Optimised CNN Architectures for Handwritten Arabic Character Recognition

Handwritten character recognition is considered challenging compared with machine-printed characters due to the different human writing styles.Arabic is morphologically rich,and its characters have a high similarity.The Arabic language includes 28 characters.Each character has up to four shapes according to its location in the word(at the beginning,middle,end,and isolated).This paper proposed 12 CNN architectures for recognizing handwritten Arabic characters.The proposed architectures were derived from the popular CNN architectures,such as VGG,ResNet,and Inception,to make them applicable to recognizing character-size images.The experimental results on three well-known datasets showed that the proposed architectures significantly enhanced the recognition rate compared to the baseline models.The experiments showed that data augmentation improved the models’accuracies on all tested datasets.The proposed model outperformed most of the existing approaches.The best achieved results were 93.05%,98.30%,and 96.88%on the HIJJA,AHCD,and AIA9K datasets.

Three novel umami peptides derived from the alcohol extract of the Pacific oyster(Crassostrea gigas):identification,characterizations and interactions with T1R1/T1R3 taste receptors

Oyster(Crassostrea gigas),the main ingredient of oyster sauce,has a strong umami taste.In this study,three potential umami peptides,FLNQDEEAR(FR-9),FNKEE(FE-5),and EEFLK(EK-5),were identified and screened from the alcoholic extracts of the oyster using nano-HPLC-MS/MS analysis,i Umami-Scoring Card Method(i Umami-SCM)database and molecular docking(MD).Sensory evaluation and electronic tongue analysis were further used to confirm their tastes.The threshold of the three peptides ranged from 0.38 to 0.55 mg/m L.MD with umami receptors T1R1/T1R3 indicated that the electrostatic interaction and hydrogen bond interaction were the main forces involved.Besides,the Phe592 and Gln853 of T1R3 were the primary docking site for MD and played an important role in umami intensity.Peptides with two Glu residues at the terminus had stronger umami,especially at the C-terminus.These results contribute to the understanding of umami peptides in oysters and the interaction mechanism between umami peptides and umami receptors.

Effect of Co on Solidification Characteristics and Microstructural Transformation of Non-equilibrium Solidified Cu-Ni Alloys

Non-equilibrium solidification structures of Cu55Ni45 and Cu55Ni43Co2 alloys were prepared by the molten glass purification cycle superheating method.The variation of the recalescence phenomenon with the degree of undercooling in the rapid solidification process was investigated using an infrared thermometer.The addition of the Co element affected the evolution of the recalescence phenomenon in Cu-Ni alloys.The images of the solid-liquid interface migration during the rapid solidification of supercooled melts were captured by using a high-speed camera.The solidification rate of Cu-Ni alloys,with the addition of Co elements,was explored.Finally,the grain refinement structure with low supercooling was characterised using electron backscatter diffraction(EBSD).The effect of Co on the microstructural evolution during nonequilibrium solidification of Cu-Ni alloys under conditions of small supercooling is investigated by comparing the microstructures of Cu55Ni45 and Cu55Ni43Co2 alloys.The experimental results show that the addition of a small amount of Co weakens the recalescence behaviour of the Cu55Ni45 alloy and significantly reduces the thermal strain in the rapid solidification phase.In the rapid solidification phase,the thermal strain is greatly reduced,and there is a significant increase in the characteristic undercooling degree.Furthermore,the addition of Co and the reduction of Cu not only result in a lower solidification rate of the alloy,but also contribute to the homogenisation of the grain size.

Instance Segmentation of Characters Recognized in Palmyrene Aramaic Inscriptions

This study presents a single-class and multi-class instance segmentation approach applied to ancient Palmyrene inscriptions,employing two state-of-the-art deep learning algorithms,namely YOLOv8 and Roboflow 3.0.The goal is to contribute to the preservation and understanding of historical texts,showcasing the potential of modern deep learning methods in archaeological research.Our research culminates in several key findings and scientific contributions.We comprehensively compare the performance of YOLOv8 and Roboflow 3.0 in the context of Palmyrene character segmentation—this comparative analysis mainly focuses on the strengths and weaknesses of each algorithm in this context.We also created and annotated an extensive dataset of Palmyrene inscriptions,a crucial resource for further research in the field.The dataset serves for training and evaluating the segmentation models.We employ comparative evaluation metrics to quantitatively assess the segmentation results,ensuring the reliability and reproducibility of our findings and we present custom visualization tools for predicted segmentation masks.Our study advances the state of the art in semi-automatic reading of Palmyrene inscriptions and establishes a benchmark for future research.The availability of the Palmyrene dataset and the insights into algorithm performance contribute to the broader understanding of historical text analysis.

Preparation and characterization of pH-responsive metal-polyphenol structure coated nanoparticles

In this paper,tannic acid(TA)and Fe~(3+)were added to form a layer of metal-polyphenol network structure on the surface of the nanoparticles which were fabricated by zein and carbon quantum dots(CQDs)encapsulating phlorotannins(PTN).pH-Responsive nanoparticles were prepared successfully(zein-PTN-CQDs-Fe-~Ⅲ).Further,the formation of composite nanoparticles was confirmed by a series of characterization methods.The zeta-potential and Fourier transform infrared spectroscopy data proved that electrostatic interaction and hydrogen bonding are dominant forces to form nanoparticles.The encapsulation efficiency(EE)revealed that metal-polyphenol network structure could improve the EE of PTN.Thermogravimetric analysis and differential scanning calorimetry experiment indicated the thermal stability of zein-PTN-CQDs-Fe~Ⅲnanoparticles increased because of metal-polyphenol network structure.The pH-responsive nanoparticles greatly increased the release rate of active substances and achieved targeted release.

Machine learning in metal-ion battery research: Advancing material prediction, characterization, and status evaluation

Metal-ion batteries(MIBs),including alkali metal-ion(Li^(+),Na^(+),and K^(3)),multi-valent metal-ion(Zn^(2+),Mg^(2+),and Al^(3+)),metal-air,and metal-sulfur batteries,play an indispensable role in electrochemical energy storage.However,the performance of MIBs is significantly influenced by numerous variables,resulting in multi-dimensional and long-term challenges in the field of battery research and performance enhancement.Machine learning(ML),with its capability to solve intricate tasks and perform robust data processing,is now catalyzing a revolutionary transformation in the development of MIB materials and devices.In this review,we summarize the utilization of ML algorithms that have expedited research on MIBs over the past five years.We present an extensive overview of existing algorithms,elucidating their details,advantages,and limitations in various applications,which encompass electrode screening,material property prediction,electrolyte formulation design,electrode material characterization,manufacturing parameter optimization,and real-time battery status monitoring.Finally,we propose potential solutions and future directions for the application of ML in advancing MIB development.

Characterization and identification towards dynamic-based electrical modeling of lithium-ion batteries

Lithium-ion batteries are widely recognized as a crucial enabling technology for the advancement of electric vehicles and energy storage systems in the grid.The design of battery state estimation and control algorithms in battery management systems is usually based on battery models,which interpret crucial battery dynamics through the utilization of mathematical functions.Therefore,the investigation of battery dynamics with the purpose of battery system identification has garnered considerable attention in the realm of battery research.Characterization methods in terms of linear and nonlinear response of lithium-ion batteries have emerged as a prominent area of study in this field.This review has undertaken an analysis and discussion of characterization methods,with a particular focus on the motivation of battery system identification.Specifically,this work encompasses the incorporation of frequency domain nonlinear characterization methods and dynamics-based battery electrical models.The aim of this study is to establish a connection between the characterization and identification of battery systems for researchers and engineers specialized in the field of batteries,with the intention of promoting the advancement of efficient battery technology for real-world applications.

Roughness characterization and shearing dislocation failure for rock-backfill interface

Shearing dislocation is a common failure type for rock–backfill interfaces because of backfill sedimentation and rock strata movement in backfill mining goaf.This paper designed a test method for rock–backfill shearing dislocation.Using digital image techno-logy and three-dimensional(3D)laser morphology scanning techniques,a set of 3D models with rough joint surfaces was established.Further,the mechanical behavior of rock–backfill shearing dislocation was investigated using a direct shear test.The effects of interface roughness on the shear–displacement curve and failure characteristics of rock–backfill specimens were considered.The 3D fractal dimen-sion,profile line joint roughness coefficient(JRC),profile line two-dimensional fractal dimension,and the surface curvature of the frac-tures were obtained.The correlation characterization of surface roughness was then analyzed,and the shear strength could be measured and calculated using JRC.The results showed the following:there were three failure threshold value points in rock–backfill shearing dis-location:30%–50%displacement before the peak,70%–90%displacement before the peak,and 100%displacement before the peak to post-peak,which could be a sign for rock–backfill shearing dislocation failure.The surface JRC could be used to judge the rock–backfill shearing dislocation failure,including post-peak sliding,uniform variations,and gradient change,corresponding to rock–backfill disloca-tion failure on the field site.The research reveals the damage mechanism for rock–backfill complexes based on the free joint surface,fills the gap of existing shearing theoretical systems for isomerism complexes,and provides a theoretical basis for the prevention and control of possible disasters in backfill mining.

Characterization, preparation, and reuse of metallic powders for laser powder bed fusion: a review

Laser powder bed fusion(L-PBF) has attracted significant attention in both the industry and academic fields since its inception, providing unprecedented advantages to fabricate complex-shaped metallic components. The printing quality and performance of L-PBF alloys are infuenced by numerous variables consisting of feedstock powders, manufacturing process,and post-treatment. As the starting materials, metallic powders play a critical role in infuencing the fabrication cost, printing consistency, and properties. Given their deterministic roles, the present review aims to retrospect the recent progress on metallic powders for L-PBF including characterization, preparation, and reuse. The powder characterization mainly serves for printing consistency while powder preparation and reuse are introduced to reduce the fabrication costs.Various powder characterization and preparation methods are presented in the beginning by analyzing the measurement principles, advantages, and limitations. Subsequently, the effect of powder reuse on the powder characteristics and mechanical performance of L-PBF parts is analyzed, focusing on steels, nickel-based superalloys, titanium and titanium alloys, and aluminum alloys. The evolution trends of powders and L-PBF parts vary depending on specific alloy systems, which makes the proposal of a unified reuse protocol infeasible. Finally,perspectives are presented to cater to the increased applications of L-PBF technologies for future investigations. The present state-of-the-art work can pave the way for the broad industrial applications of L-PBF by enhancing printing consistency and reducing the total costs from the perspective of powders.

Physicochemical and Biochemical Characterization, Total Phenolic and Energy Value from Bulbs of Different Onion (Allium cepa L.) Varieties in Senegal

The purpose of this study is to investigate the physicochemical properties of some local varieties of onion (Allium cepa L.) and compare them with an imported variety, all collected in May 2021. Proteins, reducing sugars, lipids, and polyphenol content were estimated according to the AFNOR standardized methods. The determination of calcium, magnesium, iron, sodium, potassium and phosphorus was performed by atomic absorption spectrophotometer coupled with a CCD detector. The results highlighted an average acidity of 0.377% ± 0.002% lower than the value of the imported variety which is 0.520% ± 0.001%. Local varieties have a pH ranging from 6.35 ± 0.003 to 6.42 ± 0.004, while the variety has a pH of 6.36 ± 0.003. The ash and dry matter contents vary respectively from 4.788% ± 0.004% to 8.253% ± 0.003% and 7.945% ± 0.021% to 11.945% ± 0.007% for the local varieties. Moreover, the imported one has ash and dry matter contents of 5.175% ± 0.007% and 10.035% ± 0.021% respectively. The results show that the protein, reducing sugar and lipid contents in the local onion varieties vary respectively from 2.815 ± 0.000 to 15.634 ± 0.001 g·100 g-1;4.691 ± 0.001 to 12.596 ± 0.002 g·100 g-1 and 0.006 ± 0.001 to 0.050 ± 0.057 g·100 g-1. Furthermore, the imported variety has a protein, reducing sugar and lipid content of 5.649 ± 0.002;8.565 ± 0.002 g·100 g-1 and 0.011 ± 0.010 g·100 g-1 respectively. The maximum levels of total polyphenols are obtained in the imported variety, Bellani and Gandiol, respectively 9.973 ± 0.001, 4.535 ± 0.002, and 3.425 ± 0.006 mg EAG/g of dry matter. The local varieties have a significant calorific intake of between 35.451 ± 0.001 and 112.980 ± 0.003 kcal·100 g-1 compared to the imported one with an energy value of 56.953 ± 0.001 kcal·100 g-1 of dry matter. The bulbs of different onion varieties studied have a fairly high content of mineral elements. The potassium content of local varieties is between 502.16 ± 0.06 mg·100 g-1 and 582.77 ± 0.04 mg·100 g-1 while the imported variety has a content of 536.62 ± 1.30 mg·100 g-1. They note that the local varieties have a better calcium content (249.75 ± 0.07 to 434.20 ± 0.57 mg·100 g-1) and magnesium (142.15 ± 0.07 to 162.60 ± 0.42 mg·100 g-1) than the imported variety (229.58 ± 0.04 mg·100 g-1) except for the varieties White Grano (228.29 ± 0.01 mg·100 g-1) and Rouge Amposta (117.00 ± 0.42 mg·100 g-1) respectively. These results reveal that Gandiol, Dayo and Orient F1 are nutritionally found better due to their higher antioxidant property, proteins, carbohydrates, and reducing sugar and should be included in diets to supplement our daily allowance needed by the body.

Characterization of Wastewater in School Environments for an Ecological Treatment Solution: A Case Study of Ndiebene Gandiol 1 School

The study conducted at Ndiebene Gandiol 1 school in Senegal has unveiled serious environmental and public health challenges. The wastewater analysis revealed high levels of Biochemical Oxygen Demand (BOD5), Chemical Oxygen Demand (COD), and fecal coliforms, signaling potential risks to the well-being of students and staff. This situation mirrors a wider issue in rural educational settings, where inadequate sanitation persists. Intensive wastewater treatment options are known for their effectiveness against high pollutant loads but are resource-intensive in both energy and cost. Conversely, extensive treatment systems, while requiring more land, provide a sustainable alternative by harnessing natural processes for pollutant removal. The research suggests a hybrid treatment approach could serve the school’s needs, balancing the robust capabilities of intensive methods with the ecological benefits of extensive systems. Such a solution would need to be tailored to the specific environmental, financial, and logistical context of the school, based on comprehensive feasibility studies and stakeholder engagement. This study’s findings underscore the urgency of addressing sanitation in schools, as it is intrinsically linked to the health and academic success of students. Quick, effective, and long-term strategies are vital to secure a healthier and more prosperous future for the youth. With proper implementation, the school can transform its sanitation facilities, setting a precedent for rural educational institutions in Senegal and similar contexts globally.

Structural characterization of three acidic polysaccharides from Opuntia dillenii Haw.fruits and their protective effect against hydrogen peroxide-induced oxidative stress in Huh-7 cells

Three novel acidic polysaccharide fractions(OFPP-1,OFPP-2,OFPP-3)with different m olecular weights(803.7,555.1 and 414.5 k Da)were isolated from the peeled Opuntia dillenii Haw.fruits by alkali-extraction,graded alcohol precipitation and column chromatography.Structural analysis indicated that OFPPs were pectic polysaccharides consisting of rhamnose,arabinose and galactose residues.The backbone of OFPP-1 consisted of a repeating unit→6-α-D-Galp A-(1→2)-α-L-Rhap-(1→with T-α-D-Galp A-(1→6)-α-D-Galp A-(1→4)-α-D-Glcp-(1→,T-β-D-Xylp-(1→6)-α-D-Galp A-(1→4)-α-D-Glcp-(1→or T-α-D-Galp A-(1→3)-α-L-Araf-(1→as the side chains.The backbone of OFPP-2 consisted of a disaccharide repeating unit→2)-α-L-Rhap-(1→4)-β-D-Galp A-(1→with T-β-L-Araf-(1→as the branches substituted at the O-4 position of→2,4)-α-LRhap-(1→.Whereas the backbone of OFPP-3 was→2,4)-α-L-Rhap-(1→2)-α-L-Rhap-(1→3)-β-L-Araf-(1→or→2,4)-α-L-Rhap-(1→2)-α-L-Rhap-(1→4)-β-D-Galp A-(1→,which was branched at the O-4 position of→2,4)-α-L-Rhap-(1→.Moreover,these three polysaccharide fractions could protect Huh-7 cells against H2O2-induced oxidative stress to different extents by decreasing the MDA content and increasing the SOD,CAT,GSH-Px activities and the GSH level in the Huh-7 cells.These results suggest that OFPPs have the potential to be used as natural antioxidants.

HVSR analysis of pumice sands for sediment depth characterization:A case study for Guadalajara,Mexico

The horizontal to vertical spectral ratio(HVSR)methodology is used here to characterize pumice soils and to image the three-dimensional surface geometry of Guadalajara,Mexico.Similar to other Latin American cities,Guadalajara is exposed to high seismic risk,with the particularity of being the largest urban settlement in Latin America built on pumice soils.Methodology has not yet been tested to characterize subsoil depths in pumice sands.Due to the questionable use of traditional geotechnical tests for the analysis of pumice soils,HVSR provides an alternative for its characterization without altering its fragile and porous structure.In this work,resonance frequency(F0)and peak amplitude(A0)are used to constrain the depth of the major impedance contrast that represents the interface between bedrock and pumice soil.Results were compared with borehole depths and other available geotechnical and geophysical data and show good agreement.One of the profiles estimated on the riverbanks that cross the city,reveals different subsoil thickness that could have an impact on different site responses on riverine areas to an eventual earthquake.Government and academic efforts are combined in this work to characterize depth sediments,an important parameter that impacts the regulations for construction in the city.

Characterization of alpine meadow surface crack and its correlation with root-soil properties

Quantifying surface cracks in alpine meadows is a prerequisite and a key aspect in the study of grassland crack development.Crack characterization indices are crucial for the quantitative characterization of complex cracks,serving as vital factors in assessing the degree of cracking and the development morphology.So far,research on evaluating the degree of grassland degradation through crack characterization indices is rare,especially the quantitative analysis of the development of surface cracks in alpine meadows is relatively scarce.Therefore,based on the phenomenon of surface cracking during the degradation of alpine meadows in some regions of the Qinghai-Tibet Plateau,we selected the alpine meadow in the Huangcheng Mongolian Township,Menyuan Hui Autonomous County,Qinghai Province,China as the study area,used unmanned aerial vehicle(UAV)sensing technology to acquire low-altitude images of alpine meadow surface cracks at different degrees of degradation(light,medium,and heavy degradation),and analyzed the representative metrics characterizing the degree of crack development by interpreting the crack length,length density,branch angle,and burrow(rat hole)distribution density and combining them with in situ crack width and depth measurements.Finally,the correlations between the crack characterization indices and the soil and root parameters of sample plots at different degrees of degradation in the study area were analyzed using the grey relation analysis.The results revealed that with the increase of degradation,the physical and chemical properties of soil and the mechanical properties of root-soil composite changed significantly,the vegetation coverage reduced,and the root system aggregated in the surface layer of alpine meadow.As the degree of degradation increased,the fracture morphology developed from"linear"to"dendritic",and eventually to a complex and irregular"polygonal"pattern.The crack length,width,depth,and length density were identified as the crack characterization indices via analysis of variance.The results of grey relation analysis also revealed that the crack length,width,depth,and length density were all highly correlated with root length density,and as the degradation of alpine meadows intensified,the underground biomass increased dramatically,forming a dense layer of grass felt,which has a significant impact on the formation and expansion of cracks.

Characterization of physicochemical and immunogenic properties of allergenic proteins altered by food processing:a review

Food allergens are mainly naturally-occurring proteins with immunoglobulin E(IgE)-binding epitopes.Understanding the structural and immunogenic characteristics of allergenic proteins is essential in assessing whether and how food processing techniques reduce allergenicity.We here discuss the impacts of food processing technologies on the modification of physicochemical,structural,and immunogenic properties of allergenic proteins.Detection techniques for characterizing changes in these properties of food allergens are summarized.Food processing helps to reduce allergenicity by aggregating or denaturing proteins,which masks,modifies,or destroys antigenic epitopes,whereas,it cannot eliminate allergenicity completely,and sometimes even improves allergenicity by exposing new epitopes.Moreover,most food processing techniques have been tested on purified food allergens rather than food products due to potential interference of other food components.We provide guidance for further development of processing operations that can decrease the allergenicity of allergenic food proteins without negatively impacting the nutritional profile.

A Method for Detecting and Recognizing Yi Character Based on Deep Learning

Aiming at the challenges associated with the absence of a labeled dataset for Yi characters and the complexity of Yi character detection and recognition,we present a deep learning-based approach for Yi character detection and recognition.In the detection stage,an improved Differentiable Binarization Network(DBNet)framework is introduced to detect Yi characters,in which the Omni-dimensional Dynamic Convolution(ODConv)is combined with the ResNet-18 feature extraction module to obtain multi-dimensional complementary features,thereby improving the accuracy of Yi character detection.Then,the feature pyramid network fusion module is used to further extract Yi character image features,improving target recognition at different scales.Further,the previously generated feature map is passed through a head network to produce two maps:a probability map and an adaptive threshold map of the same size as the original map.These maps are then subjected to a differentiable binarization process,resulting in an approximate binarization map.This map helps to identify the boundaries of the text boxes.Finally,the text detection box is generated after the post-processing stage.In the recognition stage,an improved lightweight MobileNetV3 framework is used to recognize the detect character regions,where the original Squeeze-and-Excitation(SE)block is replaced by the efficient Shuffle Attention(SA)that integrates spatial and channel attention,improving the accuracy of Yi characters recognition.Meanwhile,the use of depth separable convolution and reversible residual structure can reduce the number of parameters and computation of the model,so that the model can better understand the contextual information and improve the accuracy of text recognition.The experimental results illustrate that the proposed method achieves good results in detecting and recognizing Yi characters,with detection and recognition accuracy rates of 97.5%and 96.8%,respectively.And also,we have compared the detection and recognition algorithms proposed in this paper with other typical algorithms.In these comparisons,the proposed model achieves better detection and recognition results with a certain reliability.

Audio2AB:Audio-driven collaborative generation of virtual character animation

Background Considerable research has been conducted in the areas of audio-driven virtual character gestures and facial animation with some degree of success.However,few methods exist for generating full-body animations,and the portability of virtual character gestures and facial animations has not received sufficient attention.Methods Therefore,we propose a deep-learning-based audio-to-animation-and-blendshape(Audio2AB)network that generates gesture animations and ARK it's 52 facial expression parameter blendshape weights based on audio,audio-corresponding text,emotion labels,and semantic relevance labels to generate parametric data for full-body animations.This parameterization method can be used to drive full-body animations of virtual characters and improve their portability.In the experiment,we first downsampled the gesture and facial data to achieve the same temporal resolution for the input,output,and facial data.The Audio2AB network then encoded the audio,audio-corresponding text,emotion labels,and semantic relevance labels,and then fused the text,emotion labels,and semantic relevance labels into the audio to obtain better audio features.Finally,we established links between the body,gestures,and facial decoders and generated the corresponding animation sequences through our proposed GAN-GF loss function.Results By using audio,audio-corresponding text,and emotional and semantic relevance labels as input,the trained Audio2AB network could generate gesture animation data containing blendshape weights.Therefore,different 3D virtual character animations could be created through parameterization.Conclusions The experimental results showed that the proposed method could generate significant gestures and facial animations.

A Novel 6G Scalable Blockchain Clustering-Based Computer Vision Character Detection for Mobile Images

6G is envisioned as the next generation of wireless communication technology,promising unprecedented data speeds,ultra-low Latency,and ubiquitous Connectivity.In tandem with these advancements,blockchain technology is leveraged to enhance computer vision applications’security,trustworthiness,and transparency.With the widespread use of mobile devices equipped with cameras,the ability to capture and recognize Chinese characters in natural scenes has become increasingly important.Blockchain can facilitate privacy-preserving mechanisms in applications where privacy is paramount,such as facial recognition or personal healthcare monitoring.Users can control their visual data and grant or revoke access as needed.Recognizing Chinese characters from images can provide convenience in various aspects of people’s lives.However,traditional Chinese character text recognition methods often need higher accuracy,leading to recognition failures or incorrect character identification.In contrast,computer vision technologies have significantly improved image recognition accuracy.This paper proposed a Secure end-to-end recognition system(SE2ERS)for Chinese characters in natural scenes based on convolutional neural networks(CNN)using 6G technology.The proposed SE2ERS model uses the Weighted Hyperbolic Curve Cryptograph(WHCC)of the secure data transmission in the 6G network with the blockchain model.The data transmission within the computer vision system,with a 6G gradient directional histogram(GDH),is employed for character estimation.With the deployment of WHCC and GDH in the constructed SE2ERS model,secure communication is achieved for the data transmission with the 6G network.The proposed SE2ERS compares the performance of traditional Chinese text recognition methods and data transmission environment with 6G communication.Experimental results demonstrate that SE2ERS achieves an average recognition accuracy of 88%for simple Chinese characters,compared to 81.2%with traditional methods.For complex Chinese characters,the average recognition accuracy improves to 84.4%with our system,compared to 72.8%with traditional methods.Additionally,deploying the WHCC model improves data security with the increased data encryption rate complexity of∼12&higher than the traditional techniques.

Genetic Analysis of Two Novel GPI Variants Disrupting H Bonds and Localization Characteristics of 55 Gene Variants Associated with Glucose-6-phosphate Isomerase Deficiency

Objective:Glucose-6-phosphate isomerase(GPI)deficiency is a rare hereditary nonspherocytic hemolytic anemia caused by GPI gene variants.This disorder exhibits wide heterogeneity in its clinical manifestations and molecular characteristics,often posing challenges for precise diagnoses using conventional methods.To this end,this study aimed to identify the novel variants responsible for GPI deficiency in a Chinese family.Methods:The clinical manifestations of the patient were summarized and analyzed for GPI deficiency phenotype diagnosis.Novel compound heterozygous variants of the GPI gene,c.174C>A(p.Asn58Lys)and c.1538G>T(p.Trp513Leu),were identified using whole-exome and Sanger sequencing.The AlphaFold program and Chimera software were used to analyze the effects of compound heterozygous variants on GPI structure.Results:By characterizing 53 GPI missense/nonsense variants from previous literature and two novel missense variants identified in this study,we found that most variants were located in exons 3,4,12,and 18,with a few localized in exons 8,9,and 14.This study identified novel compound heterozygous variants associated with GPI deficiency.These pathogenic variants disrupt hydrogen bonds formed by highly conserved GPI amino acids.Conclusion:Early family-based sequencing analyses,especially for patients with congenital anemia,can help increase diagnostic accuracy for GPI deficiency,improve child healthcare,and enable genetic counseling.

Development of in situ characterization techniques in molecular beam epitaxy

Ex situ characterization techniques in molecular beam epitaxy(MBE)have inherent limitations,such as being prone to sample contamination and unstable surfaces during sample transfer from the MBE chamber.In recent years,the need for improved accuracy and reliability in measurement has driven the increasing adoption of in situ characterization techniques.These techniques,such as reflection high-energy electron diffraction,scanning tunneling microscopy,and X-ray photoelectron spectroscopy,allow direct observation of film growth processes in real time without exposing the sample to air,hence offering insights into the growth mechanisms of epitaxial films with controlled properties.By combining multiple in situ characterization techniques with MBE,researchers can better understand film growth processes,realizing novel materials with customized properties and extensive applications.This review aims to overview the benefits and achievements of in situ characterization techniques in MBE and their applications for material science research.In addition,through further analysis of these techniques regarding their challenges and potential solutions,particularly highlighting the assistance of machine learning to correlate in situ characterization with other material information,we hope to provide a guideline for future efforts in the development of novel monitoring and control schemes for MBE growth processes with improved material properties.