Hashmat Fida

Dr. Hashmat Fida

Computer Science & Engineering, Presidency University, Bengaluru, India
orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
23 August 2024
Verified
Conference Paper
Closed access
ASAjay Pal Singh
Ajay Pal Singh
PRParvez Rahi
Parvez Rahi
BSBharti Sahu
Bharti Sahu
NBNirmalya Basu
Nirmalya Basu
Hashmat FidaHashmat Fida
Hashmat Fida
VYVikash Yadav
Vikash Yadav
This work offers a methodical approach to detecting road signs using CNN, deep learning, and algorithms. As a one-unit regression problem, the object detection problem is defined as follows: probability classes and straight image pixels to bounding box coordinates. Many innovative ideas that are implemented to make our lives simpler and faster than they were in the past have been brought about by the rapid modernization. The Road Sign Detection Technique is one such technique. With this method, all it takes to make a forecast is a quick glance at the picture or sign. This is similar to image classification which uses Convolutional Neural Networks and makes use of AI-powered algorithms. The concept is described as the signs to be detected with the help of some rules that define the color, shape and the region where the signs are spotted. The paper describes YOLO (You Only Look Once) is a concept that is a modern approach to object detection. The object detection issue might be seen as a one-unit regression problem, with the solution representing the straight image pixels to the bounding box coordinates and class probabilities. Utilizing this method, you we can predict something just on a quick glance at the picture or sign.

31 August 2025 in ASEAN Engineering Journal
Verified
Journal Article
Open access
PDF file
Hashmat FidaHashmat Fida
Hashmat Fida
HSHarsh Sadawarti
Harsh Sadawarti
BMBinod Kumar Mishra
Binod Kumar Mishra
VTVibha Tiwari
Vibha Tiwari
Traffic congestion has become a critical issue in urban areas worldwide, leading to increased accidents and delays for emergency vehicles. This paper proposes a solution utilizing IoT-enabled technology to alleviate these challenges by implementing "Green Corridors" for emergency vehicles. By leveraging Intelligent Traffic Management Systems (ITMS), which integrate sensors, cameras, and data analysis, this research aims to evaluate the effectiveness of such systems in reducing congestion and improving road safety. A comprehensive evaluation framework will be employed to analyze the impact of ITMS implementation on traffic flow patterns and safety outcomes. The system utilizes UWB technology to identify emergency vehicles, triggering traffic lights to switch to green and notifying nearby vehicles to clear lanes, facilitating unimpeded passage for emergency services. This integrated approach addresses the dual challenges of traffic congestion and emergency response, offering valuable insights for policymakers and urban planners seeking effective solutions for smart city transportation management.

6 March 2025
Verified
Conference Paper
Closed access
ARAshish Ranjan
Ashish Ranjan
SNSnigdha Naskar
Snigdha Naskar
VBVaibhav Bajaj
Vaibhav Bajaj
DKDeepak Kumar
Deepak Kumar
Hashmat FidaHashmat Fida
Hashmat Fida
This work suggests a new model for identifying skin diseases by combining deep learning and machine learning models in a complementary way. When these methods are used in tandem, they improve the precision and effectiveness of diagnosing a variety of skin disorders. CNNs (Convolutional Neural Networks), in particular, are used in DL(deep learning) models for feature extraction because of their ability to recognize and extract relevant characteristics from complex skin images automatically. To classify the skin conditions, these features are then passed through several kinds of machine learning classification models, such as Random Forests, SVM (Support Vector Machines), and KNN (k-nearest Neighbors). The combination of deep learning and conventional machine learning techniques provides a solid framework that draws on the benefits of each methodology. Machine learning classification algorithms offer flexibility and clarity in the decision-making process, whereas deep learning models are useful in identifying complex patterns in image data. This combination increases the system’s capacity to generalize across various skin disease types and improves diagnostic accuracy. The experimental results, which demonstrate noticeable improvements in important performance metrics like accuracy, precision, and F1-score, highlight the effectiveness of the proposed strategy. The system performs better at distinguishing between related skin conditions that are frequently difficult to diagnose by implementing this hybrid approach. This study includes increasing research on AI-driven healthcare solutions, giving dermatologists and other medical professionals a more efficient and reliable tool for diagnosing skin diseases. This study ultimately shows how deep learning and machine learning models can be combined to produce more advanced and precise medical imaging diagnostic systems. Our method demonstrated its potential for real-world implementation with a noteworthy accuracy of 0.97 using the MSCV(Mobilenet Svm Cross Validation) model.


1 April 2026
Verified
Conference Paper
Closed access
Hashmat FidaHashmat Fida
Hashmat Fida
FKFaizan Anwar Khan
Faizan Anwar Khan
MHManindra S Hanspal
Manindra S Hanspal
SSShaffy Shaffy
Shaffy Shaffy
RYRahul Yadav
Rahul Yadav

1 October 2025
Verified
Book Chapter
Closed access
PDF file
SKShivansh Kumar
Shivansh Kumar
SPShive Prakash
Shive Prakash
CGChhavin Gaur
Chhavin Gaur
Hashmat FidaHashmat Fida
Hashmat Fida