Influence of Irregular Coastlines on a Tornadic Mesovortex in the Pearl River Delta during the Monsoon Season. Part Ⅰ:Pre-storm Environment and Storm Evolution

The Pearl River Delta(PRD),a tornado hotspot,forms a distinct trumpet-shaped coastline that concaves toward the South China Sea.During the summer monsoon season,low-level southwesterlies over the PRD’s sea surface tend to be turned toward the west coast,constituting a convergent wind field along with the landward-side southwesterlies,which influences regional convective weather.This two-part study explores the roles of this unique land–sea contrast of the trumpet-shaped coastline in the formation of a tornadic mesovortex within monsoonal flows in this region.Part I primarily presents observational analyses of pre-storm environments and storm evolutions.The rotating storm developed in a lowshear environment(not ideal for a supercell)under the interactions of three air masses under the influence of the land–sea contrast,monsoon,and storm cold outflows.This intersection zone(or“triple point”)is typically characterized by local enhancements of ambient vertical vorticity and convergence.Based on a rapid-scan X-band phased-array radar,finger-like echoes were recognized shortly after the gust front intruded on the triple point.Developed over the triple point,they rapidly wrapped up with a well-defined low-level mesovortex.It is thus presumed that the triple point may have played roles in the mesovortex genesis,which will be demonstrated in Part II with multiple sensitivity numerical simulations.The findings also suggest that when storms pass over the boundary intersection zone in the PRD,the expected possibility of a rotating storm occurring is relatively high,even in a low-shear environment.Improved knowledge of such environments provides additional guidance to assess the regional tornado risk.

Attribution of Biases of Interhemispheric Temperature Contrast in CMIP6 Models

One of the basic characteristics of Earth's modern climate is that the Northern Hemisphere(NH) is climatologically warmer than the Southern Hemisphere(SH). Here, model performances of this basic state are examined using simulation results from 26 CMIP6 models. Results show that the CMIP6 models underestimate the contrast in interhemispheric surface temperatures on average(0.8 K for CMIP6 mean versus 1.4 K for reanalysis data mean), and that there is a large intermodel spread, ranging from -0.7 K to 2.3 K. A box model energy budget analysis shows that the contrast in interhemispheric shortwave absorption at the top of the atmosphere, the contrast in interhemispheric greenhouse trapping, and the crossequatorial northward ocean heat transport, are all underestimated in the multimodel mean. By examining the intermodel spread, we find intermodel biases can be tracked back to biases in midlatitude shortwave cloud forcing in AGCMs. Models with a weaker interhemispheric temperature contrast underestimate the shortwave cloud reflection in the SH but overestimate the shortwave cloud reflection in the NH, which are respectively due to underestimation of the cloud fraction over the SH extratropical ocean and overestimation of the cloud liquid water content over the NH extratropical continents.Models that underestimate the interhemispheric temperature contrast exhibit larger double ITCZ biases, characterized by excessive precipitation in the SH tropics. Although this intermodel spread does not account for the multimodel ensemble mean biases, it highlights that improving cloud simulation in AGCMs is essential for simulating the climate realistically in coupled models.

Influence of Irregular Coastlines on a Tornadic Mesovortex in the Pearl River Delta during Monsoon Season.Part II:Numerical Experiments

As demonstrated in the first part of this study(Part I),wind-shift boundaries routinely form along the west coast of the Pearl River Delta due to the land-sea contrast of a“trumpet”shape coastline in the summer monsoon season.Through multiple numerical simulations,this article(Part II)aims to examine the roles of the trumpet-shaped coastline in the mesovortex genesis during the 1 June 2020 tornadic event.The modeling reproduced two mesovortices that are in close proximity in time and space to the realistic mesovortices.In addition to the modeled mesovortex over the triple point where strong ambient vertical vorticity was located,another mesovortex originated from an enhanced discrete vortex along an airmass boundary via shear instability.On the fine-scale storm morphology,finger-like echoes preceding hook echoes were also reproduced around the triple point.Results from sensitivity experiments suggest that the unique topography plays an essential role in modifying the vorticity budget during the mesovortex formation.While there is a high likelihood of an upcoming storm evolving into a rotating storm over the triple point,the simulation's accuracy is sensitive to the local environmental details and storm dynamics.The strengths of cold pool surges from upstream storms may influence the stretching of low-level vertically oriented vortex and thus the wrap-up of finger-like echoes.These findings suggest that the trumpet-shaped coastline is an important component of mesovortex production during the active monsoon season.It is hoped that this study will increase the situational awareness for forecasters regarding regional non-mesocyclone tornadic environments.

Effect of magnetic resonance imaging in liver metastases

This letter to the editor is a commentary on a study titled"Liver metastases:The role of magnetic resonance imaging."Exploring a noninvasive imaging evaluation system for the biological behavior of hepatocellular carcinoma(HCC)is the key to achieving precise diagnosis and treatment and improving prognosis.This review summarizes the role of magnetic resonance imaging in the detection and evaluation of liver metastases,describes its main imaging features,and focuses on the added value of the latest imaging tools(such as T1 weighted in phase imaging,T1 weighted out of phase imaging;diffusion-weighted imaging,T2 weighted imaging).In this study,I investigated the necessity and benefits of gadolinium ethoxybenzyl diethylenetriamine pentaacetic acid for HCC diagnostic testing and prognostic evaluation.

Influence of substrate effect on near-field radiative modulator based on biaxial hyperbolic materials

Relative rotation between the emitter and receiver could effectively modulate the near-field radiative heat transfer(NFRHT)in anisotropic media.Due to the strong in-plane anisotropy,natural hyperbolic materials can be used to construct near-field radiative modulators with excellent modulation effects.However,in practical applications,natural hyperbolic materials need to be deposited on the substrate,and the influence of substrate on modulation effect has not been studied yet.In this work,we investigate the influence of substrate effect on near-field radiative modulator based onα-MoO_(3).The results show that compared to the situation without a substrate,the presence of both lossless and lossy substrate will reduce the modulation contrast(MC)for different film thicknesses.When the real or imaginary component of the substrate permittivity increases,the mismatch of hyperbolic phonon polaritons(HPPs)weakens,resulting in a reduction in MC.By reducing the real and imaginary components of substrate permittivity,the MC can be significantly improved,reaching 4.64 forε_(s)=3 at t=10 nm.This work indicates that choosing a substrate with a smaller permittivity helps to achieve a better modulation effect,and provides guidance for the application of natural hyperbolic materials in the near-field radiative modulator.

Robust and Discriminative Feature Learning via Mutual Information Maximization for Object Detection in Aerial Images

Object detection in unmanned aerial vehicle(UAV)aerial images has become increasingly important in military and civil applications.General object detection models are not robust enough against interclass similarity and intraclass variability of small objects,and UAV-specific nuisances such as uncontrolledweather conditions.Unlike previous approaches focusing on high-level semantic information,we report the importance of underlying features to improve detection accuracy and robustness fromthe information-theoretic perspective.Specifically,we propose a robust and discriminative feature learning approach through mutual information maximization(RD-MIM),which can be integrated into numerous object detection methods for aerial images.Firstly,we present the rank sample mining method to reduce underlying feature differences between the natural image domain and the aerial image domain.Then,we design a momentum contrast learning strategy to make object features similar to the same category and dissimilar to different categories.Finally,we construct a transformer-based global attention mechanism to boost object location semantics by leveraging the high interrelation of different receptive fields.We conduct extensive experiments on the VisDrone and Unmanned Aerial Vehicle Benchmark Object Detection and Tracking(UAVDT)datasets to prove the effectiveness of the proposed method.The experimental results show that our approach brings considerable robustness gains to basic detectors and advanced detection methods,achieving relative growth rates of 51.0%and 39.4%in corruption robustness,respectively.Our code is available at https://github.com/cq100/RD-MIM(accessed on 2 August 2024).

Signal intensity changes of dentate nucleus on plain MR T1WI innasopharyngeal carcinoma patients after radiotherapy andmultiple injections of gadolinium-base contrast agent

Objective To observe changes of plain MR T1WI signal intensity of dentate nucleus in nasopharyngeal carcinoma patients after radiotherapy and multiple times of intravenous injection of gadolinium-based contrast agent(GBCA).Methods Fifty patients with pathologically confirmed nasopharyngeal carcinoma and received intensity-modulated radiotherapy were retrospectively enrolled as the nasopharyngeal carcinoma group,and 50 patients with other malignant tumors and without history of brain radiotherapy were retrospectively enrolled as the control group.All patients received yearly GBCA enhanced MR examinations for the nasopharynx or the head.T1WI signal intensities of the dentate nucleus and the pons on same plane were measured based on images in the year of confirmed diagnosis(recorded as the first year)and in the second to the fifth years.T1WI signal intensity ratio of year i(ranging from 1 to 5)was calculated with values of dentate nucleus divided by values of the pons(ΔSI i),while the percentage of relative changes of year j(ranging from 2 to 5)was calculated withΔSI j compared toΔSI 1(Rchange j).The values of these two parameters were compared,and the correlation ofΔSI and GBCA injection year-time was evaluated within each group.Results No significant difference of gender,age norΔSI 1 was found between groups(all P>0.05).The second to the fifth yearΔSI and Rchange in nasopharyngeal carcinoma group were all higher than those in control group(all P<0.05).Within both groups,ΔSI was positively correlated with GBCA injection year-time(both P<0.05).Conclusion Patients with nasopharyngeal carcinoma who underwent radiotherapy and multiple times of intravenous injection of GBCA tended to be found with gradually worsening GBCA deposition in dentate nucleus,for which radiotherapy might be a risk factor.

Gastrointestinal contrast-enhanced ultrasonography for diagnosis and treatment of peptic ulcer in children

BACKGROUND The detection rate of peptic ulcer in children is improving,with development of diagnostic procedures.Gastroscopy is the gold standard for the diagnosis of peptic ulcer,but it is an invasive procedure.Gastrointestinal contrast-enhanced ultrasonography(CEUS)has the advantages of being painless,noninvasive,nonradioactive,easy to use,and safe.AIM To investigate the clinical value of CEUS for diagnosis and treatment of peptic ulcer in children.METHODS We investigated 43 children with digestive tract symptoms in our hospital from January 2021 to June 2022.All children were examined by routine ultrasound,gastrointestinal CEUS,and gastroscopy.The pathological results of gastroscopy were taken as the gold standard.Routine ultrasonography was performed before gastrointestinal CEUS.Conventional ultrasound showed the thickness of the gastroduodenal wall,gastric peristalsis,and the adjacent organs and tissues around the abdominal cavity.Gastrointestinal CEUS recorded the thickness of the gastroduodenal wall;the size,location and shape of the ulcer;gastric peristalsis;and adjacent organs and tissues around the abdominal cavity.The results of routine ultrasound and gastrointestinal ultrasound were compared with those of gastroscopy to evaluate the diagnostic results and coincidence rate of routine ultrasound and gastrointestinal CEUS.All children received informed consent from their guardians for CEUS.This study was reviewed and approved by the hospital medical ethics committee.RESULTS Among the 43 children,17(15 male,2 female)were diagnosed with peptic ulcer by gastroscopy.There were 26 children with nonpeptic ulcer.There were eight cases of peptic ulcer and 35 of nonpeptic ulcer diagnosed by conventional ultrasound.The diagnostic coincidence rate of peptic ulcer in children diagnosed by conventional ultrasound was 79.1%(34/43),which was significantly different from that of gastroscopy(P=0.033).It indicates that the coincidence rate of gastrointestinal contrast-enhanced ultrasound and gastroscope is low.Fifteen cases of peptic ulcer and 28 of nonpeptic ulcer were diagnosed by CEUS.The diagnostic coincidence rate of peptic ulcer in children was 95.3%(41/43).There was no significant difference between CEUS and gastroscopy(P=0.655).It indicates that the coincidence rate of gastrointestinal contrast-enhanced ultrasound and gastroscope is high.CONCLUSION Gastrointestinal CEUS has a high coincidence rate in the diagnosis of peptic ulcer in children,and can be used as a preliminary examination method.

Efficient Clustering Network Based on Matrix Factorization

Contrastive learning is a significant research direction in the field of deep learning.However,existing data augmentation methods often lead to issues such as semantic drift in generated views while the complexity of model pre-training limits further improvement in the performance of existing methods.To address these challenges,we propose the Efficient Clustering Network based on Matrix Factorization(ECN-MF).Specifically,we design a batched low-rank Singular Value Decomposition(SVD)algorithm for data augmentation to eliminate redundant information and uncover major patterns of variation and key information in the data.Additionally,we design a Mutual Information-Enhanced Clustering Module(MI-ECM)to accelerate the training process by leveraging a simple architecture to bring samples from the same cluster closer while pushing samples from other clusters apart.Extensive experiments on six datasets demonstrate that ECN-MF exhibits more effective performance compared to state-of-the-art algorithms.

Theory and verification of moiréfringes for x-ray three-phase grating interferometer

Dual-phase and three-phase grating x-ray interference is a promising new technique for grating-based x-ray differential phase contrast imaging.Dual-phase grating interferometers have been relatively completely studied and discussed.In this paper,the corresponding imaging fringe formula of the three-phase grating interferometer is provided.At the same time,the similarities and differences between the three-phase grating interferometer and the dual-phase grating interferometer are investigated and verified,and that the three-phase grating interferometer can produce large-period moiréfringes without using the analyzing grating is demonstrated experimentally.Finally,a simple method of designing three-phase grating and multi-grating imaging systems from geometric optics based on the thin-lens theory of gratings is presented.These theoretical formulas and experimental results provide optimization tools for designing three-phase grating interferometer systems.

Contrastive Consistency and Attentive Complementarity for Deep Multi-View Subspace Clustering

Deep multi-view subspace clustering (DMVSC) based on self-expression has attracted increasing attention dueto its outstanding performance and nonlinear application. However, most existing methods neglect that viewprivatemeaningless information or noise may interfere with the learning of self-expression, which may lead to thedegeneration of clustering performance. In this paper, we propose a novel framework of Contrastive Consistencyand Attentive Complementarity (CCAC) for DMVsSC. CCAC aligns all the self-expressions of multiple viewsand fuses them based on their discrimination, so that it can effectively explore consistent and complementaryinformation for achieving precise clustering. Specifically, the view-specific self-expression is learned by a selfexpressionlayer embedded into the auto-encoder network for each view. To guarantee consistency across views andreduce the effect of view-private information or noise, we align all the view-specific self-expressions by contrastivelearning. The aligned self-expressions are assigned adaptive weights by channel attention mechanism according totheir discrimination. Then they are fused by convolution kernel to obtain consensus self-expression withmaximumcomplementarity ofmultiple views. Extensive experimental results on four benchmark datasets and one large-scaledataset of the CCAC method outperformother state-of-the-artmethods, demonstrating its clustering effectiveness.

Research on Improved MobileViT Image Tamper Localization Model

As image manipulation technology advances rapidly,the malicious use of image tampering has alarmingly escalated,posing a significant threat to social stability.In the realm of image tampering localization,accurately localizing limited samples,multiple types,and various sizes of regions remains a multitude of challenges.These issues impede the model’s universality and generalization capability and detrimentally affect its performance.To tackle these issues,we propose FL-MobileViT-an improved MobileViT model devised for image tampering localization.Our proposed model utilizes a dual-stream architecture that independently processes the RGB and noise domain,and captures richer traces of tampering through dual-stream integration.Meanwhile,the model incorporating the Focused Linear Attention mechanism within the lightweight network(MobileViT).This substitution significantly diminishes computational complexity and resolves homogeneity problems associated with traditional Transformer attention mechanisms,enhancing feature extraction diversity and improving the model’s localization performance.To comprehensively fuse the generated results from both feature extractors,we introduce the ASPP architecture for multi-scale feature fusion.This facilitates a more precise localization of tampered regions of various sizes.Furthermore,to bolster the model’s generalization ability,we adopt a contrastive learning method and devise a joint optimization training strategy that leverages fused features and captures the disparities in feature distribution in tampered images.This strategy enables the learning of contrastive loss at various stages of the feature extractor and employs it as an additional constraint condition in conjunction with cross-entropy loss.As a result,overfitting issues are effectively alleviated,and the differentiation between tampered and untampered regions is enhanced.Experimental evaluations on five benchmark datasets(IMD-20,CASIA,NIST-16,Columbia and Coverage)validate the effectiveness of our proposed model.The meticulously calibrated FL-MobileViT model consistently outperforms numerous existing general models regarding localization accuracy across diverse datasets,demonstrating superior adaptability.

A New Framework for Software Vulnerability Detection Based on an Advanced Computing

The detection of software vulnerabilities written in C and C++languages takes a lot of attention and interest today.This paper proposes a new framework called DrCSE to improve software vulnerability detection.It uses an intelligent computation technique based on the combination of two methods:Rebalancing data and representation learning to analyze and evaluate the code property graph(CPG)of the source code for detecting abnormal behavior of software vulnerabilities.To do that,DrCSE performs a combination of 3 main processing techniques:(i)building the source code feature profiles,(ii)rebalancing data,and(iii)contrastive learning.In which,the method(i)extracts the source code’s features based on the vertices and edges of the CPG.The method of rebalancing data has the function of supporting the training process by balancing the experimental dataset.Finally,contrastive learning techniques learn the important features of the source code by finding and pulling similar ones together while pushing the outliers away.The experiment part of this paper demonstrates the superiority of the DrCSE Framework for detecting source code security vulnerabilities using the Verum dataset.As a result,the method proposed in the article has brought a pretty good performance in all metrics,especially the Precision and Recall scores of 39.35%and 69.07%,respectively,proving the efficiency of the DrCSE Framework.It performs better than other approaches,with a 5%boost in Precision and a 5%boost in Recall.Overall,this is considered the best research result for the software vulnerability detection problem using the Verum dataset according to our survey to date.

Optical design of a novel near-infrared phase contrast imaging(NI-PCI)diagnostic on the HL-2A tokamak

The optical design of near-infrared phase contrast imaging(NI-PCI)diagnosis on HL-2A is introduced in this paper.This scheme benefits from the great progress of near-infrared laser technology and is a broadening of traditional phase contrast technology.This diagnostic can work as a keen tool to measure plasma wavenumber spectra by inferring string-integrated plasma density fluctuations.Design of both the front optical path which is the path before the laser transmitting into the tokamak plasma and the rear optics which is the path after the laser passing through the plasma is detailed.The 1550 nm laser is chosen as the probe beam and highprecision optical components are designed to fit the laser beam,in which a phase plate with a 194-nm-deep silver groove is the key.Compared with the conventional 10.6μm laser-based PCI system on HL-2A,NI-PCI significantly overcomes the unwanted phase scintillation effect and promotes the measurement capability of high-wavenumber turbulence with an increased maximal measurable wavenumber from 15 cm^(-1)to 32.6 cm^(-1).

Recommendation Method for Contrastive Enhancement of Neighborhood Information

Knowledge graph can assist in improving recommendation performance and is widely applied in various person-alized recommendation domains.However,existing knowledge-aware recommendation methods face challenges such as weak user-item interaction supervisory signals and noise in the knowledge graph.To tackle these issues,this paper proposes a neighbor information contrast-enhanced recommendation method by adding subtle noise to construct contrast views and employing contrastive learning to strengthen supervisory signals and reduce knowledge noise.Specifically,first,this paper adopts heterogeneous propagation and knowledge-aware attention networks to obtain multi-order neighbor embedding of users and items,mining the high-order neighbor informa-tion of users and items.Next,in the neighbor information,this paper introduces weak noise following a uniform distribution to construct neighbor contrast views,effectively reducing the time overhead of view construction.This paper then performs contrastive learning between neighbor views to promote the uniformity of view information,adjusting the neighbor structure,and achieving the goal of reducing the knowledge noise in the knowledge graph.Finally,this paper introduces multi-task learning to mitigate the problem of weak supervisory signals.To validate the effectiveness of our method,experiments are conducted on theMovieLens-1M,MovieLens-20M,Book-Crossing,and Last-FM datasets.The results showthat compared to the best baselines,our method shows significant improvements in AUC and F1.

Simplified liver imaging reporting and data system for the diagnosis of hepatocellular carcinoma on gadoxetic acid-enhanced magnetic resonance imaging

BACKGROUND The liver imaging reporting and data system(LI-RADS)diagnostic table has 15 cells and is too complex.The diagnostic performance of LI-RADS for hepatocellular carcinoma(HCC)is not satisfactory on gadoxetic acid-enhanced magnetic resonance imaging(EOB-MRI).AIM To evaluate the ability of the simplified LI-RADS(sLI-RADS)to diagnose HCC on EOB-MRI.METHODS A total of 331 patients with 356 hepatic observations were retrospectively analysed.The diagnostic performance of sLI-RADS A-D using a single threshold was evaluated and compared with LI-RADS v2018 to determine the optimal sLIRADS.The algorithms of sLI-RADS A-D are as follows:The single threshold for sLI-RADS A and B was 10 mm,that is,classified observations≥10mm using an algorithm of 10-19 mm observations(sLI-RADS A)and≥20 mm observations(sLI-RADS B)in the diagnosis table of LI-RADS v2018,respectively,while the classification algorithm remained unchanged for observations<10 mm;the single threshold for sLI-RADS C and D was 20 mm,that is,for<20 mm observations,the algorithms for<10 mm observations(sLI-RADS C)and 10-19 mm observations(sLI-RADS D)were used,respectively,while the algorithm remained unchanged for observations≥20 mm.With hepatobiliary phase(HBP)hypointensity as a major feature(MF),the final sLI-RADS(F-sLI-RADS)was formed according to the optimal sLI-RADS,and its diagnostic performance was evaluated.The times needed to classify the observations according to F-sLIRADS and LI-RADS v2018 were compared.RESULTS The optimal sLI-RADS was sLI-RADS D(with a single threshold of 20 mm),because its sensitivity was greater than that of LI-RADS v2018(89.8%vs 87.0%,P=0.031),and its specificity was not lower(89.4%vs 90.1%,P>0.999).With HBP hypointensity as an MF,the sensitivity of F-sLI-RADS was greater than that of LI-RADS v2018(93.0%vs 87.0%,P<0.001)and sLI-RADS D(93.0%vs 89.8%,P=0.016),without a lower specificity(86.5%vs 90.1%,P=0.062;86.5%vs 89.4%,P=0.125).Compared with that of LI-RADS v2018,the time to classify lesions according to FsLI-RADS was shorter(51±21 s vs 73±24 s,P<0.001).CONCLUSION The use of sLI-RADS with HBP hypointensity as an MF may improve the sensitivity of HCC diagnosis and reduce lesion classification time.

Laser speckle contrast imaging to predict the effect of temporary spinal cord stimulation in postherpetic neuralgia patients: A prospective observational study

Temporary spinal cord stimulation(tSCS)can effectively reduce the pain and severity of postherpetic neuralgia(PHN).However,there are no effective and objective methods for predicting the effects of tSCS on PHN.Laser speckle contrast imaging(LSCI)is frequently used in neurology to evaluate the effectiveness of treatment.To assess the accuracy of LSCI in predicting the impact of tSCS on PHN,14 adult patients receiving tSCS treatments for spinal nerve-innervated(C6-T2)PHN participated in this observational study.Visual analog scale(VAS)assessments and LSCI bloodflow images of the-ngers were recorded after the tSCS procedure.The results showed that the VAS scores of all patients decreased signi-cantly.Moreover,the bloodflow index(BFI)values were signi-cantly higher than they were before the procedure.Increased bloodflow and pain alleviation were positively correlated.The-ndings indicated that spinal nerve PHN(C6-T2)was signi-cantly reduced by tSCS.Pain alleviation by tSCS was positively correlated with increased bloodflow in the hand.The effect of tSCS on PHN may thus be predicted using an independent and consistent indicator such as LSCI.

A Second-Order Image Denoising Model for Contrast Preservation

In this work,we propose a second-order model for image denoising by employing a novel potential function recently developed in Zhu(J Sci Comput 88:46,2021)for the design of a regularization term.Due to this new second-order derivative based regularizer,the model is able to alleviate the staircase effect and preserve image contrast.The augmented Lagrangian method(ALM)is utilized to minimize the associated functional and convergence analysis is established for the proposed algorithm.Numerical experiments are presented to demonstrate the features of the proposed model.

Improved Weighted Local Contrast Method for Infrared Small Target Detection

In order to address the problem of high false alarm rate and low probabilities of infrared small target detection in complex low-altitude background,an infrared small target detection method based on improved weighted local contrast is proposed in this paper.First,the ratio information between the target and local background is utilized as an enhancement factor.The local contrast is calculated by incorporating the heterogeneity between the target and local background.Then,a local product weighted method is designed based on the spatial dissimilarity between target and background to further enhance target while suppressing background.Finally,the location of target is obtained by adaptive threshold segmentation.As experimental results demonstrate,the method shows superior performance in several evaluation metrics compared with six existing algorithms on different datasets containing targets such as unmanned aerial vehicles(UAV).

An Artificial Intelligence-Based Framework for Fruits Disease Recognition Using Deep Learning

Fruit infections have an impact on both the yield and the quality of the crop.As a result,an automated recognition system for fruit leaf diseases is important.In artificial intelligence(AI)applications,especially in agriculture,deep learning shows promising disease detection and classification results.The recent AI-based techniques have a few challenges for fruit disease recognition,such as low-resolution images,small datasets for learning models,and irrelevant feature extraction.This work proposed a new fruit leaf leaf leaf disease recognition framework using deep learning features and improved pathfinder optimization.Three fruit types have been employed in this work for the validation process,such as apple,grape,and Citrus.In the first step,a noisy dataset is prepared by employing the original images to learn the designed framework better.The EfficientNet-B0 deep model is fine-tuned on the next step and trained separately on the original and noisy data.After that,features are fused using a serial concatenation approach that is later optimized in the next step using an improved Path Finder Algorithm(PFA).This algorithm aims to select the best features based on the fitness score and ignore redundant information.The selected features are finally classified using machine learning classifiers such as Medium Neural Network,Wide Neural Network,and Support Vector Machine.The experimental process was conducted on each fruit dataset separately and obtained an accuracy of 100%,99.7%,99.7%,and 93.4%for apple,grape,Citrus fruit,and citrus plant leaves,respectively.A detailed analysis is conducted and also compared with the recent techniques,and the proposed framework shows improved accuracy.