Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Bunyodbek Ibrokhimov has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Interactive Guiding Sparse Auto-Encoder with Wasserstein Regularization for Efficient Classification

    by Haneum Lee, Cheonghwan Hur, Bunyodbek Ibrokhimov, Sanggil Kang

    In the era of big data, feature engineering has proved its efficiency and importance in dimensionality reduction and useful information extraction from original features. Feature engineering can be expressed as dimensionality reduction and is divided into two types of methods, namely, feature selection and feature extraction. Each method has its pros and cons. There are a lot of studies that combine these methods. The sparse autoencoder (SAE) is a representative deep feature learning method that combines feature selection with feature extraction. However, existing SAEs do not consider feature importance during training. It causes extracting irrelevant information. In this paper, we propose an interactive guiding sparse autoencoder (IGSAE) to guide the information by two interactive guiding layers and sparsity constraints. The interactive guiding layers keep the main distribution using Wasserstein distance, which is a metric of distribution difference, and it suppresses the leverage of guiding features to prevent overfitting. We perform our experiments using four datasets that have different dimensionalities and numbers of samples. The proposed IGSAE method produces a better classification performance compared to other dimensionality reduction methods.


  • Open Access

    Parallel Guiding Sparse Auto-Encoder with Wasserstein Regularization for Efficient Classification

    by Haneum Lee, Cheonghwan Hur, Bunyodbek Ibrokhimov, Sanggil Kang

    In the era of big data, feature engineering has proved its efficiency and importance in dimensionality reduction and useful information extraction from original features. Feature engineering can be expressed as dimensionality reduction and is divided into two types of methods such as feature selection and feature extraction. Each method has its pros and cons. There are a lot of studies to combine these methods. Sparse autoencoder (SAE) is a representative deep feature learning method that combines feature selection with feature extraction. However, existing SAEs do not consider the feature importance during training. It causes extracting irrelevant information. In this paper, we propose a parallel guiding sparse autoencoder (PGSAE) to guide the information by two parallel guiding layers and sparsity constraints. The parallel guiding layers keep the main distribution using Wasserstein distance which is a metric of distribution difference, and it suppresses the leverage of guiding features to prevent overfitting. We perform our experiments using four datasets that have different dimensionality and number of samples. The proposed PGSAE method produces a better classification performance compared to other dimensionality reduction methods.

  • Open Access

    Deep Learning Model for COVID-19-Infected Pneumonia Diagnosis Using Chest Radiography Images

    by Bunyodbek Ibrokhimov, Justin-Youngwook Kang

    Accurate and early detection of causes of pneumonia is important for implementing fast treatment and preventive strategies, reducing the burden of infections, and establishing more effective ways of interventions. After the outbreak of COVID-19, the new cases of pneumonia and conditions of breathing problems called acute respiratory distress syndrome have increased. Chest radiography, known as CXR or simply X-ray has become a significant source to diagnose COVID-19-infected pneumonia in designated institutions and hospitals. It is essential to develop automated computer systems to assist doctors and medical experts to diagnose pneumonia in a fast and reliable manner. In this work, we propose a deep learning (DL)-based computer-aided diagnosis system for rapid and easy detection of pneumonia using X-ray images. To improve classification accuracy and faster conversion of the models, we employ transfer learning and parallel computing techniques using well-known DL models such as VGG19 and ResNet50. Experiments are conducted on the large COVID-QU-Ex dataset of X-ray images with three classes, such as COVID-19-infected pneumonia, non-COVID-19 infections (other viral and bacterial pneumonia), and normal (uninfected) images. The proposed model outperformed compared methodologies, achieving an average classification accuracy of 96.6%. Experimental results demonstrate that the proposed method is effective in diagnosing pneumonia using X-ray images.


  • Open Access

    Two-Stage Deep Learning Method for Breast Cancer Detection Using High-Resolution Mammogram Images

    by Bunyodbek Ibrokhimov, Justin-Youngwook Kang

    Breast cancer screening and detection using high-resolution mammographic images have always been a difficult task in computer vision due to the presence of very small yet clinically significant abnormal growths in breast masses. The size difference between such masses and the overall mammogram image as well as difficulty in distinguishing intra-class features of the Breast Imaging Reporting and Database System (BI-RADS) categories creates challenges for accurate diagnosis. To obtain near-optimal results, object detection models should be improved by directly focusing on breast cancer detection. In this work, we propose a new two-stage deep learning method. In the first stage, the breast area is extracted from the mammogram and small square patches are generated to narrow down the region of interest (RoI). In the second stage, breast masses are detected and classified into BI-RADS categories. To improve the classification accuracy for intra-classes, we design an effective tumor classification model and combine its results with the detection model’s classification scores. Experiments conducted on the newly collected high-resolution mammography dataset demonstrate our two-stage method outperforms the original Faster R-CNN model by improving mean average precision (mAP) from 0.85 to 0.94. In addition, comparisons with existing works on a popular INbreast dataset validate the performance of our two-stage model.


  • Open Access

    Biased Pressure: Cyclic Reinforcement Learning Model for Intelligent Traffic Signal Control

    by Bunyodbek Ibrokhimov, Young-Joo Kim, Sanggil Kang

    Existing inefficient traffic signal plans are causing traffic congestions in many urban areas. In recent years, many deep reinforcement learning (RL) methods have been proposed to control traffic signals in real-time by interacting with the environment. However, most of existing state-of-the-art RL methods use complex state definition and reward functions and/or neglect the real-world constraints such as cyclic phase order and minimum/maximum duration for each traffic phase. These issues make existing methods infeasible to implement for real-world applications. In this paper, we propose an RL-based multi-intersection traffic light control model with a simple yet effective combination of state, reward, and action definitions. The proposed model uses a novel pressure method called Biased Pressure (BP). We use a state-of-the-art advantage actor-critic learning mechanism in our model. Due to the decentralized nature of our state, reward, and action definitions, we achieve a scalable model. The performance of the proposed method is compared with related methods using both synthetic and real-world datasets. Experimental results show that our method outperforms the existing cyclic phase control methods with a significant margin in terms of throughput and average travel time. Moreover, we conduct ablation studies to justify the superiority of the BP method over the existing pressure methods.


  • Open Access

    Time Series Classification with InceptionFCN

    by Saidrasul Usmankhujaev, Bunyodbek Ibrokhimov, Shokhrukh Baydadaev, Jangwoo Kwon

    Deep neural networks (DNN) have proven to be efficient in computer vision and data classification with an increasing number of successful applications. Time series classification (TSC) has been one of the challenging problems in data mining in the last decade, and significant research has been proposed with various solutions, including algorithm-based approaches as well as machine and deep learning approaches. This paper focuses on combining the two well-known deep learning techniques, namely the Inception module and the Fully Convolutional Network. The proposed method proved to be more efficient than the previous state-of-the-art InceptionTime method. We tested our model on the univariate TSC benchmark (the UCR/UEA archive), which includes 85 time-series datasets, and proved that our network outperforms the InceptionTime in terms of the training time and overall accuracy on the UCR archive.


  • Effective Filter Pruning Method Using Additional Downsampled Image for Global Pooling Applied CNN

    by Hyunseok Kim, Bunyodbek Ibrokhimov, Sanggil Kang

    Deep Convolutional Neural Networks (CNNs) show remarkable performance in many areas. However, most of the applications require huge computational costs and massive memory, which are hard to obtain in devices with a relatively weak performance like embedded devices. To reduce the computational cost, and meantime, to preserve the performance of the trained deep CNN, we propose a new filter pruning method using an additional dataset derived by downsampling the original dataset. Our method takes advantage of the fact that information in high-resolution images is lost in the downsampling process. Each trained convolutional filter reacts differently to this information loss. Based on this, the importance of the filter is evaluated by comparing the gradient obtained from two different resolution images. We validate the superiority of our filter evaluation method using a VGG-16 model trained on CIFAR-10 and CUB-200-2011 datasets. The pruned network with our method shows an average of 2.66% higher accuracy in the latter dataset, compared to existing pruning methods when about 75% of the parameters are removed.

  • A-DBNF: adaptive deep belief network framework for regression and classification tasks

    by Bunyodbek Ibrokhimov, Cheonghwan Hur, Hyunseok Kim, Sanggil Kang


  • N3-CPL: Neuroplasticity-based neuromorphic network cell proliferation learning

    by Cheonghwan Hur, Bunyodbek Ibrokhimov, Sanggil Kang


  • An Optimized Deep Belief Network Model for Accurate Breast Cancer Classification

    by Bunyodbek Ibrokhimov, Cheonghwan Hur, Hyunseok Kim, Sanggil Kang

    Breast cancer is the second most common cause of mortality in women. In the last decade, the rate of new diagnoses has increased significantly. Meanwhile, according to the World Health Organization, breast cancer can be treated effectively if it is detected in the early stages. Computer automated diagnosis systems have greatly helped researchers to learn the evolution and causes of breast cancer, as well as to monitor and detect the disease among women. However, there is a need for modern and accurate models to reduce the risk of breast cancer as well as for further improvements in diagnostic performance. In this paper, a deep belief network (DBN) model is proposed to achieve high accuracy in breast cancer classification. A particle swarm optimization algorithm is employed and integrated into the DBN to optimize the model’s parameters. The model is tested on two popular breast cancer datasets. Moreover, analysis of the datasets and improvements in data quality using data mining are shown, and an effective feature-selection method for a high-dimensional feature space is discussed. In experiments, the proposed method showed robust performance with high classification accuracy, matching, and even outperforming existing state-of-the-art algorithms.