Multimodal Deep Neural Networks for Digitized Document Classification

As digital technologies have advanced more rapidly,the number of paper documents recently converted into a digital format has exponentially increased.To respond to the urgent need to categorize the growing number of digitized documents,the classification of digitized documents in real time has been identified as the primary goal of our study.A paper classification is the first stage in automating document control and efficient knowledge discovery with no or little human involvement.Artificial intelligence methods such as Deep Learning are now combined with segmentation to study and interpret those traits,which were not conceivable ten years ago.Deep learning aids in comprehending input patterns so that object classes may be predicted.The segmentation process divides the input image into separate segments for a more thorough image study.This study proposes a deep learning-enabled framework for automated document classification,which can be implemented in higher education.To further this goal,a dataset was developed that includes seven categories:Diplomas,Personal documents,Journal of Accounting of higher education diplomas,Service letters,Orders,Production orders,and Student orders.Subsequently,a deep learning model based on Conv2D layers is proposed for the document classification process.In the final part of this research,the proposed model is evaluated and compared with other machine-learning techniques.The results demonstrate that the proposed deep learning model shows high results in document categorization overtaking the other machine learning models by reaching 94.84%,94.79%,94.62%,94.43%,94.07%in accuracy,precision,recall,F-score,and AUC-ROC,respectively.The achieved results prove that the proposed deep model is acceptable to use in practice as an assistant to an office worker.

Digitized Outcrop Geomodeling of Ramp Shoals and its Reservoirs： as an Example of Lower Triassic Feixianguan Formation of Eastern Sichuan Basin

Numerous hydrocarbon accumulations are found in ramp crest shoals worldwide and therefore this depositional setting has a high potential of being the hydrocarbon reservoir. In this paper, we combined digital outcrop geology and traditional geological mapping to build an outcrop-based geocellular model of the ramp-crest shoal complex of the Lower Triassic Feixianguan Formation in the Eastern Sichuan Basin. The outcrop model serves as an analogue for the subsurface reservoir of the Feixianguan Formation and illustrates the complexity of the lithofacies types, stratigraphic architecture, and reservoir heterogeneities at a scale below conventional subsurface data resolution. The studied ramp -crest shoal complex consists of thirteen types of lithofacies that can be grouped into three facies-groups corresponding to subtidal intraclastic shoal, sub- to inter-tidal oolitic shoal, and tidal flat depositional environments respectively. The stratigraphic architecture of the shoal complex shows mostly a strong progradation of the high energy facies associated with an overall decrease of accommodation space associated with relative sea level still stand. Two reservoir facies associations have been recognized. The first one consists of supratidai dolomudstone and upper intertidal partially dolomitized oolitic packstone with anhydrite or nodules. These facies were deposited above the high energy oolitic grainstones and occurs as thin-bedded and laterally continuous layers, characterized by high porosity and low permeability. The second reservoir facies association is composed of intertidal crystalline dolomite and subtidal intraclastic bindstone that occurs stratigraphically below the oolitic grainstones. These deposits consist of massive laterally discontinuously beds, and are characterized by high porosity and high permeability. Both types of reservoir facies tend to be stacked vertically and migrated laterally with the progradation of the shoal complex. The construction of the outcrop-based 3D geological model provide a description and quantification of the facies distribution within a robust stratigraphic framework and the style and amount of reservoir heterogeneities associated with a ramp-crest shoal complex reservoir such as the one found in Lower Triassic Feixianguan Formation and Cambrian Longwangmiao Formation in Sichuan Basin or other ramp-crest reservoir worldwide.

Resolution of Digitized Conjugate Tooth-Face Surface Based on the Theory of Digitized Conjugate Surfaces

According to the principle of meshing engagement and the theory of the digitized conjugate surface, this paper applies the software Conjugater-1.0 that is developed by ourselves to compute, respectively, the digitized conjugate curved surfaces of the straight-tooth surface and drum-tooth surface, which will establish the theoretical and technical foundation for digitized engaging analysis, simulation, and digitized manufacturing technology of the diversified gears.

Graph Digitizer在计量检定工作中的应用探讨

以"液相色谱仪"梯度误差计量检定数据处理为例,介绍应用GetData Graph Digitizer对目标图解析,获取原始数据,后运用Excel进行数据处理,得到梯度误差及判定结果。这不仅能提高计算结果的正确性,还能广泛运用到其他检定项目以及数据复核等质量监控工作中去。

Design and offline processing of an ultrafast digitizer based on internal cascaded DRS4

In this paper, we present an ultrafast digitizer utilizing the DRS4 switched capacitor array applicationspecific integrated circuit to achieve an ultrafast sampling speed of at most 5 GS/s. We cascaded all eight channels(sub-channels) of a single DRS4 chip for increased storage depth. The digitizer contains four DRS4 chips, a quadchannel analog-to-digital converter,a controlling fieldprogrammable gate array, a PXI interface, and an SFP+connector. Consequently, each DRS4 channel has a depth of 8192 points and a vertical resolution of 14 bits. The readout sequences should be broken into several segments and then reordered to obtain the correct sequential data sets, and this offline procedure varies in different readout modes. This paper describes the design and implementation of the hardware;in particular, the respective processing procedures are described in detail. Furthermore, the offset error is calibrated and corrected to improve the precision of the captured waveform in both single-channel and highresolution modes.

Theory of Digitized Conjugate Surface and Solution to Conjugate Surface

In order to meet the needs of designing and processing digitized surfaces, the method to spreading digitized surface has been proposed. The key technique is to solve the problem of digitized conjugate surface. In the paper, the digitized conjugate surface was theoretically investigated, and the solution of conjugate surface based on digitized surface was also studied. The digitized conjugate surface theory was then proposed, and applied to build the model of solving conjugate surface based on digitized surface. A corresponding algorithm was developed. This paper applies the software Conjugater-1.0 that is developed by ourselves to compute the digitized conjugate surfaces of the drum-tooth surface. This study provides theoretical and technical bases for analyzing engagement of digitized surface, simulation and numerical processing technique. Key words digitized conjugate surface - generating method - simulation CLC number O 186.1 - TH 122 Foundation item: Supported by the National Natural Science Foundation of China (50075031)Biography: Xiao Lai-yuan (1957-), male, Professor, Ph. D candidate, research direction: machanical design & theory, digital technology

A New Method to Digitize DNA Sequence

The global description uses composition, transition and distribution to describe an amino acid sequence and has been widely adopted in various fields. Here we integrate it with properties of nucleic acid and form a new method to digitize DNA sequence. Through this method we can use a 39-dimession vector to represent a DNA sequence. We use the exon-1 of β-Globin genes of eight species to verify this method and compare with other methods. A similar result with other method proves that this method is persuading. This method provides a new strategy to digitize DNA sequence and generates DNA sequence descriptor vector. It is different from other methods and this method only produces a 39-dimession vector and not depends on the length of DNA sequence.

Neural network approach for modification and fitting of digitized data in reverse engineering~

Reverse engineering in the manufacturing field is a process in which the digitized data are obtained from an existing object model or a part of it, and then the CAD model is reconstructed. This paper presents an RBF neural network approach to modify and fit the digitized data. The centers for the RBF are selected by using the orthogonal least squares learning algorithm. A mathematically known surface is used for generating a number of samples for training the networks. The trained networks then generated a number of new points which were compared with the calculating points from the equations. Moreover, a series of practice digitizing curves are used to test the approach. The results showed that this approach is effective in modifying and fitting digitized data and generating data points to reconstruct the surface model.

Getdata Graph Digitizer在物理教学中的应用——以自由落体运动为例

频闪照相技术能直观便捷地展现物体的运动特征,在物理教学中的使用越来越普遍.以自由落体运动为例,用数码相机高速拍摄运动物体的频闪照片,然后利用Getdata Graph Digitizer等图像分析软件能从这些频闪照片中迅速准确地提取运动过程的详细数据,以便于利用计算机软件对该运动特征进行定量分析,可以显著提高实验教学课堂效率.

A LINEAR APPROACH TO METRIC CIRCUMFERENCE COMPUTATIO FOR DIGITIZED CONVEX SHAPES

Metric measurement of digitized shapes is commonly applied in optical measuring systems.In this letter,three shape-related factors defined by the authors are used in the construction of amultiple linear regression model which is utilized to compute the circumference of the convex shapes inmillimeter unit.The model is first built upon the relationship hypothesis and then its adequacy ismathematically validated.The results of applying the developed model to the given number of convexshapes in a finite circumferential length range suggest that,in terms of percent error,the model pre-cision is to satisfaction by being within±4%.The test also shows the model’s robustness against theshape’s orientation anisotropy.

Digitizing the Undigitized: Converting Traditional Archaeological Records into Computerized, Three-Dimensional Site Reconstruction

Archaeological excavation involves disintegration, removal, and reassembly of the archaeological record;as such it is considered by many to be an unrepeatable, destructive activity. This perception has contributed to an advancement in archaeological practice, namely, the development of computerized recording systems that digitally record archaeological excavations spatially and volumetrically during fieldwork. This paper is concerned with those archaeological sites where digital field recording has not been done. These sites, recorded by traditional methods, should not be excluded from attempts to restructure the spatial, volumetric, and stratigraphic archaeological data. A thorough methodology for the conversion of traditional records into digitized data is presented, including the detailed procedures required for three-dimensional plotting of recorded data—both the excavated material and the drawn site maps and cross-sections. Finally, the use of these methods is demonstrated on a complex Early to Middle Pleistocene site, illustrating the benefits of digitization and three-dimensional reconstruction in resolving stratigraphic and spatial questions.

Mobile mini-fluorimeter for antibiotic aptasensing based on surface-plasmonic effect of burlike nanogolds enhanced by digitized imaging diagnosis

Antibiotic abuse now poses a grave threat to global ecology and bestirs public concerns about the residue issue in daily necessities.The traceability measurements along supply chain or logistic circulation have become increasingly essential given the labile nature of diverse synthetic residuals on site.In an attempt to answer this urgency,here a miniaturized fluorometric aptasensor prototype was contrived that catered to the point-of-care screening norm for two typical additives:chloramphenicol and enrofloxacin.The key target-indicating module worked in vitro based on the competitive binding-induced fluorescence recovery of fluorescein-labeled aptamers,which were photobleached beforehand in the format of double helix on burlike nanogold carriers.The“prickly”geometry of the latter not just enriched the capture probes at preferentially substrate-accessible spires;but also contributed to a tip-enhanced surface plasmon effect,sensitizing the signal-on during the duplex dissociation even at nanomolar threshold of the analytes.On the other hand,to encompass a full portable,a set of optical devices were mounted within a 3D-printed cartridge(adaptor)to converge the light beam and route it towards the detector,for which the smartphone camera came up in handy with a home-developed App for calibrating the emissive brightness.Enlightened by the high-dynamic-range compression,an imaging diagnostic algorithm was built in to grid and digitize each slide in the album for augmented detection performance.Thus,a novel bio-to-silico integration was invented that capable of in situ rapid reporting on the antibiotic presence with high sensitivity and selectivity.Further field practices in spiked milk on sales proved the precision and rudimentary feasibility of the well-assembled model of appliance,thus holding nice prospects in nonexpert(e.g.,family and local community)utilities for foodborne antibiotic identification.

Study of Tea Digitized Chromatographic Fingerprint Spectra Using Micellar Electrokinetic Chromatography

This paper described the principle of digitized chromatographic fingerprint spectrum and established digitized chromatographic fingerprint spectra of ten brands of Chinese famous tea by the micellar electrokinetic chromatography. This work was done using a 25 mmol·L -1 sodium dodecylsulfate in a 20 mmol·L -1 borate (pH 7 0) solution as running buffer, 20 kV applied potential and detection at 280 nm. The chromatographic fingerprint spectra were digitized by the relative retention value ( α ) and the relative area ( S r), and were analyzed to identify the tea samples. In the absence of the standard samples, the present method was easy setup and inexpensive, and provided the applicable information for the quality assessment of teas.

CSRWA:Covert and Severe Attacks Resistant Watermarking Algorithm

Watermarking is embedding visible or invisible data within media to verify its authenticity or protect copyright.The watermark is embedded in significant spatial or frequency features of the media to make it more resistant to intentional or unintentional modification.Some of these features are important perceptual features according to the human visual system(HVS),which means that the embedded watermark should be imperceptible in these features.Therefore,both the designers of watermarking algorithms and potential attackers must consider these perceptual features when carrying out their actions.The two roles will be considered in this paper when designing a robust watermarking algorithm against the most harmful attacks,like volumetric scaling,histogram equalization,and non-conventional watermarking attacks like the Denoising Convolution Neural Network(DnCNN),which must be considered in watermarking algorithm design due to its rising role in the state-of-the-art attacks.The DnCNN is initialized and trained using watermarked image samples created by our proposed Covert and Severe Attacks Resistant Watermarking Algorithm(CSRWA)to prove its robustness.For this algorithm to satisfy the robustness and imperceptibility tradeoff,implementing the Dither Modulation(DM)algorithm is boosted by utilizing the Just Noticeable Distortion(JND)principle to get an improved performance in this sense.Sensitivity,luminance,inter and intra-block contrast are used to adjust the JND values.

Enhancing Deepfake Detection:Proactive Forensics Techniques Using Digital Watermarking

With the rapid advancement of visual generative models such as Generative Adversarial Networks(GANs)and stable Diffusion,the creation of highly realistic Deepfake through automated forgery has significantly progressed.This paper examines the advancements inDeepfake detection and defense technologies,emphasizing the shift from passive detection methods to proactive digital watermarking techniques.Passive detection methods,which involve extracting features from images or videos to identify forgeries,encounter challenges such as poor performance against unknown manipulation techniques and susceptibility to counter-forensic tactics.In contrast,proactive digital watermarking techniques embed specificmarkers into images or videos,facilitating real-time detection and traceability,thereby providing a preemptive defense againstDeepfake content.We offer a comprehensive analysis of digitalwatermarking-based forensic techniques,discussing their advantages over passivemethods and highlighting four key benefits:real-time detection,embedded defense,resistance to tampering,and provision of legal evidence.Additionally,the paper identifies gaps in the literature concerning proactive forensic techniques and suggests future research directions,including cross-domain watermarking and adaptive watermarking strategies.By systematically classifying and comparing existing techniques,this review aims to contribute valuable insights for the development of more effective proactive defense strategies in Deepfake forensics.

Advancements and challenges in neuroimaging for the diagnosis of intracranial aneurysms:Addressing false positive diagnoses and emerging techniques

Despite advancements in neuroimaging,false positive diagnoses of intracranial aneurysms remain a significant concern.This article examines the causes,prevalence,and implications of such false-positive diagnoses.We discuss how conditions like arterial occlusion with vascular stump formation and infundibular widening can mimic aneurysms,particularly in the anterior circulation.The article compares various imaging modalities,including computer tomography angiogram,magnetic resonance imaging/angiography,and digital subtraction angiogram,highlighting their strengths and limitations.We emphasize the im-portance of accurate differentiation to avoid unnecessary surgical interventions.The potential of emerging technologies,such as high-resolution vessel wall ima-ging and deep neural networks for automated detection,is explored as promising avenues for improving diagnostic accuracy.This manuscript underscores the need for continued research and clinical vigilance in the diagnosis of intracranial aneurysms.

Neutron time-of-flight spectroscopy measurement using a waveform digitizer

The photoneutron source （PNS, phase 1）, an electron linear accelerator （linac）-based pulsed neutron facility that uses the time-of-flight （TOF） technique, was constructed for the acquisition of nuclear data from the Thorium Molten Salt Reactor （TMSR） at the Shanghai Institute of Applied Physics （SINAP）. The neutron detector signal used for TOF calculation, with information on the pulse arrival time, pulse shape, and pulse height, was recorded by using a waveform digitizer （WFD）. By using the pulse height and pulse-shape discrimination （PSD） analysis to identify neutrons and ＂y-rays, the neutron TOF spectrum was obtained by employing a simple electronic design, and a new WFD-based DAQ system was developed and tested in this commissioning experiment. The DAQ system developed is characterized by a very high efficiency with respect to millisecond neutron TOF spectroscopy.

Spatial Pattern and Influencing Factors of China’s Digital Trade Resilience under the Impact of Trade Frictions

In the era of the digital economy,digital trade has demonstrated strong vitality,becoming a crucial driving force for the highquality development of national and regional economies.However,understanding the resilience of digital trade in the face of external crises is an important topic.Taking the backdrop of Sino-US trade friction,this paper constructs a resilience index system for digital trade.It utilizes entropy method,kernel density estimation,and ArcGIS mapping to calculate and visually analyze the resilience of China’s digital trade from 2017 to 2021.Additionally,a Tobit model is constructed to explore the main influencing factors of digital trade resilience patterns.The research findings indicate:1)temporally,during the period of Sino-US trade friction,China’s digital trade resilience shows an overall upward trend,but there are regional differences in resilience levels across the country,with a severe polarization phenomenon.2)Spatially,high resilience is observed in the eastern and central regions of China,while the western and northeastern regions exhibit low resilience.3)From a dimensional perspective,the resistance of digital trade resilience displays a spatial distribution of high values in the east and low values in the west.The recovery force is aggregated along coastal areas,and the renewal force tends to aggregate along the eastern coastline.4)Factors such as economic scale,industrial structure,urbanization rate,government fiscal expenditure,and technological talents significantly promote the enhancement of digital trade resilience.This study reveals the dynamic characteristics and influencing factors of digital trade resilience in responding to external shocks,providing theoretical basis and policy suggestions for enhancing digital trade resilience,and promoting high-quality economic development in China.