Arshad Iqbal

Arshad Iqbal

Auto-generated profile, based on publicly available information

Arshad Iqbal

Department of Computer Science and Bioinformatics, Khushal Khan Khattak University, Karak, Pakistan

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
24 March 2025 in PLOS ONE
Verified
Journal Article
Open access
PDF file
AIArshad Iqbal
Arshad Iqbal
ASAbdul Shahid
Abdul Shahid
MRMuhammad Roman
Muhammad Roman
MAMuhammad Tanvir Afzal
Muhammad Tanvir Afzal
UHUmair Ul Hassan
Umair Ul Hassan
Citations in scientific literature act as channels for the sharing, transfer, and development of scientific knowledge. However, not all citations hold the same significance. Numerous taxonomies and machine learning models have been developed to analyze citations, but they often overlook the internal context of these citations. Moreover, it is worth noting that selecting the appropriate word embedding and classification models is crucial for achieving superior results. Word embeddings offer n-dimensional distributed representations of text, striving to capture the nuanced meanings of words. Deep learning-based word embedding techniques have garnered significant attention and found application in various Natural Language Processing (NLP) tasks, including text classification, sentiment analysis, and citation analysis. Current state-of-the-art techniques often use small datasets with fixed window sizes, resulting in the loss of contextual meaning. This study leverages two benchmark datasets encompassing a substantial volume of in-text citations to guide the selection of an optimal word embedding window size and classification approaches. A comparative analysis of various window sizes for in-text citations is conducted to identify crucial citations effectively. Additionally, Word2Vec embedding is employed in conjunction with deep learning models and machine learning models such as Convolutional Neural Networks (CNNs), Gated Recurrent Units (GRUs), Long Short-Term Memory (LSTM) networks, Support Vector Machines (SVM), Decision Trees, and Naive Bayes.The evaluation employs precision, recall, F1-score, and accuracy metrics for each combination of window sizes. The findings reveal that, particularly for lengthy in-text citations, larger citation windows are more adept at capturing the semantic essence of the references. Within the scope of this study, window sizes of 10 achieve superior accuracy and precision with both machine and deep learning models.

27 September 2023 in IEEE Access
Verified
Journal Article
Open access
AIArshad Iqbal
Arshad Iqbal
ASAbdul Shahid
Abdul Shahid
MRMuhammad Roman
Muhammad Roman
MAMuhammad Tanvir Afzal
Muhammad Tanvir Afzal
Muhammad YahyaMuhammad Yahya
Muhammad Yahya
Finding relevant research papers is a challenging task due to the enormous number of scientific publications published each year. In recent years, the scientific community has delved into the analysis of citations at a deep level, specifically examining the content of the papers, in order to identify more important documents. Citations serve as potential parameters for determining linkages between research articles. They have been extensively used for various academic purposes, such as calculating journal impact factors, determining researchers’ h-index, allocating research grants, and identifying the latest research trends. However, it has been argued by researchers that not all citations are equally influential. As a result, alternative techniques have been proposed to identify important citations based on content, metadata, and bibliographic information. Nevertheless, the current state-of-the-art approaches still require further improvement. Additionally, the use of deep learning models and word embedding techniques in this context has not been extensively studied. In this research work, we propose an approach based on two primary modules: 1) Section-wise citation count, and 2) metadata-based analysis of citation intent. Our study also involves conducting several experiments using deep learning models combined with FastText, word2vec, and BERT-based word embeddings to perform citation analysis. These experiments were conducted on two benchmark datasets, and the results were compared with a contemporary study that employed a rich set of content-based features for classification. Our findings indicate that the deep learning CNN model coupled with FastText word embedding achieves the best results in terms of accuracy, precision, and recall. It outperforms the existing state-of-the-art model with a precision score of 0. 97.

29 April 2026 in IEEE Access
Verified
Journal Article
Open access
AIArshad Iqbal
Arshad Iqbal
MHMuhammad INAM UL HAQ
Muhammad INAM UL HAQ
Abdul WahidAbdul Wahid
Abdul Wahid
SMShad Muhammad
Shad Muhammad
Muhammad YahyaMuhammad Yahya
Muhammad Yahya
ASAbdul Shahid
Abdul Shahid
Assessing the influence of scientific citations is critical to understanding the impact of scholarly research beyond the raw citation counts. Recent neural models achieve strong performance in citation classification but typically function as black boxes, limiting their suitability for transparent bibliometric evaluation. This study proposes an intrinsically interpretable framework for binary classification of in-text citation importance. The framework integrates a SciBERT encoder with a sparsity-controlled HardKuma-L0 rationale selector. This selector identifies a minimal yet contextually informative set of tokens without requiring additional annotations, enabling the model to generate faithful, human-readable rationales that directly influence predictions. Experiments on the ACL-ARC and SciCite datasets show that the proposed model achieves state-of-the-art F1 scores (0.95 and 0.92, respectively), significantly outperforming strong baselines (p < 0.01, McNemar’s test). Evaluation of Token-level rationale using ERASER metrics demonstrates improved sufficiency and comprehensiveness compared to attention-based methods, LIME and SHAP. A detailed ablation study confirms that structural cues and sparse rationale extraction contribute substantially to predictive performance. Finally, a web-based visualization interface was developed to support human-in-the-loop verification of model output. This work provides a transparent and statistically validated alternative to black-box citation classifiers, advancing interpretable bibliometric analysis.

1 January 2025 in Journal of Disability Research
Verified
Journal Article
Open access
MAMosleh Al-Adhaileh
Mosleh Al-Adhaileh
AIArshad Iqbal
Arshad Iqbal
Theyazn H.H AldhyaniTheyazn H.H Aldhyani
Theyazn H.H Aldhyani
MUM. Irfan Uddin
M. Irfan Uddin
AAAbdullah H. Al-Nefaie
Abdullah H. Al-Nefaie
Freezing of gait (FoG) is among the most disabling motor symptoms experienced by individuals with movement disorders, particularly Parkinson’s disease (PD). FoG episodes can severely limit mobility, heighten the risk of falls, disrupt daily routines, and profoundly diminish quality of life. Early and reliable detection of FoG is therefore crucial to enable timely intervention and more effective disease management. However, traditional detection methods often fall short in accuracy due to the complex and variable nature of gait patterns. In this study, we propose a novel WaveNet-based deep learning framework that effectively captures long-range temporal dependencies in gait signals, addressing key limitations of conventional models. Unlike standard recurrent or convolutional networks, WaveNet’s dilated causal convolutions allow for efficient modeling of sequential accelerometer data with minimal computational cost, making it well suited for real-time applications. To assess its performance, we benchmarked the proposed WaveNet model against established deep learning architectures, including Deep Convolutional long short-term memory and InceptionTime, using two comprehensive datasets, tDCS-FoG and DeFoG, containing annotated accelerometer recordings collected in both controlled laboratory and real-world home environments. To address the significant class imbalance present in FoG datasets, we employed the Adaptive Synthetic Sampling (ADASYN) technique alongside jerk-based features, which improves the detection of subtle gait changes. Our experimental results show that the proposed WaveNet model achieves a precision of 0.99 and a specificity of 0.98, outperforming previously reported precision levels, which ranged between 77% and 91% on comparable benchmarks. With its low inference latency and lightweight architecture, the proposed framework is well positioned for integration into wearable systems to enable continuous, real-time FoG monitoring. This advancement holds substantial promise for clinical and home use, ultimately contributing to safer mobility and an improved quality of life for individuals living with PD.