Hasan Sarker

Mulberry leaf disease detection is vital for maintaining the health and productivity of mulberry crops. In this paper, a novel approach was proposed by integrating explainable artificial intelligence (XAI) techniques with a convolutional neural network (CNN) and vision transformer (ViT) for effective mulberry leaf disease classification with three disease classes. Initially, in this proposed CNN-ViT model, features are extracted using a customized CNN architecture, and then the extracted features are fed into ViT for leaf disease classification in a more streamlined approach. The CNN-ViT model achieved promising results with a projection dimension of 64, utilizing 8 heads and 8 transformer layers, yielding an accuracy of 95.60% with notable precision of 94.75%, recalls of 92.40%, and F1-scores of 93.45%. The proposed method also took 0.0017 seconds to predict an individual image. The accuracy of the proposed method was comparable to that of other state-of-the-art (SOTA) methods reported in the literature. Finally, Grad-CAM was utilized for detecting precise region of interest for diseased leaves, leaf spots, and leaf rust, providing interpretability and insights into the model’s decision-making process. This comprehensive approach demonstrates the effectiveness of explainable artificial intelligence (XAI) integration in the CNN-ViT model for mulberry leaf disease detection, paving the way for improved agricultural disease management strategies.

Background: Examining chest radiograph images (CXR) is an intricate and time-consuming process, sometimes requiring the identification of many anomalies at the same time. Lung segmentation is key to overcoming this challenge through different deep learning (DL) techniques. Many researchers are working to improve the performance and efficiency of lung segmentation models. This article presents a DL-based approach to accurately identify the lung mask region in CXR images to assist radiologists in recognizing early signs of high-risk lung diseases. Methods: This paper proposes a novel technique, Lightweight Residual U-Net, combining the strengths of the convolutional block attention module (CBAM), the Atrous Spatial Pyramid Pooling (ASPP) block, and the attention module, which consists of only 3.24 million trainable parameters. Furthermore, the proposed model has been trained using both the RELU and LeakyReLU activation functions, with LeakyReLU yielding superior performance. The study indicates that the Dice loss function is more effective in achieving better results. Results: The proposed model is evaluated on three benchmark datasets: JSRT, SZ, and MC, achieving a Dice score of 98.72%, 97.49%, and 99.08%, respectively, outperforming the state-of-the-art models. Conclusions: Using the capabilities of DL and cutting-edge attention processes, the proposed model improves current efforts to enhance lung segmentation for the early identification of many serious lung diseases.

To effectively treat lung and colon cancer and save lives, early and accurate identification is essential. Conventional diagnosis takes a long time and requires the manual expertise of radiologists. The rising number of new cancer cases makes it challenging to process massive volumes of data quickly. Different machine learning approaches to the classification and detection of lung and colon cancer have been proposed by multiple research studies. However, when it comes to self-learning classification and detection tasks, deep learning (DL) excels. This paper suggests a novel DL convolutional neural network (CNN) model for detecting lung and colon cancer. The proposed model is lightweight and multi-scale since it uses only 1.1 million parameters, making it appropriate for real-time applications as it provides an end-to-end solution. By incorporating features extracted at multiple scales, the model can effectively capture both local and global patterns within the input data. The explainability tools such as gradient-weighted class activation mapping and Shapley additive explanation can identify potential problems by highlighting the specific input data areas that have an impact on the model’s choice. The experimental findings demonstrate that for lung and colon cancer detection, the proposed model was outperformed by the competition and accuracy rates of 99.20% have been achieved for multi-class (containing five classes) predictions.

With technological advancement, photonic crystal fibers (PCFs) are effectively used to design miniaturized, flexible, and efficient biosensors. This paper proposes an exposed core PCF biosensor based on widely known surface plasmon resonance (SPR) phenomena. An external sensing mechanism is followed to characterize the sensing performance within the refractive index (RI) range between 1.28 and 1.40. Metal strip (gold (Au) and titanium dioxide (TiO₂)) is deposited on the outer surface only along the four channels instead of the entire surface, which could decrease the difficulties associated with the metal deposition on the entire circular surface. Simulating the sensor using finite element method based COMSOL Multiphysics software, we find tremendous amplitude sensitivity of 7420.69 RIU⁻¹ and wavelength sensitivity of 87,000 nm/RIU. In addition, the sensor offers the highest resolution of 7.7×10⁻⁶ RIU, the figure of merit of 1011.63 RIU⁻¹, signal to noise ratio of 10.05 dB, the detection accuracy of 0.016598 nm⁻¹, and detection limit of 102.23 nm. However, the promising sensing performance indicates that the proposed sensor could be implemented effectively to detect different biological and chemical substances.

In this paper, a novel photonic crystal fiber (PCF) is numerically characterized by finite element method (FEM) based mode solver software for bio-analyte sensing, particularly for detecting natural sucrose having a refractive index (RI) ranging from 1.29 to 1.42. The proposed PCF consists of a solid silica core and adjacent rectangular air holes in the cladding. To introduce the widely known surface plasmon resonance (SPR) phenomenon into the proposed sensor, the entire outer surface is covered by a thin gold film. The sensing methodology is appropriately addressed, and each of the designed parameters of the sensor structure is tuned sufficiently to find out the desired sensing performance. Considering RI change at the outer surface, appealing sensing performance such as maximum wavelength sensitivity of 216,000 nm/RIU and maximum amplitude sensitivity of 1138.52 RIU - 1 are attained. In addition, the proposed sensor possesses a resolution of 4.63 × 10 - 7 RIU, linearity of 0.9891, the figure of merit of 1981.651 RIU - 1 , and detection accuracy of 0.019802 nm - 1 . However, except for sucrose detection, the promising sensing characteristics of the proposed sensor indicate its potential to be effectively used to detect biochemical and organic samples.

The ease of controlling waveguide properties through unparalleled design flexibility has made the photonic crystal fiber (PCF) an attractive platform for plasmonic structures. In this work, a dual analyte channel’s highly sensitive PCF bio-sensor is proposed based on surface plasmon resonance (SPR). In the proposed design, surface plasmons (SPs) are excited in the inner flat portion of two rectangular analyte channels where gold (Au) strip is deposited. Thus, the surface roughness that might be generated during metal deposition on circular surface could be effectively reduced. Considering the refractive index (RI) change in the analyte channels, the proposed sensor is designed and fully characterized by the finite element method based COMSOL Multiphysics software. Improved sensing characteristics including wavelength sensitivity (WS) of 186,000 nm/RIU and amplitude sensitivity (AS) of 2,792.97 RIU-1 in the wide RI range of 1.30 to 1.43 is obtained. In addition, the proposed sensor exhibits excellent resolution of 5.38 × 10-7, signal to noise ration (SNR) of 13.44 dB, figure of merits (FOM) of 2188.23, detection limit (DL) of 101.05 nm, and detection accuracy (DA) of 0.0204 nm-1. Outcomes of the analysis indicate that the proposed sensor could be suited for accurate detection of organic chemicals, bio-molecules, and biological analytes.