Papers by BILAL SHABBIR QAISAR
Muhamamd Ali Shahid, 2025
Imaging techniques are widely used for medical diagnostics. This can sometimes lead to a real bot... more Imaging techniques are widely used for medical diagnostics. This can sometimes lead to a real bottleneck when there is a shortage of medical practitioners, and the images must be manually processed. In such a situation, there is a need to reduce the amount of manual work by automating part of the analysis. In this study, we investigate the potential of a machine-learning algorithm for trauma detection in medical image processing. A new method called ResNet50V2 was developed on the trauma dataset to detect trauma disease. We compare the results of the new method analysis with other state-of-the-art networks. The proposed base model, ResNet50V2, received a score of 99.40%.
Muhammad Ali Shahid, 2025
In today's expanding and densely populated world, it's crucial to design an automatic intelligent... more In today's expanding and densely populated world, it's crucial to design an automatic intelligent garbage sorter machine that uses advanced sensors. Garbage picture classification is a fundamental computer vision problem that must be solved before sensors can be included in this system. This research presents a model for autonomous trash classification using deep learning that can be applied in high-tech garbage sorting equipment. The 2,527 photos in the rubbish dataset are categorized into six types: trash, cardboard, glass, metal, paper, and plastic. The next step is the creation of GD-DLM, a deep learning model for garbage categorization that is an upgrade from Xception and DenseNet121 models. At last, the tests are run to evaluate GD-DLM against the best-of-breed approaches to garbage classification. The suggested Xception and DenseNet-121 models scored 92.11% and 88.63%, respectively, compared to the baseline accuracy.
Springer Nature Link (Multimedia Tools and Applications), 2024
Digital tools have greatly improved the detection and diagnosis of oral and dental disorders like... more Digital tools have greatly improved the detection and diagnosis of oral and dental disorders like cancer and gum disease. Lip or oral cavity cancer is more likely to develop in those with potentially malignant oral disorders. A potentially malignant disorder (PMD) and debilitating condition of the oral mucosa, oral submucous fibrosis (OSMF), can have devastating effects on one's quality of life. Incorporating deep learning into diagnosing conditions affecting the mouth and oral cavity is challenging. Mouth and Oral Diseases Classification using InceptionResNetV2 Method was established in the current study to identify diseases such as gangivostomatitis (Gum), canker sores (CaS), cold sores (CoS), oral lichen planus (OLP), oral thrush (OT), mouth cancer (MC), and oral cancer (OC). The new collection, termed "Mouth and Oral Diseases" (MOD), comprises seven distinct categories of data. Compared to state-of-the-art approaches, the proposed InceptionResNetV2 model's 99.51% accuracy is significantly higher. Keywords InceptionResNetV2 • Mouth diseases • Mouth and oral diseases dataset • Oral diseases • Teeth diseases * Muhammad Faheem
International Journal of Innovative Science and Research Technology, 2023
Communication always needs privacy and security for many reasons and hence it increases the need ... more Communication always needs privacy and security for many reasons and hence it increases the need for securing the secret message. Image steganography is the process of concealing secret media within any format of the transmitter. In image steganography, a cover image is used in both the embedding and extracting processes. Through a systematic literature review, we have an analyzed mage steganography technique. We also have presented advantages and weaknesses along with some applications i.e., LSB, PNSR, DWT, 3D images steganography. The main challenges of image steganography in spatial and transform domains are presented. In the end, findings for future scope are also presented.
Journal of Machine Learning and Deep Learning (JMLDL), 2025
Especially common in nations of low and moderate-income, mouth disease was responsible for 177,38... more Especially common in nations of low and moderate-income, mouth disease was responsible for 177,384 fatalities worldwide in 2018. A cold sore is mild blistering of the lips or mouth area. Herpes simplex virus causes them, and they go away on their own in 7-10 days. Generally, the first three to four days of a canker sore are the most excruciating. Within 6-24 hours, the ulcer changes from a red, inflamed patch to a slight, circular depression of 3-9 mm in diameter. Canker sores cause tingling or burning before they become noticeable, but the pain subsides, and the sore heals in 10-14 days, generally without scarring. If canker and cold sores in the mouth could be automatically identified, early and cheap diagnosis of the condition could be achieved. Canker sores and cold sores are only two of the many oral disorders that can be detected and diagnosed using modern digital technologies. Diagnosing oral illnesses with deep learning is challenging. In this research, we used two classes, canker sores and cold sores, to build a novel technique. A new dataset, dubbed "Mouth Disease" (MD), has been created, and it splits diseases into two groups. An application of the Xception model is used to categorise the illness. Compared to previous approaches, the suggested Xception model showed superior performance, with an accuracy of 99.60%.
International Journal of Innovative Science and Research Technology, 2025
Imaging techniques are widely used for medical diagnostics. This can sometimes lead to a real bot... more Imaging techniques are widely used for medical diagnostics. This can sometimes lead to a real bottleneck when there is a shortage of medical practitioners, and the images must be manually processed. In such a situation, there is a need to reduce the amount of manual work by automating part of the analysis. In this study, we investigate the potential of a machine-learning algorithm for trauma detection in medical image processing. A new method called ResNet50V2 was developed on the trauma dataset to detect trauma disease. We compare the results of the new method analysis with other state-of-the-art networks. The proposed base model, ResNet50V2, received a score of 99.40%.
International Journal of Innovative Science and Research Technology, 2025
In today's expanding and densely populated world, it's crucial to design an automatic intelligent... more In today's expanding and densely populated world, it's crucial to design an automatic intelligent garbage sorter machine that uses advanced sensors. Garbage picture classification is a fundamental computer vision problem that must be solved before sensors can be included in this system. This research presents a model for autonomous trash classification using deep learning that can be applied in high-tech garbage sorting equipment. The 2,527 photos in the rubbish dataset are categorized into six types: trash, cardboard, glass, metal, paper, and plastic. The next step is the creation of GD-DLM, a deep learning model for garbage categorization that is an upgrade from Xception and DenseNet121 models. At last, the tests are run to evaluate GD-DLM against the best-of-breed approaches to garbage classification. The suggested Xception and DenseNet-121 models scored 92.11% and 88.63%, respectively, compared to the baseline accuracy.
Proceedings of the Pakistan Academy of Sciences: A. Physical and Computational Sciences
Now a days, energy is an essential resource as the number of energy resources are sinking day by ... more Now a days, energy is an essential resource as the number of energy resources are sinking day by day. Movement Aware Smart Street light is a simple yet powerful concept, which uses transistor as a switch and replaces the manual system. It instantly switches the lights ON when the sunlight goes below the visible region. As energy is the scarcest source, this requires finding innovative ways to use it efficiently. Big cities consume a large amount of electricity and it is required to save energy by operating the street-lights at the time of need. In this paper, an effective method of street-light operation is presented which detects the sun set and sun rise alongside detection of vehicle movement on roads to utilise the energy only when it is required. Furthermore, a system is proposed which reduces energy consumption by replacing manually operated street-lights as they are not switched OFF even the sunlight appears and also switched ON earlier before sunset. The proposed mehtod has s...
Uploads
Papers by BILAL SHABBIR QAISAR