KEYWORDS: Data modeling, Performance modeling, Matrices, Feature extraction, Design and modelling, Proteins, Neural networks, Data processing, Data mining
Autoencoders, as a type of generative self-supervised learning, have received increasing attention in information processing and data mining in recent years. However, existing autoencoders usually generate graph data conforming to the feature distribution from only one aspect of reconstructing edge or node features, which allows the models to extract only a single level of information, limiting their application in real-world applications. In this paper, we propose DummyMAE, a generative self-supervised learning framework that synchronously generates edge and node features. In general, it losslessly converts vertex graphs into corresponding line graphs by introducing edge-to-vertex transformations. The vertex graph provides the model with information on node features, and the line graph provides the model with the ability to capture information on the graph structure, which complements each other. The task of simultaneously reconstructing edges and features is achieved in this way. The task of graph classification serves as a pivotal component within the realm of graph learning, we have conducted sufficient experiments on four widely used graph classification datasets, and the results show that DummyMAE outperforms the current state-of-the-art baselines for the graph classification task.
KEYWORDS: Tunable filters, Social networks, Data modeling, Performance modeling, Matrices, Linear filtering, Digital filtering, Detection theory, Neural networks, Data mining
Graph anomaly detection in graph data has received significant attention due to its practical significance in various vital applications such as network security, finance, and social networks. The current mainstream approach for attribute graph anomaly detection is based on contrastive learning using graph neural networks, which only consider homogeneous low-frequency signals. However, in attribute networks, normal and anomalous nodes exhibit different frequency patterns. This motivates the proposal of a graph anomaly detection framework based on multi-frequency reconstruction to capture the signal patterns of anomaly. Specifically, our method constructs multiple filters based on target nodes and utilizes two modules, namely, low-frequency reconstruction and contrastive learning, for anomaly detection. The generative low-frequency reconstruction module enables us to capture anomalies in the high-frequency attribute space, while the contrastive learning module leverages richer structural information from multiple subgraphs to capture anomalies in the structural and mixed spaces. We conducted extensive experiments on five publicly available datasets, demonstrating that our method significantly outperforms state-of-the-art approaches.
KEYWORDS: Performance modeling, Data modeling, Ablation, Lab on a chip, Head, Education and training, Semantics, Classification systems, Proteins, Lithium
Named entity recognition (NER) involves two main types: nested NER and flat NER. The span-based approach classifies entity types by head-tail pair span representations and can handle nested and flat entities uniformly. However, the span-based approach uses a single feature and ignores the relative position information between head-tail pairs, which affects the precision of entity recognition. Therefore, we propose a nested entity recognition model that combines rotary position embedding and biaffine attention mechanism (RoPE-BAM) to improve the model performance by adding relative position features to the span representations. Concretely, we first obtain the head sequence and tail sequence representations through two feedforward networks. Then, to incorporate the relative position features, rotary position embedding is applied to both head and tail sequences. Finally, we use a biaffine attention mechanism to capture the span representations while generating the relative position information in the span. Extensive experiments were conducted on five widely-used benchmark datasets to demonstrate the effectiveness of our proposed RoPE-BAM model.
Cervical cancer is one of the most common female malignant tumors in the world. In recent years, the incidence of cervical cancer has tended to be younger, which has attracted great attention from all countries in the world. Early and accurate diagnosis of cervical cancer is of great significance to patients. At present, the common diagnostic methods of cervical cancer in China include cytological screening and HPV detection, but these methods are generally greatly affected by doctors' subjective factors and cannot fully meet the domestic clinical needs, so a rapid and accurate diagnosis of cervical cancer is of great value for exploration and research. In this paper, serum infrared spectroscopy technology combined with machine learning was used to diagnose and classify cervical cancer patients. Firstly, the spectral data were preprocessed by smoothing and normalization, and principal component analysis (PCA) was used to reduce dimension. The obtained data were imported into Support Vector Machines with Particle Swarm Optimization (PSO-SVM), Random Forest (RF) and K-Nearest Neighbor (KNN) models for classification, and ten-fold cross-validation was used to verify the performance of the model. Finally, the established models are compared.
Cervical cancer is one of the major gynecological malignancies that seriously endanger women's health. Patients with early symptoms are not obvious and prone to metastasis and recurrence, leading to poor prognosis of patients with cervical cancer. At present, cytological screening and HPV detection are the main diagnostic methods of cervical cancer in China, but both of them are greatly influenced by doctors' subjective factors, with low specificity and high rate of missed diagnosis. Therefore, a rapid and effective diagnostic method is needed to be explored. In this paper, the serum samples of patients with cervical cancer were taken as the research object, and the experimental serum samples were analyzed by infrared spectroscopy, which provided a clinical basis for the identification and classification of patients with cervical cancer by infrared spectroscopy. In this study, infrared spectral signals of serum of patients with cervical cancer were collected, and spectral signals were analyzed and preprocessed. Partial least squares regression (PLS) was used to select spectral signal features. Then, an Xgboost ensemble learning model is established using GBtree, GBlinear and Dart as the base classifier, and the performance of the model is evaluated by using the ten-dot cross-validation. Finally, the established models are compared.
In recent years, water quality testing has become an increasingly important topic. Compared with some common water quality identification methods, this study proposes a new method for identifying water samples in UV-visible spectroscopy. In this study, the UV-visible spectra of water samples from two different regions of tianchi and shuimogou in Urumqi were measured, and the pattern recognition algorithm was used to identify the two types of water samples. The acquired UV-visible spectra of water samples were extracted from 80 original high-dimensional spectral data by Partial Least Squares Regression (PLS), and the extracted features were modeled and classified by Support Vector Machine (SVM) classifier. The parameters C and g are optimized by Grid Searching (GS). The classification accuracy of the tianchi water sample and the water mill ditch water sample was 100%. The results of this study illustrate the great potential for rapid detection of water samples using UV-visible spectroscopy in the future.
Arsenic (As) is a trace element exist in the environment, and it is one of the common poisonous elements in water, excessive intake of arsenic can cause great damage to human body. At present, mainly used laboratory detection methods of arsenic such as electrochemical method, ion chromatography, atomic absorption spectroscopy and so on, can detective arsenic, but these techniques have some problems such as low sensitivity, intractable operation and expensive. Based on the specific molecules of arsenic, we tested a new rapid detection method of arsenic solution, we prepared surface-enhanced Raman enhanced scattering substrate (SERS substrate) to complete the detection of arsenic solution. Through linear discriminant analysis, the result show that Raman spectrum has high specificity and sensitivity. The study indicated the feasibility of using SERS substrate to conduct Raman spectrum detection on arsenic, which was of great significance for the detection of arsenic in aqueous solution.
Silver ions cannot exist in excess in the human body. Conventional instrumental analysis methods such as atomic emission and atomic absorption are commonly used to detect Ag +, but the sensitivity is not satisfactory. Therefore, we developed a novel surface-enhanced Raman scattering (SERS) substrate with a single-layer porous silicon structure, and we completed the detection of Ag + in domestic water and food based on this substrate. The SERS substrate with porous silicon structure has high detection sensitivity. It is found that Ag + can be oxidized and deposited on porous silicon to change the Raman spectral properties. The results show that the Raman spectral intensity is linearly related to different content of silver ions, and the maximum linear correlation coefficient is 0.95123. The exploratory research results prove that the newly prepared SERS substrate with single-layer porous silicon is has great significance for the detection of water source and food safety.
KEYWORDS: Denoising, Raman spectroscopy, Smoothing, Signal to noise ratio, Optical filters, Interference (communication), Electronic filtering, Signal processing, Wavelets, Digital filtering
In the extraction of Raman spectra, the signal will be affected by a variety of background noises, and then the effective information of Raman spectra is weakened or even submerged in noises, so the spectral analysis and denoising processing is very important. The traditional ensemble empirical mode decomposition (EEMD) method is to remove the noises by removing the IMF components that mainly contain the noises. However, it will lose some details of the Raman signal. For the problem of EEMD algorithm, the denoising method of smoothing filter combined with EEMD is proposed in this paper. First, EEMD is used to decompose the Raman noise signal into several IMF components. Then, the components mainly containing noises are selected using the self-correlation function, and the smoothing filter is used to remove the noises of the components. Finally, the sum of the denoised components is added with the remaining components to obtain the final denoised signal. The experimental results show that compared with the traditional denoising algorithm, the signal-to-noise ratio (SNR), the root mean square error (RMSE) and the correlation coefficient are significantly improved by using the proposed smoothing filter combined with EEMD.
Porous silicon has many advantages, such as biodegradability, biocompatibility, tunable pore size and active covalent and non-covalent surface chemical properties. One-dimensional porous silicon photonic crystal microcavity structure has the characteristics of porous silicon and optical microcavity, it is compatible with existing silicon micromachining technology and can be embedded into the sensitive chip so as to realize the function of micro-nano detection devices and integration. At present, there are many biosensors based on existing porous silicon microcavity, through controlling the pore size of porous silicon microcavities, the biological target molecules penetrate into the porous silicon microcavity structure, leading to increases of refractive index of porous silicon layers. In the practical test, we found that the penetration of biological molecules in the microcavity is not uniform, it is difficult to enter into the deeper porous silicon layers, according to this, the paper will explore the distributional characteristics of different biological molecules in the microcavity, and the variation of the sensing efficiency under the circumstance of nonuniform increase in refractive index. This study will be helpful to the accurate design and theoretical development of high efficiency porous silicon microcavity biosensor.
Hydatid disease is a serious parasitic disease in many regions worldwide, especially in Xinjiang, China. Raman spectrum of the serum of patients with echinococcosis was selected as the research object in this paper. The Raman spectrum of blood samples from healthy people and patients with echinococcosis are measured, of which the spectrum characteristics are analyzed. The fuzzy neural network not only has the ability of fuzzy logic to deal with uncertain information, but also has the ability to store knowledge of neural network, so it is combined with the Raman spectrum on the disease diagnosis problem based on Raman spectrum. Firstly, principal component analysis (PCA) is used to extract the principal components of the Raman spectrum, reducing the network input and accelerating the prediction speed and accuracy of Network based on remaining the original data. Then, the information of the extracted principal component is used as the input of the neural network, the hidden layer of the network is the generation of rules and the inference process, and the output layer of the network is fuzzy classification output. Finally, a part of samples are randomly selected for the use of training network, then the trained network is used for predicting the rest of the samples, and the predicted results are compared with general BP neural network to illustrate the feasibility and advantages of fuzzy neural network. Success in this endeavor would be helpful for the research work of spectroscopic diagnosis of disease and it can be applied in practice in many other spectral analysis technique fields.
Various porous silicon-based photonic device structures has attracted more attention for use as biochemical optical
sensors. In this study, we have designed and characterized porous silicon-based two-dimensional photonic crystal
waveguide structure as an optical biosensor. Field intensity distribution of two-dimensional photonic crystal waveguide
was simulated using COMSOL Multiphysics. When the refractive index changes, the field strength changes greatly. This
study lays the theoretical foundation for further work.
An increased level of alpha-fetoprotein ( AFP) in the blood may be a sign of liver cancer. Porous silicon based optical
microcavities structure is prepared as a label-free immunosensor platform for detecting AFP. After the antigen-antibody
reaction, it is monitored that the red shift of the reflection spectrum of the immunosensor increases
Agriculture and animal husbandry area, such as Xinjiang, has high rates of hydatid disease. Protein P38 of Echinococcus granulosus has practical value in diagnosis of hydatid disease, and it may be used as a diagnostic marker and a prognostic index. In recent years, the development of biosensors based on porous silicon has been developed rapidly. In this experiment, the protein P38 detection based on fluorescence changes of porous silicon following protein P38 molecule adsorption. The results of the tests indicated that, with the increase of antigen concentration, the fluorescence decrease of porous silicon is also increasing. It is provided the foundation for the basic research of the molecular mechanism of P38, and diagnosis and treatment of cystic echinococcosis.
Porous silicon suitable for optical detection as a biosensor platform is fabricated. The morphology, structure and Raman properties of porous silicon have been studied and protein P38 of Echinococcus granulosus was determined by the porous silicon Raman intensity changes following protein P38 of Echinococcus granulosus molecule adsportion. The results of the tests indicated that, when antigen is added into the porous silicon, the Fourier transform Raman intensity decrease of porous silicon is also increasing.
A TiO2/PS composite system is prepared by chemical vapor deposition which is a common technique in preparation of nano-materials. We report the measurements of the nonlinear refractive index of the TiO2/PS composite system as measured by the reflection Z-scan technique. The large magnitude of the third-order nonlinear coefficients of the TiO2/PS composite system shows that it is a promising candidate for further material development and possible photonic device applications.
Infrared spectroscopy has been widely used, but which often contains a lot of noise, so the spectral characteristic of the sample is seriously affected. Therefore the de-noising is very important in the spectrum analysis and processing. In the study of infrared spectroscopy, the least mean square (LMS) adaptive filter was applied in the field firstly. LMS adaptive filter algorithm can reserve the detail and envelope of the effective signal when the method was applied to infrared spectroscopy of breast cancer which signal-to-noise ratio (SNR) is lower than 10 dB, contrast and analysis the result with result of wavelet transform and ensemble empirical mode decomposition (EEMD). The three evaluation standards (SNR, root mean square error (RMSE) and the correlation coefficient (ρ)) fully proved de-noising advantages of LMS adaptive filter in infrared spectroscopy of breast cancer.
B ultrasound as a kind of ultrasonic imaging, which has become the indispensable diagnosis method in clinical medicine. However, the presence of speckle noise in ultrasound image greatly reduces the image quality and interferes with the accuracy of the diagnosis. Therefore, how to construct a method which can eliminate the speckle noise effectively, and at the same time keep the image details effectively is the research target of the current ultrasonic image de-noising. This paper is intended to remove the inherent speckle noise of B ultrasound image. The novel algorithm proposed is based on both wavelet transformation of B ultrasound images and data fusion of B ultrasound images, with a smaller mean squared error (MSE) and greater signal to noise ratio (SNR) compared with other algorithms. The results of this study can effectively remove speckle noise from B ultrasound images, and can well preserved the details and edge information which will produce better visual effects.
We have designed a novel evanescent field fiber optic biosensors with porous silicon dioxide cladding. The pore size of porous silicon dioxide cladding is about 100 nm in diameter. Biological molecules were immobilized to the porous silicon dioxide cladding used APTES and glutaraldehyde. Refractive index of cladding used Bruggemann's effective medium theory. We carried out simulations of changing in light intensity in optical fiber before and after chemical coupling of biomolecules. This novel optical fiber evanescent wave biosensor has a great potential in clinical chemistry for rapid and convenient determination of biological molecule.
Detection of protein kinases P38 of Echinococcus granulosus and its homologous antibody have great value for early diagnosis and treatment of hydatidosis hydatid disease. In this experiment, n-type mesoporous silicon microcavities have been successfully fabricated without KOH etching or oxidants treatment that reported in other literature. We observed the changes of the reflectivity spectrum before and after the antigen-antibody reaction by n-type mesoporous silicon microcavities. The binding of protein kinases P38 and its homologous antibody causes red shifts in the reflection spectrum of the sensor, and the red shift was proportional to the protein kinases P38 concentration with linear relationship.
Porous silicon material and device has attracted more attention for use as biochemical optical sensors. In this paper, A novel porous silicon-based multilayer dielectric-grating structures by adding high-reflectivity porous silicon stacks between the substrate and grating was fabricated, and the porous silicon grating height was set to be about 200 nm, the grating period was 4 μm, the air filling factor was 50%. A new better method of preparing this porous silicon-based multilayer dielectric-grating structures have also been employed.
We fabricated a one-dimensional nanoporous silicon photonic crystal on a silicon insulator substrate by a cost-effective electrochemical method as an optical biosensor for the detection of DNA hybridization. In the first step, a transfer matrix method was used to calculate the corresponding reflectivity spectrum for the design of nanoporous silicon photonic crystals. Then silicon-on-insulator-based photonic crystals were prepared by a novel simple electrochemical etching. Genes were hybridized inside the porous silicon (PS) pores by aminopropyltriethoxysilane and glutaraldehyde and detected through frequency resolved reflectance measurements. A detection sensitivity of 17.445 nm/μM is demonstrated with good specific detection. The linear response range covers a concentration range of antifreeze protein gene from 0.625 to 10.000 μM. This high responsivity indicates that the silicon-on-insulator-based PS photonic crystal has significant potential for application in biological micro-electro-mechanical-systems technologies.
Highly active and sensitive surface-enhanced Raman scattering (SERS) substrates were prepared by n -type (1 to 10 Ω⋅cm in resistivity) porous silicon (PS) substrates of Ag nanoparticles. SERS studies were carried on these substrates with R6G as a test molecule with a λ ex =785 nm laser. We optimized the fabrication procedure, which is easy and rapid, for nanostructured silver particles on the surface of PS. The maximum of SERS enhancement for R6G is observed for PS with an anodization current density of 6 mA/cm 2 and an etching time of 8 min. The detection limit for R6G absorbed on Ag-coated PS (Ag-PS) is 10 nM and SERS spectra show that the Ag-PS substrate has high SERS activity. The larger pore diameter of this new Ag-PS substrate is expected and the size of the pore diameter is about 1.2 μm, which permits better biomolecule infiltration. This new Ag-PS substrate can be applied in SERS in biochemical and biomedical fields.
We present a fast, novel method for building porous silicon-based silicon-on-insulator photonic crystals in which a periodic modulation of the refractive index is built by alternating different electrochemical etching currents. The morphology and reflectance spectra of the photonic crystals, prepared by the proposed method, are investigated. The scanning electron micrograph and atomic force microscopy images show a very uniform structure and the porous silicon demonstrates an 829 nm wide photonic band gap.
We report the measurements of the nonlinear refractive index of a metal/porous silicon composite system as measured by the reflection Z-scan technique. The composite system is formed by using magnetron sputtering to deposit thin metallic films onto porous silicon anodized on p-type silicon. The experiment results indicate an enhancement over the nonlinear refractive index of the composite system, which suggests an opportunity to form new-type nonlinear-optical media consisting of porous silicon for nonlinear optical applications such as power limiting or optical switching.
We have designed and characterized a novel fractal Cantor multilayer porous silicon photonic crystal with a defect
embedded in its middle as an optical sensor for sensing of various chemical and biological species. Compared with the
common periodic structure one (such as Bragg) and some aperiodic structure (such as Thue-morse), it is more sensitive
because of the lower number of interfaces. This research lays the foundation for design all-silicon sensor for biochemical
sensing and can also be good applied in excellent filter.
Third order nonlinear properties of new composite materials obtained by embedding A new type π-conjugated poly
[2,1,3-benzoselenadiazole-(2,5-didodecyloxy-1,4-phenylene)ethynylene](PPE)in porous silicon are measured in 532nm.
The picoseconds measurements show a significant increase of nonlinear refractive index not only with respect to the
standard optical materials. The reason can be explained as follows, the Π-electron conjugation bond would be expected
to have a significant effect on the ground and excited state dipole moments and electronic transition energies of the
molecule and, consequently, could affect the third-order nonlinear optical property of the molecule. The result shows that
it is a promising candidate for further material development and possible photonic device applications.
Porous silicon has attracted a great deal of attention and research for biochemical sensing applications. In this study, we
report a novel porous silicon based resonant grating filters as an optical sensor platform. A narrow bandwidth in the
reflectance spectrum is shown of this porous silicon grating filters and this resonance dip shift obviously after little
infiltration. This research also played a potential role for the extensive applications in all-silicon biosensor.
We report the experimental demonstration of a novel label-free optical immunosensor based on porous silicon
microcavity for the detection of Hydroxysafflor yellow A (HYSA). HYSA antibodies were immobilized into the porous
silicon using standard amino-silane and glutaraldehyde chemistry. We monitor the shift of the resonance dip in the
reflectance spectrum when HYSA-BSA is attached to the porous silicon microcavity. The label-free immunosensor is
simple and exhibit excellent sensitivity for HYSA antibodies with a sensitivity of 0.91nm/ng.
Photoluminescence of Ar+ implanted porous silicon and porous structure of Ar+-implanted silicon (porous silicon by
preanodization ion implantation) at energy of middle-energy (30keV) are investigated to gain insight into the
photoluminescence properties and photoluminescence mechanism. The results show that the photoluminescence intensity
of Ar+ implanted porous silicon was reduced, which was attributed to the removal of surface oxygen and creation of
defects that act as nonradiative recombination; And whether samples were prepared by p-type or n-type silicon wafers,
the photoluminescence intensity of porous structure of Ar+-implanted silicon was enhanced that we attribute these to the
enhanced formation of porous silicon microstructure induced by ion implantation and oxygen-related defects were
increased.
We report on the design of porous silicon based polarization band-pass filters, which is not only have excellent optical properties with p-polarization transmittance and s-polarization reflectance in the NIR field, but also can be used for excellent biosensor and gas sensing applications.
ZnS/CdS were deposited by chemical vapor deposition (CVD) technique on porous silicon substrates formed by electrochemical anodization of n-type (100) silicon wafer. The optical properties of ZnS/CdS porous silicon composite materials are studied. The results showed that new luminescence characteristics such as strong and stable visible-light emissions with different colors were observed from the ZnS/CdS-PS nanocomposite materials at room temperature.
It was found that the porosity of porous silicon has a maximum value under certain illumination intensity in our experiment. According to the experimental result, the grating was fabricated from porous silicon by controlling illumination intensity. As the refractive index of porous silicon decreases with an increase of the porosity, so the index distributing of porous silicon can be controlled by illumination intensity. A holographic process allows obtaining a mask of light on top layer during fabricating the multilayer porous silicon optical waveguides. The interference of two coherent Ar+ laser beams produces at the sample surface bright parallel lines. The porosity is modulated in the plane. The effective deep of modulation is directly related to the penetration of the illuminating beam. We have developed an experimental setup that allows guide light at 1064nm incidents vertically into the grating in porous silicon optical waveguides. The diffractive efficiency of the first order diffraction light in TE and TM polarization are measured in our experiment respectively.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.