DeepSVDNet:A Deep Learning-Based Approach for Detecting and Classifying Vision-Threatening Diabetic Retinopathy in Retinal Fundus Images

Artificial Intelligence(AI)is being increasingly used for diagnosing Vision-Threatening Diabetic Retinopathy(VTDR),which is a leading cause of visual impairment and blindness worldwide.However,previous automated VTDR detection methods have mainly relied on manual feature extraction and classification,leading to errors.This paper proposes a novel VTDR detection and classification model that combines different models through majority voting.Our proposed methodology involves preprocessing,data augmentation,feature extraction,and classification stages.We use a hybrid convolutional neural network-singular value decomposition(CNN-SVD)model for feature extraction and selection and an improved SVM-RBF with a Decision Tree(DT)and K-Nearest Neighbor(KNN)for classification.We tested our model on the IDRiD dataset and achieved an accuracy of 98.06%,a sensitivity of 83.67%,and a specificity of 100%for DR detection and evaluation tests,respectively.Our proposed approach outperforms baseline techniques and provides a more robust and accurate method for VTDR detection.

Diffraction deep neural network-based classification for vector vortex beams

The vector vortex beam(VVB)has attracted significant attention due to its intrinsic diversity of information and has found great applications in both classical and quantum communications.However,a VVB is unavoidably affected by atmospheric turbulence(AT)when it propagates through the free-space optical communication environment,which results in detection errors at the receiver.In this paper,we propose a VVB classification scheme to detect VVBs with continuously changing polarization states under AT,where a diffractive deep neural network(DDNN)is designed and trained to classify the intensity distribution of the input distorted VVBs,and the horizontal direction of polarization of the input distorted beam is adopted as the feature for the classification through the DDNN.The numerical simulations and experimental results demonstrate that the proposed scheme has high accuracy in classification tasks.The energy distribution percentage remains above 95%from weak to medium AT,and the classification accuracy can remain above 95%for various strengths of turbulence.It has a faster convergence and better accuracy than that based on a convolutional neural network.

Secure Transmission of Compressed Medical Image Sequences on Communication Networks Using Motion Vector Watermarking

Medical imaging plays a key role within modern hospital management systems for diagnostic purposes.Compression methodologies are extensively employed to mitigate storage demands and enhance transmission speed,all while upholding image quality.Moreover,an increasing number of hospitals are embracing cloud computing for patient data storage,necessitating meticulous scrutiny of server security and privacy protocols.Nevertheless,considering the widespread availability of multimedia tools,the preservation of digital data integrity surpasses the significance of compression alone.In response to this concern,we propose a secure storage and transmission solution for compressed medical image sequences,such as ultrasound images,utilizing a motion vector watermarking scheme.The watermark is generated employing an error-correcting code known as Bose-Chaudhuri-Hocquenghem(BCH)and is subsequently embedded into the compressed sequence via block-based motion vectors.In the process of watermark embedding,motion vectors are selected based on their magnitude and phase angle.When embedding watermarks,no specific spatial area,such as a region of interest(ROI),is used in the images.The embedding of watermark bits is dependent on motion vectors.Although reversible watermarking allows the restoration of the original image sequences,we use the irreversible watermarking method.The reason for this is that the use of reversible watermarks may impede the claims of ownership and legal rights.The restoration of original data or images may call into question ownership or other legal claims.The peak signal-to-noise ratio(PSNR)and structural similarity index(SSIM)serve as metrics for evaluating the watermarked image quality.Across all images,the PSNR value exceeds 46 dB,and the SSIM value exceeds 0.92.Experimental results substantiate the efficacy of the proposed technique in preserving data integrity.

Underwater Image Classification Based on EfficientnetB0 and Two-Hidden-Layer Random Vector Functional Link

The ocean plays an important role in maintaining the equilibrium of Earth’s ecology and providing humans access to a wealth of resources.To obtain a high-precision underwater image classification model,we propose a classification model that combines an EfficientnetB0 neural network and a two-hidden-layer random vector functional link network(EfficientnetB0-TRVFL).The features of underwater images were extracted using the EfficientnetB0 neural network pretrained via ImageNet,and a new fully connected layer was trained on the underwater image dataset using the transfer learning method.Transfer learning ensures the initial performance of the network and helps in the development of a high-precision classification model.Subsequently,a TRVFL was proposed to improve the classification property of the model.Net construction of the two hidden layers exhibited a high accuracy when the same hidden layer nodes were used.The parameters of the second hidden layer were obtained using a novel calculation method,which reduced the outcome error to improve the performance instability caused by the random generation of parameters of RVFL.Finally,the TRVFL classifier was used to classify features and obtain classification results.The proposed EfficientnetB0-TRVFL classification model achieved 87.28%,74.06%,and 99.59%accuracy on the MLC2008,MLC2009,and Fish-gres datasets,respectively.The best convolutional neural networks and existing methods were stacked up through box plots and Kolmogorov-Smirnov tests,respectively.The increases imply improved systematization properties in underwater image classification tasks.The image classification model offers important performance advantages and better stability compared with existing methods.

Increasingβ-hexosaminidase A activity using genetically modified mesenchymal stem cells

GM2 gangliosidoses are a group of autosomal-recessive lysosomal storage disorde rs.These diseases result from a deficiency of lysosomal enzymeβ-hexosaminidase A(HexA),which is responsible for GM2 ganglioside degradation.HexA deficiency causes the accumulation of GM2-gangliosides mainly in the nervous system cells,leading to severe progressive neurodegeneration and neuroinflammation.To date,there is no treatment for these diseases.Cell-mediated gene therapy is considered a promising treatment for GM2 gangliosidoses.This study aimed to evaluate the ability of genetically modified mesenchymal stem cells(MSCs-HEXA-HEXB)to restore HexA deficiency in Tay-Sachs disease patient cells,as well as to analyze the functionality and biodistribution of MSCs in vivo.The effectiveness of HexA deficiency cross-correction was shown in mutant MSCs upon intera ction with MSCs-HEXA-HEXB.The results also showed that the MSCs-HEXA-HEXB express the functionally active HexA enzyme,detectable in vivo,and intravenous injection of the cells does not cause an immune response in animals.These data suggest that genetically modified mesenchymal stem cells have the potentials to treat GM2 gangliosidoses.

Vector magnetometry in zero bias magnetic field using nitrogen-vacancy ensembles

The application of the vector magnetometry based on nitrogen-vacancy(NV)ensembles has been widely investigatedin multiple areas.It has the superiority of high sensitivity and high stability in ambient conditions with microscale spatialresolution.However,a bias magnetic field is necessary to fully separate the resonance lines of optically detected magneticresonance(ODMR)spectrum of NV ensembles.This brings disturbances in samples being detected and limits the rangeof application.Here,we demonstrate a method of vector magnetometry in zero bias magnetic field using NV ensembles.By utilizing the anisotropy property of fluorescence excited from NV centers,we analyzed the ODMR spectrum of NVensembles under various polarized angles of excitation laser in zero bias magnetic field with a quantitative numerical modeland reconstructed the magnetic field vector.The minimum magnetic field modulus that can be resolved accurately is downto~0.64 G theoretically depending on the ODMR spectral line width(1.8 MHz),and~2 G experimentally due to noisesin fluorescence signals and errors in calibration.By using 13C purified and low nitrogen concentration diamond combinedwith improving calibration of unknown parameters,the ODMR spectral line width can be further decreased below 0.5 MHz,corresponding to~0.18 G minimum resolvable magnetic field modulus.

Enhanced Wolf Pack Algorithm (EWPA) and Dense-kUNet Segmentation for Arterial Calcifications in Mammograms

Breast Arterial Calcification(BAC)is a mammographic decision dissimilar to cancer and commonly observed in elderly women.Thus identifying BAC could provide an expense,and be inaccurate.Recently Deep Learning(DL)methods have been introduced for automatic BAC detection and quantification with increased accuracy.Previously,classification with deep learning had reached higher efficiency,but designing the structure of DL proved to be an extremely challenging task due to overfitting models.It also is not able to capture the patterns and irregularities presented in the images.To solve the overfitting problem,an optimal feature set has been formed by Enhanced Wolf Pack Algorithm(EWPA),and their irregularities are identified by Dense-kUNet segmentation.In this paper,Dense-kUNet for segmentation and optimal feature has been introduced for classification(severe,mild,light)that integrates DenseUNet and kU-Net.Longer bound links exist among adjacent modules,allowing relatively rough data to be sent to the following component and assisting the system in finding higher qualities.The major contribution of the work is to design the best features selected by Enhanced Wolf Pack Algorithm(EWPA),and Modified Support Vector Machine(MSVM)based learning for classification.k-Dense-UNet is introduced which combines the procedure of Dense-UNet and kU-Net for image segmentation.Longer bound associations occur among nearby sections,allowing relatively granular data to be sent to the next subsystem and benefiting the system in recognizing smaller characteristics.The proposed techniques and the performance are tested using several types of analysis techniques 826 filled digitized mammography.The proposed method achieved the highest precision,recall,F-measure,and accuracy of 84.4333%,84.5333%,84.4833%,and 86.8667%when compared to other methods on the Digital Database for Screening Mammography(DDSM).

Demagnetization Analysis and Velocity Tracking Control of In-wheel Motor

The error caused by irreversible demagnetization damages the accurate velocity tracking of an in-wheel motor in a mobile robot.A current feedforward vector control system based on ESO is proposed to compensate it for the demagnetization motor.A demagnetization mathematical model is established to describe a permanent magnet synchronous motor,which took the change of permanent magnet flux linkage parameters as a factor to count the demagnetization error in velocity tracking.The uncertain disturbance estimation model of the control system is built based on ESO,which eliminates the system error by the feedforward current compensation.It is compared with the vector control method in terms of control accuracy.The simulation results show that the current feedforward vector control method based on ESO reduces the velocity tracking error greatly in conditions of motor demagnetization less than 30%.It is effective to improve the operation accuracy of the mobile robot.

Vector Dominance with Threshold Searchable Encryption (VDTSE) for the Internet of Things

The Internet of Medical Things(IoMT)is an application of the Internet of Things(IoT)in the medical field.It is a cutting-edge technique that connects medical sensors and their applications to healthcare systems,which is essential in smart healthcare.However,Personal Health Records(PHRs)are normally kept in public cloud servers controlled by IoMT service providers,so privacy and security incidents may be frequent.Fortunately,Searchable Encryption(SE),which can be used to execute queries on encrypted data,can address the issue above.Nevertheless,most existing SE schemes cannot solve the vector dominance threshold problem.In response to this,we present a SE scheme called Vector Dominance with Threshold Searchable Encryption(VDTSE)in this study.We use a Lagrangian polynomial technique and convert the vector dominance threshold problem into a constraint that the number of two equal-length vectors’corresponding bits excluding wildcards is not less than a threshold t.Then,we solve the problem using the proposed technique modified in Hidden Vector Encryption(HVE).This technique makes the trapdoor size linear to the number of attributes and thus much smaller than that of other similar SE schemes.A rigorous experimental analysis of a specific application for privacy-preserving diabetes demonstrates the feasibility of the proposed VDTSE scheme.

Resting-state functional magnetic resonance imaging and support vector machines for the diagnosis of major depressive disorder in adolescents

BACKGROUND Research has found that the amygdala plays a significant role in underlying pathology of major depressive disorder(MDD).However,few studies have explored machine learning-assisted diagnostic biomarkers based on amygdala functional connectivity(FC).AIM To investigate the analysis of neuroimaging biomarkers as a streamlined approach for the diagnosis of MDD in adolescents.METHODS Forty-four adolescents diagnosed with MDD and 43 healthy controls were enrolled in the study.Using resting-state functional magnetic resonance imaging,the FC was compared between the adolescents with MDD and the healthy controls,with the bilateral amygdala serving as the seed point,followed by statistical analysis of the results.The support vector machine(SVM)method was then applied to classify functional connections in various brain regions and to evaluate the neurophysiological characteristics associated with MDD.RESULTS Compared to the controls and using the bilateral amygdala as the region of interest,patients with MDD showed significantly lower FC values in the left inferior temporal gyrus,bilateral calcarine,right lingual gyrus,and left superior occipital gyrus.However,there was an increase in the FC value in Vermis-10.The SVM analysis revealed that the reduction in the FC value in the right lingual gyrus could effectively differentiate patients with MDD from healthy controls,achieving a diagnostic accuracy of 83.91%,sensitivity of 79.55%,specificity of 88.37%,and an area under the curve of 67.65%.CONCLUSION The results showed that an abnormal FC value in the right lingual gyrus was effective as a neuroimaging biomarker to distinguish patients with MDD from healthy controls.

The Aharonov-Bohm Effect: An Exploration of Quantum Interference and Electromagnetic Potentials

The AB(Aharonov-Bohm)effect is a pivotal quantum mechanical phenomenon that illustrates the fundamental role of the electromagnetic vector potential A in determining the phase of a charged particle’s wave function,even in regions where the magnetic field B is zero.This effect demonstrates that quantum particles are influenced not only by the fields directly present but also by the potentials associated with those fields.In the AB effect,an electron beam is split into two paths,with one path encircling a solenoid and the other bypassing it.Despite the absence of a magnetic field in the regions traversed by the beams,the vector potential A associated with the magnetic flux Φ through the solenoid induces a phase shift in the electron’s wave function.This phase shift,quantified by △φ=qΦ/hc,manifests as a change in the interference pattern observed in the detection screen.The phenomenon underscores the principle of gauge invariance in QED(quantum electrodynamics),where physical observables remain invariant under local gauge transformations of the vector and scalar potentials.This reinforces the notion that the vector potential A has a profound impact on quantum systems,beyond its classical role.This article outlines the AB effect,including its theoretical framework,experimental observations,and implications.The focus on the role of the vector potential in quantum mechanics provides a comprehensive understanding of this important phenomenon.

Utilizing Iso-Value Field Curves in Lieu of Magnetic Field Lines Amid Infinite and Parallel Electrical Wires

Building on a new model proposed recently for calculating constant electro-magnetic field values, the present article explores the electro-magnetic field configuration generated by parallel electrical wires. This imposes a reevaluation of the drawing procedure for constructing field curves with a constant field values around multiple parallel electrical conducting wires. To achieve this, we employ methods akin to those used for creating contours on topographical maps, ensuring a consistent numerical field value along the entire length of the field curves. Subsequent calculations will be conducted for scenarios where wires are not parallel.

Magnetic Field Curves and Magnetic Equipotential Surfaces around Crossing Electrical Wires Replacing Classical Magnetic Field Lines

This article is based on a recent model specifically defining magnetic field values around electrical wires. With this model, calculations of field around parallel wires were obtained. Now, this model is extended with the new concept of magnetic equipotential surface to magnetic field curves around crossing wires. Cases of single, double, and triple wires are described. Subsequent article will be conducted for more general scenarios where wires are neither infinite nor parallel.

China’s Monetary Policy Impacts on Money and Stock Markets

This study investigated the impact of China’s monetary policy on both the money market and stock markets,assuming that non-policy variables would not respond contemporaneously to changes in policy variables.Monetary policy adjustments are swiftly observed in money markets and gradually extend to the stock market.The study examined the effects of monetary policy shocks using three primary instruments:interest rate policy,reserve requirement ratio,and open market operations.Monthly data from 2007 to 2013 were analyzed using vector error correction(VEC)models.The findings suggest a likely presence of long-lasting and stable relationships among monetary policy,the money market,and stock markets.This research holds practical implications for Chinese policymakers,particularly in managing the challenges associated with fluctuation risks linked to high foreign exchange reserves,aiming to achieve autonomy in monetary policy and formulate effective monetary strategies to stimulate economic growth.

Fully Distributed Learning for Deep Random Vector Functional-Link Networks

In the contemporary era, the proliferation of information technology has led to an unprecedented surge in data generation, with this data being dispersed across a multitude of mobile devices. Facing these situations and the training of deep learning model that needs great computing power support, the distributed algorithm that can carry out multi-party joint modeling has attracted everyone’s attention. The distributed training mode relieves the huge pressure of centralized model on computer computing power and communication. However, most distributed algorithms currently work in a master-slave mode, often including a central server for coordination, which to some extent will cause communication pressure, data leakage, privacy violations and other issues. To solve these problems, a decentralized fully distributed algorithm based on deep random weight neural network is proposed. The algorithm decomposes the original objective function into several sub-problems under consistency constraints, combines the decentralized average consensus (DAC) and alternating direction method of multipliers (ADMM), and achieves the goal of joint modeling and training through local calculation and communication of each node. Finally, we compare the proposed decentralized algorithm with several centralized deep neural networks with random weights, and experimental results demonstrate the effectiveness of the proposed algorithm.

Molecular and cellular changes in the post-traumatic spinal cord remodeling after autoinfusion of a genetically-enriched leucoconcentrate in a mini-pig model

Post-traumatic spinal cord remodeling includes both degenerating and regenerating processes,which affect the potency of the functional recovery after spinal cord injury(SCI).Gene therapy for spinal cord injury is proposed as a promising therapeutic strategy to induce positive changes in remodeling of the affected neural tissue.In our previous studies for delivering the therapeutic genes at the site of spinal cord injury,we developed a new approach using an autologous leucoconcentrate transduced ex vivo with chimeric adenoviruses(Ad5/35)carrying recombinant cDNA.In the present study,the efficacy of the intravenous infusion of an autologous genetically-enriched leucoconcentrate simultaneously producing recombinant vascular endothelial growth factor(VEGF),glial cell line-derived neurotrophic factor(GDNF),and neural cell adhesion molecule(NCAM)was evaluated with regard to the molecular and cellular changes in remodeling of the spinal cord tissue at the site of damage in a model of mini-pigs with moderate spinal cord injury.Experimental animals were randomly divided into two groups of 4 pigs each:the therapeutic(infused with the leucoconcentrate simultaneously transduced with a combination of the three chimeric adenoviral vectors Ad5/35‐VEGF165,Ad5/35‐GDNF,and Ad5/35‐NCAM1)and control groups(infused with intact leucoconcentrate).The morphometric and immunofluorescence analysis of the spinal cord regeneration in the rostral and caudal segments according to the epicenter of the injury in the treated animals compared to the control mini-pigs showed:(1)higher sparing of the grey matter and increased survivability of the spinal cord cells(lower number of Caspase-3-positive cells and decreased expression of Hsp27);(2)recovery of synaptophysin expression;(3)prevention of astrogliosis(lower area of glial fibrillary acidic protein-positive astrocytes and ionized calcium binding adaptor molecule 1-positive microglial cells);(4)higher growth rates of regeneratingβIII-tubulin-positive axons accompanied by a higher number of oligodendrocyte transcription factor 2-positive oligodendroglial cells in the lateral corticospinal tract region.These results revealed the efficacy of intravenous infusion of the autologous genetically-enriched leucoconcentrate producing recombinant VEGF,GDNF,and NCAM in the acute phase of spinal cord injury on the positive changes in the post-traumatic remodeling nervous tissue at the site of direct injury.Our data provide a solid platform for a new ex vivo gene therapy for spinal cord injury and will facilitate further translation of regenerative therapies in clinical neurology.

Whole genome SNPs among 8 chicken breeds enable identification of genetic signatures that underlie breed features

Many different chicken breeds are found around the world,their features vary among them,and they are valuable resources.Currently,there is a huge lack of knowledge of the genetic determinants responsible for phenotypic and biochemical properties of these breeds of chickens.Understanding the underlying genetic mechanisms that explain across-breed variation can help breeders develop improved chicken breeds.The whole-genomes of 140 chickens from 7 Shandong native breeds and 20 introduced recessive white chickens from China were re-sequenced.Comparative population genomics based on autosomal single nucleotide polymorphisms(SNPs)revealed geographically based clusters among the chickens.Through genome-wide scans for selective sweeps,we identified thyroid stimulating hormone receptor(TSHR,reproductive traits,circadian rhythm),erythrocyte membrane protein band 4.1 like 1(EPB41L1,body size),and alkylglycerol monooxygenase(AGMO,aggressive behavior),as major candidate breed-specific determining genes in chickens.In addition,we used a machine learning classification model to predict chicken breeds based on the SNPs significantly associated with recourse characteristics,and the prediction accuracy was 92%,which can effectively achieve the breed identification of Laiwu Black chickens.We provide the first comprehensive genomic data of the Shandong indigenous chickens.Our analyses revealed phylogeographic patterns among the Shandong indigenous chickens and candidate genes that potentially contribute to breed-specific traits of the chickens.In addition,we developed a machine learning-based prediction model using SNP data to identify chicken breeds.The genetic basis of indigenous chicken breeds revealed in this study is useful to better understand the mechanisms underlying the resource characteristics of chicken.

Characteristics of electromagnetic vector field generated from rock fracturing

Rock fracturing is often accompanied by electromagnetic phenomenon.As a vector field,in addition to the intensity that is widely concerned,the generated electromagnetic field also has obvious direction-ality.To this end,a set of electromagnetic antennas capable of simultaneous three-axis measurement is used to monitor the electromagnetic vector field generated from rock fracturing based on Brazilian tests.The signal amplitude on each axis can represent the magnitude of actual magnetic flux density component on the three axes.The intensity and directional characteristics of electromagnetic signals received at different positions are studied using vector synthesis.The directionality of electromagnetic radiation measured using a three-axis electromagnetic antenna shows that the direction of the magnetic flux intensity generated by rock fracturing tends to be parallel to the crack surface,and the measured signal intensity is greater in a direction closer to the crack surface.

A New Selective Neural Network Ensemble Method Based on Error Vectorization and Its Application in High-density Polyethylene (HDPE) Cascade Reaction Process

Chemical processes are complex, for which traditional neural network models usually can not lead to satisfactory accuracy. Selective neural network ensemble is an effective way to enhance the generalization accuracy of networks, but there are some problems, e.g., lacking of unified definition of diversity among component neural networks and difficult to improve the accuracy by selecting if the diversities of available networks are small. In this study, the output errors of networks are vectorized, the diversity of networks is defined based on the error vectors, and the size of ensemble is analyzed. Then an error vectorization based selective neural network ensemble (EVSNE) is proposed, in which the error vector of each network can offset that of the other networks by training the component networks orderly. Thus the component networks have large diversity. Experiments and comparisons over standard data sets and actual chemical process data set for production of high-density polyethylene demonstrate that EVSNE performs better in generalization ability.

Lung Cancer Detection Using Modified AlexNet Architecture and Support Vector Machine

Lung cancer is the most dangerous and death-causing disease indicated by the presence of pulmonary nodules in the lung.It is mostly caused by the instinctive growth of cells in the lung.Lung nodule detection has a significant role in detecting and screening lung cancer in Computed tomography(CT)scan images.Early detection plays an important role in the survival rate and treatment of lung cancer patients.Moreover,pulmonary nodule classification techniques based on the convolutional neural network can be used for the accurate and efficient detection of lung cancer.This work proposed an automatic nodule detection method in CT images based on modified AlexNet architecture and Support vector machine(SVM)algorithm namely LungNet-SVM.The proposed model consists of seven convolutional layers,three pooling layers,and two fully connected layers used to extract features.Support vector machine classifier is applied for the binary classification of nodules into benign andmalignant.The experimental analysis is performed by using the publicly available benchmark dataset Lung nodule analysis 2016(LUNA16).The proposed model has achieved 97.64%of accuracy,96.37%of sensitivity,and 99.08%of specificity.A comparative analysis has been carried out between the proposed LungNet-SVM model and existing stateof-the-art approaches for the classification of lung cancer.The experimental results indicate that the proposed LungNet-SVM model achieved remarkable performance on a LUNA16 dataset in terms of accuracy.