Bilal Ashfaq Ahmed

ORCID: 0000-0002-3981-7558
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Generative Adversarial Networks and Image Synthesis
  • Digital Media Forensic Detection
  • Microgrid Control and Optimization
  • Smart Grid Energy Management
  • Islanding Detection in Power Systems
  • Gastrointestinal disorders and treatments
  • Human Pose and Action Recognition
  • Digital Imaging for Blood Diseases
  • Retinal Imaging and Analysis
  • Retinal Diseases and Treatments
  • Radiation Dose and Imaging
  • Face recognition and analysis
  • Advanced Radiotherapy Techniques
  • Hand Gesture Recognition Systems
  • Software-Defined Networks and 5G
  • Wireless Communication Networks Research
  • Research on Leishmaniasis Studies
  • Trypanosoma species research and implications
  • Gait Recognition and Analysis
  • Ear and Head Tumors
  • IPv6, Mobility, Handover, Networks, Security
  • Advanced Welding Techniques Analysis
  • Research Data Management Practices
  • Medical Imaging Techniques and Applications
  • Adversarial Robustness in Machine Learning

University of Technology Malaysia
2022-2024

University of Poonch Rawalakot
2023

University of Lahore
2014-2023

University of Azad Jammu and Kashmir
2023

Mehran University of Engineering and Technology
2021

Services Hospital
2019

COMSATS University Islamabad
2018

Eindhoven University of Technology
2013

University of Toronto
2010

Hospital for Sick Children
2010

Abstract Advancements in facial manipulation technology have resulted highly realistic and indistinguishable face expression swap videos. However, this has also raised concerns regarding the security risks associated with deepfakes. In field of multimedia forensics, detection precise localization image forgery become essential tasks. Current deepfake detectors perform well high-quality faces within specific datasets, but often struggle to maintain their performance when evaluated across...

10.1186/s13640-023-00614-z article EN cc-by EURASIP Journal on Image and Video Processing 2023-08-18

Our aim was to estimate the cumulative effective doses (CEDs) from radiologic procedures for a cohort of pediatric oncology patients.A retrospective study imaging histories 150 patients (30 each in 5 subgroups, that is, leukemia, lymphomas, brain tumors, neuroblastomas, and assorted solid tumors) years after diagnosis performed. All involving ionizing radiation were recorded, including radiography, computed tomography (CT), nuclear medicine (NM) studies, fluoroscopy, interventional...

10.1542/peds.2009-2675 article EN PEDIATRICS 2010-09-28

Abstract Objectives To design and develop a classifier, named Sewing Driving Training based Optimization-Deep Residual Network (SDTO_DRN) for hand gesture recognition. Methods The electrical activity of forearm muscles generates the signals that can be captured with Surface Electromyography (sEMG) sensors includes meaningful data decoding both muscle actions movement. This research develops an efficacious scheme recognition using SDTO_DRN. Here, signal pre-processing is done through Gaussian...

10.1515/bmt-2023-0208 article EN Biomedical Engineering / Biomedizinische Technik 2024-03-08

Despite concerns regarding ionizing radiation exposures from diagnostic imaging procedures in pediatric patients, many are deemed unavoidable or even mandated by treatment protocols. A prior review at our institution found patients with lymphoma had a higher median cumulative exposure (191 mSv) versus other oncology subgroups (61 mSv).Estimations of were tabulated for 5 years the first scan 30 consecutive diagnosed 2001. Each individual procedure was reviewed and classified as protocol...

10.1002/pbc.22575 article EN Pediatric Blood & Cancer 2010-05-27

DC microgrids look attractive in distribution systems due to their high reliability, efficiency, and easy integration with renewable energy sources. The key objectives of the microgrid include proportional load sharing precise voltage regulation. Droop controllers are based on decentralized control architectures which not effective achieving these simultaneously error power variation. A centralized controller can achieve using a speed communication link. However, it loses reliability single...

10.1155/2018/2717129 article EN Mathematical Problems in Engineering 2018-01-01

Age related Macular degeneration (AMD) is an ocular disease caused by the extracellular material deposit at retinal pigment level known as drusen. AMD major cause of gradual vision loss. Early detection can be helpful to prevent blindness. Automatic fundus image analysis plays important role for early diagnose AMD. In this paper a novel method presented soft and hard After preprocessing step proposed computes color Gabor filter based features each pixel classify extract all possible drusen...

10.1109/iciafs.2014.7069581 article EN 2014-12-01

The current surge in hyper-realistic faces created artificially using DeepFakes necessitates media forensics solutions suited to video streams and perform reliably with a low false alarm rate at the level. paper proposes spatial temporal aware pipeline detect DeepFake videos automatically. Our method employed two-stream convolutional neural network extract local features independently. These are then fed fully connected layers classify whether has been subject manipulation. proposed...

10.1109/icprs54038.2022.9853853 article EN 2022-06-07

Automatic screening and diagnosis of ocular disease through fundus images are in place considered worldwide. One the leading sight loosing known as age related macular degeneration (AMD) has many proposed automatic systems. These systems detect yellow bright lesion number their size is graded advance earlier stage. It becomes difficult for these to differentiate drusens from exudates another associated with Diabetic retinopathy. two lesions look similar on retinal surface. Differentiating...

10.1109/his.2014.7086193 article EN 2014-12-01

The intermittent nature of wind flow hinders the effective prediction power generation, causing imbalances between estimated and actual values. Therefore, large-scale integration generation is limited by its consequences to whole system. This paper focuses on a two-step approach mitigate imbalance caused energy sources in electric grid. First, an artificial neural network based forecasting tool will be developed for short-term that aims quantify imbalance. In second step, agent-aggregator...

10.1109/upec.2013.6714962 article EN 2022 57th International Universities Power Engineering Conference (UPEC) 2013-09-01

DC microgrids are gaining popularity due to their lack of reactive power compensation, frequency synchronization, and skin effect problems. However, not exempted from stability issues. The based on decentralized architecture is presented in this paper. Centralized can degrade system performance reliability the failure a single central controller. Droop with proportional integral (PI) controller being used for microgrid stability. droop control requires tradeoff between voltage regulation...

10.3390/engproc2021012023 article EN cc-by 2021-12-23

This research paper aims to find the performance difference of 3Com Core Builder 3500 Switch and Cisco 3550 Multilayer switch at various levels. There are 5 test beds designed these devices individual level then compare against each other. The topology used perform tests very simple easy implement. Though collecting samples is easy, however it time consuming. data capture in all done using network analyzer tool, Wireshark file transfer application called as FileZilla Server Client. These...

10.1109/iswsn.2017.8250041 article EN 2017-11-01

Abstract Digital media forensics focuses heavily on the detection of altered photos and videos. The likelihood an image being is often determined by a approach using binary classi cation. key problem identifying parts that have been (i.e., performing segmentation). We propose attention-based to improve process feature maps for cation localization tasks. learned attention show areas contain useful information give visual representation manipulated regions, which improves (real face vs. fake...

10.21203/rs.3.rs-2198055/v1 preprint EN cc-by Research Square (Research Square) 2022-11-29

One of the emerging problems deep learning technology is deepfake videos with easy access to powerful and inexpensive computing power; The internet littered fake material like photos, videos, audios. People's identities, privacy reputations are at risk due widespread proliferation media content. Since can have a potentially destructive effect on society, establishing their legitimacy crucial. Thus, we investigate different attention mechanisms in this paper for detection. In responsible...

10.1145/3631991.3632037 article EN 2023-09-22

There are several pathologies causing intussusception. Benign diseases the typical causes for childhood bowel obstruction. However, malignant or adhesive common in adults. Although cases of illeal intussusception adults due to inflammatory fibroid polyp is quite rare but few has been reported literature. A 35 year old presented with a history multiple episodes abdominal pain, distention, relative constipation and vomiting over period 3 month. He also had appendectomy 2 months back....

10.29309/tpmj/2019.26.04.3350 article EN The Professional Medical Journal 2019-04-09
Coming Soon ...