Muhammad Shadab Alam Hashmi

Mr. Muhammad Shadab Alam Hashmi

Khwaja Fareed University of Engineering and IT, Rahimyar Khan, Punjab, Pakistan
orcid

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
3 March 2022 in Sensors
Verified
Journal Article
Open access
PDF file
Muhammad Shadab Alam HashmiMuhammad Shadab Alam Hashmi
Muhammad Shadab Alam Hashmi
MIMuhammad Ibrahim
Muhammad Ibrahim
IBImran Sarwar Bajwa
Imran Sarwar Bajwa
Hafeez Ur Rehman SiddiquiHafeez Ur Rehman Siddiqui
Hafeez Ur Rehman Siddiqui
Furqan RustamFurqan Rustam
Furqan Rustam
Imran AshrafImran Ashraf
Imran Ashraf
The periodic inspection of railroad tracks is very important to find structural and geometrical problems that lead to railway accidents. Currently, in Pakistan, rail tracks are inspected by an acoustic-based manual system that requires a railway engineer as a domain expert to differentiate between different rail tracks’ faults, which is cumbersome, laborious, and error-prone. This study proposes the use of traditional acoustic-based systems with deep learning models to increase performance and reduce train accidents. Two convolutional neural networks (CNN) models, convolutional 1D and convolutional 2D, and one recurrent neural network (RNN) model, a long short-term memory (LSTM) model, are used in this regard. Initially, three types of faults are considered, including superelevation, wheel burnt, and normal tracks. Contrary to traditional acoustic-based systems where the spectrogram dataset is generated before the model training, the proposed approach uses on-the-fly feature extraction by generating spectrograms as a deep learning model’s layer. Different lengths of audio samples are used to analyze their performance with each model. Each audio sample of 17 s is split into 3 variations of 1.7, 3.4, and 8.5 s, and all 3 deep learning models are trained and tested against each split time. Various combinations of audio data augmentation are analyzed extensively to investigate models’ performance. The results suggest that the LSTM with 8.5 split time gives the best results with the accuracy of 99.7%, the precision of 99.5%, recall of 99.5%, and F1 score of 99.5%.

12 May 2025 in IEEE Access
Verified
Journal Article
Open access
Muhammad Shadab Alam HashmiMuhammad Shadab Alam Hashmi
Muhammad Shadab Alam Hashmi
AQAzam Mehmood Qadri
Azam Mehmood Qadri
Ali RazaAli Raza
Ali Raza
SUSaleem Ullah
Saleem Ullah
ASAseel Smerat
Aseel Smerat
NFNorma Latif Fitriyani
Norma Latif Fitriyani
Although coffee is a crucial commodity for developing nations’ economies, processing defects can significantly impact the safety, commercial value, and quality of coffee beans. Traditional coffee bean grading methods are labor-intensive and prone to error, necessitating automated and accurate classification of bean diseases. This study proposes a novel transfer learning-based deep neural network, VGGBM-Net, for classifying coffee bean diseases. It focuses on the timely and precise identification of diseases to improve export quality without compromising safety during production. In this research, the proposed approach is trained using a dataset USK-Coffee of coffee beans to classify healthy and unhealthy beans. The performance of multiple machine learning classifiers, including Random Forest (RF), Logistic Regression (LoR), LightGBM (LGBM), and K-Nearest Neighbor Classifier (KNC), is evaluated alongside neural network techniques such as Convolutional Neural Networks (CNN) and VGG-19. A novel transformation of the VGG-19 model for feature engineering based on transfer learning is introduced, where spatial features extracted from coffee bean images are transformed into class prediction probabilities using LGBM. These enhanced features are then used as inputs for advanced machine-learning algorithms. Unlike traditional models, this feature extraction enhances classification accuracy and robustness. This transformation improves feature extraction by capturing more discriminative patterns, leading to superior performance compared to conventional methods. Experimental results highlight the superior performance of the LGBM classifier, achieving an impressive 99% accuracy, recall, f1, and precision score of 98% with a computational runtime of just 0.084 seconds. K-fold cross-validation ensured the robustness of the models, and optimization techniques were applied to fine-tune parameters for maximum accuracy. This research establishes a highly effective framework for automated coffee bean classification, setting a benchmark for future studies in agricultural image analysis.

8 August 2023 in Sensors
Verified
Journal Article
Open access
PDF file
Furqan RustamFurqan Rustam
Furqan Rustam
AIAbid Ishaq
Abid Ishaq
Muhammad Shadab Alam HashmiMuhammad Shadab Alam Hashmi
Muhammad Shadab Alam Hashmi
Hafeez Ur Rehman SiddiquiHafeez Ur Rehman Siddiqui
Hafeez Ur Rehman Siddiqui
Luis Alonso Dzul  LópezLuis Alonso Dzul López
Luis Alonso Dzul López
Imran AshrafImran Ashraf
Imran Ashraf
Railway track faults may lead to railway accidents and cause human and financial loss. Spatial, temporal, and weather elements, and wear and tear, lead to ballast, loose nuts, misalignment, and cracks leading to accidents. Manual inspection of such defects is time-consuming and prone to errors. Automatic inspection provides a fast, reliable, and unbiased solution. However, highly accurate fault detection is challenging due to the lack of public datasets, noisy data, inefficient models, etc. To obtain better performance, this study presents a novel approach that relies on mel frequency cepstral coefficient features from acoustic data. The primary objective of this study is to increase fault detection performance. As well as designing an ensemble model, we utilize selective features using chi-square(chi2) that have high importance with respect to the target class. Extensive experiments were carried out to analyze the efficiency of the proposed approach. The experimental results suggest that using 60 features, 40 original features, and 20 chi2 features produces optimal results both regarding accuracy and computational complexity. A mean accuracy score of 0.99 was obtained using the proposed approach with machine learning models using the collected data. Moreover, this performance was significantly better than that of existing approaches; however, the performance of models may vary in real-world settings.

24 June 2024 in Mathematics
Verified
Journal Article
Open access
PDF file
MHMoin Haider
Moin Haider
Muhammad Shadab Alam HashmiMuhammad Shadab Alam Hashmi
Muhammad Shadab Alam Hashmi
Ali RazaAli Raza
Ali Raza
MIMuhammad Ibrahim
Muhammad Ibrahim
NFNorma Latif Fitriyani
Norma Latif Fitriyani
Seung Won LeeSeung Won Lee
Seung Won Lee
Lower back pain (LBP) is a musculoskeletal condition that affects millions of people worldwide and significantly limits their mobility and daily activities. Appropriate ergonomics and exercise are crucial preventive measures that play a vital role in managing and reducing the risk of LBP. Individuals with LBP often exhibit spinal anomalies, which can serve as valuable indicators for early diagnosis. We propose an advanced machine learning methodology for LBP detection that incorporates data balancing and bootstrapping techniques. Leveraging the features associated with spinal anomalies, our method offers a promising approach for the early detection of LBP. Our study utilizes a standard dataset comprising 310 patient records, including spinal anomaly features. We propose an ensemble method called the random forest gradient boosting XGBoost Ensemble (RGXE), which integrates the combined power of the random forest, gradient boosting, and XGBoost methods for LBP detection. Experimental results demonstrate that the proposed ensemble method, RGXE Voting, outperforms state-of-the-art methods, achieving a high accuracy of 0.99. We fine-tuned each method and validated its performance using k-fold cross-validation in addition to determining the computational complexity of the methods. This innovative research holds significant potential to revolutionize the early detection of LBP, thereby improving the quality of life.

17 September 2025 in IEEE Access
Verified
Journal Article
Open access
SNSaba Naseeb
Saba Naseeb
SRShabana Ramzan
Shabana Ramzan
Ali RazaAli Raza
Ali Raza
Muhammad Shadab Alam HashmiMuhammad Shadab Alam Hashmi
Muhammad Shadab Alam Hashmi
YGYeonghyeon Gu
Yeonghyeon Gu
NFNorma Latif Fitriyani
Norma Latif Fitriyani
Phishing remains the most pervasive cybersecurity threat, exploiting human vulnerabilities through sophisticated social engineering. While traditional heuristic and blacklist-based solutions struggle against evolving attacks, this paper proposes a novel stacked ensemble model combining Artificial Neural Networks (ANN) and Bagging K-Nearest Neighbors (KNN) with Logistic Regression (LR) as a meta-learner classifier. Our hybrid framework leverages the strength of ANN in identifying global non-linear patterns and the proficiency of Bagging KNN in local pattern detection, achieving superior performance through optimal decision-level fusion. Experimental results on 2019-2024 datasets demonstrate that the proposed ensemble model outperformed state-of-the-art techniques with a 97.20% accuracy score, a precision of 98%, and a recall of 98%. The proposed model employs hyperparameter-optimised architectures including a 512-256-128-128 layer ANN with Relu activation and 30% dropout, along with a Bagging KNN configuration using 10 estimators with K=7 and Euclidean distance. Key advantages of our stacking approach include enhanced generalization with 2.16% accuracy improvement over the best standalone model, adaptability to emerging attack patterns through weighted averaging, and scalability through the modular design that allows incremental model additions. This study introduces an innovative hybrid ensemble method that stacks ANN and Bagging KNN, incorporating a meta-learning strategy optimized for real-time phishing detection. The model also utilizes SMOTE oversampling to overcome the problem of class disproportion and uses k-fold cross-validation to establish stable performance testing. This study highlights the significance of feature engineering, ensemble methods, and hybrid approaches in enhancing phishing detection.

26 November 2025 in Scientific Reports
Verified
Journal Article
Open access
PDF file
MMMuhammad Mohsin
Muhammad Mohsin
Muhammad Shadab Alam HashmiMuhammad Shadab Alam Hashmi
Muhammad Shadab Alam Hashmi
INIrene Delgado Noya
Irene Delgado Noya
HGHelena Garay
Helena Garay
NSNagwan Abdel Samee
Nagwan Abdel Samee
IAImran Ashraf
Imran Ashraf
Mango is one of the most beloved fruits and plays an indispensable role in the agricultural economies of many tropical countries like Pakistan, India, and other Southeast Asian countries. Similar to other fruits, mango cultivation is also threatened by various diseases, including Anthracnose and Red Rust. Although farmers try to mitigate such situations on time, early and accurate detection of mango diseases remains challenging due to multiple factors, such as limited understanding of disease diversity, similarity in symptoms, and frequent misclassification. To avoid such instances, this study proposes a multimodal deep learning framework that leverages both leaf and fruit images to improve classification performance and generalization. Individual CNN-based pre-trained models, including ResNet-50, MobileNetV2, EfficientNet-B0, and ConvNeXt, were trained separately on curated datasets of mango leaf and fruit diseases. A novel Modality Attention Fusion (MAF) mechanism was introduced to dynamically weight and combine predictions from both modalities based on their discriminative strength, as some diseases are more prominent on leaves than on fruits, and vice versa. To address overfitting and improve generalization, a class-aware augmentation pipeline was integrated, which performs augmentation according to the specific characteristics of each class. The proposed attention-based fusion strategy significantly outperformed individual models and static fusion approaches, achieving a test accuracy of 99.08%, an F1 score of 99.03%, and a perfect ROC-AUC of 99.96% using EfficientNet-B0 as the base. To evaluate the model’s real-world applicability, an interactive web application was developed using the Django framework and evaluated through out-of-distribution (OOD) testing on diverse mango samples collected from public sources. These findings underline the importance of combining visual cues from multiple organs of plants and adapting model attention to contextual features for real-world agricultural diagnostics.