Probability Of Correct Classification Research Articles

What Should Be Typical about the Way We Calculate Typicality?

The probability of correct classification, and ultimately identification, lies at the heart of forensic anthropological analyses. To this end, practitioners rely on a variety of ways to assess the error or uncertainty of their estimates, including the use of statistically based analytical packages such as FORDISC. This article addresses typicality probabilities and specifically examines issues and assumptions with calculating F-statistic typicalities both statistically and within FORDISC. It uses multiple methods to calculate F-test typicality from publicly accessible craniometric data drawn from the Howells data set, a data set also included as reference groups within FORDISC. While the results of these calculations agree across various F-tests proposed by different authors, the results do not match the “TypF” values generated by FORDISC when using the “resubstitution” option. Through additional calculations and various reproducibility exercises, the authors demonstrate how and why “TypF” in FORDISC produces erroneous typicality values with the “resubstitution” option. They also identify the correct equation to incorporate into the software to rectify this problem. This work represents the logical conclusion of a long-running debate the authors had with Stephen D. Ousley and a desire to improve the accuracy and interpretability of analyses generated in FORDISC.

Estimation of sex assigned at birth using dental crown and cervical measurements in a modern global sample.

Despite developing prior to the appearance of secondary sexual characteristics of the skeleton, the permanent dentition exhibits sexual dimorphism. Therefore, teeth can serve as a means to estimate sex assigned at birth even in young individuals. This project takes a large global sample of maximum dimensions of the crown as well as measurements of the crown at the cervix to explore sexual dimorphism. Dimorphism is noted in teeth throughout the dental arcade, particularly in the canines. We provide sectioning points as well as the probability of correct classification (ranging from 50.9% to 81.3%) for each measurement to aid the practitioner in sex estimation from the dentition. This research provides a method to estimate sex without arbitrary population specifications. We argue for a global approach that incorporates more population variation to remove the need to estimate "ancestry," (which in actuality is translated to a social race category) and therefore does not force sexual dimorphism-related variation into these mutable and ambiguous categories. Further, this paper demonstrates the utility of the dentition as an additional indicator to aid with the estimation of sex assigned at birth in forensic anthropology. The goal of this research is to better understand the expression of sexual dimorphism across the skeleton in a global context.

Analysis of informativeness of features of classification of dangerous weather events based on radar observation results

One of the crucial factors affecting the safety and regularity of state and civil aviation flights is the meteorological situation. The European territory of Russia is most characterized by dangerous meteorological phenomena associated with cumulonimbus clouds: shower, thunderstorms, hail, accompanied by high atmospheric turbulence. Currently, meteorological radar stations are an indispensable source of information about the weather situation for air transport. The criteria for the classification of meteorological phenomena used in modern radar stations are formed for each event separately and are based on knowledge only about the altitude distribution of radar reflectivity and air temperature, despite the fact that radar data assess the wind characteristics of the atmosphere. It is shown that optimization of the classification criteria for the mentioned meteorological phenomena should be realized by generalization of the criteria and their construction in accordance with the theory of statistical hypothesis distinction, as well as by additional use of information on atmospheric turbulence. Based on the analysis of radar signals reflected from the meteorological events of shower, thunderstorm, and hail, probability distributions of reflectivity and specific dissipation rate of turbulent energy were obtained. Statistical analysis of probability distribution densities was carried out for: the maximum value of reflectivity Zmax, its dependence on height H(Zmax), as well as the maximum specific dissipation rate of turbulent energy EDRmax and the value H(EDRmax). The classification criterion based on the maximum probability functional was chosen to determine the structure of classification algorithms and decision rules. At the same time under the acceptable confidence is accepted the value of the probability of correct classification not lower than 0.8. For the accepted criterion the decision thresholds are constructed and the complete matrices of classification probabilities are calculated. The results of calculations showed that the worst informativeness in the classification of dangerous meteorological events of cumulonimbus cloudiness have parameters H(Zmax), H(EDRmax). Parameters Zmax, EDRmax have greater separating ability, but even for them the confidence of classification is unacceptable. In the article to increase the confidence of classification the joint use of features in the form of multivariate probability distribution densities of information parameters was applied. The best results are achieved when three p(Zmax,H(Zmax),EDRmax) and four p(Zmax,H(Zmax),EDRmax,H(EDRmax)) features are used. In the probability matrices for these cases, the maximum and acceptable at 0.8 level of probabilities of correct classification are achieved. Thus, the expansion of the feature space due to atmospheric turbulence is justified in the problem under consideration. These results will be refined with increasing observation time and will vary for different climatic zones. In general, the decision thresholds for classifying dangerous meteorological events of cumulonimbus cloudiness should be adaptive.

Asymptotic behavior of some multicategory classification methods for high-dimensional data

We consider multicategory extensions of binary discrimination methods via one-versus-one (OVO) or one-versus-rest (OVR) methodologies, focusing on extensions of the binary classification by linear mean difference (MD), support vector machine (SVM), maximal data piling (MDP), and distance weighted discrimination (DWD) via OVO, and the multicategory extension of MD via OVR, in the context of high-dimensional and low sample size (HDLSS) data. The asymptotic behavior of OVO-MD, OVO-SVM, OVO-MDP and OVO-DWD is described when the dimension of the data increases and the sample size is fixed, in terms of the probabilities of correct classification of a new data point, finding sufficient conditions for the correct classification probabilities to converge to one as the dimension approaches infinity. As in the binary case, OVO-MD, OVO-SVM and OVO-MDP have the same asymptotic behavior while OVO-DWD could behave differently. We also consider the asymptotic behavior of the OVR-MD methodology providing necessary and sufficient conditions for a new data point of a given class to be correctly classified with probability tending to one. A simulation experiment is conducted to further compare the methodologies, and consider the four binary methods in the OVR case. We evaluate the performance of the considered methods using a microarray data set.

Federated learning based modulation classification for multipath channels

Deep learning (DL)-based automatic modulation classification (AMC) is a primary research field for identifying modulation types. However, traditional DL-based AMC approaches rely on hand-crafted features, which can be time-consuming and may not capture all relevant information in the signal. Additionally, they are centralized solutions that are trained on large amounts of data acquired from local clients and stored on a server, leading to weak performance in terms of correct classification probability. To address these issues, a federated learning (FL)-based AMC approach is proposed, called FL-MP-CNN-AMC, which takes into account the effects of multipath channels (reflected and scattered paths) and considers the use of a modified loss function for solving the class imbalance problem caused by these channels. In addition, hyperparameter tuning and optimization of the loss function are discussed and analyzed to improve the performance of the proposed approach. The classification performance is investigated by considering the effects of interference level, delay spread, scattered and reflected paths, phase offset, and frequency offset. The simulation results show that the proposed approach provides excellent performance in terms of correct classification probability, confusion matrix, convergence and communication overhead when compared to contemporary methods.

QBinning: Data Quality-Based Algorithm for Automized Ion Chromatogram Extraction from High-Resolution Mass Spectrometry.

Due to the complexity and volume of data generated through non-target screening (NTS) using chromatographic couplings with high-resolution mass spectrometry, automized processing routines are necessary. The processing routines usually consist of many individual steps that are user-parameter-dependent and, thus, require labor-intensive optimization. Additionally, the effect of variations in raw data quality on the processing results is unclear and not fully understood. Within this work, we present qBinning, a novel algorithm for constructing extracted ion chromatograms (EICs) based on statistical principles and, thus, without the need to set user parameters. Furthermore, we give the user feedback on the specific qualities of the generated EICs using a scoring system (DQSbin). The DQSbin measures reliability as it correlates with the probability of correct classification of masses into EICs and the degree of overlap between different EIC construction algorithms. This work is a big step forward in understanding the behavior of NTS data and increasing the overall transparency in the results of NTS.

Predicting Cognitive Function Impairment through Game-based Intelligence Tests Combined with Heart Rate Variability in Older Adults

Objectives: In this study, we explored the feasibility of predicting the risks of older adults′ cognitive function impairment using game-based intelligence tests combined with heart rate variability. Methods: We recruited 110 elderly participants from a dementia center in central Taiwan using cluster sampling. The research tools included the Mini-Mental State Examination (MMSE), the Game-based Intelligence Test (GBIT), and dynamic and static heart rate variability (HRV). Results: Multivariate stepwise regression analysis was performed for the GBIT on MMSE scores (65.1%). The key factors included the correct number of memory recalls and average attention time. Moreover, logistic regression analysis was conducted for GBIT combined with HRV to predict the high-risk group for cognitive function impairment. Key factors included the correct number of reactions, the correct number of memory recalls, and a very low-frequency power peak. The probability of correct classification was 78.18%. Conclusions: GBIT combined with HRV has predictive power on the risk of elderly cognitive function impairment. Hence, this study recommends that GBIT combined with HRV could be used at home or community bases as a feasible tool in predicting older adults′ cognitive function impairment.

Multi-scale and multi-modal imaging study of mantle xenoliths and petrological implications

Abstract The accurate textural characterization of mantle xenoliths is one of the fundamental steps to understanding the main processes occurring in the upper mantle, such as sub-solidus recrystallization, magmatic crystallization, and metasomatism. Texture, composition, and mineralogy reflect the temperature, pressure, stress conditions, melting, and/or contamination events undergone before and during the entrapment in the host magma. For these reasons, characterizing the three-dimensional (3D) texture of silicate, oxide, sulfide, and glass phases has great importance in the study of mantle xenoliths. We performed a multi-scale and multi-modal 3D textural analysis based on X-ray computed microtomography (µ-CT) data of three mantle xenoliths from different geodynamic settings (i.e., mobile belt zone, pericraton, oceanic hotspot). The samples were selected to represent different, variably complex internal structures composed of grains of different phases, fractures, voids, and fluid inclusions of different sizes. We used an approach structured in increasing steps of spatial and contrast resolution, starting with in-house X-ray µ-CT imaging (spatial resolution from 30 µm down to 6.25 µm) and moving to high-resolution synchrotron X-ray µ-CT at the micrometer scale. We performed a 3D characterization of mantle xenoliths, comparing the results with the analysis of conventional 2D images (thin sections) obtained by optical microscopy and simulating the random sectioning of several thin sections to estimate the probability of correct modal classification. The 3D models allow the extraction of textural information that cannot be quantified solely from thin sections: spinel layering, distribution of silicic glass, and related vesicles. Moreover, high-density volumes identified as sulfides were detected in two xenoliths, showing no relation with the spinel layering in one case and a preferential concentration along fractures in the other. Given the variety of textures and mineral assemblages of mantle xenoliths worldwide, the results are used to suggest experimental and analytical protocols for the characterization of these materials.

TS-WHT: A Two-Step Walsh–Hadamard Transform Approach for Blind Error Correcting Code Classification

Blind classification of error-correcting codes is essential for intelligent wireless communication, cognitive radio, and non-cooperative communication. The object of this paper is to investigate the differences in the Walsh spectrum between linear block code, convolutional code, and Turbo code. Based on these differences, a two-step Walsh Hadamard transform (TS-WHT) strategy is proposed for error-correcting code blind classification. Further, according to the detection theory, the peak detection threshold is detailed and optimized with the cyclic feature of CRC codes. The results indicate that when employing the optimized threshold, probabilities of correct classification are superior for linear block codes and convolutional codes. Moreover, with the help of the fault-tolerant feature of the WHT technique, the classification accuracy of the proposed method is substantially better than existing approaches under low signal-to-noise ratio(SNR) conditions.

Fiber-Optic Telecommunication Network Wells Monitoring by Phase-Sensitive Optical Time-Domain Reflectometer with Disturbance Recognition

The paper presents the application of a phase-sensitive optical time-domain reflectometer (phi-OTDR) in the field of urban infrastructure monitoring. In particular, the branched structure of the urban network of telecommunication wells. The encountered tasks and difficulties are described. The possibilities of usage are substantiated, and the numerical values of the event quality classification algorithms applied to experimental data are calculated using machine learning methods. Among the considered methods, the best results were shown by convolutional neural networks, with a probability of correct classification as high as 98.55%.

Detection of Malicious Network Activity by Artificial Neural Network

This paper presents a deep learning approach to detect malicious communication in a computer network. The intercepted communication is transformed into behavioral feature vectors that are reduced (using principal component analysis and stepwise selection methods) and normalized to create training and test sets. A feed-forward artificial neural network is then used as a classifier to determine the type of malicious communication. Three training algorithms were used to train the neural network: the Levenberg-Marquardt algorithm, Bayesian regularization, and the scaled conjugate gradient backpropagation algorithm. The proposed artificial neural network topology after reducing the size of the training and test sets achieves a correct classification probability of 81.5 % for each type of malicious communication and of 99.6 % (and better) for normal communication.

A one-dimension convolutional neural network based interference classification method

Interference is a common problem in wireless communication, navigation and radar systems. A wide variety of interferences are used to degrade the communication quality especially in electronic warfare environment. In modern military communication systems, interference classification is an important module for its ability to obtain prior interference information before adopting related anti-interference method. This paper proposes a deep learning based interference classification method, which applies one-dimension convolutional neural networks to automatically extract interference features for classification. Computer simulations show better classification performance and lower computational complexity. Meanwhile, this proposed method is implied on software defined radios (SDR) hardware, more than 99% correct classification probability can be achieved with limited samples of the received signal, which verifies the robustness of this proposed method.

Quantum Pattern Classification in a Three-Qubit System

The problem of pattern classification in quantum data has been of great importance over the past few years. This study investigates the effect of deploying Grover’s, the partial diffusion, and the fixed-phase algorithms separately to amplify the amplitudes of a desired pattern in an unstructured dataset. These quantum search operators were applied to symmetric and antisymmetric input superpositions on a three-qubit system for 20 iterations each. After each iteration, different probabilities of classification were calculated in order to determine the accuracy of classification for each of the three quantum search operators. The results indicated that, in the case of applying the three quantum search operators to incomplete superposition input states, the partial diffusion operator outperformed the other operators with a probability of correct classification that reached 100% in certain iterations. It also showed that the classification accuracy of the fixed-phase operator exceeded the accuracy of the other two operators by 40% in most cases when the input state was a uniform superposition, and some of the basis states were phase-inverted.

LPI Waveform Recognition Using Adaptive Feature Construction and Convolutional Neural Networks

Low probability of intercept (LPI) radar waveform recognition is one of the crucial functions in electronic intelligence systems. Advances in artificial intelligence promote the performance of the LPI waveform recognition with various signal features defined with analytical expressions. However, noisy LPI waveform recognition is still a challenge for traditional approaches even with noise elimination techniques, especially for the heavily contaminated noisy LPI signals. Recently, the adaptive analysis techniques, such as variational mode decomposition (VMD) and empirical mode decomposition (EMD) provide potential methods that explore the inherent features of signals and formulate adaptive features for signal recognition. In this article, we propose an adaptive feature construction framework that utilizes both the adaptive features (via VMD and EMD) and predefined analytical features (via Wigner–Ville distribution, Choi–William distribution, and wavelet analysis) to construct the fusion feature, which is further applied on the convolutional neural networks-based LPI waveform recognition system. The experimental results show that the proposed feature adaptive LPI network-based exploitation (FALPINE) approach achieves higher probability of correct classification than the state-of-the-art works, which demonstrates the superior performance of the proposed approach.

Selection of Potential Regions for the Creation of Intelligent Transportation Systems Based on the Machine Learning Algorithm Random Forest

The planning and management of traffic flow networks with multiple input data sources for decision-making generate the need for a mathematical approach. The program of measures for the development of the transport infrastructure of the Russian Federation provides for the selection of pilot regions for the creation of intelligent transportation systems. With extensive knowledge of theoretical and applied mathematics, it is important to select and adapt mathematical methods for solving problems. In this regard, the aim of the study is to develop and validate an algorithm for solving the problem of classifying objects according to the potential of creating intelligent transportation systems. The main mathematical apparatus for classification is the «random forest» machine learning algorithm method. A bagging machine learning meta-algorithm for high accuracy of the algorithm was used. This paper proposes the author’s method of sequential classification analysis for identifying objects with the potential to create intelligent transportation systems. The choice of using this method is justified by its best behavior under the large number of predictor variables required for an objective aggregate assessment of digital development and quality of territories. The proposed algorithm on the example of Russian regions was tested. A technique and algorithm for statistical data processing based on descriptive analytics tools have been developed. The quality of the classification analysis algorithm was assessed by the random forest method based on misclassification coefficients. The admissibility of retrained algorithms and formation of a «fine-grained» «random forest» model for solving classification problems under the condition of no prediction was proven to be successful. The most productive models with the highest probability of correct classification were «reached» and «finalized» on the basis of logistic regression analysis of relationships between predictors and categorical dependent variables. The regions of class 1 with «high potential for the creation of intelligent transportation systems» are most likely to be ready for the reorganization of infrastructure facilities; the introduction of digital technologies in the management of traffic flows was found.

Анализ возможностей мультиспектрального оптического метода мониторинга лесных территорий

The paper analyzes possibilities of the multispectral remote optical method in monitoring the forest areas. Results of mathematical simulation are provided of classification of the forest areas elements in the created neural network using experimentally measured reflection of the forest vegetation coefficients. It is demonstrated that the created neural network ensures high probability of correct classification within the classification problem (according to the multispectral remote optical monitoring data) of the forest probed areas. The selected spectral probing channels in a wide spectral range of ~ 400--2400 nm and the created neural network used seven spectral channels in the visible and in the near infrared spectral range, as well as the active laser sensor to measure the trees height. They provided a probability of correct classification of the forest areas elements (green deciduous trees, green coniferous trees, dry deciduous and coniferous trees, swamps, pastures with different vegetation cover and different types of soils) of more than 0.74 and the probability of misclassification of the forest areas elements of less than 0.08. The multispectral remote optical method could be used in operational monitoring of the vast forest areas from an aircraft (light aircraft or unmanned aerial vehicle)

Multispectral lidar method for monitoring the forest ecosystem under the forest canopy

This study demonstrates the potential of the multispectral lidar method to monitor the forest ecosystem under the forest canopy. The mathematical modeling results of forest territories elements classification on the created neural network using experimentally measured reflection coefficients are presented. It is shown that the neural network provides a high probability of correct classification for the forest ecosystem elements classification task (when using lidar measurement data about the height of the forest ecosystem elements). Laser pulse sounding at two wavelengths in near infrared spectral range 1064 and 2030 nm and the created neural network provide the probabilities of correctly classify the undergrowth of green broadleaved and coniferous trees, swamps and soils more than 0.84 and the probability of incorrect classification less than 0.08.

Assessing good environmental status through mesozooplankton biodiversity: a step forward.

We developed a zooplankton-based water-quality evaluating method using indices of alpha diversity. Two key objectives were set: (i) the comparison of two-different quality-samples from different areas, and the verification of their differentiation, based on mesozooplankton biodiversity indices; and (ii) the development of a methodology, which was able to assess the quality of new marine water samples. Our analysis was based on a 24-year-long in situ dataset (1987-2010) of 139 samples in which 86 mesozooplankton taxa were identified. High-diversity and high evenness values were reported in the case of the "good" status sample, while low diversity, low evenness and high dominance values occurred at the lower quality one. A linear discriminant analysis (LDA) was conducted that discriminated the tested samples at 100%. This LDA was then used to evaluate samples of unknown quality. Finally, 90% of them were classified with a probability of correct classification (posterior probability) >95%. The present study proves that mesozooplankton diversity indices can discriminate different levels of anthropogenic impacts. In this sense, it can be used as a reliable indicator for environmental assessment in the pelagic habitats of the Mediterranean Sea.

Сalprotectin in the blood plasma as a new biomarker for assessing the activity of rheumatoid arthritis

Aim. To study the potential use and information value of calprotectin in the blood plasma as a new biomarker for determining the activity of rheumatoid arthritis (RA).Materials and methods. The study included 113 people. The treatment group consisted of 79 patients diagnosed with RA; the average age was 58 (± 11.66) years, the median duration of the disease was 10 [6; 15] years. The control group encompassed 34 healthy volunteers; the average age was 40 (± 11.14) years. RA activity was determined according to the Disease Activity Score (DAS) 28 and the Clinical Disease Activity Index (CDAI). The concentration of calprotectin in the blood plasma was determined by the solid-phase enzyme-linked immunosorbent assay. The obtained results were compared with laboratory and clinical parameters, as well as with composite indices (DAS28, CDAI) of RA activity. For mathematical data processing, Spearman’s rank correlation coefficient, linear discriminant analysis, and ROC analysis were used.Results. In the group of patients with RA, the level of calprotectin in the blood was higher than in the control group. A statistically significant relationship was revealed between the level of calprotectin in the blood and all standard parameters of RA activity. The ROC analysis showed that the sensitivity, specificity, and diagnostic accuracy in assessing articular syndrome, as well as moderate and high RA activity according to the composite indices DAS28 and CDAI were higher for calprotectin than for erythrocyte sedimentation rate (ESR) and C-reactive protein (CRP). The linear discriminant analysis showed that a combination of ESR and calprotectin levels was the most informative; following it, the probability of correct classification of RA activity, according to the DAS28 index, was 71%. For the CDAI index, only one marker, calprotectin, resulted in a statistically significant classification with a probability of 70.5 %.Conclusion. Сalprotectin in the blood plasma is a promising laboratory biomarker for assessing synovitis activity in RA demonstrating higher accuracy, sensitivity, and specificity than traditional acute-phase reactants.

Multi-Scale Analysis for Coherent Change Detection: A Method for Extracting Typical Changed Area

Coherent change detection is a technology that utilizes phase information in complex-valued synthetic aperture radar images. It is mostly used to detect subtle changes that cannot be detected by amplitude images on the ground, and it also has excellent detection performance when it comes to low-coherence typical changed areas. However, due to its high sensitivity to changes, this technology will falsely detect areas of natural change such as vegetation disturbance, river flow, and low signal-to-noise ratio areas (e.g., uninteresting areas) as changes, resulting in false-alarm interference areas. In order to tackle this problem, this paper studies a coherent change detection method based on multi-scale analysis to extract typical changed areas in complicated scenes. The method uses an equal variance coherence estimator to calculate the coherence value, separates the interference areas and the typical changed areas using a multi-scale method, and then extracts a binary image of the typical changed areas through noise filtering and threshold segmentation. The method in this paper is experimentally verified with publicly available Airbus spaceborne SAR data, and ESAR airborne data, which is provided by the ESA. The experimental results are visualized and quantitatively evaluated. Through the results, by calculating the probability of correct classification and false-positive and other performance parameters, as well as drawing the receiver operating characteristic curve and the kappa coefficient curve of different threshold values, we find that the method has the capability to suppress the interference areas and the high detection performance of the typical changed areas. The experimental data are complicated scenes that include various types of ground object changes. The results show that the method is effective and universal and can provide reference value for the application of coherent change detection.