The advent of Network Function Virtualization(NFV)and Service Function Chains(SFCs)unleashes the power of dynamic creation of network services using Virtual Network Functions(VNFs).This is of great interest to network...The advent of Network Function Virtualization(NFV)and Service Function Chains(SFCs)unleashes the power of dynamic creation of network services using Virtual Network Functions(VNFs).This is of great interest to network operators since poor service quality and resource wastage can potentially hurt their revenue in the long term.However,the study shows with a set of test-bed experiments that packet loss at certain positions(i.e.,different VNFs)in an SFC can cause various degrees of resource wastage and performance degradation because of repeated upstream processing and transmission of retransmitted packets.To overcome this challenge,this study focuses on resource scheduling and deployment of SFCs while considering packet loss positions.This study developed a novel SFC packet dropping cost model and formulated an SFC scheduling problem that aims to minimize overall packet dropping cost as a Mixed-Integer Linear Programming(MILP)and proved that it is NP-hard.In this study,Palos is proposed as an efficient scheme in exploiting the functional characteristics of VNFs and their positions in SFCs for scheduling resources and deployment to optimize packet dropping cost.Extensive experiment results show that Palos can achieve up to 42.73%improvement on packet dropping cost and up to 33.03%reduction on average SFC latency when compared with two other state-of-the-art schemes.展开更多
The current existing problem of deep learning framework for the detection and segmentation of electrical equipment is dominantly related to low precision.Because of the reliable,safe and easy-to-operate technology pro...The current existing problem of deep learning framework for the detection and segmentation of electrical equipment is dominantly related to low precision.Because of the reliable,safe and easy-to-operate technology provided by deep learning-based video surveillance for unmanned inspection of electrical equipment,this paper uses the bottleneck attention module(BAM)attention mechanism to improve the Solov2 model and proposes a new electrical equipment segmentation mode.Firstly,the BAM attention mechanism is integrated into the feature extraction network to adaptively learn the correlation between feature channels,thereby improving the expression ability of the feature map;secondly,the weighted sum of CrossEntropy Loss and Dice loss is designed as the mask loss to improve the segmentation accuracy and robustness of the model;finally,the non-maximal suppression(NMS)algorithm to better handle the overlap problem in instance segmentation.Experimental results show that the proposed method achieves an average segmentation accuracy of mAP of 80.4% on three types of electrical equipment datasets,including transformers,insulators and voltage transformers,which improve the detection accuracy by more than 5.7% compared with the original Solov2 model.The segmentation model proposed can provide a focusing technical means for the intelligent management of power systems.展开更多
BACKGROUND Understanding the impact of early sensory deficits on brain development is essential for understanding developmental processes and developing potential interventions.While previous studies have looked into ...BACKGROUND Understanding the impact of early sensory deficits on brain development is essential for understanding developmental processes and developing potential interventions.While previous studies have looked into the impact of prenatal experiences on language development,there is a lack of research on how these experiences affect early language and brain function development in individuals with sensorineural hearing loss(SNHL).AIM To investigate SNHL effects on early brain development and connectivity in 4-month-olds vs healthy newborns and controls.METHODS The research involved analyzing the functional brain networks of 65 infants,categorized into three groups:28 healthy newborns,224-month-old participants with SNHL,and 15 age-matched healthy participants.The resting-state functional connectivity was measured and compared between the groups using functional near-infrared spectroscopy and graph theory to assess the brain network properties.RESULTS Significant differences were found in resting-state functional connectivity between participants with SNHL and age-matched controls,indicating a developmental lag in brain connectivity for those with SNHL.Surprisingly,SNHL participants showed better connectivity development compared to healthy newborns,with connectivity strengths of 0.13±0.04 for SNHL,0.16±0.08 for controls,and 0.098±0.04 for newborns.Graph theory analysis revealed enhanced global brain network properties for the SNHL group,suggesting higher communication efficiency at 4 months.No significant differences were noted in network properties between 4-month-old SNHL participants and neonates.A unique pattern of central hubs was observed in the SNHL group,with 2 hubs in the left hemisphere compared to 6 in controls.CONCLUSION 4-month-old infants with SNHL have a distinct brain network pattern with efficient long-distance information transmission but less effective local communication compared to age-matched controls.展开更多
In this paper, the isogeometric analysis (IGA) is employed to develop an acoustic radiation model for a double plate-acoustic cavity coupling system, with a focus on analyzing the sound transmission loss (STL). The fu...In this paper, the isogeometric analysis (IGA) is employed to develop an acoustic radiation model for a double plate-acoustic cavity coupling system, with a focus on analyzing the sound transmission loss (STL). The functionally graded (FG) plate exhibits a different material properties in-plane, and the power-law rule is adopted as the governing principle for material mixing. To validate the harmonic response and demonstrate the accuracy and convergence of the isogeometric modeling, ANASYS is utilized to compare with numerical examples. A plane wave serves as the acoustic excitation, and the Rayleigh integral is applied to discretize the radiated plate. The STL results are compared with the literature, confirming the reliability of the coupling system. Finally, the investigation is conducted to study impact of cavity depth and power-law parameter on the STL.展开更多
In the Internet era,recommendation systems play a crucial role in helping users find relevant information from large datasets.Class imbalance is known to severely affect data quality,and therefore reduce the performan...In the Internet era,recommendation systems play a crucial role in helping users find relevant information from large datasets.Class imbalance is known to severely affect data quality,and therefore reduce the performance of recommendation systems.Due to the imbalance,machine learning algorithms tend to classify inputs into the positive(majority)class every time to achieve high prediction accuracy.Imbalance can be categorized such as by features and classes,but most studies consider only class imbalance.In this paper,we propose a recommendation system that can integrate multiple networks to adapt to a large number of imbalanced features and can deal with highly skewed and imbalanced datasets through a loss function.We propose a loss aware feature attention mechanism(LAFAM)to solve the issue of feature imbalance.The network incorporates an attention mechanism and uses multiple sub-networks to classify and learn features.For better results,the network can learn the weights of sub-networks and assign higher weights to important features.We propose suppression loss to address class imbalance,which favors negative loss by penalizing positive loss,and pays more attention to sample points near the decision boundary.Experiments on two large-scale datasets verify that the performance of the proposed system is greatly improved compared to baseline methods.展开更多
Maxillary bone loss impairs essential functions (chewing, swallowing, speech) and gives patients a very unaesthetic appearance due to the removal of facial support tissues, leading to serious psychological consequence...Maxillary bone loss impairs essential functions (chewing, swallowing, speech) and gives patients a very unaesthetic appearance due to the removal of facial support tissues, leading to serious psychological consequences. Treatment is multidisciplinary and requires a resective surgery if the cause is tumor-related, or an additive surgery if the cause is traumatic. This article aims to show the role of making a prosthesis to restore function (chewing, swallowing, speech) and aesthetics following maxillary bone loss. We will eighter present a clinical case involving a right maxillary tumor that was surgically resected followed by radiotherapy, and subsequently rehabilitated with a maxillofacial prosthesis in the consultation and dental treatment center of the university hospital center of Casablanca.展开更多
The cochlea is one of the most complex organs in the human body,exhibiting a complex interplay of characteristics in acoustic,mechanical,electrical,and biological functions.Functional cochlea models are an essential p...The cochlea is one of the most complex organs in the human body,exhibiting a complex interplay of characteristics in acoustic,mechanical,electrical,and biological functions.Functional cochlea models are an essential platform for studying hearing mechanics and are crucial for developing next-generation auditory prostheses and artificial hearing systems for sensorineural hearing restoration.Recent advances in additive manufacturing,organ-on-a-chip models,drug delivery platforms,and artificial intelligence have provided valuable insights into how to manufacture artificial cochlea models that more accurately replicate the complex anatomy and physiology of the inner ear.This paper reviews recent advancements in the applications of advanced manufacturing techniques in reproducing the physical,biological,and intelligent functions of the cochlea.It also outlines the current challenges to developing mechanically,electrically,and anatomically accurate functional models of the inner ear.Finally,this review identifies the major requirements and outlook for impactful research in this field going forward.Through interdisciplinary collaboration and innovation,these functional cochlea models are poised to drive significant advancements in hearing treatments,and ultimately enhance the quality of life for individuals with hearing loss.展开更多
This study proposes a new component of the composite loss function minimised during training of the Super-Resolution(SR)algorithms—the normalised structural similarity index loss LSSIMN,which has the potential to imp...This study proposes a new component of the composite loss function minimised during training of the Super-Resolution(SR)algorithms—the normalised structural similarity index loss LSSIMN,which has the potential to improve the natural appearance of reconstructed images.Deep learning-based super-resolution(SR)algorithms reconstruct high-resolution images from low-resolution inputs,offering a practical means to enhance image quality without requiring superior imaging hardware,which is particularly important in medical applications where diagnostic accuracy is critical.Although recent SR methods employing convolutional and generative adversarial networks achieve high pixel fidelity,visual artefacts may persist,making the design of the loss function during training essential for ensuring reliable and naturalistic image reconstruction.Our research shows on two models—SR and Invertible Rescaling Neural Network(IRN)—trained on multiple benchmark datasets that the function LSSIMN significantly contributes to the visual quality,preserving the structural fidelity on the reference datasets.The quantitative analysis of results while incorporating LSSIMN shows that including this loss function component has a mean 2.88%impact on the improvement of the final structural similarity of the reconstructed images in the validation set,in comparison to leaving it out and 0.218%in comparison when this component is non-normalised.展开更多
The application of organic fertilizers has become an increasingly popular practice in maize production to reduce thegaseous nitrogen(N) loss and soil degradation caused by inorganic fertilizers. Organic fertilizer pla...The application of organic fertilizers has become an increasingly popular practice in maize production to reduce thegaseous nitrogen(N) loss and soil degradation caused by inorganic fertilizers. Organic fertilizer plays a key rolein improving soil quality and stabilizing maize yields, but few studies have compared different substitution rates. Afield study was carried out in 2021 and 2022, based on a long-term trial initiated in 2016, which included five organicfertilizer N substitution rates with equal inputs of 200 kg N ha^(–1): 0% organic fertilizer(T1, 100% inorganic fertilizer),50.0% organic+50.0% inorganic fertilizer(T2), 37.5% organic+62.5% inorganic fertilizer(T3), 25.0% organic+75.0%inorganic fertilizer(T4), and 12.5% organic+87.5% inorganic fertilizer(T5), as well as a no fertilizer control(T6). Theresults of the two years showed that T3 and T1 had the highest grain yield and biomass, respectively, and there wasno significant difference between T1 and T3. Compared with T1, the 12.5, 25.0, 37.5, and 50.0% substitution rates in T5, T4, T3, and T2 significantly reduced total nitrogen losses(NH_(3), N_(2)O) by 8.3, 16.1, 18.7, and 27.0%, respectively.Nitrogen use efficiency(NUE) was higher in T5, T3, and T1, and there were no significant differences among them.Organic fertilizer substitution directly reduced NH_(3)volatilization and N_(2)O emission from farmland by lowering theammonium nitrogen and alkali-dissolved N contents and by increasing soil moisture. These substitution treatmentsreduced N_(2)O emissions indirectly by regulating the abundances of AOB and nirK-harboring genes by promotingsoil moisture. Specifically, the 37.5% organic fertilizer substitution reduces NH_(3)volatilization and N_(2)O emission from farmland by reducing the ammonium nitrogen and alkali-dissolved N contents and increasing moisture, which negatively regulate the abundance of AOB and nir K-harboring genes to reduce N_(2)O emissions indirectly in rainfed maize fields on the Loess Plateau of China.展开更多
Traditional meteorological downscaling methods face limitations due to the complex distribution of meteorological variables,which can lead to unstable forecasting results,especially in extreme scenarios.To overcome th...Traditional meteorological downscaling methods face limitations due to the complex distribution of meteorological variables,which can lead to unstable forecasting results,especially in extreme scenarios.To overcome this issue,we propose a convolutional graph neural network(CGNN)model,which we enhance with multilayer feature fusion and a squeeze-and-excitation block.Additionally,we introduce a spatially balanced mean squared error(SBMSE)loss function to address the imbalanced distribution and spatial variability of meteorological variables.The CGNN is capable of extracting essential spatial features and aggregating them from a global perspective,thereby improving the accuracy of prediction and enhancing the model's generalization ability.Based on the experimental results,CGNN has certain advantages in terms of bias distribution,exhibiting a smaller variance.When it comes to precipitation,both UNet and AE also demonstrate relatively small biases.As for temperature,AE and CNNdense perform outstandingly during the winter.The time correlation coefficients show an improvement of at least 10%at daily and monthly scales for both temperature and precipitation.Furthermore,the SBMSE loss function displays an advantage over existing loss functions in predicting the98th percentile and identifying areas where extreme events occur.However,the SBMSE tends to overestimate the distribution of extreme precipitation,which may be due to the theoretical assumptions about the posterior distribution of data that partially limit the effectiveness of the loss function.In future work,we will further optimize the SBMSE to improve prediction accuracy.展开更多
Currently,challenges such as small object size and occlusion lead to a lack of accuracy and robustness in small object detection.Since small objects occupy only a few pixels in an image,the extracted features are limi...Currently,challenges such as small object size and occlusion lead to a lack of accuracy and robustness in small object detection.Since small objects occupy only a few pixels in an image,the extracted features are limited,and mainstream downsampling convolution operations further exacerbate feature loss.Additionally,due to the occlusionprone nature of small objects and their higher sensitivity to localization deviations,conventional Intersection over Union(IoU)loss functions struggle to achieve stable convergence.To address these limitations,LR-Net is proposed for small object detection.Specifically,the proposed Lossless Feature Fusion(LFF)method transfers spatial features into the channel domain while leveraging a hybrid attentionmechanism to focus on critical features,mitigating feature loss caused by downsampling.Furthermore,RSIoU is proposed to enhance the convergence performance of IoU-based losses for small objects.RSIoU corrects the inherent convergence direction issues in SIoU and proposes a penalty term as a Dynamic Focusing Mechanism parameter,enabling it to dynamically emphasize the loss contribution of small object samples.Ultimately,RSIoU significantly improves the convergence performance of the loss function for small objects,particularly under occlusion scenarios.Experiments demonstrate that LR-Net achieves significant improvements across variousmetrics onmultiple datasets compared with YOLOv8n,achieving a 3.7% increase in mean Average Precision(AP)on the VisDrone2019 dataset,along with improvements of 3.3% on the AI-TOD dataset and 1.2% on the COCO dataset.展开更多
AIM: To explore the effects and mechanism of action of antidepressant mirtazapine in functional dyspepsia(FD) patients with weight loss.METHODS: Sixty depressive FD patients with weight loss were randomly divided into...AIM: To explore the effects and mechanism of action of antidepressant mirtazapine in functional dyspepsia(FD) patients with weight loss.METHODS: Sixty depressive FD patients with weight loss were randomly divided into a mirtazapine group(MG), a paroxetine group(PG) or a conventional therapy group(CG) for an 8-wk clinical trial. Adverse effects and treatment response were recorded. The Nepean Dyspepsia Index-symptom(NDSI) checklist and the 17-item Hamilton Rating Scale of Depression(HAMD-17) were used to evaluate dyspepsia and depressive symptoms, respectively. The body composition analyzer was used to measure body weight and fat. Serum hormone levels were measured by ELISA.RESULTS:(1) After 2 wk of treatment, NDSI scores were significantly lower for the MG than for the PG and CG;(2) After 4 or 8 wk of treatment, HAMD-17 scores were significantly lower for the MG and PG than for the CG;(3) After 8 wk of treatment, patients in the MG experienced a weight gain of 3.58 ± 1.57 kg, which was significantly higher than that observed for patients in the PG and CG. Body fat increased by 2.77 ± 0.14kg, the body fat ratio rose by 4%, and the visceral fat area increased by 7.56 ± 2.25 cm2; and(4) For the MG, serum hormone levels of ghrelin, neuropeptide Y(NPY), motilin(MTL) and gastrin(GAS) were significantly upregulated; in contrast, those of leptin, 5-hydroxytryptamine(5-HT) and cholecystokinin(CCK) were significantly downregulated. CONCLUSION: Mirtazapine not only alleviates symptoms associated with dyspepsia and depression linked to FD in patients with weight loss but also significantly increases body weight(mainly the visceral fat in body fat). The likely mechanism of mirtazapine action is regulation of brain-gut or gastrointestinal hormone levels.展开更多
LINEX(linear and exponential) loss function is a useful asymmetric loss function. The purpose of using a LINEX loss function in credibility models is to solve the problem of very high premium by suing a symmetric quad...LINEX(linear and exponential) loss function is a useful asymmetric loss function. The purpose of using a LINEX loss function in credibility models is to solve the problem of very high premium by suing a symmetric quadratic loss function in most of classical credibility models. The Bayes premium and the credibility premium are derived under LINEX loss function. The consistency of Bayes premium and credibility premium were also checked. Finally, the simulation was introduced to show the differences between the credibility estimator we derived and the classical one.展开更多
This study investigates the vibration and acoustic properties of porous foam functionally graded(FG)plates under the influence of the temperature field.The dynamics equations of the system are established based on Ham...This study investigates the vibration and acoustic properties of porous foam functionally graded(FG)plates under the influence of the temperature field.The dynamics equations of the system are established based on Hamilton's principle by using the higher-order shear deformation theory under the linear displacement-strain assumption.The displacement shape function is assumed according to the four-sided simply-supported(SSSS)boundary condition,and the characteristic equations of the system are derived by combining the motion control equations.The theoretical model of vibro-acoustic coupling is established by using the acoustic theory and fluid-structure coupling solution method under the simple harmonic acoustic wave.The system's natural frequency and sound transmission loss(STL)are obtained through programming calculations and compared with the literature and COMSOL simulation to verify the validity and reliability of the theoretical model.The effects of various factors,such as temperature,porosity coefficients,gradient index,core thickness,width-to-thickness ratio on the vibration,and STL characteristics of the system,are discussed.The results provide a theoretical basis for the application of porous foam FG plates in engineering to optimize vibration and sound transmission properties.展开更多
The deep learning model is overfitted and the accuracy of the test set is reduced when the deep learning model is trained in the network intrusion detection parameters, due to the traditional loss function convergence...The deep learning model is overfitted and the accuracy of the test set is reduced when the deep learning model is trained in the network intrusion detection parameters, due to the traditional loss function convergence problem. Firstly, we utilize a network model architecture combining Gelu activation function and deep neural network;Secondly, the cross-entropy loss function is improved to a weighted cross entropy loss function, and at last it is applied to intrusion detection to improve the accuracy of intrusion detection. In order to compare the effect of the experiment, the KDDcup99 data set, which is commonly used in intrusion detection, is selected as the experimental data and use accuracy, precision, recall and F1-score as evaluation parameters. The experimental results show that the model using the weighted cross-entropy loss function combined with the Gelu activation function under the deep neural network architecture improves the evaluation parameters by about 2% compared with the ordinary cross-entropy loss function model. Experiments prove that the weighted cross-entropy loss function can enhance the model’s ability to discriminate samples.展开更多
Recently,the evolution of Generative Adversarial Networks(GANs)has embarked on a journey of revolutionizing the field of artificial and computational intelligence.To improve the generating ability of GANs,various loss...Recently,the evolution of Generative Adversarial Networks(GANs)has embarked on a journey of revolutionizing the field of artificial and computational intelligence.To improve the generating ability of GANs,various loss functions are introduced to measure the degree of similarity between the samples generated by the generator and the real data samples,and the effectiveness of the loss functions in improving the generating ability of GANs.In this paper,we present a detailed survey for the loss functions used in GANs,and provide a critical analysis on the pros and cons of these loss functions.First,the basic theory of GANs along with the training mechanism are introduced.Then,the most commonly used loss functions in GANs are introduced and analyzed.Third,the experimental analyses and comparison of these loss functions are presented in different GAN architectures.Finally,several suggestions on choosing suitable loss functions for image synthesis tasks are given.展开更多
Path loss prediction models are vital for accurate signal propagation in wireless channels. Empirical and deterministic models used in path loss predictions have not produced optimal results. In this paper, we introdu...Path loss prediction models are vital for accurate signal propagation in wireless channels. Empirical and deterministic models used in path loss predictions have not produced optimal results. In this paper, we introduced machine learning algorithms to path loss predictions because it offers a flexible network architecture and extensive data can be used. We introduced support vector regression (SVR) and radial basis function (RBF) models to path loss predictions in the investigated environments. The SVR model was able to process several input parameters without introducing complexity to the network architecture. The RBF on its part provides a good function approximation. Hyperparameter tuning of the machine learning models was carried out in order to achieve optimal results. The performances of the SVR and RBF models were compared and result validated using the root-mean squared error (RMSE). The two machine learning algorithms were also compared with the Cost-231, SUI, Egli, Freespace, Cost-231 W-I models. The analytical models overpredicted path loss. Overall, the machine learning models predicted path loss with greater accuracy than the empirical models. The SVR model performed best across all the indices with RMSE values of 1.378 dB, 1.4523 dB, 2.1568 dB in rural, suburban and urban settings respectively and should therefore be adopted for signal propagation in the investigated environments and beyond.展开更多
BACKGROUND Our study contributes to the further understanding of the mechanism of foot reflexology.Foot reflexology has been reported to affect hearing recovery,but no physiological evidence has been provided.This lac...BACKGROUND Our study contributes to the further understanding of the mechanism of foot reflexology.Foot reflexology has been reported to affect hearing recovery,but no physiological evidence has been provided.This lack of evidence hampers the acceptance of the technique in clinical practice.CASE SUMMARY A girl was taken to North Sichuan Medical University Affiliated Hospital for a hearing screen by her parents.Her parents reported that her hearing level was the same as when she was born.The girl was diagnosed with sensorineural hearing loss(SNHL)by a doctor in the otolaryngology department.After we introduced the foot reflexology project,the parents agreed to participate in the experiment.After 6 months of foot reflexology treatment,the hearing threshold of the girl recovered to a normal level,below 30 dB.CONCLUSION Foot reflexology should be encouraged in clinical practice and for families of infants with SNHL.展开更多
基金supported by the National Natural Science Foundation of China(NSFC)No.62172189 and 61772235the Natural Science Foundation of Guangdong Province No.2020A1515010771+1 种基金the Science and Technology Program of Guangzhou No.202002030372the UK Engineering and Physical Sciences Research Council(EPSRC)grants EP/P004407/2 and EP/P004024/1,and Innovate UK grant 106199-47198.
文摘The advent of Network Function Virtualization(NFV)and Service Function Chains(SFCs)unleashes the power of dynamic creation of network services using Virtual Network Functions(VNFs).This is of great interest to network operators since poor service quality and resource wastage can potentially hurt their revenue in the long term.However,the study shows with a set of test-bed experiments that packet loss at certain positions(i.e.,different VNFs)in an SFC can cause various degrees of resource wastage and performance degradation because of repeated upstream processing and transmission of retransmitted packets.To overcome this challenge,this study focuses on resource scheduling and deployment of SFCs while considering packet loss positions.This study developed a novel SFC packet dropping cost model and formulated an SFC scheduling problem that aims to minimize overall packet dropping cost as a Mixed-Integer Linear Programming(MILP)and proved that it is NP-hard.In this study,Palos is proposed as an efficient scheme in exploiting the functional characteristics of VNFs and their positions in SFCs for scheduling resources and deployment to optimize packet dropping cost.Extensive experiment results show that Palos can achieve up to 42.73%improvement on packet dropping cost and up to 33.03%reduction on average SFC latency when compared with two other state-of-the-art schemes.
基金Jilin Science and Technology Development Plan Project(No.20200403075SF)Doctoral Research Start-Up Fund of Northeast Electric Power University(No.BSJXM-2018202).
文摘The current existing problem of deep learning framework for the detection and segmentation of electrical equipment is dominantly related to low precision.Because of the reliable,safe and easy-to-operate technology provided by deep learning-based video surveillance for unmanned inspection of electrical equipment,this paper uses the bottleneck attention module(BAM)attention mechanism to improve the Solov2 model and proposes a new electrical equipment segmentation mode.Firstly,the BAM attention mechanism is integrated into the feature extraction network to adaptively learn the correlation between feature channels,thereby improving the expression ability of the feature map;secondly,the weighted sum of CrossEntropy Loss and Dice loss is designed as the mask loss to improve the segmentation accuracy and robustness of the model;finally,the non-maximal suppression(NMS)algorithm to better handle the overlap problem in instance segmentation.Experimental results show that the proposed method achieves an average segmentation accuracy of mAP of 80.4% on three types of electrical equipment datasets,including transformers,insulators and voltage transformers,which improve the detection accuracy by more than 5.7% compared with the original Solov2 model.The segmentation model proposed can provide a focusing technical means for the intelligent management of power systems.
基金Supported by the National Social Science Foundation,No.18BY0911.
文摘BACKGROUND Understanding the impact of early sensory deficits on brain development is essential for understanding developmental processes and developing potential interventions.While previous studies have looked into the impact of prenatal experiences on language development,there is a lack of research on how these experiences affect early language and brain function development in individuals with sensorineural hearing loss(SNHL).AIM To investigate SNHL effects on early brain development and connectivity in 4-month-olds vs healthy newborns and controls.METHODS The research involved analyzing the functional brain networks of 65 infants,categorized into three groups:28 healthy newborns,224-month-old participants with SNHL,and 15 age-matched healthy participants.The resting-state functional connectivity was measured and compared between the groups using functional near-infrared spectroscopy and graph theory to assess the brain network properties.RESULTS Significant differences were found in resting-state functional connectivity between participants with SNHL and age-matched controls,indicating a developmental lag in brain connectivity for those with SNHL.Surprisingly,SNHL participants showed better connectivity development compared to healthy newborns,with connectivity strengths of 0.13±0.04 for SNHL,0.16±0.08 for controls,and 0.098±0.04 for newborns.Graph theory analysis revealed enhanced global brain network properties for the SNHL group,suggesting higher communication efficiency at 4 months.No significant differences were noted in network properties between 4-month-old SNHL participants and neonates.A unique pattern of central hubs was observed in the SNHL group,with 2 hubs in the left hemisphere compared to 6 in controls.CONCLUSION 4-month-old infants with SNHL have a distinct brain network pattern with efficient long-distance information transmission but less effective local communication compared to age-matched controls.
文摘In this paper, the isogeometric analysis (IGA) is employed to develop an acoustic radiation model for a double plate-acoustic cavity coupling system, with a focus on analyzing the sound transmission loss (STL). The functionally graded (FG) plate exhibits a different material properties in-plane, and the power-law rule is adopted as the governing principle for material mixing. To validate the harmonic response and demonstrate the accuracy and convergence of the isogeometric modeling, ANASYS is utilized to compare with numerical examples. A plane wave serves as the acoustic excitation, and the Rayleigh integral is applied to discretize the radiated plate. The STL results are compared with the literature, confirming the reliability of the coupling system. Finally, the investigation is conducted to study impact of cavity depth and power-law parameter on the STL.
基金supported by the National Key Research and Development Program of China(Grant numbers:2021YFF0901705,2021YFF0901700)the State Key Laboratory of Media Convergence and Communication,Communication University of China+1 种基金the Fundamental Research Funds for the Central Universitiesthe High-Quality and Cutting-Edge Disciplines Construction Project for Universities in Beijing(Internet Information,Communication University of China).
文摘In the Internet era,recommendation systems play a crucial role in helping users find relevant information from large datasets.Class imbalance is known to severely affect data quality,and therefore reduce the performance of recommendation systems.Due to the imbalance,machine learning algorithms tend to classify inputs into the positive(majority)class every time to achieve high prediction accuracy.Imbalance can be categorized such as by features and classes,but most studies consider only class imbalance.In this paper,we propose a recommendation system that can integrate multiple networks to adapt to a large number of imbalanced features and can deal with highly skewed and imbalanced datasets through a loss function.We propose a loss aware feature attention mechanism(LAFAM)to solve the issue of feature imbalance.The network incorporates an attention mechanism and uses multiple sub-networks to classify and learn features.For better results,the network can learn the weights of sub-networks and assign higher weights to important features.We propose suppression loss to address class imbalance,which favors negative loss by penalizing positive loss,and pays more attention to sample points near the decision boundary.Experiments on two large-scale datasets verify that the performance of the proposed system is greatly improved compared to baseline methods.
文摘Maxillary bone loss impairs essential functions (chewing, swallowing, speech) and gives patients a very unaesthetic appearance due to the removal of facial support tissues, leading to serious psychological consequences. Treatment is multidisciplinary and requires a resective surgery if the cause is tumor-related, or an additive surgery if the cause is traumatic. This article aims to show the role of making a prosthesis to restore function (chewing, swallowing, speech) and aesthetics following maxillary bone loss. We will eighter present a clinical case involving a right maxillary tumor that was surgically resected followed by radiotherapy, and subsequently rehabilitated with a maxillofacial prosthesis in the consultation and dental treatment center of the university hospital center of Casablanca.
基金support from the UCL GRS/ORS scholarshipUCL Fellowship Incubator Award+9 种基金supported by the NIHR Cambridge Biomedical Research Centre(NIHR203312)funded by the Royal National Institute for Deaf People(RNID,G100138)funded by the Rosetrees Trust Enterprise Fellowship(EF2020100099)RNID Flexigrant(F112)Wellcome Trust Developing Concept Fund(RG93172/BANCE/40181)by the Evelyn Trustfunded by the Woolf Fisher Trust,New Zealandthe Cambridge Commonwealth,European,&International Trustby Trinity CollegeUniversity of Cambridge。
文摘The cochlea is one of the most complex organs in the human body,exhibiting a complex interplay of characteristics in acoustic,mechanical,electrical,and biological functions.Functional cochlea models are an essential platform for studying hearing mechanics and are crucial for developing next-generation auditory prostheses and artificial hearing systems for sensorineural hearing restoration.Recent advances in additive manufacturing,organ-on-a-chip models,drug delivery platforms,and artificial intelligence have provided valuable insights into how to manufacture artificial cochlea models that more accurately replicate the complex anatomy and physiology of the inner ear.This paper reviews recent advancements in the applications of advanced manufacturing techniques in reproducing the physical,biological,and intelligent functions of the cochlea.It also outlines the current challenges to developing mechanically,electrically,and anatomically accurate functional models of the inner ear.Finally,this review identifies the major requirements and outlook for impactful research in this field going forward.Through interdisciplinary collaboration and innovation,these functional cochlea models are poised to drive significant advancements in hearing treatments,and ultimately enhance the quality of life for individuals with hearing loss.
基金support from the following institutional grant.Internal Grant Agency of the Faculty of Economics and Management,Czech University of Life Sciences Prague,grant no.2023A0004(https://iga.pef.czu.cz/,accessed on 6 June 2025).
文摘This study proposes a new component of the composite loss function minimised during training of the Super-Resolution(SR)algorithms—the normalised structural similarity index loss LSSIMN,which has the potential to improve the natural appearance of reconstructed images.Deep learning-based super-resolution(SR)algorithms reconstruct high-resolution images from low-resolution inputs,offering a practical means to enhance image quality without requiring superior imaging hardware,which is particularly important in medical applications where diagnostic accuracy is critical.Although recent SR methods employing convolutional and generative adversarial networks achieve high pixel fidelity,visual artefacts may persist,making the design of the loss function during training essential for ensuring reliable and naturalistic image reconstruction.Our research shows on two models—SR and Invertible Rescaling Neural Network(IRN)—trained on multiple benchmark datasets that the function LSSIMN significantly contributes to the visual quality,preserving the structural fidelity on the reference datasets.The quantitative analysis of results while incorporating LSSIMN shows that including this loss function component has a mean 2.88%impact on the improvement of the final structural similarity of the reconstructed images in the validation set,in comparison to leaving it out and 0.218%in comparison when this component is non-normalised.
基金supported by the State Key Laboratory of Arid Land Crop Science, Gansu Agricultural University,China (GSCS-2022-Z02)the National Key R&D Program of China (2022YFD1900300)+2 种基金the National Natural Science Foundation of China (32260549)the Innovation Group of Basic Research in Gansu Province, China (25JRRA807)the Major Special Research Projects in Gansu Province, China (22ZD6NA009)。
文摘The application of organic fertilizers has become an increasingly popular practice in maize production to reduce thegaseous nitrogen(N) loss and soil degradation caused by inorganic fertilizers. Organic fertilizer plays a key rolein improving soil quality and stabilizing maize yields, but few studies have compared different substitution rates. Afield study was carried out in 2021 and 2022, based on a long-term trial initiated in 2016, which included five organicfertilizer N substitution rates with equal inputs of 200 kg N ha^(–1): 0% organic fertilizer(T1, 100% inorganic fertilizer),50.0% organic+50.0% inorganic fertilizer(T2), 37.5% organic+62.5% inorganic fertilizer(T3), 25.0% organic+75.0%inorganic fertilizer(T4), and 12.5% organic+87.5% inorganic fertilizer(T5), as well as a no fertilizer control(T6). Theresults of the two years showed that T3 and T1 had the highest grain yield and biomass, respectively, and there wasno significant difference between T1 and T3. Compared with T1, the 12.5, 25.0, 37.5, and 50.0% substitution rates in T5, T4, T3, and T2 significantly reduced total nitrogen losses(NH_(3), N_(2)O) by 8.3, 16.1, 18.7, and 27.0%, respectively.Nitrogen use efficiency(NUE) was higher in T5, T3, and T1, and there were no significant differences among them.Organic fertilizer substitution directly reduced NH_(3)volatilization and N_(2)O emission from farmland by lowering theammonium nitrogen and alkali-dissolved N contents and by increasing soil moisture. These substitution treatmentsreduced N_(2)O emissions indirectly by regulating the abundances of AOB and nirK-harboring genes by promotingsoil moisture. Specifically, the 37.5% organic fertilizer substitution reduces NH_(3)volatilization and N_(2)O emission from farmland by reducing the ammonium nitrogen and alkali-dissolved N contents and increasing moisture, which negatively regulate the abundance of AOB and nir K-harboring genes to reduce N_(2)O emissions indirectly in rainfed maize fields on the Loess Plateau of China.
基金partially funded by the National Natural Science Foundation of China(U2142205)the Guangdong Major Project of Basic and Applied Basic Research(2020B0301030004)+1 种基金the Special Fund for Forecasters of China Meteorological Administration(CMAYBY2020-094)the Graduate Student Research and Innovation Program of Central South University(2023ZZTS0347)。
文摘Traditional meteorological downscaling methods face limitations due to the complex distribution of meteorological variables,which can lead to unstable forecasting results,especially in extreme scenarios.To overcome this issue,we propose a convolutional graph neural network(CGNN)model,which we enhance with multilayer feature fusion and a squeeze-and-excitation block.Additionally,we introduce a spatially balanced mean squared error(SBMSE)loss function to address the imbalanced distribution and spatial variability of meteorological variables.The CGNN is capable of extracting essential spatial features and aggregating them from a global perspective,thereby improving the accuracy of prediction and enhancing the model's generalization ability.Based on the experimental results,CGNN has certain advantages in terms of bias distribution,exhibiting a smaller variance.When it comes to precipitation,both UNet and AE also demonstrate relatively small biases.As for temperature,AE and CNNdense perform outstandingly during the winter.The time correlation coefficients show an improvement of at least 10%at daily and monthly scales for both temperature and precipitation.Furthermore,the SBMSE loss function displays an advantage over existing loss functions in predicting the98th percentile and identifying areas where extreme events occur.However,the SBMSE tends to overestimate the distribution of extreme precipitation,which may be due to the theoretical assumptions about the posterior distribution of data that partially limit the effectiveness of the loss function.In future work,we will further optimize the SBMSE to improve prediction accuracy.
基金supported by Chongqing Municipal Commission of Housing and Urban-Rural Development(Grant No.CKZ2024-87)China Chongqing Municipal Science and Technology Bureau(Grant No.2024TIAD-CYKJCXX0121).
文摘Currently,challenges such as small object size and occlusion lead to a lack of accuracy and robustness in small object detection.Since small objects occupy only a few pixels in an image,the extracted features are limited,and mainstream downsampling convolution operations further exacerbate feature loss.Additionally,due to the occlusionprone nature of small objects and their higher sensitivity to localization deviations,conventional Intersection over Union(IoU)loss functions struggle to achieve stable convergence.To address these limitations,LR-Net is proposed for small object detection.Specifically,the proposed Lossless Feature Fusion(LFF)method transfers spatial features into the channel domain while leveraging a hybrid attentionmechanism to focus on critical features,mitigating feature loss caused by downsampling.Furthermore,RSIoU is proposed to enhance the convergence performance of IoU-based losses for small objects.RSIoU corrects the inherent convergence direction issues in SIoU and proposes a penalty term as a Dynamic Focusing Mechanism parameter,enabling it to dynamically emphasize the loss contribution of small object samples.Ultimately,RSIoU significantly improves the convergence performance of the loss function for small objects,particularly under occlusion scenarios.Experiments demonstrate that LR-Net achieves significant improvements across variousmetrics onmultiple datasets compared with YOLOv8n,achieving a 3.7% increase in mean Average Precision(AP)on the VisDrone2019 dataset,along with improvements of 3.3% on the AI-TOD dataset and 1.2% on the COCO dataset.
文摘AIM: To explore the effects and mechanism of action of antidepressant mirtazapine in functional dyspepsia(FD) patients with weight loss.METHODS: Sixty depressive FD patients with weight loss were randomly divided into a mirtazapine group(MG), a paroxetine group(PG) or a conventional therapy group(CG) for an 8-wk clinical trial. Adverse effects and treatment response were recorded. The Nepean Dyspepsia Index-symptom(NDSI) checklist and the 17-item Hamilton Rating Scale of Depression(HAMD-17) were used to evaluate dyspepsia and depressive symptoms, respectively. The body composition analyzer was used to measure body weight and fat. Serum hormone levels were measured by ELISA.RESULTS:(1) After 2 wk of treatment, NDSI scores were significantly lower for the MG than for the PG and CG;(2) After 4 or 8 wk of treatment, HAMD-17 scores were significantly lower for the MG and PG than for the CG;(3) After 8 wk of treatment, patients in the MG experienced a weight gain of 3.58 ± 1.57 kg, which was significantly higher than that observed for patients in the PG and CG. Body fat increased by 2.77 ± 0.14kg, the body fat ratio rose by 4%, and the visceral fat area increased by 7.56 ± 2.25 cm2; and(4) For the MG, serum hormone levels of ghrelin, neuropeptide Y(NPY), motilin(MTL) and gastrin(GAS) were significantly upregulated; in contrast, those of leptin, 5-hydroxytryptamine(5-HT) and cholecystokinin(CCK) were significantly downregulated. CONCLUSION: Mirtazapine not only alleviates symptoms associated with dyspepsia and depression linked to FD in patients with weight loss but also significantly increases body weight(mainly the visceral fat in body fat). The likely mechanism of mirtazapine action is regulation of brain-gut or gastrointestinal hormone levels.
基金Supported by the NNSF of China(71001046)Supported by the NSF of Jiangxi Province(20114BAB211004)
文摘LINEX(linear and exponential) loss function is a useful asymmetric loss function. The purpose of using a LINEX loss function in credibility models is to solve the problem of very high premium by suing a symmetric quadratic loss function in most of classical credibility models. The Bayes premium and the credibility premium are derived under LINEX loss function. The consistency of Bayes premium and credibility premium were also checked. Finally, the simulation was introduced to show the differences between the credibility estimator we derived and the classical one.
基金Project supported by the National Natural Science Foundation of China(No.11972082)。
文摘This study investigates the vibration and acoustic properties of porous foam functionally graded(FG)plates under the influence of the temperature field.The dynamics equations of the system are established based on Hamilton's principle by using the higher-order shear deformation theory under the linear displacement-strain assumption.The displacement shape function is assumed according to the four-sided simply-supported(SSSS)boundary condition,and the characteristic equations of the system are derived by combining the motion control equations.The theoretical model of vibro-acoustic coupling is established by using the acoustic theory and fluid-structure coupling solution method under the simple harmonic acoustic wave.The system's natural frequency and sound transmission loss(STL)are obtained through programming calculations and compared with the literature and COMSOL simulation to verify the validity and reliability of the theoretical model.The effects of various factors,such as temperature,porosity coefficients,gradient index,core thickness,width-to-thickness ratio on the vibration,and STL characteristics of the system,are discussed.The results provide a theoretical basis for the application of porous foam FG plates in engineering to optimize vibration and sound transmission properties.
文摘The deep learning model is overfitted and the accuracy of the test set is reduced when the deep learning model is trained in the network intrusion detection parameters, due to the traditional loss function convergence problem. Firstly, we utilize a network model architecture combining Gelu activation function and deep neural network;Secondly, the cross-entropy loss function is improved to a weighted cross entropy loss function, and at last it is applied to intrusion detection to improve the accuracy of intrusion detection. In order to compare the effect of the experiment, the KDDcup99 data set, which is commonly used in intrusion detection, is selected as the experimental data and use accuracy, precision, recall and F1-score as evaluation parameters. The experimental results show that the model using the weighted cross-entropy loss function combined with the Gelu activation function under the deep neural network architecture improves the evaluation parameters by about 2% compared with the ordinary cross-entropy loss function model. Experiments prove that the weighted cross-entropy loss function can enhance the model’s ability to discriminate samples.
文摘Recently,the evolution of Generative Adversarial Networks(GANs)has embarked on a journey of revolutionizing the field of artificial and computational intelligence.To improve the generating ability of GANs,various loss functions are introduced to measure the degree of similarity between the samples generated by the generator and the real data samples,and the effectiveness of the loss functions in improving the generating ability of GANs.In this paper,we present a detailed survey for the loss functions used in GANs,and provide a critical analysis on the pros and cons of these loss functions.First,the basic theory of GANs along with the training mechanism are introduced.Then,the most commonly used loss functions in GANs are introduced and analyzed.Third,the experimental analyses and comparison of these loss functions are presented in different GAN architectures.Finally,several suggestions on choosing suitable loss functions for image synthesis tasks are given.
文摘Path loss prediction models are vital for accurate signal propagation in wireless channels. Empirical and deterministic models used in path loss predictions have not produced optimal results. In this paper, we introduced machine learning algorithms to path loss predictions because it offers a flexible network architecture and extensive data can be used. We introduced support vector regression (SVR) and radial basis function (RBF) models to path loss predictions in the investigated environments. The SVR model was able to process several input parameters without introducing complexity to the network architecture. The RBF on its part provides a good function approximation. Hyperparameter tuning of the machine learning models was carried out in order to achieve optimal results. The performances of the SVR and RBF models were compared and result validated using the root-mean squared error (RMSE). The two machine learning algorithms were also compared with the Cost-231, SUI, Egli, Freespace, Cost-231 W-I models. The analytical models overpredicted path loss. Overall, the machine learning models predicted path loss with greater accuracy than the empirical models. The SVR model performed best across all the indices with RMSE values of 1.378 dB, 1.4523 dB, 2.1568 dB in rural, suburban and urban settings respectively and should therefore be adopted for signal propagation in the investigated environments and beyond.
基金Graduate Student Project of Xi’an International Studies University,No.2021BS012Nanchong City-Universities Project,No.22SXCXTD0004.
文摘BACKGROUND Our study contributes to the further understanding of the mechanism of foot reflexology.Foot reflexology has been reported to affect hearing recovery,but no physiological evidence has been provided.This lack of evidence hampers the acceptance of the technique in clinical practice.CASE SUMMARY A girl was taken to North Sichuan Medical University Affiliated Hospital for a hearing screen by her parents.Her parents reported that her hearing level was the same as when she was born.The girl was diagnosed with sensorineural hearing loss(SNHL)by a doctor in the otolaryngology department.After we introduced the foot reflexology project,the parents agreed to participate in the experiment.After 6 months of foot reflexology treatment,the hearing threshold of the girl recovered to a normal level,below 30 dB.CONCLUSION Foot reflexology should be encouraged in clinical practice and for families of infants with SNHL.
