The authors suggest a novel detection method for ceiling damage using image differencing and Grad-CAM. The proposed method requires the latest image and the past image of the facility to compare. It ...adjusts the difference due to camera position, sunlight condition, etc. The authors show validity of this method showing four pairs of input images. The proposed method can appropriately detect damaged areas with better accuracy for facility inspection by narrowing the areas of inspection using image differencing and Grad-CAM procedures.
Osteoarthritis (OA) is a major cause for mobility impairment, specifically among women. Due to lack of medical facilities and expertise in the remote areas, OA detection occurs at quite severe stages ...when already it has started affecting the mobility and the recovery is difficult. OA severity is usu-ally measured through Kelligen-Lawrence (KL) grades. Simple radiography (X-ray imaging), being non-invasive, cost-effective and easily available, is considered an important tool for early detection and mass scanning. But, it is less accurate. The state-of-art literature shows that the accuracy obtained on OA severity detection using radiograph has a better scope of improvement. It is expected that deep learning will provide a better accuracy given good amount of training data. Also, most of the work done till now is on the datasets from the western subjects. Due to the difference in knee structure, it is expected that the systems developed for OA severity stage detection on western subjects will not be equivalently accurate for Indian subjects. Accordingly, the current article targets deep learning based OA severity detection with better accuracy for Indian subjects. It successfully achieves it by employing transfer learning through EfficientNetB1 with the test accuracy of almost 89% on the database from Indian subjects.
We develop an approach of the Grad–Shafranov (GS) reconstruction for toroidal structures in space plasmas, based on
in situ
spacecraft measurements. The underlying theory is the GS equation that ...describes two-dimensional magnetohydrostatic equilibrium, as widely applied in fusion plasmas. The geometry is such that the arbitrary cross-section of the torus has rotational symmetry about the rotation axis,
Z
, with a major radius,
r
0
. The magnetic field configuration is thus determined by a scalar flux function,
Ψ
, and a functional
F
that is a single-variable function of
Ψ
. The algorithm is implemented through a two-step approach: i) a trial-and-error process by minimizing the residue of the functional
F
(
Ψ
)
to determine an optimal
Z
-axis orientation, and ii) for the chosen
Z
, a
χ
2
minimization process resulting in a range of
r
0
. Benchmark studies of known analytic solutions to the toroidal GS equation with noise additions are presented to illustrate the two-step procedure and to demonstrate the performance of the numerical GS solver, separately. For the cases presented, the errors in
Z
and
r
0
are
9
∘
and 22%, respectively, and the relative percent error in the numerical GS solutions is smaller than 10%. We also make public the computer codes for these implementations and benchmark studies.
The dark web has been confronted with a significant increase in the number and variety of onion services of illegitimate and criminal intent. Anonymity, encryption, and the technical complexity of ...the Tor network are key challenges in detecting, disabling, and regulating such services. Instead of tracking an operational location, cyber threat intelligence can become more proactive by utilizing recent advances in Artificial Intelligence (AI) to detect and classify onion services based on the content, as well as provide an interpretation of the classification outcome. In this paper, we propose a novel multimodal classification approach based on explainable deep learning that classifies onion services based on the image and text content of each site. A Convolutional Neural Network with Gradient-weighted Class Activation Mapping (Grad-CAM) and a pre-trained word embedding with Bahdanau additive attention are the core capabilities of this approach that classify and contextualize the representative features of an onion service. We demonstrate the superior classification accuracy of this approach as well as the role of explainability in decision-making that collectively enables proactive cyber threat intelligence in the dark web.
This reprint showcases a selection of bleeding-edge articles about medical image processing and segmentation workflows based on artificial intelligence algorithms. The proposed papers are applied to ...multiple and different anatomical districts and clinical scenarios.
Početkom Domovinskog rata na području Osijeka vodile su se najžešće borbe. Postojala je intenzivna ratna dinamika hrvatskih oružanih snaga protiv dijela pobunjenih Srba i Jugoslavenske narodne ...armije, što je rezultiralo najvećim brojem vojnih i civilnih žrtava. Zbog položaja Osijeka u istočnoj Hrvatskoj, gdje Srbija izravno graniči s Republikom Hrvatskom, pobunjeni Srbi i Jugoslavenska narodna armija imali su neograničenu logističku podršku. Nadalje, nacionalna struktura stanovništva u istočnoj Hrvatskoj, gdje su postojale srpske enklave (Tenja, Bobota, Vera, Pačetin, Trpinja, Bijelo Brdo i druga sela), olakšavala je velikosrpsku agresiju i ometala obrambene aktivnosti hrvatskih vlasti. Grad Osijek bio je stožerni grad koji je pridonio obrani istočne Hrvatske. Gradsko gospodarstvo kontinuirano je funkcioniralo tijekom Domovinskog rata, snažno podržavajući njegovu obranu, unatoč brojnim ratnim štetama i demografskim gubicima.
In response to the current lack of annotations for flower images and insufficient focus on key image features in traditional fine-grained flower image classification based on deep learning, this ...study proposes the SA-ConvNeXt flower image classification model. Initially, in the image preprocessing stage, a padding algorithm was used to prevent image deformation and loss of detail caused by scaling. Subsequently, the model was integrated using multi-level feature extraction within the Efficient Channel Attention (ECA) mechanism, forming an M-ECA structure to capture channel features at different levels; a pixel attention mechanism was also introduced to filter out irrelevant or noisy information in the images. Following this, a parameter-free attention module (SimAM) was introduced after deep convolution in the ConvNeXt Block to reweight the input features. SANet, which combines M-ECA and pixel attention mechanisms, was employed at the end of the module to further enhance the model’s dynamic extraction capability of channel and pixel features. Considering the model’s generalization capability, transfer learning was utilized to migrate the pretrained weights of ConvNeXt on the ImageNet dataset to the SA-ConvNeXt model. During training, the Focal Loss function and the Adam optimizer were used to address sample imbalance and reduce gradient fluctuations, thereby enhancing training stability. Finally, the Grad-CAM++ technique was used to generate heatmaps of classification predictions, facilitating the visualization of effective features and deepening the understanding of the model’s focus areas. Comparative experiments were conducted on the Oxford Flowers102 flower image dataset. Compared to existing flower image classification technologies, SA-ConvNeXt performed excellently, achieving a high accuracy of 96.7% and a recall rate of 98.2%, with improvements of 4.0% and 3.7%, respectively, compared to the original ConvNeXt. The results demonstrate that SA-ConvNeXt can effectively capture more accurate key features of flower images, providing an effective technical means for flower recognition and classification.
Since early 2020, coronavirus has spread extensively throughout the globe. It was first detected in Wuhan, a province in China. Many researchers have proposed various models to solve problems related ...to COVID-19 detection. As traditional medical approaches take a lot of time to detect the virus and require specific laboratory tests, the adoption of artificial intelligence (AI), including machine learning, might play an important role in handling the problem. A great deal of research has seen the adoption of AI succeed in the early detection of COVID-19 using X-ray images. Unfortunately, the majority of deep learning adoption for COVID-19 detection has the shortcomings of high error detection and high computation costs. In this study, we employed a hybrid model using an auto-encoder (AE) and a convolutional neural network (CNN) (named AMIKOMNET) with a small number of layers and parameters. We implemented an ensemble learning mechanism in the AMIKOMNET model using Adaboost with the aim of reducing error detection in COVID-19 classification tasks. The experimental results for the binary class show that our model achieved high effectiveness, with 96.90% accuracy, 95.06% recall, 94.67% F1-score, and 96.03% precision. The experimental result for the multiclass achieved 95.13% accuracy, 94.93% recall, 95.75% F1-score, and 96.19% precision. The adoption of Adaboost in AMIKOMNET for the binary class increased the effectiveness of the model to 98.45% accuracy, 96.16% recall, 95.70% F1-score, and 96.87% precision. The adoption of Adaboost in AMIKOMNET in the multiclass classification task also saw an increase in performance, with an accuracy of 96.65%, a recall of 94.93%, an F1-score of 95.76%, and a precision of 96.19%. The implementation of AE to handle image feature extraction combined with a CNN used to handle dimensional image feature reduction achieved outstanding performance when compared to previous work using a deep learning platform. Exploiting Adaboost also increased the effectiveness of the AMIKOMNET model in detecting COVID-19.
Deep learning architectures like ResNet and Inception have produced accurate predictions for classifying benign and malignant tumors in the healthcare domain. This enables healthcare institutions to ...make data-driven decisions and potentially enable early detection of malignancy by employing computer-vision-based deep learning algorithms. These CNN algorithms, in addition to requiring huge amounts of data, can identify higher- and lower-level features that are significant while classifying tumors into benign or malignant. However, the existing literature is limited in terms of the explainability of the resultant classification, and identifying the exact features that are of importance, which is essential in the decision-making process for healthcare practitioners. Thus, the motivation of this work is to implement a custom classifier on the ovarian tumor dataset, which exhibits high classification performance and subsequently interpret the classification results qualitatively, using various Explainable AI methods, to identify which pixels or regions of interest are given highest importance by the model for classification. The dataset comprises CT scanned images of ovarian tumors taken from to the axial, saggital and coronal planes. State-of-the-art architectures, including a modified ResNet50 derived from the standard pre-trained ResNet50, are implemented in the paper. When compared to the existing state-of-the-art techniques, the proposed modified ResNet50 exhibited a classification accuracy of 97.5 % on the test dataset without increasing the the complexity of the architecture. The results then were carried for interpretation using several explainable AI techniques. The results show that the shape and localized nature of the tumors play important roles for qualitatively determining the ability of the tumor to metastasize and thereafter to be classified as benign or malignant.
Breast cancer is a significant health concern among women. Prompt diagnosis can diminish the mortality rate and direct patients to take steps for cancer treatment. Recently, deep learning has been ...employed to diagnose breast cancer in the context of digital pathology. To help in this area, a transfer learning-based model called 'HE-HER2Net' has been proposed to diagnose multiple stages of HER2 breast cancer (HER2-0, HER2-1+, HER2-2+, HER2-3+) on H&E (hematoxylin & eosin) images from the BCI dataset. HE-HER2Net is the modified version of the Xception model, which is additionally comprised of global average pooling, several batch normalization layers, dropout layers, and dense layers with a swish activation function. This proposed model exceeds all existing models in terms of accuracy (0.87), precision (0.88), recall (0.86), and AUC score (0.98) immensely. In addition, our proposed model has been explained through a class-discriminative localization technique using Grad-CAM to build trust and to make the model more transparent. Finally, nuclei segmentation has been performed through the StarDist method.