Mango farming significantly contributes to the economy,particularly in developing countries.However,mango trees are susceptible to various diseases caused by fungi,viruses,and bacteria,and diagnosing these diseases at...Mango farming significantly contributes to the economy,particularly in developing countries.However,mango trees are susceptible to various diseases caused by fungi,viruses,and bacteria,and diagnosing these diseases at an early stage is crucial to prevent their spread,which can lead to substantial losses.The development of deep learning models for detecting crop diseases is an active area of research in smart agriculture.This study focuses on mango plant diseases and employs the ConvNeXt and Vision Transformer(ViT)architectures.Two datasets were used.The first,MangoLeafBD,contains data for mango leaf diseases such as anthracnose,bacterial canker,gall midge,and powdery mildew.The second,SenMangoFruitDDS,includes data for mango fruit diseases such as Alternaria,Anthracnose,Black Mould Rot,Healthy,and Stem and Rot.Both datasets were obtained from publicly available sources.The proposed model achieved an accuracy of 99.87%on the MangoLeafBD dataset and 98.40%on the MangoFruitDDS dataset.The results demonstrate that ConvNeXt and ViT models can effectively diagnose mango diseases,enabling farmers to identify these conditions more efficiently.The system contributes to increased mango production and minimizes economic losses by reducing the time and effort needed for manual diagnostics.Additionally,the proposed system is integrated into a mobile application that utilizes the model as a backend to detect mango diseases instantly.展开更多
Background Agroecological cropping systems are recognised as an alternative way to ensure the sustainability of cotton(Gossypium hirsutum L.) production in the context of climate change and degradation of soil fertili...Background Agroecological cropping systems are recognised as an alternative way to ensure the sustainability of cotton(Gossypium hirsutum L.) production in the context of climate change and degradation of soil fertility. A study was conducted in Benin from 2020 to 2023 to compare six different cotton cultivars in three agroecological cropping systems in two cotton-growing zones. Plough-based tillage plus incorporation of cover crop biomass(PTI), conservation agriculture with strip tillage(CA_ST), and conservation agriculture with no tillage(CA_NT) were compared with the reference plough-based tillage(PT). The objective was to identify morpho-physiological traits of cotton that increase yield in agroecological cropping systems. Our approach combined a field experiment and crop simulation model(CSM) of CROPGRO-Cotton to evaluate the effects of genotype(G) × environment(E) × management(M) interactions on seed cotton yield(SCY).Results Cultivars Tamcot_camde and Okp768 and simulated ideotypes performed best in CA systems. Increased seed mass, large and thick leaves, and later maturity were identified as beneficial for yield enhancement in CA systems. Cultivars and ideotypes that combine these traits also resulted in better nitrogen and water use efficiencies in CA systems. Under different climate scenarios up to 2050, ideotypes designed could increase SCY in Benin.Conclusion A set of morpho-physiological traits associated with vegetative vigour is required to ensure a good SCY in agroecological cropping systems. These results provide scientific evidence and useful knowledge for breeders and research programmes on cropping systems focused on the adaptation of cotton to climate change.展开更多
Innovation in learning algorithms has made retinal vessel segmentation and automatic grading tech-niques crucial for clinical diagnosis and prevention of diabetic retinopathy.The traditional methods struggle with accu...Innovation in learning algorithms has made retinal vessel segmentation and automatic grading tech-niques crucial for clinical diagnosis and prevention of diabetic retinopathy.The traditional methods struggle with accuracy and reliability due to multi-scale variations in retinal blood vessels and the complex pathological relationship in fundus images associated with diabetic retinopathy.While the single-modal diabetic retinopathy grading network addresses class imbalance challenges and lesion representation in fundus image data,dual-modal diabetic retinopathy grading methods offer superior performance.However,the scarcity of dual-modal data and the lack of effective feature fusion methods limit their potential due to multi-scale variations.This paper addresses these issues by focusing on multi-scale retinal vessel segmentation,dual feature fusion,data augmentation,and attention-based grading.The proposed model aims to improve comprehensive segmentation for retinal images with varying vessel thicknesses.It employs a dual-branch parallel architecture that integrates a transformer encoder with a convolutional neural network encoder to extract local and global information for synergistic saliency learning.Besides that,the model uses residual structures and attention modules to extract critical lesions,enhancing the accuracy and reliability of diabetic retinopathy grading.To evaluate the efficacy of the proposed approach,this study compared it with other pre-trained publicly open models,ResNet152V2,ConvNext,Efficient Net,DenseNet,and Swin Transform,with the same developmental parameters.All models achieved approximately 85%accuracy with the same image preparation method.However,the proposed approach outperforms and optimizes existing models by achieving an accuracy of 99.17%,99.04%,and 99.24%,on Kaggle APTOS19,IDRiD,and EyePACS datasets,respectively.These results support the model’s utility in helping ophthalmologists diagnose diabetic retinopathy more rapidly and accurately.展开更多
The increasing frequency and intensity of natural disasters necessitate advanced prediction techniques to mitigate potential damage.This study presents a comprehensive multi-hazard early warning framework by integrati...The increasing frequency and intensity of natural disasters necessitate advanced prediction techniques to mitigate potential damage.This study presents a comprehensive multi-hazard early warning framework by integrating the multi-source data fusion technique.A multi-source data extraction method was introduced by extracting pressure level and average precipitation data based on the hazard event from the Cooperative Open Online Landslide Repository(COOLR)dataset across multiple temporal intervals(12 h to 1 h prior to events).Feature engineering was performed using Choquet fuzzy integral-based importance scoring,which enables the model to account for interactions and uncertainty across multiple features.Three individual Long Short-Term Memory(LSTM)models were trained for hazard location,average precipitation,and hazard category(i.e.,to detect the potential of natural disasters).These models were trained on varying temporal scales from 12 to 1 h prior to the event.These individual models achieved the performance of Mean Absolute Error(MAE)2.2 and 3.2,respectively,for the hazard location and average precipitation models,and an F1-score of 0.825 for the hazard category model.The results also indicate that the LSTM model outperformed traditional Machine Learning(ML)models,and the use of the fuzzy integral enhanced the prediction capability by 8.12%,2.6%,and 6.37%,respectively,for all three individual models.Furthermore,a rule-based algorithm was developed to synthesize the outputs from the individual models into a 3×3 grid of multi-hazard warnings.These findings underscore the effectiveness of the proposed framework in advancing multi-hazard forecasting and situational awareness,offering valuable support for timely and data-driven emergency response planning.展开更多
Nowadays,renewable energy has been emerging as the major source of energy and is driven by its aggressive expansion and falling costs.Most of the renewable energy sources involve turbines and their operation and maint...Nowadays,renewable energy has been emerging as the major source of energy and is driven by its aggressive expansion and falling costs.Most of the renewable energy sources involve turbines and their operation and maintenance are vital and a difficult task.Condition monitoring and fault diagnosis have seen remarkable and revolutionary up-gradation in approaches,practices and technology during the last decade.Turbines mostly do use a rotating type of machinery and analysis of those signals has been challenging to localize the defect.This paper proposes a new hybrid model wherein multiple swarm intelligence models have been evaluated to optimize the conventional Long Short-Term Memory(LSTM)model in classifying the faults from the vibration signals data acquired from the gearbox.This helps to analyze the performance and behavioral patterns of the system more effectively and efficiently which helps to suggest for replacement of the unit with higher precision.The results have demonstrated that the proposed hybrid modeling approach is effective in classifying the faults of the gearbox from the time series data and achieve higher diagnostic accuracy in comparison to the conventional LSTM methods.展开更多
Rain-induced fruit cracking is a major problem in sweet cherry cultivation.Basic research has been conducted to disentangle the physiological and mechanistic bases of this complex phenomenon,whereas genetic studies ha...Rain-induced fruit cracking is a major problem in sweet cherry cultivation.Basic research has been conducted to disentangle the physiological and mechanistic bases of this complex phenomenon,whereas genetic studies have lagged behind.The objective of this work was to disentangle the genetic determinism of rain-induced fruit cracking.We hypothesized that a large genetic variation would be revealed,by visual field observations conducted on mapping populations derived from well-contrasted cultivars for cracking tolerance.Three populations were evaluated over 7–8 years by estimating the proportion of cracked fruits for each genotype at maturity,at three different areas of the sweet cherry fruit:pistillar end,stem end,and fruit side.An original approach was adopted to integrate,within simple linear models,covariates potentially related to cracking,such as rainfall accumulation before harvest,fruit weight,and firmness.We found the first stable quantitative trait loci(QTLs)for cherry fruit cracking,explaining percentages of phenotypic variance above 20%,for each of these three types of cracking tolerance,in different linkage groups,confirming the high complexity of this trait.For these and other QTLs,further analyses suggested the existence of at least two-linked QTLs in each linkage group,some of which showed confidence intervals close to 5 cM.These promising results open the possibility of developing marker-assisted selection strategies to select cracking-tolerant sweet cherry cultivars.Further studies are needed to confirm the stability of the reported QTLs over different genetic backgrounds and environments and to narrow down the QTL confidence intervals,allowing the exploration of underlying candidate genes.展开更多
The growing usage of Android smartphones has led to a significant rise in incidents of Android malware andprivacy breaches.This escalating security concern necessitates the development of advanced technologies capable...The growing usage of Android smartphones has led to a significant rise in incidents of Android malware andprivacy breaches.This escalating security concern necessitates the development of advanced technologies capableof automatically detecting andmitigatingmalicious activities in Android applications(apps).Such technologies arecrucial for safeguarding user data and maintaining the integrity of mobile devices in an increasingly digital world.Current methods employed to detect sensitive data leaks in Android apps are hampered by two major limitationsthey require substantial computational resources and are prone to a high frequency of false positives.This meansthat while attempting to identify security breaches,these methods often consume considerable processing powerand mistakenly flag benign activities as malicious,leading to inefficiencies and reduced reliability in malwaredetection.The proposed approach includes a data preprocessing step that removes duplicate samples,managesunbalanced datasets,corrects inconsistencies,and imputes missing values to ensure data accuracy.The Minimaxmethod is then used to normalize numerical data,followed by feature vector extraction using the Gain ratio andChi-squared test to identify and extract the most significant characteristics using an appropriate prediction model.This study focuses on extracting a subset of attributes best suited for the task and recommending a predictivemodel based on domain expert opinion.The proposed method is evaluated using Drebin and TUANDROMDdatasets containing 15,036 and 4,464 benign and malicious samples,respectively.The empirical result shows thatthe RandomForest(RF)and Support VectorMachine(SVC)classifiers achieved impressive accuracy rates of 98.9%and 98.8%,respectively,in detecting unknown Androidmalware.A sensitivity analysis experiment was also carriedout on all three ML-based classifiers based on MAE,MSE,R2,and sensitivity parameters,resulting in a flawlessperformance for both datasets.This approach has substantial potential for real-world applications and can serve asa valuable tool for preventing the spread of Androidmalware and enhancing mobile device security.展开更多
Small cell prostate carcinoma (SCPC) is an extremely rare pathology with an aggressive behavior, characterized by early brain metastases. We describe three cases of SCPC where brain metastases occurred despite respons...Small cell prostate carcinoma (SCPC) is an extremely rare pathology with an aggressive behavior, characterized by early brain metastases. We describe three cases of SCPC where brain metastases occurred despite response to chemotherapy. The benefit of prophylactic brain irradiation (PBI), as part of the management of SCPC, is discussed and compared to its indications in small cell lung cancer.展开更多
Ectopic testis predisposes to a high risk of germ cell tumor development. Treatment of advanced testicular germ cell tumor developing in an uncorrected abdominal testis is based on primary chemotherapy followed by rem...Ectopic testis predisposes to a high risk of germ cell tumor development. Treatment of advanced testicular germ cell tumor developing in an uncorrected abdominal testis is based on primary chemotherapy followed by removal of the testis along with residual masses. However, persistence of viable tumor particularly in the testis is always noted since testis penetration of chemotherapeutic agents is reduced. We report a case of complete pathological remission of a patient with advanced non-seminomatous germ cell tumor in intra-abdominal testis by primary chemotherapy alone, with a review of the literature.展开更多
Many countries developed and increased greenery in their country sights to attract international tourists.This planning is now significantly contributing to their economy.The next task is to facilitate the tourists by...Many countries developed and increased greenery in their country sights to attract international tourists.This planning is now significantly contributing to their economy.The next task is to facilitate the tourists by sufficient arrangements and providing a green and clean environment;it is only possible if an upcoming number of tourists’arrivals are accurately predicted.But accurate prediction is not easy as empirical evidence shows that the tourists’arrival data often contains linear,nonlinear,and seasonal patterns.The traditional model,like the seasonal autoregressive fractional integrated moving average(SARFIMA),handles seasonal trends with seasonality.In contrast,the artificial neural network(ANN)model deals better with nonlinear time series.To get a better forecasting result,this study combines the merits of the SARFIMA and the ANN models and the purpose of the hybrid SARFIMA-ANN model.Then,we have used the proposed model to predict the tourists’arrival inNew Zealand,Australia,and London.Empirical results showed that the proposed hybrid model outperforms in predicting tourists’arrival compared to the traditional SARFIMA and ANN models.Moreover,these results can be generalized to predict tourists’arrival in any country or region with a complicated data pattern.展开更多
Dear Editor,Malignant tumours of the hand are relatively uncommon.Acrometastasis,defined as metastatic bone lesions of the hand or feet are exceedingly rare,with a reported incidence rate of between 0.007%and 0.2%of a...Dear Editor,Malignant tumours of the hand are relatively uncommon.Acrometastasis,defined as metastatic bone lesions of the hand or feet are exceedingly rare,with a reported incidence rate of between 0.007%and 0.2%of all metastatic lesions[1].Acrometastasis of metastatic renal cell carcinoma(mRCC)accounts for only 10%e12%of the reported cases with majority of cases originating from primary lung cancer.The presentation poses a diagnostic and management dilemma and is usually delayed as the symptoms and signs are similar to infective or benign conditions.Typically the prognosis is grim[2,3].In this rarest of rare cases,we report a patient of renal cell carcinoma(RCC)with metastasis to the right shoulder and acrometastasis of the right thumb.We highlight the multidisciplinary team approach utilized and the management by multimodal therapy to achieve the best palliative outcome.展开更多
Recently,there have been several uses for digital image processing.Image fusion has become a prominent application in the domain of imaging processing.To create one final image that provesmore informative and helpful ...Recently,there have been several uses for digital image processing.Image fusion has become a prominent application in the domain of imaging processing.To create one final image that provesmore informative and helpful compared to the original input images,image fusion merges two or more initial images of the same item.Image fusion aims to produce,enhance,and transform significant elements of the source images into combined images for the sake of human visual perception.Image fusion is commonly employed for feature extraction in smart robots,clinical imaging,audiovisual camera integration,manufacturing process monitoring,electronic circuit design,advanced device diagnostics,and intelligent assembly line robots,with image quality varying depending on application.The research paper presents various methods for merging images in spatial and frequency domains,including a blend of stable and curvelet transformations,everageMax-Min,weighted principal component analysis(PCA),HIS(Hue,Intensity,Saturation),wavelet transform,discrete cosine transform(DCT),dual-tree Complex Wavelet Transform(CWT),and multiple wavelet transform.Image fusion methods integrate data from several source images of an identical target,thereby enhancing information in an extremely efficient manner.More precisely,in imaging techniques,the depth of field constraint precludes images from focusing on every object,leading to the exclusion of certain characteristics.To tackle thess challanges,a very efficient multi-focus wavelet decomposition and recompositionmethod is proposed.The use of these wavelet decomposition and recomposition techniques enables this method to make use of existing optimized wavelet code and filter choice.The simulated outcomes provide evidence that the suggested approach initially extracts particular characteristics from images in order to accurately reflect the level of clarity portrayed in the original images.This study enhances the performance of the eXtreme Gradient Boosting(XGBoost)algorithm in detecting brain malignancies with greater precision through the integration of computational image analysis and feature selection.The performance of images is improved by segmenting them employing the K-Means algorithm.The segmentation method aids in identifying specific regions of interest,using Particle Swarm Optimization(PCA)for trait selection and XGBoost for data classification.Extensive trials confirm the model’s exceptional visual performance,achieving an accuracy of up to 97.067%and providing good objective indicators.展开更多
Background:Since the commercial release of Bt cotton in Burkina Faso in 2009,the issue of seed purity in producers’fields has rarely been addressed in an unbiased and objective manner.The potential for contamination ...Background:Since the commercial release of Bt cotton in Burkina Faso in 2009,the issue of seed purity in producers’fields has rarely been addressed in an unbiased and objective manner.The potential for contamination of conventional seed varieties with Bt traits and the consequent threat to the continuation of organic cotton production has been documented.However,studies are rare on the varietal purity of Bt cotton seeds,despite the implications for the effectiveness and sustainability of their use.This paper compensates for the lack of research on the varietal purity of cotton seeds in Burkina Faso by reporting the results of Enzyme linked immunosorbent assay tests collected in 2015 on samples of both conventional and Bt varieties from 646 fields.Results:According to the conservative criteria used to declare the presence of a Bt gene in a given variety(more than 10%of seeds of conventional variety exhibit Bt traits,and at least 90%of seeds of Bt variety exhibit Bt traits),seed purity was very questionable for both types of variety.For the supposedly conventional variety,the Cry1Ac gene was observed in 63.6%of samples,the Cry2Ab gene was observed in 59.3%of samples,and both genes were detected in 52.2%of the seed samples.Only 29.3%of the seeds that were supposed to be of conventional type contained no Bt genes.Conversely,for the labeled Bt variety,the Cry1Ac gene was found in only 59.6%of samples,the Cry2Ab gene was found in 53.6%of the samples,and both genes were found in 40.4%of the samples.Finally,for the seeds that were supposed to contain both genes(Bollguard 2),both Cry1Ac and Cry2Ab genes were found in only 40.4%of the samples,only one of the genes was found in 32.4%of the samples,and 27.2%of the seeds in the samples contained neither.Two factors are responsible for the severe lack of seed purity.First,conventional varieties are being contaminated with Bt traits because of a failure to revise the seed production scheme in Burkina Faso to prevent cross-pollination.Second,the original Bt seeds provided to Burkina Faso lacked varietal purity.The organic sector plays a very minor role in the cotton sector of Burkina Faso(production of organic cotton totaled 453 t in 2018/2019,out of national cotton production of 183000 t).Nevertheless,the lack of purity in conventional seed varieties is a threat to efforts to expand certified organic cotton production.The poor presence of Bt proteins in supposed Bt varieties undermines their effectiveness in controlling pests and increases the likelihood of the development of resistance among pest populations.Conclusion:Our results show the extent of purity loss when inadequate attention is paid to the preservation of seed purity.Pure conventional seeds could vanish in Burkina Faso,while Bt seeds do not carry the combination of the expected Bt traits.Any country wishing to embark on the use of Bt cotton,or to resume its use,as in the case of Burkina Faso,must first adjust its national seed production scheme to ensure that procedures to preserve varietal purity are enforced.The preservation of varietal purity is necessary to enable the launch or the continuation of identity-cotton production.In addition,the preservation of varietal purity is necessary to ensure the sustainable effectiveness of Bt cotton.In order to ensure that procedures to preserve varietal purity are observed,seed purity must be tested regularly,and test results must be published.展开更多
Aims Invasive species,which recently expanded,may help understand how climatic niche can shift at the time scale of the current global change.Here,we address the climatic niche shift of an invasive shrub(common gorse,...Aims Invasive species,which recently expanded,may help understand how climatic niche can shift at the time scale of the current global change.Here,we address the climatic niche shift of an invasive shrub(common gorse,Ulex europaeus)at the world and regional scales to assess how it could contribute to increasing invasibility.Methods Based on a 28187 occurrences database,we used a combination of 9 species distribution models(SDM)to assess regional climatic niche from both the native range(Western Europe)and the introduced range in different parts of the world(North-West America,South America,North Europe,Australia and New Zealand).Important Findings Despite being restricted to annual mean temperature between 4℃ and 22℃,as well as annual precipitation higher than 300 mm/year,the range of bioclimatic conditions suitable for gorse was very large.Based on a native versus introduced SDM comparison,we highlighted a niche expansion in North-West America,South America and to a lesser degree in Australia,while a niche displacement was assessed in North Europe.These niche changes induced an increase in potential occupied areas by gorse by 49,111,202 and 283%in Australia,North Europe,North-West America and South America,respectively.On the contrary,we found no evidence of niche change in New Zealand,which presents similar climatic condition to the native environment(Western Europe).This study highlights how niche expansion and displacement of gorse might increase invasibility at regional scale.The change in gorse niche toward new climatic conditions may result from adaptive plasticity or genetic evolution and may explain why it has such a high level of invasibility.Taking into account the possibility of a niche shift is crucial to improve invasive plants management and control.展开更多
基金funded by Princess Nourah bint Abdulrahman University and Researchers Supporting Project number(PNURSP2025R346)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Mango farming significantly contributes to the economy,particularly in developing countries.However,mango trees are susceptible to various diseases caused by fungi,viruses,and bacteria,and diagnosing these diseases at an early stage is crucial to prevent their spread,which can lead to substantial losses.The development of deep learning models for detecting crop diseases is an active area of research in smart agriculture.This study focuses on mango plant diseases and employs the ConvNeXt and Vision Transformer(ViT)architectures.Two datasets were used.The first,MangoLeafBD,contains data for mango leaf diseases such as anthracnose,bacterial canker,gall midge,and powdery mildew.The second,SenMangoFruitDDS,includes data for mango fruit diseases such as Alternaria,Anthracnose,Black Mould Rot,Healthy,and Stem and Rot.Both datasets were obtained from publicly available sources.The proposed model achieved an accuracy of 99.87%on the MangoLeafBD dataset and 98.40%on the MangoFruitDDS dataset.The results demonstrate that ConvNeXt and ViT models can effectively diagnose mango diseases,enabling farmers to identify these conditions more efficiently.The system contributes to increased mango production and minimizes economic losses by reducing the time and effort needed for manual diagnostics.Additionally,the proposed system is integrated into a mobile application that utilizes the model as a backend to detect mango diseases instantly.
基金supported by the Benin Cotton Research Institute (IRC)the Cotton Interprofessional Association (AIC)+1 种基金the French Agricultural Research Centre for International Development (CIRAD)the TAZCO_(2) project (Transition Agroécologique des Zones Cotonnières du Bénin),which is funded by the Republic of Benin and the French Development Agency (AFD)。
文摘Background Agroecological cropping systems are recognised as an alternative way to ensure the sustainability of cotton(Gossypium hirsutum L.) production in the context of climate change and degradation of soil fertility. A study was conducted in Benin from 2020 to 2023 to compare six different cotton cultivars in three agroecological cropping systems in two cotton-growing zones. Plough-based tillage plus incorporation of cover crop biomass(PTI), conservation agriculture with strip tillage(CA_ST), and conservation agriculture with no tillage(CA_NT) were compared with the reference plough-based tillage(PT). The objective was to identify morpho-physiological traits of cotton that increase yield in agroecological cropping systems. Our approach combined a field experiment and crop simulation model(CSM) of CROPGRO-Cotton to evaluate the effects of genotype(G) × environment(E) × management(M) interactions on seed cotton yield(SCY).Results Cultivars Tamcot_camde and Okp768 and simulated ideotypes performed best in CA systems. Increased seed mass, large and thick leaves, and later maturity were identified as beneficial for yield enhancement in CA systems. Cultivars and ideotypes that combine these traits also resulted in better nitrogen and water use efficiencies in CA systems. Under different climate scenarios up to 2050, ideotypes designed could increase SCY in Benin.Conclusion A set of morpho-physiological traits associated with vegetative vigour is required to ensure a good SCY in agroecological cropping systems. These results provide scientific evidence and useful knowledge for breeders and research programmes on cropping systems focused on the adaptation of cotton to climate change.
基金funded by Princess Nourah bint Abdulrahman University and Researchers Supporting Project number(PNURSP2025R346)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Innovation in learning algorithms has made retinal vessel segmentation and automatic grading tech-niques crucial for clinical diagnosis and prevention of diabetic retinopathy.The traditional methods struggle with accuracy and reliability due to multi-scale variations in retinal blood vessels and the complex pathological relationship in fundus images associated with diabetic retinopathy.While the single-modal diabetic retinopathy grading network addresses class imbalance challenges and lesion representation in fundus image data,dual-modal diabetic retinopathy grading methods offer superior performance.However,the scarcity of dual-modal data and the lack of effective feature fusion methods limit their potential due to multi-scale variations.This paper addresses these issues by focusing on multi-scale retinal vessel segmentation,dual feature fusion,data augmentation,and attention-based grading.The proposed model aims to improve comprehensive segmentation for retinal images with varying vessel thicknesses.It employs a dual-branch parallel architecture that integrates a transformer encoder with a convolutional neural network encoder to extract local and global information for synergistic saliency learning.Besides that,the model uses residual structures and attention modules to extract critical lesions,enhancing the accuracy and reliability of diabetic retinopathy grading.To evaluate the efficacy of the proposed approach,this study compared it with other pre-trained publicly open models,ResNet152V2,ConvNext,Efficient Net,DenseNet,and Swin Transform,with the same developmental parameters.All models achieved approximately 85%accuracy with the same image preparation method.However,the proposed approach outperforms and optimizes existing models by achieving an accuracy of 99.17%,99.04%,and 99.24%,on Kaggle APTOS19,IDRiD,and EyePACS datasets,respectively.These results support the model’s utility in helping ophthalmologists diagnose diabetic retinopathy more rapidly and accurately.
文摘The increasing frequency and intensity of natural disasters necessitate advanced prediction techniques to mitigate potential damage.This study presents a comprehensive multi-hazard early warning framework by integrating the multi-source data fusion technique.A multi-source data extraction method was introduced by extracting pressure level and average precipitation data based on the hazard event from the Cooperative Open Online Landslide Repository(COOLR)dataset across multiple temporal intervals(12 h to 1 h prior to events).Feature engineering was performed using Choquet fuzzy integral-based importance scoring,which enables the model to account for interactions and uncertainty across multiple features.Three individual Long Short-Term Memory(LSTM)models were trained for hazard location,average precipitation,and hazard category(i.e.,to detect the potential of natural disasters).These models were trained on varying temporal scales from 12 to 1 h prior to the event.These individual models achieved the performance of Mean Absolute Error(MAE)2.2 and 3.2,respectively,for the hazard location and average precipitation models,and an F1-score of 0.825 for the hazard category model.The results also indicate that the LSTM model outperformed traditional Machine Learning(ML)models,and the use of the fuzzy integral enhanced the prediction capability by 8.12%,2.6%,and 6.37%,respectively,for all three individual models.Furthermore,a rule-based algorithm was developed to synthesize the outputs from the individual models into a 3×3 grid of multi-hazard warnings.These findings underscore the effectiveness of the proposed framework in advancing multi-hazard forecasting and situational awareness,offering valuable support for timely and data-driven emergency response planning.
文摘Nowadays,renewable energy has been emerging as the major source of energy and is driven by its aggressive expansion and falling costs.Most of the renewable energy sources involve turbines and their operation and maintenance are vital and a difficult task.Condition monitoring and fault diagnosis have seen remarkable and revolutionary up-gradation in approaches,practices and technology during the last decade.Turbines mostly do use a rotating type of machinery and analysis of those signals has been challenging to localize the defect.This paper proposes a new hybrid model wherein multiple swarm intelligence models have been evaluated to optimize the conventional Long Short-Term Memory(LSTM)model in classifying the faults from the vibration signals data acquired from the gearbox.This helps to analyze the performance and behavioral patterns of the system more effectively and efficiently which helps to suggest for replacement of the unit with higher precision.The results have demonstrated that the proposed hybrid modeling approach is effective in classifying the faults of the gearbox from the time series data and achieve higher diagnostic accuracy in comparison to the conventional LSTM methods.
基金the INRAE sweet cherry breeding program,which is supported by INRAE BAP division and by INRAE’s private partner,CEP Innovation.
文摘Rain-induced fruit cracking is a major problem in sweet cherry cultivation.Basic research has been conducted to disentangle the physiological and mechanistic bases of this complex phenomenon,whereas genetic studies have lagged behind.The objective of this work was to disentangle the genetic determinism of rain-induced fruit cracking.We hypothesized that a large genetic variation would be revealed,by visual field observations conducted on mapping populations derived from well-contrasted cultivars for cracking tolerance.Three populations were evaluated over 7–8 years by estimating the proportion of cracked fruits for each genotype at maturity,at three different areas of the sweet cherry fruit:pistillar end,stem end,and fruit side.An original approach was adopted to integrate,within simple linear models,covariates potentially related to cracking,such as rainfall accumulation before harvest,fruit weight,and firmness.We found the first stable quantitative trait loci(QTLs)for cherry fruit cracking,explaining percentages of phenotypic variance above 20%,for each of these three types of cracking tolerance,in different linkage groups,confirming the high complexity of this trait.For these and other QTLs,further analyses suggested the existence of at least two-linked QTLs in each linkage group,some of which showed confidence intervals close to 5 cM.These promising results open the possibility of developing marker-assisted selection strategies to select cracking-tolerant sweet cherry cultivars.Further studies are needed to confirm the stability of the reported QTLs over different genetic backgrounds and environments and to narrow down the QTL confidence intervals,allowing the exploration of underlying candidate genes.
基金Princess Nourah bint Abdulrahman University and Researchers Supporting Project Number(PNURSP2024R346)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘The growing usage of Android smartphones has led to a significant rise in incidents of Android malware andprivacy breaches.This escalating security concern necessitates the development of advanced technologies capableof automatically detecting andmitigatingmalicious activities in Android applications(apps).Such technologies arecrucial for safeguarding user data and maintaining the integrity of mobile devices in an increasingly digital world.Current methods employed to detect sensitive data leaks in Android apps are hampered by two major limitationsthey require substantial computational resources and are prone to a high frequency of false positives.This meansthat while attempting to identify security breaches,these methods often consume considerable processing powerand mistakenly flag benign activities as malicious,leading to inefficiencies and reduced reliability in malwaredetection.The proposed approach includes a data preprocessing step that removes duplicate samples,managesunbalanced datasets,corrects inconsistencies,and imputes missing values to ensure data accuracy.The Minimaxmethod is then used to normalize numerical data,followed by feature vector extraction using the Gain ratio andChi-squared test to identify and extract the most significant characteristics using an appropriate prediction model.This study focuses on extracting a subset of attributes best suited for the task and recommending a predictivemodel based on domain expert opinion.The proposed method is evaluated using Drebin and TUANDROMDdatasets containing 15,036 and 4,464 benign and malicious samples,respectively.The empirical result shows thatthe RandomForest(RF)and Support VectorMachine(SVC)classifiers achieved impressive accuracy rates of 98.9%and 98.8%,respectively,in detecting unknown Androidmalware.A sensitivity analysis experiment was also carriedout on all three ML-based classifiers based on MAE,MSE,R2,and sensitivity parameters,resulting in a flawlessperformance for both datasets.This approach has substantial potential for real-world applications and can serve asa valuable tool for preventing the spread of Androidmalware and enhancing mobile device security.
文摘Small cell prostate carcinoma (SCPC) is an extremely rare pathology with an aggressive behavior, characterized by early brain metastases. We describe three cases of SCPC where brain metastases occurred despite response to chemotherapy. The benefit of prophylactic brain irradiation (PBI), as part of the management of SCPC, is discussed and compared to its indications in small cell lung cancer.
文摘Ectopic testis predisposes to a high risk of germ cell tumor development. Treatment of advanced testicular germ cell tumor developing in an uncorrected abdominal testis is based on primary chemotherapy followed by removal of the testis along with residual masses. However, persistence of viable tumor particularly in the testis is always noted since testis penetration of chemotherapeutic agents is reduced. We report a case of complete pathological remission of a patient with advanced non-seminomatous germ cell tumor in intra-abdominal testis by primary chemotherapy alone, with a review of the literature.
文摘Many countries developed and increased greenery in their country sights to attract international tourists.This planning is now significantly contributing to their economy.The next task is to facilitate the tourists by sufficient arrangements and providing a green and clean environment;it is only possible if an upcoming number of tourists’arrivals are accurately predicted.But accurate prediction is not easy as empirical evidence shows that the tourists’arrival data often contains linear,nonlinear,and seasonal patterns.The traditional model,like the seasonal autoregressive fractional integrated moving average(SARFIMA),handles seasonal trends with seasonality.In contrast,the artificial neural network(ANN)model deals better with nonlinear time series.To get a better forecasting result,this study combines the merits of the SARFIMA and the ANN models and the purpose of the hybrid SARFIMA-ANN model.Then,we have used the proposed model to predict the tourists’arrival inNew Zealand,Australia,and London.Empirical results showed that the proposed hybrid model outperforms in predicting tourists’arrival compared to the traditional SARFIMA and ANN models.Moreover,these results can be generalized to predict tourists’arrival in any country or region with a complicated data pattern.
文摘Dear Editor,Malignant tumours of the hand are relatively uncommon.Acrometastasis,defined as metastatic bone lesions of the hand or feet are exceedingly rare,with a reported incidence rate of between 0.007%and 0.2%of all metastatic lesions[1].Acrometastasis of metastatic renal cell carcinoma(mRCC)accounts for only 10%e12%of the reported cases with majority of cases originating from primary lung cancer.The presentation poses a diagnostic and management dilemma and is usually delayed as the symptoms and signs are similar to infective or benign conditions.Typically the prognosis is grim[2,3].In this rarest of rare cases,we report a patient of renal cell carcinoma(RCC)with metastasis to the right shoulder and acrometastasis of the right thumb.We highlight the multidisciplinary team approach utilized and the management by multimodal therapy to achieve the best palliative outcome.
基金Princess Nourah bint Abdulrahman University and Researchers Supporting Project Number(PNURSP2024R346)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘Recently,there have been several uses for digital image processing.Image fusion has become a prominent application in the domain of imaging processing.To create one final image that provesmore informative and helpful compared to the original input images,image fusion merges two or more initial images of the same item.Image fusion aims to produce,enhance,and transform significant elements of the source images into combined images for the sake of human visual perception.Image fusion is commonly employed for feature extraction in smart robots,clinical imaging,audiovisual camera integration,manufacturing process monitoring,electronic circuit design,advanced device diagnostics,and intelligent assembly line robots,with image quality varying depending on application.The research paper presents various methods for merging images in spatial and frequency domains,including a blend of stable and curvelet transformations,everageMax-Min,weighted principal component analysis(PCA),HIS(Hue,Intensity,Saturation),wavelet transform,discrete cosine transform(DCT),dual-tree Complex Wavelet Transform(CWT),and multiple wavelet transform.Image fusion methods integrate data from several source images of an identical target,thereby enhancing information in an extremely efficient manner.More precisely,in imaging techniques,the depth of field constraint precludes images from focusing on every object,leading to the exclusion of certain characteristics.To tackle thess challanges,a very efficient multi-focus wavelet decomposition and recompositionmethod is proposed.The use of these wavelet decomposition and recomposition techniques enables this method to make use of existing optimized wavelet code and filter choice.The simulated outcomes provide evidence that the suggested approach initially extracts particular characteristics from images in order to accurately reflect the level of clarity portrayed in the original images.This study enhances the performance of the eXtreme Gradient Boosting(XGBoost)algorithm in detecting brain malignancies with greater precision through the integration of computational image analysis and feature selection.The performance of images is improved by segmenting them employing the K-Means algorithm.The segmentation method aids in identifying specific regions of interest,using Particle Swarm Optimization(PCA)for trait selection and XGBoost for data classification.Extensive trials confirm the model’s exceptional visual performance,achieving an accuracy of up to 97.067%and providing good objective indicators.
基金The study was implemented on request of the interprofessional body of the cotton sector in Burkina Faso(AICB)with the allocation of a specific fund.
文摘Background:Since the commercial release of Bt cotton in Burkina Faso in 2009,the issue of seed purity in producers’fields has rarely been addressed in an unbiased and objective manner.The potential for contamination of conventional seed varieties with Bt traits and the consequent threat to the continuation of organic cotton production has been documented.However,studies are rare on the varietal purity of Bt cotton seeds,despite the implications for the effectiveness and sustainability of their use.This paper compensates for the lack of research on the varietal purity of cotton seeds in Burkina Faso by reporting the results of Enzyme linked immunosorbent assay tests collected in 2015 on samples of both conventional and Bt varieties from 646 fields.Results:According to the conservative criteria used to declare the presence of a Bt gene in a given variety(more than 10%of seeds of conventional variety exhibit Bt traits,and at least 90%of seeds of Bt variety exhibit Bt traits),seed purity was very questionable for both types of variety.For the supposedly conventional variety,the Cry1Ac gene was observed in 63.6%of samples,the Cry2Ab gene was observed in 59.3%of samples,and both genes were detected in 52.2%of the seed samples.Only 29.3%of the seeds that were supposed to be of conventional type contained no Bt genes.Conversely,for the labeled Bt variety,the Cry1Ac gene was found in only 59.6%of samples,the Cry2Ab gene was found in 53.6%of the samples,and both genes were found in 40.4%of the samples.Finally,for the seeds that were supposed to contain both genes(Bollguard 2),both Cry1Ac and Cry2Ab genes were found in only 40.4%of the samples,only one of the genes was found in 32.4%of the samples,and 27.2%of the seeds in the samples contained neither.Two factors are responsible for the severe lack of seed purity.First,conventional varieties are being contaminated with Bt traits because of a failure to revise the seed production scheme in Burkina Faso to prevent cross-pollination.Second,the original Bt seeds provided to Burkina Faso lacked varietal purity.The organic sector plays a very minor role in the cotton sector of Burkina Faso(production of organic cotton totaled 453 t in 2018/2019,out of national cotton production of 183000 t).Nevertheless,the lack of purity in conventional seed varieties is a threat to efforts to expand certified organic cotton production.The poor presence of Bt proteins in supposed Bt varieties undermines their effectiveness in controlling pests and increases the likelihood of the development of resistance among pest populations.Conclusion:Our results show the extent of purity loss when inadequate attention is paid to the preservation of seed purity.Pure conventional seeds could vanish in Burkina Faso,while Bt seeds do not carry the combination of the expected Bt traits.Any country wishing to embark on the use of Bt cotton,or to resume its use,as in the case of Burkina Faso,must first adjust its national seed production scheme to ensure that procedures to preserve varietal purity are enforced.The preservation of varietal purity is necessary to enable the launch or the continuation of identity-cotton production.In addition,the preservation of varietal purity is necessary to ensure the sustainable effectiveness of Bt cotton.In order to ensure that procedures to preserve varietal purity are observed,seed purity must be tested regularly,and test results must be published.
基金supported by the Centre Nationale de la Recherche Scientifique(CNRS)the MARIS Agence Nationale de la Recherche project(ANR grant ANR-14-CE03-0007-01)Institut National de la Recherche Agronomique(INRA Institute).
文摘Aims Invasive species,which recently expanded,may help understand how climatic niche can shift at the time scale of the current global change.Here,we address the climatic niche shift of an invasive shrub(common gorse,Ulex europaeus)at the world and regional scales to assess how it could contribute to increasing invasibility.Methods Based on a 28187 occurrences database,we used a combination of 9 species distribution models(SDM)to assess regional climatic niche from both the native range(Western Europe)and the introduced range in different parts of the world(North-West America,South America,North Europe,Australia and New Zealand).Important Findings Despite being restricted to annual mean temperature between 4℃ and 22℃,as well as annual precipitation higher than 300 mm/year,the range of bioclimatic conditions suitable for gorse was very large.Based on a native versus introduced SDM comparison,we highlighted a niche expansion in North-West America,South America and to a lesser degree in Australia,while a niche displacement was assessed in North Europe.These niche changes induced an increase in potential occupied areas by gorse by 49,111,202 and 283%in Australia,North Europe,North-West America and South America,respectively.On the contrary,we found no evidence of niche change in New Zealand,which presents similar climatic condition to the native environment(Western Europe).This study highlights how niche expansion and displacement of gorse might increase invasibility at regional scale.The change in gorse niche toward new climatic conditions may result from adaptive plasticity or genetic evolution and may explain why it has such a high level of invasibility.Taking into account the possibility of a niche shift is crucial to improve invasive plants management and control.
基金supported by the French Agence Nationale de la Recherche(project MARIS ANR-14-CE03-0007-01andprojectSWATCHANR-18-PRIM-0006)by the'Institut national de recherche pour I'agriculture,I'alimentation et I'environnement'(INRAE)supported by the Conseil Regional de La Réunion,the French Ministry of Agriculture and Food,the European Union(Feader program,grant n°AG/974/DAAF/2016-00096 and Feder program,grant n°GURTDI20151501-0000735).
