Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Bahram Sadeghi Bigham has a total of 127 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Straw-K: Geometric Optimization of Cluster-Number Selection Using a ShortStraw-Inspired Elbow Criterion

    by Mohadese Khosravi, Bahram Sadeghi Bigham, Mazyar Zahedi-Seresht

    Background: Choosing the number of clusters is still one of the least settled steps in a K-means analysis. The within-cluster sum of squares (WCSS) elbow plot is easy to understand, yet visual inspection is difficult to reproduce, and different validity indices often favor different values because they measure different aspects of the partition. Methods: We propose and evaluate Straw-K, a geometric cluster-number selection method that scores local bends on the normalized WCSS curve. Straw-K is a coined method name, not an acronym. Its construction adapts the local-window and chord-to-path geometry used in ShortStraw corner detection to discrete cluster-number selection; the contribution is the WCSS-specific criterion and its minimization over candidate values of K, rather than a claim that the chord-to-path relation itself is new. Twelve empirical datasets were analyzed without a general sample-size cap. Seven selectors were compared over eight K-means random-state seeds: Straw-K, the official Kneedle implementation, Silhouette, Calinski–Harabasz, Davies–Bouldin, the Gap statistic with B = 50, and the L-method. Agreement with the recorded class count, absolute error, seed stability, runtime, the Friedman test, Holm-adjusted paired Wilcoxon tests, an exploratory ambiguity margin, and a separate Digits/PCA analysis were examined. Results: Across the 96 dataset–seed evaluations available for each method, Straw-K matched the recorded class count in 44.8% of cases and produced a mean absolute error of 1.54, the highest exact-match rate and lowest mean error in the descriptive table. The Friedman test detected an overall difference among the seven selectors (χ2=13.51, p = 0.036), but none of the 21 paired Wilcoxon comparisons remained significant after Holm correction (minimum adjusted p = 0.123). Gap was the slowest method in the independent uncached timing analysis. The ambiguity index showed only a weak, non-significant association with seed instability (Spearman ρ = 0.33, p = 0.303) and is therefore treated as descriptive rather than calibrated uncertainty. Conclusions: Taken together, the experiments suggest a fairly specific use for Straw-K: it offers an inspectable ranking of bends once the short WCSS support curve has been computed. The method did not recover a unique cluster count in every dataset, and Digits remained particularly difficult. The class labels used in the benchmark are best understood as external comparison points; they do not by themselves define the geometry that K-means will uncover.

  • Open Access

    A Trust-Aware Hybrid Unsupervised Framework for Robust ECG Anomaly Detection in IoMT Monitoring Networks

    by Venus Mohammadi, Bahram Sadeghi Bigham

    A reliable anomaly detection mechanism is paramount for ensuring trustworthy electrocardiogram (ECG) monitoring within the Internet of Medical Things (IoMT) ecosystems, where diverse noise sources and acquisition variability frequently compromise signals. This study introduces a hybrid unsupervised framework that integrates a Long Short-Term Memory (LSTM) autoencoder with an Isolation Forest to enable robust signal-trust assessment under unlabeled and noisy conditions. The proposed methodology synergizes temporal reconstruction learning with distribution-based outlier isolation through a trust-driven decision logic. This integration enables the explicit differentiation of true pathological abnormalities from noise-induced distortions, addressing a critical gap in conventional diagnostic systems. The framework was rigorously evaluated using the MIT-BIH Arrhythmia benchmark dataset in a single-modal, label-free learning environment. Experimental results demonstrate superior performance over both standalone architectures and contemporary state-of-the-art methods, achieving an accuracy of 99.71%, sensitivity of 99.92%, specificity of 99.46%, and an ROC-AUC of 99.96%. Ablation studies confirm that the hybrid synergy significantly enhances detection reliability compared to individual LSTM-AE or Isolation Forest implementations. Furthermore, the model exhibits a substantial reduction in both false-negative risk (FNR: 0.08) and false-alarm rate (FPR: 0.54%), thereby bolstering clinical confidence in continuous monitoring scenarios. The findings suggest that the proposed trust-based framework provides a robust and operationally efficient solution for ECG anomaly detection without requiring extensive labeled datasets, supporting sustainable long-term monitoring in real-world IoMT healthcare applications.


  • Enhanced multi-task learning using optimization methods

    by Fatemeh Bazikar, Bahram Sadeghi Bigham, Hossein Moosaei

  • TSLS and TSLSU: Two Novel Approximation SINR-Based Shortest Link Scheduling Algorithms in Wireless Networks

    by Neda Mohammadi, Bahram Sadeghi Bigham, Mehdi Kadivar

    In this paper, we address the fundamental problem of shortest link scheduling (SLS) in wireless networks under the Signal-to-Interference-plus-Noise-Ratio ($\text{SINR}$) constraints and propose two efficient Triangle-based Shortest Link Scheduling (TSLS and TSLSU) algorithms by assuming both oblivious power control and uniform power assignment scenarios. Many existing algorithms, to solve SLS under the $\text{SINR}$ constraints, partition the set of links into classes and for each class, schedule the links by partitioning the link deployment plane into small regions. In this paper, we present a new triangle-based method for plane partitioning, showing that it significantly improves efficiency by increasing the number of simultaneously schedulable same-color regions. Consequently, more links can be activated within a time slot compared to other partitioning methods. Theoretical analysis indicates the correctness and effectiveness of our algorithms. Theoretical analysis demonstrates that our plane partition and approximation ratios are respectively much more efficient and tighter than those of state-of-the-art algorithms' results. In summary, both theoretical analysis and simulation results confirm that our algorithms offer superior performance in terms of efficiency and solution quality compared to the state-of-the-art algorithms.

  • Open Access

    A More Accurate Metaheuristic Approach for the Art Gallery Problem

    by Bahram Sadeghi Bigham, Sahar Badri, Mazyar Zahedi-Seresht, Shahrzad Khosravi, Nazanin Padkan

    The Art Gallery problem is one of the most important non-deterministic polynomial (NP)-hard optimization problems in computational geometry, with many applications in localization, robotics, telecommunications, etc. The goal of the Art Gallery problem is to find the minimum number of guards needed within a simple polygon to observe and protect its entirety. There are several approaches to solving the Art Gallery problem, and this paper presents an efficient method based on the Particle Filter algorithm, which solves the most fundamental case of the problem in a nearly optimal manner. Experimental results on random polygons generated show that the new method is more accurate, providing solutions that are, on average, 9.94% better than Bottino's results for the same sample set. The approach was also applied to four groups of random orthogonal polygons and compared with the optimal solution. Results show that the new method finds the optimal solution with a 0.16% error. Furthermore, this paper discusses the impact of resampling and particle numbers in minimizing runtime.

  • Open Access

    Review of: "Patterns of Squares Around an Arbitrary Triangle"

    by Bahram Sadeghi Bigham

    The manuscript, "Patterns of Squares Around an Arbitrary Triangle," is a commendable effort to extend geometric concepts related to squares and generalize the Pythagorean theorem. The use of vector-based methods instead of trigonometric calculations...

  • Open Access

    Supplier Selection Utilizing AHP and TOPSIS in a Fuzzy Environment Based on KPIs

    by Asal Safavi, Bahram Sadeghi Bigham, Mazyar Zahedi-Seresht

    In today’s competitive and rapidly changing business landscape, organizations face significant challenges such as resource limitations, fluctuating demand, and evolving customer needs. Addressing these challenges requires effective strategies, with supplier selection playing a vital role in building resilient and efficient supply chains. This study introduces an innovative framework for supplier evaluation and selection, integrating the analytic hierarchy process (AHP) and the technique for order preference by similarity to the ideal solution (TOPSIS) within a fuzzy environment. The AHP method was employed to systematically identify and prioritize key performance indicators (KPIs) critical for evaluating suppliers. Criteria such as transportation cost, flexibility in meeting product requirements, defect reduction, and effective communication and responsiveness were identified as the most significant factors. These priorities formed the foundation for applying the fuzzy TOPSIS method, which facilitated the ranking of suppliers under conditions of uncertainty. The analysis revealed Sepidar Darb, Aram Plastic Sabalan, Sanaye Plastic Markaz, and Amin Avar Plastic as the top-performing suppliers, followed by Pegah Zanjan Company. The relevance of this research is heightened by the impact of the COVID-19 pandemic, which has disrupted global supply chains and fundamentally altered supplier selection criteria. While pre-pandemic evaluations predominantly focused on cost efficiency and product quality, the pandemic has underscored the importance of additional criteria such as supplier agility, risk management capabilities, geographical proximity, and digital integration. These emerging priorities highlight the necessity of rethinking traditional approaches to supplier selection and adapting to the evolving demands of global supply chains. By incorporating these updated criteria into the AHP-TOPSIS framework, this study offers a robust and practical tool for supplier evaluation in uncertain and dynamic environments. The proposed framework not only improves upon traditional methods but also provides valuable insights for organizations striving to create resilient and adaptable supply chains capable of withstanding future disruptions.