibin and FSH hormone pathways that might open the way toward gene therapy for granulosa cell tumors. Also, these genes could be used as biomarkers for tracking the changes in inhibin and FSH hormone from the changes in the nutrition pattern.

15 January 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
FTFauzia Talpur
Fauzia Talpur
IKImtiaz Ali ALi KOREJO
Imtiaz Ali ALi KOREJO
ACAftab A. Chandio
Aftab A. Chandio
AGAli Ghulam
Ali Ghulam
MTMir Sajjad Hussain TALPUR
Mir Sajjad Hussain TALPUR
The escalating reliance of modern society on information and communication technology has rendered it vulnerable to an array of cyber-attacks, with distributed denial-of-service (DDoS) at-tacks emerging as one of the most prevalent threats. This paper delves into the intricacies of DDoS attacks, which exploit compromised machines numbering in the thousands or more to disrupt data services and online commercial platforms, resulting in significant downtime and financial losses. Recognizing the gravity of this issue, various detection techniques have been explored, yet the quantitative and prior detection of DDoS attacks has seen a decline in recent methods. This research introduces an innovative approach by integrating evolutionary optimization algorithms and machine learning techniques. Specifically, the study proposes XGB-GA Optimization, RF-GA Optimization, and SVM-GA Optimization methods, employing Evolutionary Algorithms Opti-mization with TOPOT-Genetic Programming. Datasets pertaining to DDoS attacks were utilized to train machine learning models based on XGB, RF, and SVM algorithms, and 10-fold cross-validation was employed. The models were further optimized using evolutionary algo-rithms, achieving remarkable accuracy scores: 99.99% with the XGB-GA method, 99.50% with RF-GA, and 99.99% with SVM-GA. Furthermore, the study employed TPOT to identify the optimal algorithm for constructing a machine learning model, with the genetic algorithm pinpointing XGB-GA as the most effective choice. This research significantly advances the field of DDoS attack detection by presenting a robust and accurate methodology, thereby enhancing the cybersecurity landscape and fortifying digital infrastructures against these pervasive threats.

13 September 2026 in Electronics
Verified
Journal Article
Open access
PDF file
ZNZeeshan Ahmed Nizamani
Zeeshan Ahmed Nizamani
MTMir Sajjad Hussain TALPUR
Mir Sajjad Hussain TALPUR
PBPinial Khan Butt
Pinial Khan Butt
RBRiaz Ali Buriro
Riaz Ali Buriro
Catastrophic forgetting is a major challenge for deep learning models when they are incrementally trained on a sequence of new data. Reducing this forgetting in image and video data has been the primary research focus, but less attention has been given to textual domains, where discrete token distributions and semantic shifts occur across different topics. Furthermore, standalone strategies proposed for reducing catastrophic forgetting still have room for improvement. To this end, this paper proposes a synergy of stratified memory replay with parameter regularization for a BiLSTM-based incremental learning model to mitigate catastrophic forgetting in sequential text datasets. The stratified replay mechanism replays a small buffer of historical data samples into current training phases to preserve the old data patterns, while the parameter regularization penalizes modifications to the neural network weights crucial to the past tasks. The proposed approach is evaluated in an incremental training pipeline on distinct textual datasets, including software bug reports (Task A), a news dataset (Task B), and emails (Task C). The evaluation results demonstrate that the baseline neural network experiences catastrophic forgetting as its initial dataset (Task A) accuracy drops from 87.53% to 11.75%. The standalone experience replay approach manages to retain Task A accuracy at 80.01%, down from its peak of 86.56%, while for Task B, it achieves 93.97%, down from the peak of 98.37%. The buffer sensitivity analysis indicates the model accuracy improves with increasing replay buffer size. The parameter regularization approach effectively reduces catastrophic forgetting, but it remains less effective for disruptive text distribution sequences, resulting in noticeable forgetting on prior tasks and reduced plasticity on later tasks. Evaluations of this approach show that Task A accuracy is reduced from 87.87% to 71.09% after training on Task C. The proposed hybrid approach reduces forgetting and preserves Task A and Task B accuracies at 83.73% and 95.04%, respectively. Thus, the empirical evaluations demonstrate that the proposed approach is effective and outperforms the standalone experience replay strategy and parameter regularization, limiting the forgetting on the earliest task to just 4.65% compared to 6.55% forgetting of the replay-based method, while allowing enough plasticity for the final task to reach 98.92% accuracy.