A. Hasib Uddin

Mr. A. Hasib Uddin

Computer Science and Engineering, Khulna University, Khulna, Bangladesh
+1

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

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

Representative Publications

View All Publications
2 May 2024 in Heliyon
Verified
Journal Article
Open access
AUA. Hasib Uddin
A. Hasib Uddin
Yen-Lin ChenYen-Lin Chen
Yen-Lin Chen
RARokeya Akter
Rokeya Akter
CKChin Soon Ku
Chin Soon Ku
JYJing Yang
Jing Yang
Lip Yee PorLip Yee Por
Lip Yee Por
Automatic classification of colon and lung cancer images is crucial for early detection and accurate diagnostics. However, there is room for improvement to enhance accuracy, ensuring better diagnostic precision. This study introduces two novel dense architectures (D1 and D2) and emphasizes their effectiveness in classifying colon and lung cancer from diverse images. It also highlights their resilience, efficiency, and superior performance across multiple datasets. These architectures were tested on various types of datasets, including NCT-CRC-HE-100K (set of 100,000 non-overlapping image patches from hematoxylin and eosin (H&E) stained histological images of human colorectal cancer (CRC) and normal tissue), CRC-VAL-HE-7K (set of 7180 image patches from N = 50 patients with colorectal adenocarcinoma, no overlap with patients in NCT-CRC-HE-100K), LC25000 (Lung and Colon Cancer Histopathological Image), and IQ-OTHNCCD (Iraq-Oncology Teaching Hospital/National Center for Cancer Diseases), showcasing their effectiveness in classifying colon and lung cancers from histopathological and Computed Tomography (CT) scan images. This underscores the multi-modal image classification capability of the proposed models. Moreover, the study addresses imbalanced datasets, particularly in CRC-VAL-HE-7K and IQ-OTHNCCD, with a specific focus on model resilience and robustness. To assess overall performance, the study conducted experiments in different scenarios. The D1 model achieved an impressive 99.80 % accuracy on the NCT-CRC-HE-100K dataset, with a Jaccard Index (J) of 0.8371, a Matthew's Correlation Coefficient (MCC) of 0.9073, a Cohen's Kappa (Kp) of 0.9057, and a Critical Success Index (CSI) of 0.8213. When subjected to 10-fold cross-validation on LC25000, the D1 model averaged (avg) 99.96 % accuracy (avg J, MCC, Kp, and CSI of 0.9993, 0.9987, 0.9853, and 0.9990), surpassing recent reported performances. Furthermore, the ensemble of D1 and D2 reached 93 % accuracy (J, MCC, Kp, and CSI of 0.7556, 0.8839, 0.8796, and 0.7140) on the IQ-OTHNCCD dataset, exceeding recent benchmarks and aligning with other reported results. Efficiency evaluations were conducted in various scenarios. For instance, training on only 10 % of LC25000 resulted in high accuracy rates of 99.19 % (J, MCC, Kp, and CSI of 0.9840, 0.9898, 0.9898, and 0.9837) (D1) and 99.30 % (J, MCC, Kp, and CSI of 0.9863, 0.9913, 0.9913, and 0.9861) (D2). In NCT-CRC-HE-100K, D2 achieved an impressive 99.53 % accuracy (J, MCC, Kp, and CSI of 0.9906, 0.9946, 0.9946, and 0.9906) with training on only 30 % of the dataset and testing on the remaining 70 %. When tested on CRC-VAL-HE-7K, D1 and D2 achieved 95 % accuracy (J, MCC, Kp, and CSI of 0.8845, 0.9455, 0.9452, and 0.8745) and 96 % accuracy (J, MCC, Kp, and CSI of 0.8926, 0.9504, 0.9503, and 0.8798), respectively, outperforming previously reported results and aligning closely with others. Lastly, training D2 on just 10 % of NCT-CRC-HE-100K and testing on CRC-VAL-HE-7K resulted in significant outperformance of InceptionV3, Xception, and DenseNet201 benchmarks, achieving an accuracy rate of 82.98 % (J, MCC, Kp, and CSI of 0.7227, 0.8095, 0.8081, and 0.6671). Finally, using explainable AI algorithms such as Grad-CAM, Grad-CAM++, Score-CAM, and Faster Score-CAM, along with their emphasized versions, we visualized the features from the last layer of DenseNet201 for histopathological as well as CT-scan image samples. The proposed dense models, with their multi-modality, robustness, and efficiency in cancer image classification, hold the promise of significant advancements in medical diagnostics. They have the potential to revolutionize early cancer detection and improve healthcare accessibility worldwide.

1 July 2019
Verified
Conference Paper
Closed access
AUA. Hasib Uddin
A. Hasib Uddin
DBDurjoy Bapery
Durjoy Bapery
AAAbu Shamim Mohammad Arif
Abu Shamim Mohammad Arif
Human emotions like depression are inner sentiments of human beings which expose actual behaviors of a person. Analyzing and determining these type of emotions from people’s social activities in virtual world can be very helpful to understand their behaviors. Existing approaches may be useful for analyzing common sentiments, such as positive, negative or neutral expressions. However, human emotions, such as depression, are very critical and sometimes almost impossible to analyze using these approaches. In this work, we deployed Long Short Term Memory (LSTM) Deep Recurrent Network for depression analysis on Bangla social media data. We created a small dataset of Bangla tweets and stratified it. In this paper, we have shown the effects of hyper-parameter tuning and how it can be helpful for depression analysis on a small Bangla social media dataset. The result shows that 5 layered LSTM of size 128 with batch size 25, learning rate 0.0001 over 20 epochs, the depression detection accuracy is high for stratified dataset with repeated sampling. This result will help psychologists and other researchers to detect depression of individuals from their social activities in virtual world and help them to take necessary measures to prevent undesirable doings resulted from depression.

14 August 2023 in Mathematics
Verified
Journal Article
Open access
PDF file
AUA. Hasib Uddin
A. Hasib Uddin
Yen-Lin ChenYen-Lin Chen
Yen-Lin Chen
BBBijly Borkatullah
Bijly Borkatullah
MKMst. Sathi Khatun
Mst. Sathi Khatun
JFJannatul Ferdous
Jannatul Ferdous
Lip Yee PorLip Yee Por
Lip Yee Por
This research addresses the lack of publicly available datasets for Bangladeshi medicinal plants by presenting a comprehensive dataset comprising 5000 images of ten species collected under controlled conditions. To improve performance, several preprocessing techniques were employed, such as image selection, background removal, unsharp masking, contrast-limited adaptive histogram equalization, and morphological gradient. Then, we applied five state-of-the-art deep learning models to achieve benchmark performance on the dataset: VGG16, ResNet50, DenseNet201, InceptionV3, and Xception. Among these models, DenseNet201 demonstrated the highest accuracy of 85.28%. In addition to benchmarking the deep learning models, three novel neural network architectures were developed: dense-residual–dense (DRD), dense-residual–ConvLSTM-dense (DRCD), and inception-residual–ConvLSTM-dense (IRCD). The DRCD model achieved the highest accuracy of 97%, surpassing the benchmark performances of individual models. This highlights the effectiveness of the proposed architectures in capturing complex patterns and dependencies within the data. To further enhance classification accuracy, an ensemble approach was adopted, employing both hard ensemble and soft ensemble techniques. The hard ensemble achieved an accuracy of 98%, while the soft ensemble achieved the highest accuracy of 99%. These results demonstrate the effectiveness of ensembling techniques in boosting overall classification performance. The outcomes of this study have significant implications for the accurate identification and classification of Bangladeshi medicinal plants. This research provides valuable resources for traditional medicine, drug discovery, and biodiversity conservation efforts. The developed models and ensemble techniques can aid researchers, botanists, and practitioners in accurately identifying medicinal plant species, thereby facilitating the utilization of their therapeutic potential and contributing to the preservation of biodiversity.

1 May 2019
Verified
Conference Paper
Closed access
AUA. Hasib Uddin
A. Hasib Uddin
DBDurjoy Bapery
Durjoy Bapery
AAAbu Shamim Mohammad Arif
Abu Shamim Mohammad Arif

8 June 2023 in Journal of Agriculture and Food Research
Verified
Journal Article
Open access
AAAsif Ahmed
Asif Ahmed
SHShakil Hossain
Shakil Hossain
Md Wahidur RahmanMd Wahidur Rahman
Md Wahidur Rahman
AUA. Hasib Uddin
A. Hasib Uddin
TITarequl Islam
Tarequl Islam

7 May 2023 in Data in Brief
Verified
Journal Article
Open access
BBBijly Borkatulla
Bijly Borkatulla
JFJannatul Ferdous
Jannatul Ferdous
AUA. Hasib Uddin
A. Hasib Uddin
PMPrince Mahmud
Prince Mahmud
Medicinal plants have been used to treat diseases since ancient times. Plants used as raw materials for herbal medicine are known as medicinal plants [2]. The U. S. Forest Service estimates that 40% of pharmaceutical drugs in the Western world are derived from plants [1]. Seven thousand medical compounds are derived from plants in the modern pharmacopeia. Herbal medicine combines traditional empirical knowledge with modern science [2]. A medicinal plant is considered an important source of prevention against various diseases [2]. The essential medicine component is extracted from different parts of the plants [8]. In underdeveloped countries, people use medicinal plants as a substitute for medicine. There are various species of plants in the world. Herbs are one of them, which are of different shapes, colors, and leaves [5]. It is difficult for ordinary people to recognize these species of herbs. People use more than 50000 plants in the world for medicinal purposes. There are 8000 medicinal plants in India with evidence of medicinal properties [7]. Automatic classification of these plant species is important because it requires intensive domain knowledge to manually classify the proper species. Machine learning techniques are extensively used in classifying medicinal plant species from photographs, which is challenging but intriguing to academics. Artificial Neural Network classifiers' effective performance depends on the quality of the image dataset [4]. This article represents a medicinal plant dataset: an image dataset of ten different Bangladeshi plant species. Images of medicinal plant leaves were from various gardens, including the Pharmacy Garden at Khwaja Yunus Ali University and the Khwaja Yunus Ali Medical College & Hospital in Sirajganj, Bangladesh. Images were collected by taking pictures with high-resolution mobile phone cameras. Ten medicinal species, 500 images per species are included in the data set, namely, Nayantara (Catharanthus roseus), Pathor kuchi (Kalanchoe pinnata), Gynura procumbens (Longevity spinach), Bohera (Terminalia bellirica), Haritaki (Terminalia chebula), Thankuni (Centella asiatica), Neem (Azadirachta indica), Tulsi (Ocimum tenniflorum), Lemon grass (Cymbopogon citratus), and Devil backbone (Euphorbia tithymaloides). This dataset will benefit researchers applying machine learning and computer vision algorithms in several ways. For example, training and evaluation of machine learning models with this well-curated high-quality dataset, development of new computer vision algorithms, automatic medicinal plant identification in the field of botany and pharmacology for drug discovery and conservation, and data augmentation. Overall, this medicinal plant image dataset can provide researchers in the field of machine learning and computer vision with a valuable resource to develop and evaluate algorithms for plant phenotyping, disease detection, plant identification, drug development, and other tasks related to medicinal plants.