Probabilistic Neural Network Method Research Articles

Abstract 5488: AI-enhanced spatial proteomics reveals B-cells & FoxP3+ cells interactions in HPV(+) oropharyngeal squamous cell carcinoma Progression

Abstract Background: Analyzing interactions and the microanatomical distribution of the tumor immune microenvironment (TIME) is essential for a comprehensive understanding of tumor progression. Imaging Mass Cytometry (IMC) is a high-dimensional tissue imaging system that enables the deeper and multiparametric in situ exploration of tumor microenvironments at a single-cell level. This study describes a pipeline for analyzing 39-plex IMC images of human HPV(+) oropharyngeal squamous cell carcinoma (OPSCC) tumor sections, elucidating immune cells' nature, functions, and interactions with tumor cells. The IMC data analysis provides valuable information for clinical studies that could be used for the identification of prognostic biomarkers and mechanisms of resistance to current immunotherapies. Methods: A retrospective study was conducted on (N=20) patients (10 progressors and 10 non-progressors) with HPV(+) OPSCC. The dataset comprises paired hematoxylin and eosin (H&E) images with IMC data from multiple Regions of Interest (ROIs) (N=82), enabling the in-situ profiling of 39 proteins in primary tumor tissue. Cell segmentation was followed by employing original images and their segmentation masks for cell phenotype identification using a probabilistic neural network method to spatially profile cancer cells, macrophages, NK-M cells, B-cells, and distinct T-cell populations. We identified protein expression at single-cell resolution and investigated the impact of multicellular spatial organization on the disease progression. The spatial neighborhood interaction score of tumor cells with various other cells was computed for all the ROIs across the two groups. Results: The markers showed varying expression levels of intensity distribution, likely due to differences in tissue sample composition. Specifically, CD3, CD4, CD8, CD19, CD20, and CD68 showed significantly higher intensity in non-progressors. Interestingly, FoxP3 also had a significantly higher intensity level in non-progressors. Cell phenotyping emphasized that non-progressors generally have increased levels of NK-M cell markers. Spatial analysis revealed a significant increase in interaction between CD3 cells and tumor cells in non-progressors (p-value=0.07, Mann-Whitney U test). Furthermore, a significant rise in the interaction between B-cells and FoxP3+ cells was observed in non-progressors (p-value<0.05, Mann-Whitney U test) suggesting a coordinated suppression of tumor growth. Conclusion: We developed a deep learning-based pipeline to analyze spatial relationships in the TIME of IMC data, demonstrating its clinical relevance in predicting disease progression. Our findings emphasize the importance of spatial relationships in the TME for response and suggest that proximity between either CD3+ T-cells to cancer cells or B-cells to FoxP3+ cells are candidate biomarkers. Citation Format: Sumanth Reddy Nakkireddy, Routman David, Kathleen Bartemes, Daniel Ma, Tae Hyun Hwang, Kathryn Van Abel, Chadi Nimeh Abdel-Halim. AI-enhanced spatial proteomics reveals B-cells & FoxP3+ cells interactions in HPV(+) oropharyngeal squamous cell carcinoma Progression [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 1 (Regular Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(6_Suppl):Abstract nr 5488.

Rapid identification of bacteria in water by multi-wavelength transmittance spectroscopy and the artificial neural network

Background: Multi-wavelength transmittance spectroscopy, in combination with the artificial neural network, has been a novel tool used to identify and classify microorganisms in recent years.Methods: In our work, the transmittance spectra in the region from 200 to 900 nm for four bacterial species of interest, Escherichia coli (E. coli), Staphylococcus aureus (S. aureus), Klebsiella pneumoniae (K.pneumoniae), and Salmonella typhimurium (S. typhi), were recorded using an ultraviolet–visible spectrophotometer. Considering too much redundant data on the full-wave band spectra, the characteristic wavelength variables were selected using the competitive adaptive reweighting sampling (CARS) algorithm. Spectra of the initial training set of these targeted microorganisms were used to create identification models representing the spectral variability of each species using four kinds of neural networks, namely, backpropagation (BP), radial basis function network (RBF), generalized regression neural network (GRNN), and probabilistic neural network (PNN).Results: The blinded isolate spectra of targeted species were identified using the four identification models given above. Compared to fullband modeling, after using CARS to screen the wavelength variables, four identification models are established for the 35 preferred characteristic wavelengths, and the prediction performance of the four models is notably improved. Among them, the CARS–PNN model is the best, and the identification rates of all targeted bacteria were achieved with 100% accuracy; the calculation time is just approximately 0.04 s.Discussion: The use of CARS can effectively remove useless information from the spectra, reduce model complexity, and enhance model prediction performance. Multi-wavelength transmission spectroscopy, combined with the CARS–PNN method, can provide a new method for the rapid detection of bacteria in water and could be readily extended for bacterial microbiological detection in blood and food.

The Evaluation of Groundwater Carrying Capacity in Xi’an

With the development of the economy and society, the importance of water as a necessary resource has increased. The resource attribute capacity of groundwater is limited, and excessive consumption depletes groundwater resources. The extremely serious and highly integrated groundwater problem necessitates the determination of the carrying capacity of groundwater resources. Based on the research findings of the carrying capacity of groundwater resources in China and other parts of the world, in this study, we proposed a new method to determine the carrying capacity of groundwater resources. We evaluated the carrying capacity of groundwater resources in Xi’an by using the probabilistic neural network method based on the ‘W–F extension law’. The results showed that the extremely low and low bearing capacity areas of groundwater in Xi’an are located in the southern plain area of Zhouzhi county and Huyi district, the southern suburbs of Xi’an city, and the loess platform source area. Due to the constant supply from the riverside water source, the groundwater associated with the Bahe river, Fengzaohe river, and Weibin water sources have a higher bearing capacity than other evaluation areas. Compared to the traditional evaluation method, in this study, we redefined the evaluation index standard of the carrying capacity of groundwater. The groundwater carrying capacity is only related to groundwater and its storage medium. The pressure index of groundwater carrying, such as the population, economy, and environment in the traditional evaluation method, is considered overexploitation. The interaction between surface water and groundwater can be distinguished, and the level limit of the evaluation index can be determined more accurately. Additionally, the probabilistic neural network method of the ‘W–F extension law’ does not allocate weights but calculates the clustering center. Thus, to avoid subjectivity, parameter weighting is not required. This method does not have regional restrictions and can reflect the non-linear relationship of the groundwater system. It can reflect the sensitivity and recovery ability of groundwater under the same future exploitation load. The evaluation results of this method were consistent with the evaluation results of the third groundwater resources survey in Xi’an in 2019, and the evaluation results were very similar to the actual situation. The accuracy and practicability of the evaluation method were verified.

Two-Dimensional RSSI-Based Indoor Localization Using Multiple Leaky Coaxial Cables With a Probabilistic Neural Network

Received signal strength indicator (RSSI) based indoor localization technology has its irreplaceable advantages for many location-aware applications. It is becoming obvious that in the development of fifth-generation (5G) and future communication technology, indoor localization technology will play a key role in location-based application scenarios including smart home systems, manufacturing automation, health care, and robotics. Compared with wireless coverage using conventional monopole antenna, leaky coaxial cables (LCX) can generate a uniform and stable wireless coverage over a long-narrow linear-cell or irregular environment such as railway station and underground shopping-mall, especially for some manufacturing factories with wireless zone areas from a large number of mental machines. This paper presents a localization method using multiple leaky coaxial cables (LCX) for an indoor multipath-rich environment. Different from conventional localization methods based on time of arrival (TOA) or time difference of arrival (TDOA), we consider improving the localization accuracy by machine learning RSSI from LCX. We will present a probabilistic neural network (PNN) approach by utilizing RSSI from LCX. The proposal is aimed at the two-dimensional (2-D) localization in a trajectory. In addition, we also compared the performance of the RSSI-based PNN (RSSI-PNN) method and conventional TDOA method over the same environment. The results show the RSSI-PNN method is promising and more than 90% of the localization errors in the RSSI-PNN method are within 1 m. Compared with the conventional TDOA method, the RSSI-PNN method has better localization performance especially in the middle area of the wireless coverage of LCXs in the indoor environment.

Application of Probabilistic Neural Networks Using High-Frequency Components’ Differential Current for Transformer Protection Schemes to Discriminate between External Faults and Internal Winding Faults in Power Transformers

Internal and external faults in a power transformer are discriminated in this paper using an algorithm based on a combination of a discrete wavelet transform (DWT) and a probabilistic neural network (PNN). DWT decomposes high-frequency fault components using the maximum coefficients of a ¼ cycle DWT as input patterns for the training process in a decision algorithm. A division algorithm between a zero sequence of post-fault differential current waveforms and the differential current coefficient in the ¼ cycle DWT is used to detect the maximum ratio and faults. The simulation system uses various study cases based on Thailand’s electricity transmission and distribution systems. The simulation results demonstrated that the PNN and BPNN are effectively implemented and perform fault detection with satisfactory accuracy. However, the PNN method is most suitable for detecting internal and external faults, and the maximum coefficient algorithm is the most effective in detecting the fault. This study will be useful in differential protection for power transformers.

Classification of traditional ulos of Batak Toba ssing probabilistic neural network

Ulos are commonly used in traditional Batak events. Ulos has many variations of pattern and the pattern almost similar to one another. Ulos also have different functions in its use. So, people are often wrong to call the name of Ulos because the similarity of its pattern. Therefore, the research is doing Ulos classification to increase the introduction of Batak Toba’s Ulos. In this research, the method used in classification is Probabilistic Neural Network method. The stages before classification are pre-processing, extraction feature using Gray Level Co-Occurrence Matrix, and then classified using Probabilistic Neural Network. The research uses 650 data to be used as training data and test data. After testing in this research, it was concluded that the Probabilistic Neural Network method had the ability to classify Ulos into five patterns namely Bintang Maratur, Ragi Hidup, Ragi Hotang, Mangiring and Sibolang. The result showed that the accuracy level is 80%.

Analysis of Factors Affecting Birth Weight Using Probabilistic Neural Network (PNN)

The hight mortality rate in newborns is caused by the fact that many babies are born with low birth weight. LBW is one of the factors of infant mortality in Indonesia. Mitra Medika hospital Bandar Kippa is one of the pregnant women who has a Low Birth Weight (LBW) baby. Prevention and treatment of pregnant women when they know that they will give birth to a baby withlow birth weight is very necessary, in order to minimize death during the bieth process. So it is hoped that the existence of a factor analysis that affects birth weight in babies cas help to identify the condition of the baby in pregnant women before the baby is born. In this study, Probabilistic Neural Network (PNN) method was used with 150 data and 7 features including maternal age, maternal weight, maternal height, maternal hemoglobin, gestational distance, parity and maternal education. To get the best accuracy results, training data and testing data are shared using K-Means Clustering. Furthermore, an analysis of the factors that affect BBL using the Probabilistic Neural Network method is carried out, therefore it can be obtained that the probability value affecting BBL is found in the mother’s weight of 0,856 with the highest output layer value in the normal class of 6,741 and an accuracy value of 88,67.

A comprehensive evaluation algorithm for project-level bridge maintenance decision-making

Abstract As an indispensable process to identify the optimal treatment measures for bridge maintenance, the importance of decision-making techniques have been recently highlighted. In this paper, a multi-parameters project level bridge maintenance decision-making algorithm, conducted by the Probabilistic Neural Networks method, radial basis function method, and the Principal Component Analysis method, is investigated. A detailed study on the parameter selection, data classification, and prediction are performed by using the former two methods for the time-series index data, in terms of technical condition, average daily traffic, and sufficiency rating. The sub-item weight among different parameter indexes is calculated by the Principal Component Analysis method and evaluated by correlation evaluation. Besides, an overall evaluation model for the project level bridge maintenance decision-making is also suggested, in which the comprehensive state index model, target-based reliability model, the degradation rate factor model, and the life-cycle cost estimate and determination of maintenance time, are conducted. The optimal process is chosen and applied in three bridges as a case study. Results demonstrate that the optimal algorithm is preferable for bridge maintenance decision-making.

A New Sensor Fault Diagnosis Method for Gas Leakage Monitoring Based on the Naive Bayes and Probabilistic Neural Network Method

A New Sensor Fault Diagnosis Method for Gas Leakage Monitoring Based on the Naive Bayes and Probabilistic Neural Network Method

A new assessment method for the vulnerability of confined water: W-F&PNN method

At present, groundwater vulnerability assessment is mainly aimed at phreatic aquifer, but in most areas, people draw water from confined aquifer, so it is necessary to assess the vulnerability of confined water. As the existing groundwater vulnerability assessment methods are greatly influenced by subjectivity. The purpose of this study is to put forward W-F&PNN method to avoid subjectivity. Weber-Fechner (W-F) law in psychophysics and Probabilistic Neural Network (PNN) are combined in this paper. W-F law is a theory for describing the people's response to a stimulus, which is used to calculate the cluster center and determine the assessment standard; Probabilistic Neural Network is a widely used algorithm for classification, which is used to classify the vulnerability of confined water. According to the influence factors of confined water, the assessment parameters D3A2C2 were determined, and the vulnerability of confined water in plain area of Xi'an city in 2005 was assessed by W-F&PNN method and were divided into four categories. The vulnerability of confined water gradually reduces from the flood plain, the first terrace, the second terrace, the third terrace, the alluvial fan, to the loess tableland. Results of vulnerability assessment were validated by nitrate concentration in 2016 over the area. The results show that the distribution of vulnerability region is mostly consistent with that of nitrate concentration region. The W-F&PNN method does not assign rate, but calculate the cluster center; and not need to assign weight for parameters, avoiding subjectivity, is a reliable method for groundwater vulnerability assessment and suitable for the area with insufficient data.

Comparison and Application of Neural Networks in LWD Lithology Identification

Aiming at the problems of poor fault tolerance, low automation and low interpretation accuracy of traditional lithology identification methods, through the application of neural network autonomous learning prediction analysis methods, different neural network prediction methods were compared to select a more suitable field practical method for the logging-while-drilling (LWD) system. It has been found that, with the same prediction method and the same logging curve, the more training samples obtained in the standard interval, the higher the accuracy. The result is obtained through comparison: the PNN probabilistic neural network method has better effect in production application, high recognition accuracy, and the shortest training recognition time. It can still maintain a high recognition level when acquiring fewer logging data information.

Fault diagnosis model of adaptive miniature circuit breaker based on fractal theory and probabilistic neural network

In recent years, with the development of national economy and the continuous improvement of the electrical level of daily life, various household appliances have gradually entered the field of life. Small circuit breakers have become the most widely used terminal protection equipment in electrical terminal distribution equipment of buildings, its performance plays a key role in the safety of circuits and electrical appliances. Although the size of the small circuit breaker is small, its working principle is not simple. Especially the short circuit breaking of miniature circuit breaker is very complicated. However, most of the faults of small circuit breakers are mechanical ones. The vibration signal of the circuit breaker during closing and closing contains its state characteristic information, the vibration signals of different faults will have certain differences. This paper studies the fault characteristics of small circuit breaker engine, combining fractal technology and probabilistic neural network, a research method of fault diagnosis model for small circuit breaker is proposed. In this paper, the characteristics of probabilistic neural network (PNN) are analyzed in detail, and the fault diagnosis method of probabilistic neural network is used to train samples and classify the faults accurately. Probabilistic neural network is an effective method for fault identification of small circuit breakers. A sample training library was established to facilitate fault classification. In order to classify and identify faults, a fault diagnosis method for miniature circuit breaker based on fractal technique and probabilistic neural network is adopted. The feasibility of this method is verified by data analysis.

Estimation of the Smoothing Parameter in Probabilistic Neural Network Using Evolutionary Algorithms

The probabilistic neural network (PNN) is an efficient approach that can compute nonlinear decision boundaries, widely used for classification. In this paper, the often used Gaussian distribution function is replaced by a new probability density function which provides a new variant of the PNN method. Most of the higher-dimensional data are statistically found to be not from the normal distribution, and hence, we have replaced it by the symmetric Laplace distribution. Further, the estimation of the smoothing parameter in the proposed PNN model is carried out with three different evolutionary algorithms, namely bat algorithm (BA), grey wolf optimizer (GWO), and whale optimization algorithm (WOA) with a novel fitness function. These different proposed PNN models with variable smoothing parameter estimation methods are tested on five different benchmark data sets. The performance of proposed three Laplace distribution-based variants of PNN incorporated with BA, GWO, and WOA are reported and compared with Gaussian-based variants of PNN and also other commonly used classifiers: the conventional PNN, extreme learning machine, and K-nearest neighbor in terms of measurement accuracy. The results demonstrate that the proposed approaches using evolutionary algorithms can provide as much as a ten percent increase in accuracy over the conventional PNN method.

A hybrid improved kernel LDA and PNN algorithm for efficient face recognition

This paper proposes a hybrid approach to face recognition based on a combination of probabilistic neural networks (PNNs) and improved kernel linear discriminant analysis (IKLDA). The dimensions of a sample’s features are first of all reduced, whilst retaining its relevant information, A PNN method is then adopted to solve face recognition problems. The proposed IKLDA+PNN method not only improves the overall computing efficiency, but also its precision. Face recognition experiments conducted on the ORL, YALE and AR datasets, which contain a wide variety of facial expressions, facial details, and degrees of scale, were used to validate the feasibility of the IKLDA+PNN method. The results showed that it can obtain an average recognition accuracy of 97.22%, 83.8% and 99.12%, across the three datasets, respectively.

Diagenesis and diagenetic facies distribution prediction of Chang 8 tight oil reservoir in Maling area, Ordos Basin, NW China

In this study, characteristics of Chang 8 tight sandstone pore structure and diagenesis are analyzed. A classification standard for sandstone diagenetic facies is established. Combined with the probabilistic neural network method, logging curves are used to predict the distribution of diagenetic facies. The following results are found: the Chang 8 reservoir has low porosity-low permeability characteristics, and the pore-throat structures have strong microscopic heterogeneity; both compaction and siliceous and carbonate cementation promote reservoir densification; chlorite cement lining, hydrocarbon emplacement, and the dissolution of feldspar and rock fragments have constructive effects on reservoir development; and two favorable diagenetic facies, a weakly compacted and chlorite-authigenic quartz cementation facies and an intensely compacted-dissolution facies, are developed in the middle of the thick sandstone and are a good match in their horizontal distribution with distributary channel sands. The Chang 81 member has a much larger area that is more favorable for the development of reservoir diagenetic facies than the Chang 82

Porosity Prediction Using Neural Network Based on Seismic Inversion and Seismic Attributes

It has done a study of porosity prediction by using neural network. The study uses 2D seismic data post-stack time migration (PSTM) and 2 well data at field “T”. The objective is determining distribution of porosity. Porosity in carbonate reservoir is actually heterogeneous, complex and random. To face the complexity the neural network method has been implemented. The neural network algorithm uses probabilistic neural network based on best seismic attributes. It has been selected by using multi-attribute method with has high correlation. The best attributes which have been selected are amplitude envelope, average frequency, amplitude weighted phase, integrated absolute amplitude, acoustic impedance, and dominant frequency. The attribute is used as input to probabilistic neural network method process. The result porosity prediction based on probabilistic neural network use non-linear equation obtained high correlation coefficient 0.86 and approach actual log. The result has a better correlation than using multi-attribute method with correlation 0.58. The value of distribution porosity is 0.05–0.3 and it indicates the heterogeneous porosity distribution generally from the bottom to up are decreasing value.

Parameter optimization criteria guided 3D point cloud classification

3D point cloud classification is one of the basic topics in multimedia analysis and understanding. By the construction of the discriminant model and efficient parameter optimization, point cloud classification can be achieved after the training. However, most parameter optimization methods do not guarantee the highest global classification accuracy with a high classification accuracy on smaller classes. In addition, geometric features of the point cloud are not sufficiently utilized. In this paper, we use local geometric shape features including the nearest neighbor tetrahedral volume, Gaussian curvature, the neighbourhood normal vector consistency and the neighbourhood minimum principal curvature direction consistency. We propose three discrete criteria for parameter optimization to design explicit functions, and we present concrete algorithms, in which Monte Carlo method and Probabilistic Neural Network method are employed to estimate these parameters respectively. Experimental results show that our criteria can be applied to the classification of the 3D point cloud of the scene, and can be used to improve the classification accuracy of small-scale point sets when different classes have great disparities in the number.

A Novel Classification and Identification Scheme of Emitter Signals Based on Ward's Clustering and Probabilistic Neural Networks with Correlation Analysis.

The rapid development of modern communication technology makes the identification of emitter signals more complicated. Based on Ward's clustering and probabilistic neural networks method with correlation analysis, an ensemble identification algorithm for mixed emitter signals is proposed in this paper. The algorithm mainly consists of two parts, one is the classification of signals and the other is the identification of signals. First, self-adaptive filtering and Fourier transform are used to obtain the frequency spectrum of the signals. Then, the Ward clustering method and some clustering validity indexes are used to determine the range of the optimal number of clusters. In order to narrow this scope and find the optimal number of classifications, a sufficient number of samples are selected in the vicinity of each class center to train probabilistic neural networks, which correspond to different number of classifications. Then, the classifier of the optimal probabilistic neural network is obtained by calculating the maximum value of classification validity index. Finally, the identification accuracy of the classifier is improved effectively by using the method of Bivariable correlation analysis. Simulation results also illustrate that the proposed algorithms can accurately identify the pulse emitter signals.

A Computer-Based Brain Tumor Detection Approach with Advanced Image Processing and Probabilistic Neural Network Methods

For years, automation in tumor detection area has been commonly required because there might be a shortage of skilled radiologists in this area. In this study, a computer based brain tumor detection approach in magnetic resonance imaging (MRI) is proposed. The purpose of this study is to detect and to localize the tumor areas in the brain with using advanced image processing techniques and probabilistic neural network (PNN) method. For this study, firstly, a special clustering technique is used on the MRI images. Secondly, with using thresholding and level-set segmentation, tumor areas are detected successfully. Thirdly, with using the obtained tumor areas, automatic brain tumor classification and analysis are achieved with using PNN method. In the experimental part of the study, 25 neuroimages are used to optimize our system and 25 out-of-sample neuroimages are also used to test the approach. The preliminary diagnostic results can demonstrate the high classification accuracy for the image processing and the neural network structures.

An enhanced machine learning based approach for failures detection and diagnosis of PV systems

In this paper, a novel procedure for fault detection and diagnosis in the direct current (DC) side of PV system, based on probabilistic neural network (PNN) classifier, is proposed. The suggested procedure consists of four main stages: (i) PV module parameters extraction, (ii) PV array simulation and experimental validation (iii) elaboration of a relevant database of both healthy and faulty operations, and (iv) network construction, training and testing. In the first stage, the unknown electrical parameters of the one diode model (ODM) are accurately identified using the best-so-far ABC algorithm. Then, based on these parameters the PV array is simulated and experimentally validated by using a PSIM™/Matlab™ co-simulation. Finally, efficient fault detection and diagnosis procedure based on PNN classifier is implemented. Four operating cases were tested in a grid connected PV system of 9.54kWp: Healthy system, three modules short-circuited in one string, ten modules short-circuited in one string, and a string disconnected from the array. Moreover, the PNN method was compared, under real operating conditions, with the feed forward back-propagation Artificial Neural Network (ANN) classifiers method, for noiseless and noisy data to evaluate the suggested method’s accuracy and test its aptitude to support noisy data. The obtained results have demonstrated the high efficiency of the proposed method to detect and diagnose DC side anomalies for both noiseless and noisy data cases.