Homogenous coating of Li^(+)conductive Li_(5)AlO_(4)on single-crystalline nonstoichiometric Li_(1.04)Ni_(0.92)Al_(0.04)O_(2)for rechargeable lithium-ion batteries

Cobalt-free,nickel-rich LiNi_(1-x)Al_(x)O_(2)(x≤0.1)is an attractive cathode material because of high energy density and low cost but suffers from severe structural degradation and poor rate performance.In this study,we propose a molten salt-assisted synthesis in combination with a Li-refeeding induced aluminum segregation strategy to prepare Li_(5)AlO_(4)-coated single-crystalline slightly Li-rich Li_(1.04)Ni_(0.92)Al_(0.04)O_(2).The symbiotic formation of Li_(5)AlO_(4)from reaction between molten lithium hydroxide and doped aluminum in the bulk ensures a high lattice matching between the Ni-rich oxide and the homogenous conductive Li_(5)AlO_(4)that permits high Li^(+)conductivity.Benefiting from mitigated undesirable side reactions and phase evolution,the Li_(5)AlO_(4)-coated single-crystalline Li_(1.04)Ni_(0.92)Al_(0.04)O_(2)delivers a high specific capacity of220.2 mA h g^(-1)at 0.1 C and considerable rate capability(182.5 mA h g^(-1)at 10 C).Besides,superior capacity retention of 90.8%is obtained at 1/3 C after 100 cycles in a 498.1 mA h pouch full cell.Furthermore,the particulate morphology of Li_(1.04)Ni_(0.92)Al_(0.04)O_(2)remains intact after cycling at a cutoff voltage of 4.3 V,whereas slightly Li-deficient Li_(0.98)Ni_(0.97)Al_(0.05)O_(2)features intragranular cracks and irreversible lattice distortion.The results highlight the value of molten salt-assisted synthesis and Li-refeeding induced elemental segregation strategy to upgrade Ni-based layered oxide cathode materials for advanced Li-ion batteries.

ThyroidNet:A Deep Learning Network for Localization and Classification of Thyroid Nodules

Aim:This study aims to establish an artificial intelligence model,ThyroidNet,to diagnose thyroid nodules using deep learning techniques accurately.Methods:A novel method,ThyroidNet,is introduced and evaluated based on deep learning for the localization and classification of thyroid nodules.First,we propose the multitask TransUnet,which combines the TransUnet encoder and decoder with multitask learning.Second,we propose the DualLoss function,tailored to the thyroid nodule localization and classification tasks.It balances the learning of the localization and classification tasks to help improve the model’s generalization ability.Third,we introduce strategies for augmenting the data.Finally,we submit a novel deep learning model,ThyroidNet,to accurately detect thyroid nodules.Results:ThyroidNet was evaluated on private datasets and was comparable to other existing methods,including U-Net and TransUnet.Experimental results show that ThyroidNet outperformed these methods in localizing and classifying thyroid nodules.It achieved improved accuracy of 3.9%and 1.5%,respectively.Conclusion:ThyroidNet significantly improves the clinical diagnosis of thyroid nodules and supports medical image analysis tasks.Future research directions include optimization of the model structure,expansion of the dataset size,reduction of computational complexity and memory requirements,and exploration of additional applications of ThyroidNet in medical image analysis.

A Survey on Chinese Sign Language Recognition:From Traditional Methods to Artificial Intelligence

Research on Chinese Sign Language(CSL)provides convenience and support for individuals with hearing impairments to communicate and integrate into society.This article reviews the relevant literature on Chinese Sign Language Recognition(CSLR)in the past 20 years.Hidden Markov Models(HMM),Support Vector Machines(SVM),and Dynamic Time Warping(DTW)were found to be the most commonly employed technologies among traditional identificationmethods.Benefiting from the rapid development of computer vision and artificial intelligence technology,Convolutional Neural Networks(CNN),3D-CNN,YOLO,Capsule Network(CapsNet)and various deep neural networks have sprung up.Deep Neural Networks(DNNs)and their derived models are integral tomodern artificial intelligence recognitionmethods.In addition,technologies thatwerewidely used in the early days have also been integrated and applied to specific hybrid models and customized identification methods.Sign language data collection includes acquiring data from data gloves,data sensors(such as Kinect,LeapMotion,etc.),and high-definition photography.Meanwhile,facial expression recognition,complex background processing,and 3D sign language recognition have also attracted research interests among scholars.Due to the uniqueness and complexity of Chinese sign language,accuracy,robustness,real-time performance,and user independence are significant challenges for future sign language recognition research.Additionally,suitable datasets and evaluation criteria are also worth pursuing.

Efficient Ship:A Hybrid Deep Learning Framework for Ship Detection in the River

Optical image-based ship detection can ensure the safety of ships and promote the orderly management of ships in offshore waters.Current deep learning researches on optical image-based ship detection mainly focus on improving one-stage detectors for real-time ship detection but sacrifices the accuracy of detection.To solve this problem,we present a hybrid ship detection framework which is named EfficientShip in this paper.The core parts of the EfficientShip are DLA-backboned object location(DBOL)and CascadeRCNN-guided object classification(CROC).The DBOL is responsible for finding potential ship objects,and the CROC is used to categorize the potential ship objects.We also design a pixel-spatial-level data augmentation(PSDA)to reduce the risk of detection model overfitting.We compare the proposed EfficientShip with state-of-the-art(SOTA)literature on a ship detection dataset called Seaships.Experiments show our ship detection framework achieves a result of 99.63%(mAP)at 45 fps,which is much better than 8 SOTA approaches on detection accuracy and can also meet the requirements of real-time application scenarios.

Noise-tolerate and adaptive coefficient zeroing neural network for solving dynamic matrix square root

The solving of dynamic matrix square root(DMSR)problems is frequently encountered in many scientific and engineering fields.Although the original zeroing neural network is powerful for solving the DMSR,it cannot vanish the influence of the noise perturbations,and its constant-coefficient design scheme cannot accelerate the convergence speed.Therefore,a noise-tolerate and adaptive coefficient zeroing neural network(NTACZNN)is raised to enhance the robust noise immunity performance and accelerate the conver-gence speed simultaneously.Then,the global convergence and robustness of the pro-posed NTACZNN are theoretically analysed under an ideal environment and noise-perturbed circumstances.Furthermore,some illustrative simulation examples are designed and performed in order to substantiate the efficacy and advantage of the NTACZNN for the DMSR problem solution.Compared with some existing ZNNs,the proposed NTACZNN possesses advanced performance in terms of noise tolerance,solution accuracy,and convergence rate.

Impact of W alloying on microstructure, mechanical property and corrosion resistance of face-centered cubic high entropy alloys: A review

Face-centered cubic (f.c.c.) high entropy alloys (HEAs) are attracting more and more attention owing to their excellent strength and ductility synergy, irradiation resistance, etc. However, the yield strength of f.c.c. HEAs is generally low, significantly limiting their practical applications. Recently, the alloying of W has been evidenced to be able to remarkably improve the mechanical properties of f.c.c. HEAs and is becoming a hot topic in the community of HEAs. To date, when W is introduced, multiple strengthening mechanisms, including solid-solution strengthening, precipitation strengthening (μphase,σphase, and b.c.c. phase), and grain-refinement strengthening, have been discovered to be activated or enhanced. Apart from mechanical properties, the addition of W improves corrosion resistance as W helps to form a dense WO_(3) film on the alloy surface. Until now, despite the extensive studies in the literature, there is no available review paper focusing on the W doping of the f.c.c. HEAs. In that context, the effects of W doping on f.c.c. HEAs were reviewed in this work from three aspects, i.e., microstructure,mechanical property, and corrosion resistance. We expect this work can advance the application of the W alloying strategy in the f.c.c. HEAs.

A Survey on Artificial Intelligence in Posture Recognition

Over the years,the continuous development of new technology has promoted research in the field of posture recognition and also made the application field of posture recognition have been greatly expanded.The purpose of this paper is to introduce the latest methods of posture recognition and review the various techniques and algorithms of posture recognition in recent years,such as scale-invariant feature transform,histogram of oriented gradients,support vectormachine(SVM),Gaussian mixturemodel,dynamic time warping,hiddenMarkovmodel(HMM),lightweight network,convolutional neural network(CNN).We also investigate improved methods of CNN,such as stacked hourglass networks,multi-stage pose estimation networks,convolutional posemachines,and high-resolution nets.The general process and datasets of posture recognition are analyzed and summarized,and several improved CNNmethods and threemain recognition techniques are compared.In addition,the applications of advanced neural networks in posture recognition,such as transfer learning,ensemble learning,graph neural networks,and explainable deep neural networks,are introduced.It was found that CNN has achieved great success in posture recognition and is favored by researchers.Still,a more in-depth research is needed in feature extraction,information fusion,and other aspects.Among classification methods,HMM and SVM are the most widely used,and lightweight network gradually attracts the attention of researchers.In addition,due to the lack of 3Dbenchmark data sets,data generation is a critical research direction.

SNELM:SqueezeNet-Guided ELM for COVID-19 Recognition

(Aim)The COVID-19 has caused 6.26 million deaths and 522.06 million confirmed cases till 17/May/2022.Chest computed tomography is a precise way to help clinicians diagnose COVID-19 patients.(Method)Two datasets are chosen for this study.The multiple-way data augmentation,including speckle noise,random translation,scaling,salt-and-pepper noise,vertical shear,Gamma correction,rotation,Gaussian noise,and horizontal shear,is harnessed to increase the size of the training set.Then,the SqueezeNet(SN)with complex bypass is used to generate SN features.Finally,the extreme learning machine(ELM)is used to serve as the classifier due to its simplicity of usage,quick learning speed,and great generalization performances.The number of hidden neurons in ELM is set to 2000.Ten runs of 10-fold cross-validation are implemented to generate impartial results.(Result)For the 296-image dataset,our SNELM model attains a sensitivity of 96.35±1.50%,a specificity of 96.08±1.05%,a precision of 96.10±1.00%,and an accuracy of 96.22±0.94%.For the 640-image dataset,the SNELM attains a sensitivity of 96.00±1.25%,a specificity of 96.28±1.16%,a precision of 96.28±1.13%,and an accuracy of 96.14±0.96%.(Conclusion)The proposed SNELM model is successful in diagnosing COVID-19.The performances of our model are higher than seven state-of-the-art COVID-19 recognition models.

Grad-CAM:Understanding AI Models

Artificial intelligence(AI)[1,2]allows computers to think and behave like humans,so it is now becoming more and more influential in almost every field[3].Hence,users in businesses,industries,hospitals[4],etc.,need to understand how these AI models work[5]and the potential impact of using them.

Brain Functional Network Generation Using Distribution-Regularized Adversarial Graph Autoencoder with Transformer for Dementia Diagnosis

The topological connectivity information derived from the brain functional network can bring new insights for diagnosing and analyzing dementia disorders.The brain functional network is suitable to bridge the correlation between abnormal connectivities and dementia disorders.However,it is challenging to access considerable amounts of brain functional network data,which hinders the widespread application of data-driven models in dementia diagnosis.In this study,a novel distribution-regularized adversarial graph auto-Encoder(DAGAE)with transformer is proposed to generate new fake brain functional networks to augment the brain functional network dataset,improving the dementia diagnosis accuracy of data-driven models.Specifically,the label distribution is estimated to regularize the latent space learned by the graph encoder,which canmake the learning process stable and the learned representation robust.Also,the transformer generator is devised to map the node representations into node-to-node connections by exploring the long-term dependence of highly-correlated distant brain regions.The typical topological properties and discriminative features can be preserved entirely.Furthermore,the generated brain functional networks improve the prediction performance using different classifiers,which can be applied to analyze other cognitive diseases.Attempts on the Alzheimer’s Disease Neuroimaging Initiative(ADNI)dataset demonstrate that the proposed model can generate good brain functional networks.The classification results show adding generated data can achieve the best accuracy value of 85.33%,sensitivity value of 84.00%,specificity value of 86.67%.The proposed model also achieves superior performance compared with other related augmentedmodels.Overall,the proposedmodel effectively improves cognitive disease diagnosis by generating diverse brain functional networks.

Bio-Inspired Optimization in Engineering and Sciences

Bio-inspired optimization algorithms[1,2]are a set of optimization algorithms inspired by natural phenomena,such as evolutionary processes,social behaviours,and swarm intelligence[3].These algorithms attempt to simulate these processes to solve optimization problems[4,5].Classical bio-inspired algorithms include genetic algorithm,ant colony optimization,artificial bee colony,particle swarm optimization,firefly algorithm,Japanese tree frog algorithm,Harris hawks optimization[6],slime mould algorithm[7],grey wolf optimization,sparrow search algorithm,whale optimization algorithm,etc.Fig.1 shows the taxonomy of common bio-inspired optimization algorithms.There are some recent newly proposed bio-inspired algorithms,such as Siberian tiger optimization[8],jellyfish search algorithm[9],etc.

Deep Learning for COVID-19 Diagnosis via Chest Images

COVID-19 is a vastly infectious disease caused by the new coronavirus,officially recognized as severe acute respiratory syndrome coronavirus 2[1].This virus has multiplied fast worldwide,causing a global pandemic[2].It has caused 6.87 million death tolls until 20/March/2023.

SNSVM:SqueezeNet-Guided SVM for Breast Cancer Diagnosis

Breast cancer is a major public health concern that affects women worldwide.It is a leading cause of cancer-related deaths among women,and early detection is crucial for successful treatment.Unfortunately,breast cancer can often go undetected until it has reached advanced stages,making it more difficult to treat.Therefore,there is a pressing need for accurate and efficient diagnostic tools to detect breast cancer at an early stage.The proposed approach utilizes SqueezeNet with fire modules and complex bypass to extract informative features from mammography images.The extracted features are then utilized to train a support vector machine(SVM)for mammography image classification.The SqueezeNet-guided SVMmodel,known as SNSVM,achieved promising results,with an accuracy of 94.10% and a sensitivity of 94.30%.A 10-fold cross-validation was performed to ensure the robustness of the results,and the mean and standard deviation of various performance indicators were calculated across multiple runs.This model also outperforms state-of-the-art models in all performance indicators,indicating its superior performance.This demonstrates the effectiveness of the proposed approach for breast cancer diagnosis using mammography images.The superior performance of the proposed model across all indicators makes it a promising tool for early breast cancer diagnosis.This may have significant implications for reducing breast cancer mortality rates.

Weakly supervised machine learning

Supervised learning aims to build a function or model that seeks as many mappings as possible between the training data and outputs,where each training data will predict as a label to match its corresponding ground‐truth value.Although supervised learning has achieved great success in many tasks,sufficient data supervision for labels is not accessible in many domains because accurate data labelling is costly and laborious,particularly in medical image analysis.The cost of the dataset with ground‐truth labels is much higher than in other domains.Therefore,it is noteworthy to focus on weakly supervised learning for medical image analysis,as it is more applicable for practical applications.In this re-view,the authors give an overview of the latest process of weakly supervised learning in medical image analysis,including incomplete,inexact,and inaccurate supervision,and introduce the related works on different applications for medical image analysis.Related concepts are illustrated to help readers get an overview ranging from supervised to un-supervised learning within the scope of machine learning.Furthermore,the challenges and future works of weakly supervised learning in medical image analysis are discussed.

DeepCNN:Spectro-temporal feature representation for speech emotion recognition

Speech emotion recognition(SER)is an important research problem in human-computer interaction systems.The representation and extraction of features are significant challenges in SER systems.Despite the promising results of recent studies,they generally do not leverage progressive fusion techniques for effective feature representation and increasing receptive fields.To mitigate this problem,this article proposes DeepCNN,which is a fusion of spectral and temporal features of emotional speech by parallelising convolutional neural networks(CNNs)and a convolution layer-based transformer.Two parallel CNNs are applied to extract the spectral features(2D-CNN)and temporal features(1D-CNN)representations.A 2D-convolution layer-based transformer module extracts spectro-temporal features and concatenates them with features from parallel CNNs.The learnt low-level concatenated features are then applied to a deep framework of convolutional blocks,which retrieves high-level feature representation and subsequently categorises the emotional states using an attention gated recurrent unit and classification layer.This fusion technique results in a deeper hierarchical feature representation at a lower computational cost while simultaneously expanding the filter depth and reducing the feature map.The Berlin Database of Emotional Speech(EMO-BD)and Interactive Emotional Dyadic Motion Capture(IEMOCAP)datasets are used in experiments to recognise distinct speech emotions.With efficient spectral and temporal feature representation,the proposed SER model achieves 94.2%accuracy for different emotions on the EMO-BD and 81.1%accuracy on the IEMOCAP dataset respectively.The proposed SER system,DeepCNN,outperforms the baseline SER systems in terms of emotion recognition accuracy on the EMO-BD and IEMOCAP datasets.

ANC: Attention Network for COVID-19 Explainable Diagnosis Based on Convolutional Block Attention Module

Aim: To diagnose COVID-19 more efficiently and more correctly, this study proposed a novel attention network forCOVID-19 (ANC). Methods: Two datasets were used in this study. An 18-way data augmentation was proposed toavoid overfitting. Then, convolutional block attention module (CBAM) was integrated to our model, the structureof which is fine-tuned. Finally, Grad-CAM was used to provide an explainable diagnosis. Results: The accuracyof our ANC methods on two datasets are 96.32% ± 1.06%, and 96.00% ± 1.03%, respectively. Conclusions: Thisproposed ANC method is superior to 9 state-of-the-art approaches.

Enhancing Li NiO_(2) cathode materials by concentration-gradient yttrium modification for rechargeable lithium-ion batteries

Lithium nickel oxide(LiNiO_(2)) cathode materials are featured with high capacity and low cost for rechargeable lithium-ion batteries but suffer from severe interface and structure instability.Here we report that rationally designed LiNiO_(2) via concentration-gradient yttrium modification exhibits alleviative side reactions and improved electrochemical performance.The LiNiO_(2) cathode with LiYO_(2)-Y_(2) O_(3) coating layer delivers a discharge capacity of 225 mAh g^(-1) with a high initial Coulombic efficiency of 93.4%.These improvements can be attributed to the formation of in-situ modified hybrid LiYO_(2)-Y_(2 O3) coating layer,which suppresses phase transformation,electrolyte oxidation and salt dissociation due to the formation of protective cathode electrolyte interface.The results indicate promising application of concentration-gradient yttrium coating as a facile approach to stabilize nickel-rich cathode materials.

Improved wavelet hierarchical threshold filter method for optical coherence tomography image de-noising

According to the speckle feature in Optical coherence tomography(OCT),images with speckleindicate not only noise but also signals,an improved wavelet hierarchical threshold filter(IWHTF)method is proposed.At first,a modified hierarchical threshold-selected algorithm isused to prevent signals from being removed by asssing suitable thresholds for different noiselevels,Then,an improved wavelet threshold function based on two traditional threshold fumnc.tions is proposed to trade-ff betwen speckle removing and sharpness degradation.The de-noising results of an OCT finger skin image shows that the IWHTF method obtains betterobjective evaluation metrics and visual image quality improvement,Whenαa=0.2,β=5.0 andK=1.2,the improved method can achieve 9.58 dB improvement in signal-to-noise ratio,withsharpnesdegraded by 3.81%.

Syntheses,challenges and modifications of single-crystal cathodes for lithium-ion battery

Single-crystal cathodes(SCCs)are promising substitute materials for polycrystal cathodes(PCCs)in lithium-ion batteries(LIBs),because of their unique ordered structure,excellent cycling stability and high safety performance.Cathode materials with layered(LiCoO_(2),LiNi_xCo_yMnzO_(2),LiNi_xCo_yAl_(2)O_(2))and spinel structure(LiMn_(2)O_(4),LiNi_(0.5)Mn_(1.5)O_(4))show a relatively stable electrochemical performance,but still lack of sufficient attention in research field.In this review,we begin with the definition,structural features and electrochemical advantages of SCCs.Common SCCs synthesis methods and the thermodynamic growth mechanism of SCCs with oriented facet exposure are summarized in the following part.Then we introduce the problems and challenges of SCCs faced and the corresponding modification strategies.Finally,the industrialization progress of SCCs is brifly outlined.We intend to tease out the difficulties and advances of SCCs to provide insights for future development of high-performance SCCs for practical LIBs.

TIME-DOMAIN INTERPOLATION ON GRAPHICS PROCESSING UNIT

The signal processing speed of spectral domain optical coherence tomography(SD-OCT)has become a bottleneck in a lot of medical applications.Recently,a time-domain interpolation method was proposed.This method can get better signal-to-noise ratio(SNR)but much-reduced signal processing time in SD-OCT data processing as compared with the commonly used zeropadding interpolation method.Additionally,the resampled data can be obtained by a few data and coefficients in the cutoff window.Thus,a lot of interpolations can be performed simultaneously.So,this interpolation method is suitable for parallel computing.By using graphics processing unit(GPU)and the compute unified device architecture(CUDA)program model,time-domain interpolation can be accelerated significantly.The computing capability can be achieved more than 250,000 A-lines,200,000 A-lines,and 160,000 A-lines in a second for 2,048 pixel OCT when the cutoff length is L=11,L=21,and L=31,respectively.A frame SD-OCT data(400A-lines×2,048 pixel per line)is acquired and processed on GPU in real time.The results show that signal processing time of SD-OCT can befinished in 6.223 ms when the cutoff length L=21,which is much faster than that on central processing unit(CPU).Real-time signal processing of acquired data can be realized.