Bisma Amjad
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Bisma Amjad has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Pavlos I. Lazaridis
School of Computing and Engineering, University of Huddersfield, Huddersfield HD1 3DH, UK
3 shared publications - Faheem Ahmad Khan
School of Computing and Engineering, University of Huddersfield, Huddersfield, U.K.
2 shared publications - Qasim Zeeshan Ahmed
University of Huddersfield
2 shared publications Faheem Khan
University of Huddersfield
1 shared publicationFuhu Che
School of Computing and Engineering, University of Huddersfield,Huddersfield,UK
1 shared publicationMaryam Hafeez
University of Huddersfield
1 shared publication
Latest Publications
- 30 May 2024
- Published by Springer Nature
- p. 25-35
A Machine Learning Approach for Reliable Object Tracking
- 30 May 2024
- Published by Springer Nature
- p. 25-35
A Machine Learning Approach for Reliable Object Tracking
- 5 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-15
Deep Learning Approach for Optimal Localization Using an mm-Wave Sensor
Short-range indoor localization is one of the key necessities in automation industries and healthcare setups. With its increasing demand, the need for more precise positioning systems is rapidly increasing. Millimeter-wave (mm-wave) technology is emerging to enable highly precise localization performance. However, due to the limited availability of low-cost mm-wave sensors, it is challenging to accelerate research on real data. Furthermore, noise due to the hardware components of a sensor incurs perturbation in the received signal, which corrupts the estimation of range and the angle of arrival (AoA). Owing to the huge success of data-driven algorithms in solving regression problems, we propose a data-driven approach, which employs two deep learning (DL) based regression models i.e., dense neural network and convolutional neural network, and compare their performance with two machine learning based regression models, linear regression and support vector regression, to reduce errors in the estimate of AoA and range obtained via a mm-wave sensor. Our main goal is to optimize the localization measurements acquired from a low-cost mm-wave sensor for short-range applications. This will accelerate the development of proof of concepts and foster research on cost-effective mm-wave based indoor positioning systems. All experiments were conducted using over-the-air data collected with a mm-wave sensor, and the validity of the experiments was verified in unseen environments. The results obtained from our experimental evaluations, both for in-sample and out-of-sample testing, indicate improvements in the estimation of AoA and range with our proposed DL models. The improvements achieved were greater than 15% for AoA estimation and over 85% for range estimation compared to the baseline methods.
- 5 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 72 (00189456) , 1-15
Deep Learning Approach for Optimal Localization Using an mm-Wave Sensor
Short-range indoor localization is one of the key necessities in automation industries and healthcare setups. With its increasing demand, the need for more precise positioning systems is rapidly increasing. Millimeter-wave (mm-wave) technology is emerging to enable highly precise localization performance. However, due to the limited availability of low-cost mm-wave sensors, it is challenging to accelerate research on real data. Furthermore, noise due to the hardware components of a sensor incurs perturbation in the received signal, which corrupts the estimation of range and the angle of arrival (AoA). Owing to the huge success of data-driven algorithms in solving regression problems, we propose a data-driven approach, which employs two deep learning (DL) based regression models i.e., dense neural network and convolutional neural network, and compare their performance with two machine learning based regression models, linear regression and support vector regression, to reduce errors in the estimate of AoA and range obtained via a mm-wave sensor. Our main goal is to optimize the localization measurements acquired from a low-cost mm-wave sensor for short-range applications. This will accelerate the development of proof of concepts and foster research on cost-effective mm-wave based indoor positioning systems. All experiments were conducted using over-the-air data collected with a mm-wave sensor, and the validity of the experiments was verified in unseen environments. The results obtained from our experimental evaluations, both for in-sample and out-of-sample testing, indicate improvements in the estimation of AoA and range with our proposed DL models. The improvements achieved were greater than 15% for AoA estimation and over 85% for range estimation compared to the baseline methods.
- 6 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 72-76
Weighted Naive Bayes Approach for Imbalanced Indoor Positioning System Using UWB
The accuracy and reliability of an Ultra- WideBand (UWB) Indoor Positioning System (IPS) are compromised owing to the positioning error caused by the Non-Line-of-Sight (NLoS) signals. To address this, Machine Learning (ML) has been employed to classify Line-of-Sight (LoS) and NLoS components. However, the performance of ML algorithms degrades due to the disproportion of the number of LoS and NLoS signal components. A Weighted Naive Bayes (WNB) algorithm is proposed in this paper to mitigate this issue. The performance of the proposed algorithm is compared with conventional state-of-the-art ML algorithms such as K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Decision Tree (DT) using the Receiver Operating Characteristic (ROC) and Area Under the Curve (AUC). The results prove that the WNB classifier can significantly reduce the impact of the limited number of NLoS components that are available for training the model. The proposed WNB algorithm also maintains a high classification accuracy and robustness in mixed LoS/NLoS conditions.
- 6 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 72-76
Weighted Naive Bayes Approach for Imbalanced Indoor Positioning System Using UWB
The accuracy and reliability of an Ultra- WideBand (UWB) Indoor Positioning System (IPS) are compromised owing to the positioning error caused by the Non-Line-of-Sight (NLoS) signals. To address this, Machine Learning (ML) has been employed to classify Line-of-Sight (LoS) and NLoS components. However, the performance of ML algorithms degrades due to the disproportion of the number of LoS and NLoS signal components. A Weighted Naive Bayes (WNB) algorithm is proposed in this paper to mitigate this issue. The performance of the proposed algorithm is compared with conventional state-of-the-art ML algorithms such as K-Nearest Neighbor (KNN), Support Vector Machine (SVM), and Decision Tree (DT) using the Receiver Operating Characteristic (ROC) and Area Under the Curve (AUC). The results prove that the WNB classifier can significantly reduce the impact of the limited number of NLoS components that are available for training the model. The proposed WNB algorithm also maintains a high classification accuracy and robustness in mixed LoS/NLoS conditions.