DHFS-ECM: Design of a Dual Heuristic Feature Selection-based Ensemble Classification Model for the Identification of Bamboo Species from Genomic Sequences.

Background: Analyzing genomic sequences plays a crucial role in understanding biological diversity and classifying Bamboo species. Existing methods for genomic sequence analysis suffer from limitations such as complexity, low accuracy, and the need for constant reconfiguration in response to evolving genomic datasets. Aim: This study addresses these limitations by introducing a novel Dual Heuristic Feature Selection-based Ensemble Classification Model (DHFS-ECM) for the precise identification of Bamboo species from genomic sequences. Methods: The proposed DHFS-ECM method employs a Genetic Algorithm to perform dual heuristic feature selection. This process maximizes inter-class variance, leading to the selection of informative N-gram feature sets. Subsequently, intra-class variance levels are used to create optimal training and validation sets, ensuring comprehensive coverage of class-specific features. The selected features are then processed through an ensemble classification layer, combining multiple stratification models for species-specific categorization. Results: Comparative analysis with state-of-the-art methods demonstrate that DHFS-ECM achieves remarkable improvements in accuracy (9.5%), precision (5.9%), recall (8.5%), and AUC performance (4.5%). Importantly, the model maintains its performance even with an increased number of species classes due to the continuous learning facilitated by the Dual Heuristic Genetic Algorithm Model. Conclusion: DHFS-ECM offers several key advantages, including efficient feature extraction, reduced model complexity, enhanced interpretability, and increased robustness and accuracy through the ensemble classification layer. These attributes make DHFS-ECM a promising tool for real-time clinical applications and a valuable contribution to the field of genomic sequence analysis.

Intelligent skin-removal photoacoustic computed tomography for human based on deep learning.

Photoacoustic computed tomography (PACT) has centimeter-level imaging ability and can be used to detect the human body. However, strong photoacoustic signals from skin cover deep tissue information, hindering the frontal display and analysis of photoacoustic images of deep regions of interest. Therefore, we propose a 2.5 D deep learning model based on feature pyramid structure and single-type skin annotation to extract the skin region, and design a mask generation algorithm to remove skin automatically. PACT imaging experiments on the human periphery blood vessel verified the correctness our proposed skin-removal method. Compared with previous studies, our method exhibits high robustness to the uneven illumination, irregular skin boundary, and reconstruction artifacts in the images, and the reconstruction errors of PACT images decreased by 20% ~ 90% with a 1.65 dB improvement in the signal-to-noise ratio at the same time. This study may provide a promising way for high-definition PACT imaging of deep tissues.

Feature reassembly and L1 preemption: Acquiring CLLD in L2 Italian and L2 Romanian.

This study investigates feature acquisition and feature reassembly associated with Clitic Left Dislocation (CLLD). The article compares the acquisition of CLLD in second language (L2) Italian to L2 Romanian to examine effects of first language (L1) transfer, construction frequency and the type of interface involved (external vs. internal interface) within the same syntactic construction. The results from an acceptability judgment task and a written elicitation task show that while English near-native speakers of Italian/Romanian acquired the L2 constraints on CLLD, which is [+anaphor] for Italian and [+specific] for Romanian, data from both Romanian L2 learners of Italian and Italian L2 learners of Romanian showed persistent L1 transfer effects. Target-like acquisition for these groups requires both grammatical expansion and retraction; Romanian CLLD requires the addition of an L1-unavailable [+specific] feature and the loss of a [+anaphor] feature, while Italian CLLD requires the addition of an L1-unavailable [+anaphor] and the loss of a [+specific] feature. The reported findings extend evidence in favour of the Feature Reassembly Hypothesis to the syntax-discourse interface, as reassembly of interpretational features associated with CLLD proved more difficult than feature acquisition. While learners at the near-native levels were able to broaden the contexts that allow a clitic in the L2 (grammatical expansion), L1 preemption difficulties were attested as well. This was the case regardless of the frequency of the relevant construction in the input and the type of L2 feature that needed to be added/removed.

Classification of tomato leaf images for detection of plant disease using conformable polynomials image features.

Plant diseases can spread rapidly, leading to significant crop losses if not detected early. By accurately identifying diseased plants, farmers can target treatment only to the affected areas, reducing the number of pesticides or fungicides needed and minimizing environmental impact. Tomatoes are among the most significant and extensively consumed crops worldwide. The main factor affecting crop yield quantity and quality is leaf disease. Various diseases can affect tomato production, impacting both yield and quality. Automated classification of leaf images allows for the early identification of diseased plants, enabling prompt intervention and control measures. Many creative approaches to diagnosing and categorizing specific illnesses have been widely employed. The manual method is costly and labor-intensive. Without the assistance of an agricultural specialist, disease detection can be facilitated by image processing combined with machine learning algorithms. In this study, the diseases in tomato leaves will be detected using new feature extraction method using conformable polynomials image features for accurate solution and faster detection of plant diseases through a machine learning model. The methodology of this study based on:•Preprocessing, feature extraction, dimension reduction and classification modules.•Conformable polynomials method is used to extract the texture features which is passed classifier.•The proposed texture feature is constructed by two parts the enhanced based term, and the texture detail part for textual analysis.•The tomato leaf samples from the plant village image dataset were used to gather the data for this model. The disease detected are 98.80 % accurate for tomato leaf images using SVM classifier. In addition to lowering financial loss, the suggested feature extraction method can help manage plant diseases effectively, improving crop yield and food security.

FCSU-Net: A novel full-scale Cross-dimension Self-attention U-Net with collaborative fusion of multi-scale feature for medical image segmentation.

Recently, ViT and CNNs based on encoder-decoder architecture have become the dominant model in the field of medical image segmentation. However, there are some deficiencies for each of them: (1) It is difficult for CNNs to capture the interaction between two locations with consideration of the longer distance. (2) ViT cannot acquire the interaction of local context information and carries high computational complexity. To optimize the above deficiencies, we propose a new network for medical image segmentation, which is called FCSU-Net. FCSU-Net uses the proposed collaborative fusion of multi-scale feature block that enables the network to obtain more abundant and more accurate features. In addition, FCSU-Net fuses full-scale feature information through the FFF (Full-scale Feature Fusion) structure instead of simple skip connections, and establishes long-range dependencies on multiple dimensions through the CS (Cross-dimension Self-attention) mechanism. Meantime, every dimension is complementary to each other. Also, CS mechanism has the advantage of convolutions capturing local contextual weights. Finally, FCSU-Net is validated on several datasets, and the results show that FCSU-Net not only has a relatively small number of parameters, but also has a leading segmentation performance.

Gated SPECT-Derived Myocardial Strain Estimated From Deep-Learning Image Translation Validated From N-13 Ammonia PET.

RATIONALE AND OBJECTIVES: This study investigated the use of deep learning-generated virtual positron emission tomography (PET)-like gated single-photon emission tomography (SPECTVP) for assessing myocardial strain, overcoming limitations of conventional SPECT. MATERIALS AND METHODS: SPECT-to-PET translation models for short-axis, horizontal, and vertical long-axis planes were trained using image pairs from the same patients in stress (720 image pairs from 18 patients) and resting states (920 image pairs from 23 patients). Patients without ejection-fraction changes during SPECT and PET were selected for training. We independently analyzed circumferential strains from short-axis-gated SPECT, PET, and model-generated SPECTVP images using a feature-tracking algorithm. Longitudinal strains were similarly measured from horizontal and vertical long-axis images. Intraclass correlation coefficients (ICCs) were calculated with two-way random single-measure SPECT and SPECTVP (PET). ICCs (95% confidence intervals) were defined as excellent (≥0.75), good (0.60-0.74), moderate (0.40-0.59), or poor (≤0.39). RESULTS: Moderate ICCs were observed for SPECT-derived stressed circumferential strains (0.56 [0.41-0.69]). Excellent ICCs were observed for SPECTVP-derived stressed circumferential strains (0.78 [0.68-0.85]). Excellent ICCs of stressed longitudinal strains from horizontal and vertical long axes, derived from SPECT and SPECTVP, were observed (0.83 [0.73-0.90], 0.91 [0.85-0.94]). CONCLUSION: Deep-learning SPECT-to-PET transformation improves circumferential strain measurement accuracy using standard-gated SPECT. Furthermore, the possibility of applying longitudinal strain measurements via both PET and SPECTVP was demonstrated. This study provides preliminary evidence that SPECTVP obtained from standard-gated SPECT with postprocessing potentially adds clinical value through PET-equivalent myocardial strain analysis without increasing the patient burden.

FPWT: Filter pruning via wavelet transform for CNNs.

The enormous data and computational resources required by Convolutional Neural Networks (CNNs) hinder the practical application on mobile devices. To solve this restrictive problem, filter pruning has become one of the practical approaches. At present, most existing pruning methods are currently developed and practiced with respect to the spatial domain, which ignores the potential interconnections in the model structure and the decentralized distribution of image energy in the spatial domain. The image frequency domain transform method can remove the correlation between image pixels and concentrate the image energy distribution, which results in lossy compression of images. In this study, we find that the frequency domain transform method is also applicable to the feature maps of CNNs. The filter pruning via wavelet transform (WT) is proposed in this paper (FPWT), which combines the frequency domain information of WT with the output feature map to more obviously find the correlation between feature maps and make the energy into a relatively concentrated distribution in the frequency domain. Moreover, the importance score of each feature map is calculated by the cosine similarity and the energy-weighted coefficients of the high and low frequency components, and prune the filter based on its importance score. Experiments on two image classification datasets validate the effectiveness of FPWT. For ResNet-110 on CIFAR-10, FPWT reduces FLOPs and parameters by more than 60.0 % with 0.53 % accuracy improvement. For ResNet-50 on ImageNet, FPWT reduces FLOPs by 53.8 % and removes parameters by 49.7 % with only 0.97 % loss of Top-1 accuracy.

Cardiac MR Feature Tracking Derived Strain Analysis can Predict Return to Training following Exertional Heatstroke.

BACKGROUND: Exertional heatstroke (EHS) is increasingly common in young trained soldiers. However, the prognosis marker in EHS patients remains unclear. To evaluate cardiac MRI feature tracking (CMR-FT) derived left ventricle (LV) strain as a biomarker for return to training (RTT) in trained soldiers with EHS in a prospective CMR cohort. METHODS: Trained soldiers (participants) with EHS underwent cardiac MR cine sequences between June 2020 and August 2023. Two-dimensional (2D) LV strain parameters were derived. At 3 months after index CMR, the participants with persistent cardiac symptoms including chest pain, dyspnea, palpitations, syncope, and recurrent heat-related illness were defined as non-RTT. Multivariable logistic regression analysis is used to develop a predictive RTT model. The performance of different models was compared using the area under curve (AUC). RESULTS: A total of 80 participants (median age, 21 years; interquartile range (IQR), 20-23 years) and 27 health controls (median age, 21 years; IQR, 20-22 years) were prospectively included. Of the 77 participants, 32 (41.6%) had persistent cardiac symptoms and were not able to RTT at 3 months follow-up after experiencing EHS. The 2D global longitudinal strain (GLS) was significantly impaired in EHS participants compared to the healthy control group (-15.81 ± 1.67% vs -16.93 ± 1.22%, P =.001), which also showed significantly statistical differences between participants with RTT and non-RTT (-14.99 ± 3.54% vs -16.53 ± 1.43%, P <.001). 2D-GLS (≤ -15.00%) (odds ratio, 1.53; 95% confidence interval (CI): 1.08, 2.17; P =.016) was an independent predictor for RTT even after adjusting known risk factors. 2D-GLS provided incremental prognostic value over the clinical model and conventional CMR parameters model (AUCs: 0.72 vs 0.88, P =.013; 0.79 vs 0.88, P =.023; respectively). CONCLUSIONS: Two-dimensional global longitudinal strain (≤ -15.00%) is an incremental prognostic CMR biomarker to predict return to training in exertional heatstroke soldiers.

Unsupervised Feature Selection to Identify Important ICD-10 and ATC Codes for Machine Learning on a Cohort of Patients With Coronary Heart Disease: Retrospective Study.

Background: The application of machine learning in health care often necessitates the use of hierarchical codes such as the International Classification of Diseases (ICD) and Anatomical Therapeutic Chemical (ATC) systems. These codes classify diseases and medications, respectively, thereby forming extensive data dimensions. Unsupervised feature selection tackles the "curse of dimensionality" and helps to improve the accuracy and performance of supervised learning models by reducing the number of irrelevant or redundant features and avoiding overfitting. Techniques for unsupervised feature selection, such as filter, wrapper, and embedded methods, are implemented to select the most important features with the most intrinsic information. However, they face challenges due to the sheer volume of ICD and ATC codes and the hierarchical structures of these systems. Objective: The objective of this study was to compare several unsupervised feature selection methods for ICD and ATC code databases of patients with coronary artery disease in different aspects of performance and complexity and select the best set of features representing these patients. Methods: We compared several unsupervised feature selection methods for 2 ICD and 1 ATC code databases of 51,506 patients with coronary artery disease in Alberta, Canada. Specifically, we used the Laplacian score, unsupervised feature selection for multicluster data, autoencoder-inspired unsupervised feature selection, principal feature analysis, and concrete autoencoders with and without ICD or ATC tree weight adjustment to select the 100 best features from over 9000 ICD and 2000 ATC codes. We assessed the selected features based on their ability to reconstruct the initial feature space and predict 90-day mortality following discharge. We also compared the complexity of the selected features by mean code level in the ICD or ATC tree and the interpretability of the features in the mortality prediction task using Shapley analysis. Results: In feature space reconstruction and mortality prediction, the concrete autoencoder-based methods outperformed other techniques. Particularly, a weight-adjusted concrete autoencoder variant demonstrated improved reconstruction accuracy and significant predictive performance enhancement, confirmed by DeLong and McNemar tests (P<.05). Concrete autoencoders preferred more general codes, and they consistently reconstructed all features accurately. Additionally, features selected by weight-adjusted concrete autoencoders yielded higher Shapley values in mortality prediction than most alternatives. Conclusions: This study scrutinized 5 feature selection methods in ICD and ATC code data sets in an unsupervised context. Our findings underscore the superiority of the concrete autoencoder method in selecting salient features that represent the entire data set, offering a potential asset for subsequent machine learning research. We also present a novel weight adjustment approach for the concrete autoencoders specifically tailored for ICD and ATC code data sets to enhance the generalizability and interpretability of the selected features.

StackedEnC-AOP: prediction of antioxidant proteins using transform evolutionary and sequential features based multi-scale vector with stacked ensemble learning.

BACKGROUND: Antioxidant proteins are involved in several biological processes and can protect DNA and cells from the damage of free radicals. These proteins regulate the body's oxidative stress and perform a significant role in many antioxidant-based drugs. The current invitro-based medications are costly, time-consuming, and unable to efficiently screen and identify the targeted motif of antioxidant proteins. METHODS: In this model, we proposed an accurate prediction method to discriminate antioxidant proteins namely StackedEnC-AOP. The training sequences are formulation encoded via incorporating a discrete wavelet transform (DWT) into the evolutionary matrix to decompose the PSSM-based images via two levels of DWT to form a Pseudo position-specific scoring matrix (PsePSSM-DWT) based embedded vector. Additionally, the Evolutionary difference formula and composite physiochemical properties methods are also employed to collect the structural and sequential descriptors. Then the combined vector of sequential features, evolutionary descriptors, and physiochemical properties is produced to cover the flaws of individual encoding schemes. To reduce the computational cost of the combined features vector, the optimal features are chosen using Minimum redundancy and maximum relevance (mRMR). The optimal feature vector is trained using a stacking-based ensemble meta-model. RESULTS: Our developed StackedEnC-AOP method reported a prediction accuracy of 98.40% and an AUC of 0.99 via training sequences. To evaluate model validation, the StackedEnC-AOP training model using an independent set achieved an accuracy of 96.92% and an AUC of 0.98. CONCLUSION: Our proposed StackedEnC-AOP strategy performed significantly better than current computational models with a ~ 5% and ~ 3% improved accuracy via training and independent sets, respectively. The efficacy and consistency of our proposed StackedEnC-AOP make it a valuable tool for data scientists and can execute a key role in research academia and drug design.

GA-GBLUP: leveraging the genetic algorithm to improve the predictability of genomic selection.

Genomic selection (GS) has emerged as an effective technology to accelerate crop hybrid breeding by enabling early selection prior to phenotype collection. Genomic best linear unbiased prediction (GBLUP) is a robust method that has been routinely used in GS breeding programs. However, GBLUP assumes that markers contribute equally to the total genetic variance, which may not be the case. In this study, we developed a novel GS method called GA-GBLUP that leverages the genetic algorithm (GA) to select markers related to the target trait. We defined four fitness functions for optimization, including AIC, BIC, R2, and HAT, to improve the predictability and bin adjacent markers based on the principle of linkage disequilibrium to reduce model dimension. The results demonstrate that the GA-GBLUP model, equipped with R2 and HAT fitness function, produces much higher predictability than GBLUP for most traits in rice and maize datasets, particularly for traits with low heritability. Moreover, we have developed a user-friendly R package, GAGBLUP, for GS, and the package is freely available on CRAN (https://CRAN.R-project.org/package=GAGBLUP).

Rigdelet neural network and improved partial reinforcement effect optimizer for music genre classification from sound spectrum images.

In this paper, a new approach has been introduced for classifying the music genres. The proposed approach involves transforming an audio signal into a unified representation known as a sound spectrum, from which texture features have been extracted using an enhanced Rigdelet Neural Network (RNN). Additionally, the RNN has been optimized using an improved version of the partial reinforcement effect optimizer (IPREO) that effectively avoids local optima and enhances the RNN's generalization capability. The GTZAN dataset has been utilized in experiments to assess the effectiveness of the proposed RNN/IPREO model for music genre classification. The results show an impressive accuracy of 92 % by incorporating a combination of spectral centroid, Mel-spectrogram, and Mel-frequency cepstral coefficients (MFCCs) as features. This performance significantly outperformed K-Means (58 %) and Support Vector Machines (up to 68 %). Furthermore, the RNN/IPREO model outshined various deep learning architectures such as Neural Networks (65 %), RNNs (84 %), CNNs (88 %), DNNs (86 %), VGG-16 (91 %), and ResNet-50 (90 %). It is worth noting that the RNN/IPREO model was able to achieve comparable results to well-known deep models like VGG-16, ResNet-50, and RNN-LSTM, sometimes even surpassing their scores. This highlights the strength of its hybrid CNN-Bi-directional RNN design in conjunction with the IPREO parameter optimization algorithm for extracting intricate and sequential auditory data.

Machine learning algorithms predict canine structural epilepsy with high accuracy.

Introduction: Clinical reasoning in veterinary medicine is often based on clinicians' personal experience in combination with information derived from publications describing cohorts of patients. Studies on the use of scientific methods for patient individual decision making are largely lacking. This applies to the prediction of the individual underlying pathology in seizuring dogs as well. The aim of this study was to apply machine learning to the prediction of the risk of structural epilepsy in dogs with seizures. Materials and methods: Dogs with a history of seizures were retrospectively as well as prospectively included. Data about clinical history, neurological examination, diagnostic tests performed as well as the final diagnosis were collected. For data analysis, the Bayesian Network and Random Forest algorithms were used. A total of 33 features for Random Forest and 17 for Bayesian Network were available for analysis. The following four feature selection methods were applied to select features for further analysis: Permutation Importance, Forward Selection, Random Selection and Expert Opinion. The two algorithms Bayesian Network and Random Forest were trained to predict structural epilepsy using the selected features. Results: A total of 328 dogs of 119 different breeds were identified retrospectively between January 2017 and June 2021, of which 33.2% were diagnosed with structural epilepsy. An overall of 89,848 models were trained. The Bayesian Network in combination with the Random feature selection performed best. It was able to predict structural epilepsy with an accuracy of 0.969 (sensitivity: 0.857, specificity: 1.000) among all dogs with seizures using the following features: age at first seizure, cluster seizures, seizure in last 24 h, seizure in last 6 month, and seizure in last year. Conclusion: Machine learning algorithms such as Bayesian Networks and Random Forests identify dogs with structural epilepsy with a high sensitivity and specificity. This information could provide some guidance to clinicians and pet owners in their clinical decision-making process.

Transformer-based decoder of melanoma classification using hand-crafted texture feature fusion and Gray Wolf Optimization algorithm.

Melanoma is a type of skin cancer that poses significant health risks and requires early detection for effective treatment. This study proposing a novel approach that integrates a transformer-based model with hand-crafted texture features and Gray Wolf Optimization, aiming to enhance efficiency of melanoma classification. Preprocessing involves standardizing image dimensions and enhancing image quality through median filtering techniques. Texture features, including GLCM and LBP, are extracted to capture spatial patterns indicative of melanoma. The GWO algorithm is applied to select the most discriminative features. A transformer-based decoder is then employed for classification, leveraging attention mechanisms to capture contextual dependencies. The experimental validation on the HAM10000 dataset and ISIC2019 dataset showcases the effectiveness of the proposed methodology. The transformer-based model, integrated with hand-crafted texture features and guided by Gray Wolf Optimization, achieves outstanding results. The results showed that the proposed method performed well in melanoma detection tasks, achieving an accuracy and F1-score of 99.54% and 99.11% on the HAM10000 dataset, and an accuracy of 99.47%, and F1-score of 99.25% on the ISIC2019 dataset. • We use the concepts of LBP and GLCM to extract features from the skin lesion images. • The Gray Wolf Optimization (GWO) algorithm is employed for feature selection. • A decoder based on Transformers is utilized for melanoma classification.

Association study of NAFLD with pericoronary adipose tissue and pericardial adipose tissue: Diagnosis of stable CAD patients with NAFLD based on radiomic features.

BACKGROUND AND AIM: Nonalcoholic fatty liver disease (NAFLD) is prone to complicated cardiovascular disease, and we aimed to identify patients with NAFLD who are prone to developing stable coronary artery disease (CAD). METHODS AND RESULTS: We retrospectively recruited adults who underwent coronary computed tomography angiography (CTA). A total of 127 NAFLD patients and 127 non-NAFLD patients were included in this study. Clinical features and imaging parameters were analysed, mainly including pericardial adipose tissue (PAT), pericoronary adipose tissue (PCAT), and radiomic features of 6792 PCATs. The inflammatory associations of NAFLD patients with PAT and PCAT were analysed. Clinical features (model 1), CTA parameters (model 2), the radscore (model 3), and a composite model (model 4) were constructed to identify patients with NAFLD with stable CAD. The presence of NAFLD resulted in a greater inflammatory involvement in all three coronary arteries (all P < 0.01) and was associated with increased PAT volume (r = 0.178**, P < 0.05). In the presence of NAFLD, the mean CT value of the PAT was significantly correlated with the fat attenuation index (FAI) in all three vessels and had the strongest correlation with the RCA FAI (r = 0.55, p < 0.001). A total of 9 radiomic features were screened by LASSO regression to calculate radiomic scores. In the model comparison, model 4 had the best performance of all models (AUC 0.914 [0.863-0.965]) and the highest overall diagnostic value of the model (sensitivity: 0.814, specificity: 0.941). CONCLUSIONS: NAFLD correlates with PAT volume and PCAT inflammation. Furthermore, combining clinical features, CTA parameters, and radiomic scores can improve the efficiency of early diagnosis of stable CAD in patients with NAFLD.

Open your black box classifier.

A priority for machine learning in healthcare and other high stakes applications is to enable end-users to easily interpret individual predictions. This opinion piece outlines recent developments in interpretable classifiers and methods to open black box models.

DEAF-Net: Detail-Enhanced Attention Feature Fusion Network for Retinal Vessel Segmentation.

Retinal vessel segmentation is crucial for the diagnosis of ophthalmic and cardiovascular diseases. However, retinal vessels are densely and irregularly distributed, with many capillaries blending into the background, and exhibit low contrast. Moreover, the encoder-decoder-based network for retinal vessel segmentation suffers from irreversible loss of detailed features due to multiple encoding and decoding, leading to incorrect segmentation of the vessels. Meanwhile, the single-dimensional attention mechanisms possess limitations, neglecting the importance of multidimensional features. To solve these issues, in this paper, we propose a detail-enhanced attention feature fusion network (DEAF-Net) for retinal vessel segmentation. First, the detail-enhanced residual block (DERB) module is proposed to strengthen the capacity for detailed representation, ensuring that intricate features are efficiently maintained during the segmentation of delicate vessels. Second, the multidimensional collaborative attention encoder (MCAE) module is proposed to optimize the extraction of multidimensional information. Then, the dynamic decoder (DYD) module is introduced to preserve spatial information during the decoding process and reduce the information loss caused by upsampling operations. Finally, the proposed detail-enhanced feature fusion (DEFF) module composed of DERB, MCAE and DYD modules fuses feature maps from both encoding and decoding and achieves effective aggregation of multi-scale contextual information. The experiments conducted on the datasets of DRIVE, CHASEDB1, and STARE, achieving Sen of 0.8305, 0.8784, and 0.8654, and AUC of 0.9886, 0.9913, and 0.9911 on DRIVE, CHASEDB1, and STARE, respectively, demonstrate the performance of our proposed network, particularly in the segmentation of fine retinal vessels.

MARes-Net: multi-scale attention residual network for jaw cyst image segmentation.

Jaw cyst is a fluid-containing cystic lesion that can occur in any part of the jaw and cause facial swelling, dental lesions, jaw fractures, and other associated issues. Due to the diversity and complexity of jaw images, existing deep-learning methods still have challenges in segmentation. To this end, we propose MARes-Net, an innovative multi-scale attentional residual network architecture. Firstly, the residual connection is used to optimize the encoder-decoder process, which effectively solves the gradient disappearance problem and improves the training efficiency and optimization ability. Secondly, the scale-aware feature extraction module (SFEM) significantly enhances the network's perceptual abilities by extending its receptive field across various scales, spaces, and channel dimensions. Thirdly, the multi-scale compression excitation module (MCEM) compresses and excites the feature map, and combines it with contextual information to obtain better model performance capabilities. Furthermore, the introduction of the attention gate module marks a significant advancement in refining the feature map output. Finally, rigorous experimentation conducted on the original jaw cyst dataset provided by Quzhou People's Hospital to verify the validity of MARes-Net architecture. The experimental data showed that precision, recall, IoU and F1-score of MARes-Net reached 93.84%, 93.70%, 86.17%, and 93.21%, respectively. Compared with existing models, our MARes-Net shows its unparalleled capabilities in accurately delineating and localizing anatomical structures in the jaw cyst image segmentation.

Large-scale IoT attack detection scheme based on LightGBM and feature selection using an improved salp swarm algorithm.

Due to the swift advancement of the Internet of Things (IoT), there has been a significant surge in the quantity of interconnected IoT devices that send and exchange vital data across the network. Nevertheless, the frequency of attacks on the Internet of Things is steadily rising, posing a persistent risk to the security and privacy of IoT data. Therefore, it is crucial to develop a highly efficient method for detecting cyber threats on the Internet of Things. Nevertheless, several current network attack detection schemes encounter issues such as insufficient detection accuracy, the curse of dimensionality due to excessively high data dimensions, and the sluggish efficiency of complex models. Employing metaheuristic algorithms for feature selection in network data represents an effective strategy among the myriad of solutions. This study introduces a more comprehensive metaheuristic algorithm called GQBWSSA, which is an enhanced version of the Salp Swarm Algorithm with several strategy improvements. Utilizing this algorithm, a threshold voting-based feature selection framework is designed to obtain an optimized set of features. This procedure efficiently decreases the number of dimensions in the data, hence preventing the negative effects of having a high number of dimensions and effectively extracting the most significant and crucial information. Subsequently, the extracted feature data is combined with the LightGBM algorithm to form a lightweight and efficient ensemble learning scheme for IoT attack detection. The proposed enhanced metaheuristic algorithm has superior performance in feature selection compared to the recent metaheuristic algorithms, as evidenced by the experimental evaluation conducted using the NSLKDD and CICIoT2023 datasets. Compared to current popular ensemble learning solutions, the proposed overall solution exhibits excellent performance on multiple key indicators, including accuracy, precision, as well as training and detection time. Especially on the large-scale dataset CICIoT2023, the proposed scheme achieves an accuracy rate of 99.70% in binary classification and 99.41% in multi classification.

Development of a CNN for Adult Brain Tumour Characterisation: Implications and Future Directions for Transfer Learning.

Brain tumours are the most commonly occurring solid tumours in children, albeit with lower incidence rates compared to adults. However, their inherent heterogeneity, ethical considerations regarding paediatric patients, and difficulty in long-term follow-up make it challenging to gather large homogenous datasets for analysis. This study focuses on the development of a Convolutional Neural Network (CNN) for brain tumour characterisation using the adult BraTS 2020 dataset. We propose to transfer knowledge, from models pre-trained on extensive adult brain tumour datasets to smaller cohort datasets (e.g., paediatric brain tumours) in future studies, by leveraging Transfer Learning (TL). This approach aims to extract relevant features from pre-trained models, addressing the limited availability of annotated paediatric datasets and enhancing tumour characterisation in children. The implications and potential applications of this methodology in paediatric neuro-oncology are discussed.