Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Hongbo Du has a total of 64 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Cement Plant Power Demand Prediction Using 1D Convolutional Neural Network Model: A Case Study

    by Tawfeeq E. Abdulabbas, Sawsan M. Mahmoud, Hanan A. Al-Jubouri, Hongbo Du, Khalid Salem Ali Aleja, Mustafa Salim Agha Agha

    The management and operation of the power system would be significantly enhanced if accurate prior knowledge of power exchanges were provided, which could provide valuable insights into the system and help predict the required energy, enabling appropriate solutions to various challenges and preventing failures. The power consumption, reactive power, and power factor are critical parameters for assessing the performance of power system operations and planning. This paper presents One-Dimensional Convolutional Neural Networks (1DCNN) models for forecasting fluctuations of these parameters within the electrical power demand of a cement factory, thereby enabling effective monitoring of the cement production line. In addition, Long Short-Term Memory (LSTM) and Bidirectional Long Short-Term Memory (Bi-LSTM) models are modified to improve their effectiveness. Subsequently, the outcomes of the models were compared with those of conventional ARIMA models. Meanwhile, Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Bias Error (MBE), and Mean Absolute Percentage Error (MAPE) are used to evaluate the predictive model's accuracy. It is a frequently used metric, especially in regression tasks. The results indicated that the suggested models can effectively predict the behavior of such a power system with an RMSE of less than 3%.

  • Open Access

    Automatic Detection of Landmark Points for Estimating the Brain’s Dimensions of the Mouse in X-ray Images Using Machine Learning Approache

    by Omar Al Okashi, Hongbo Du, Hisham Al-Assam

    Measure of brain dimensions is an important metric for discovering brain abnormalities associated with certain diseases. Using an animal model to measure brain dimensions, followed by a discovery of possible genes responsible for changes in the dimensions, enables better understanding of the underlying genetic cause of the brain’s abnormalities in humans. This paper presents a three-stage automatic solution for estimating brain dimensions from dorsal-ventral X-ray images of mouse heads based on machine learning techniques. At the first stage, a skull modelling technique based on circular Hough transform is used to determine region of interests of the key landmarks on the skull. In stage 2, the procedures for the width and length landmarks ROIs estimation based on a circle model are presented. The landmark locations are then obtained in stage 3 using the random forests classification method based on texture features derived from the local binary patterns and histogram of oriented gradients and then brain dimensions are measured in terms of relevant width and length of the skull. Experimental results on a set of X-ray head images of 798 wild type and 6,090 mutant mice have demonstrated the effectiveness of the proposed solution in separating images of abnormal brain dimensions from those of normal ones. Furthermore, the estimated dimensions have also led to identifying 7 possible genes responsible for changes in the brain size of the mutant mice, some of which were already linked to Down’s syndromes, which further demonstrates the practical usefulness of the proposed solution.

  • Open Access

    Integrating multimodal ultrasound imaging for improved radiomics sentinel lymph node assessment in breast cancer

    by Zhe-Qin Yang, Yuan Zhang, Feng Lu, Tian Yang, Jun Shan, Quan Jiang, Geok Hoon Lim, François Bertucci, Hongbo Du, Yi-Cheng Zhu

    Background: Accurate preoperative assessment of sentinel lymph node (SLN) is critical for treatment planning in breast cancer (BC). While SLN biopsy (SLNB) remains the gold standard, it is invasive and may be unnecessary for all patients, particularly those with clinically node-negative disease. Combining conventional B-mode ultrasound (BMUS) and color Doppler ultrasound (CDUS) with new techniques like radiomics and deep learning may improve SLN prediction, but this approach has not been widely studied yet. This retrospective study aims to develop and validate a deep learning radiomics model that combining BMUS and CDUS imaging to noninvasively predict SLN metastasis in patients with BC. Methods: A total of 450 women with invasive BC who were treated at 2 hospitals between October 2021 and March 2025 were retrospectively analyzed. Patients were divided into training (n=276), external validation (n=105), and testing (n=69) sets. Handcrafted features were extracted from the breast lesion areas and its surrounding areas in BMUS images. Deep learning-based features were derived by applying a fine-tuned dual-stream MobileNetV2-based model, ultrasound and color doppler network, to both BMUS and CDUS images. The extracted deep features were then subjected to dimensionality reduction using principal component analysis. Following this, both handcrafted and deep learning features underwent further feature selection and dimensionality reduction process via application of inter- and intraclass correlation coefficient filtering, Pearson correlation analysis, and least absolute shrinkage and selection operator (LASSO) regression. Three models were constructed: only handcrafted features (ONLY_HF), only deep-learning features (ONLY_DF), and combined features (COMB). Each model’s performance was evaluated using the area under the curve (AUC). Results: The COMB model integrated ten features (six handcrafted and four deep learning) following LASSO regression. In predicting SLN metastasis between N0 and N≥1, COMB achieved a higher AUC (0.888, 0.861, and 0.837 in the training, validation, and testing sets, respectively) compared to ONLY_HF (0.792, 0.765, and 0.739) and ONLY_DF (0.781, 0.748, and 0.717). The negative prediction value of COMB was the highest (88.89%, 76.60%, and 71.23%), followed by ONLY_HF (83.33%, 72.00%, and 43.10%), and ONLY_DF (78.38%, 67.57%, and 52.69%). Conclusions: By integrating BMUS and CDUS imaging with advanced deep learning techniques, the COMB model achieved a high negative predictive value, which could guide axillary treatment decisions and reducing unnecessary invasive procedures. These findings highlight the potential of multimodal imaging and machine learning strategies to serve as noninvasive, supplementary tools for personalized BC management.


  • Open Access

    Comparative Study of Sentiment Analysis Techniques: Traditional Machine Learning vs. Deep Learning Approaches

    by Grace Diri, Philip Obiorah, Hongbo Du

    Aim/Purpose This paper presents a comparative analysis of sentiment classification models, focusing on the performance differences between lexicon-based sentiment analysis, traditional machine learning techniques, and transformer-based deep learning approaches across multiple benchmark datasets. Background While numerous methods exist for sentiment analysis, a systematic comparison across modeling paradigms and datasets remains limited. This study addresses this gap by evaluating representative models on IMDB, Yelp Polarity, and Amazon Polarity datasets using unified metrics and preprocessing pipelines. Methodology The evaluation includes (a) VADER as a lexicon-based baseline, (b) Logistic Regression, Decision Tree and Naive Bayes models built on three types of features: Bag of Words, TF-IDF, and Word2Vec as the traditional machine learning alternatives, and (c) two transformer models, Distil-BERT-SST-2 and RoBERTa-Sentiment, without fine-tuning as the deep learning methods. Performance is assessed using Accuracy, Precision, Re-call, and F1 Score. Contribution This study offers a comprehensive, side-by-side comparison of conventional and modern sentiment classification techniques, identifying model-feature synergies and highlighting limitations in generalizability across the domains. Findings Test results show that VADER, although efficient, underperforms on complex texts. Traditional models particularly Logistic Regression paired with TF-IDF yield strong performance. Recommendations for Practitioners DistilBERT demonstrates superior performance across all datasets, while RoBERTa’s performance suffers due to domain mismatch. Recommendations for Researchers When computational resources are constrained, TF-IDF with Logistic Regression offers a competitive alternative to deep learning. For best performance, transformer models like DistilBERT should be prioritized. Impact on Society The study can improve applications in customer feedback systems, social media monitoring, and public opinion analysis, contributing to more responsive and adaptive services. Future Research Future work should explore domain-specific fine-tuning strategies and evaluate multilingual sentiment performance, especially for transformer models.


  • Open Access

    Explainable DCNN Decision Framework for Breast Lesion Classification from Ultrasound Images Based on Cancer Characteristics

    by Alaa AlZoubi, Ali Eskandari, Harry Yu, Hongbo Du

    In recent years, deep convolutional neural networks (DCNNs) have shown promising performance in medical image analysis, including breast lesion classification in 2D ultrasound (US) images. Despite the outstanding performance of DCNN solutions, explaining their decisions remains an open investigation. Yet, the explainability of DCNN models has become essential for healthcare systems to accept and trust the models. This paper presents a novel framework for explaining DCNN classification decisions of lesions in ultrasound images using the saliency maps linking the DCNN decisions to known cancer characteristics in the medical domain. The proposed framework consists of three main phases. First, DCNN models for classification in ultrasound images are built. Next, selected methods for visualization are applied to obtain saliency maps on the input images of the DCNN models. In the final phase, the visualization outputs and domain-known cancer characteristics are mapped. The paper then demonstrates the use of the framework for breast lesion classification from ultrasound images. We first follow the transfer learning approach and build two DCNN models. We then analyze the visualization outputs of the trained DCNN models using the EGrad-CAM and Ablation-CAM methods. We map the DCNN model decisions of benign and malignant lesions through the visualization outputs to the characteristics such as echogenicity, calcification, shape, and margin. A retrospective dataset of 1298 US images collected from different hospitals is used to evaluate the effectiveness of the framework. The test results show that these characteristics contribute differently to the benign and malignant lesions’ decisions. Our study provides the foundation for other researchers to explain the DCNN classification decisions of other cancer types.


  • ENAS-B: Combining ENAS With Bayesian Optimization for Automatic Design of Optimal CNN Architectures for Breast Lesion Classification From Ultrasound Images

    by Mohammed Ahmed, Hongbo Du, Alaa AlZoubi

    Efficient Neural Architecture Search (ENAS) is a recent development in searching for optimal cell structures for Convolutional Neural Network (CNN) design. It has been successfully used in various applications including ultrasound image classification for breast lesions. However, the existing ENAS approach only optimizes cell structures rather than the whole CNN architecture nor its trainable hyperparameters. This paper presents a novel framework for automatic design of CNN architectures by combining strengths of ENAS and Bayesian Optimization in two-folds. Firstly, we use ENAS to search for optimal normal and reduction cells. Secondly, with the optimal cells and a suitable hyperparameter search space, we adopt Bayesian Optimization to find the optimal depth of the network and optimal configuration of the trainable hyperparameters. To test the validity of the proposed framework, a dataset of 1522 breast lesion ultrasound images is used for the searching and modeling. We then evaluate the robustness of the proposed approach by testing the optimized CNN model on three external datasets consisting of 727 benign and 506 malignant lesion images. We further compare the CNN model with the default ENAS-based CNN model, and then with CNN models based on the state-of-the-art architectures. The results (error rate of no more than 20.6% on internal tests and 17.3% on average of external tests) show that the proposed framework generates robust and light CNN models.


  • Automatic Detection of Thyroid Nodule Characteristics From 2D Ultrasound Images

    by Dongxu Han, Nasir Ibrahim, Feng Lu, Yicheng Zhu, Hongbo Du, Alaa AlZoubi

    Thyroid cancer is one of the common types of cancer worldwide, and Ultrasound (US) imaging is a modality normally used for thyroid cancer diagnostics. The American College of Radiology Thyroid Imaging Reporting and Data System (ACR TIRADS) has been widely adopted to identify and classify US image characteristics for thyroid nodules. This paper presents novel methods for detecting the characteristic descriptors derived from TIRADS. Our methods return descriptions of the nodule margin irregularity, margin smoothness, calcification as well as shape and echogenicity using conventional computer vision and deep learning techniques. We evaluate our methods using datasets of 471 US images of thyroid nodules acquired from US machines of different makes and labeled by multiple radiologists. The proposed methods achieved overall accuracies of 88.00%, 93.18%, and 89.13% in classifying nodule calcification, margin irregularity, and margin smoothness respectively. Further tests with limited data also show a promising overall accuracy of 90.60% for echogenicity and 100.00% for nodule shape. This study provides an automated annotation of thyroid nodule characteristics from 2D ultrasound images. The experimental results showed promising performance of our methods for thyroid nodule analysis. The automatic detection of correct characteristics not only offers supporting evidence for diagnosis, but also generates patient reports rapidly, thereby decreasing the workload of radiologists and enhancing productivity.


  • Open Access

    Classification of breast lesions in ultrasound images using deep convolutional neural networks: transfer learning versus automatic architecture design

    by Alaa AlZoubi, Feng Lu, Yicheng Zhu, Tao Ying, Mohmmed Ahmed, Hongbo Du

    Deep convolutional neural networks (DCNNs) have demonstrated promising performance in classifying breast lesions in 2D ultrasound (US) images. Exiting approaches typically use pre-trained models based on architectures designed for natural images with transfer learning. Fewer attempts have been made to design customized architectures specifically for this purpose. This paper presents a comprehensive evaluation on transfer learning based solutions and automatically designed networks, analyzing the accuracy and robustness of different recognition models in three folds. First, we develop six different DCNN models (BNet, GNet, SqNet, DsNet, RsNet, IncReNet) based on transfer learning. Second, we adapt the Bayesian optimization method to optimize a CNN network (BONet) for classifying breast lesions. A retrospective dataset of 3034 US images collected from various hospitals is then used for evaluation. Extensive tests show that the BONet outperforms other models, exhibiting higher accuracy (83.33%), lower generalization gap (1.85%), shorter training time (66 min), and less model complexity (approximately 0.5 million weight parameters). We also compare the diagnostic performance of all models against that by three experienced radiologists. Finally, we explore the use of saliency maps to explain the classification decisions made by different models. Our investigation shows that saliency maps can assist in comprehending the classification decisions. Graphical Abstract