Using multithreshold quadratic sigmoidal neurons to improve classification capability of multilayer perceptrons

In this paper, the classification capabilities of perceptron and radial neural networks are compared using the identification of selected pests feeding in apple tree orchards in Poland as an example. The goal of the study was the neural separation of five selected apple tree orchard pests. The classification was based on graphical information coded as selected characteristic features of the pests, presented in digital images. In the paper, MLP (MultiLayer Perceptrons), RBF (Radial Basis Function) and DNN (Deep Neural Networks) neural classification models are compared, generated using learning files acquired on the basis of information contained in digital photographs of five selected pests. In order to classify the pests, neural modeling methods were used, including digital image analysis techniques. The qualitative analysis of the neural models enabled the selection of optimal neuron topology that was characterized by the highest classification capability. As representative graphic features were selected five selected coefficients of shape and two defined graphical features of the classified objects. The created neuron model is dedicated as a core for computer systems supporting the decision processes occurring during apple production, particularly in the context of apple tree orchard pest protection automation.

Download Full-text

The Use of Artificial Neural Networks and a General Discriminant Analysis for Predicting Culling Reasons in Holstein-Friesian Cows Based on First-Lactation Performance Records

Animals ◽

10.3390/ani11030721 ◽

2021 ◽

Vol 11 (3) ◽

pp. 721

Author(s):

Krzysztof Adamczyk ◽

Wilhelm Grzesiak ◽

Daniel Zaborski

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Discriminant Analysis ◽

Multilayer Perceptrons ◽

Correct Classification ◽

Correct Classification Rate ◽

Classification Rate ◽

Holstein Friesian ◽

Artificial Neural ◽

Friesian Cows

The aim of the present study was to verify whether artificial neural networks (ANN) may be an effective tool for predicting the culling reasons in cows based on routinely collected first-lactation records. Data on Holstein-Friesian cows culled in Poland between 2017 and 2018 were used in the present study. A general discriminant analysis (GDA) was applied as a reference method for ANN. Considering all predictive performance measures, ANN were the most effective in predicting the culling of cows due to old age (99.76–99.88% of correctly classified cases). In addition, a very high correct classification rate (99.24–99.98%) was obtained for culling the animals due to reproductive problems. It is significant because infertility is one of the conditions that are the most difficult to eliminate in dairy herds. The correct classification rate for individual culling reasons obtained with GDA (0.00–97.63%) was, in general, lower than that for multilayer perceptrons (MLP). The obtained results indicated that, in order to effectively predict the previously mentioned culling reasons, the following first-lactation parameters should be used: calving age, calving difficulty, and the characteristics of the lactation curve based on Wood’s model parameters.

Download Full-text

Minimization of the Line Resistance Impact on Memdiode-Based Simulations of Multilayer Perceptron Arrays Applied to Pattern Recognition

Journal of Low Power Electronics and Applications ◽

10.3390/jlpea11010009 ◽

2021 ◽

Vol 11 (1) ◽

pp. 9

Author(s):

Fernando Leonel Aguirre ◽

Nicolás M. Gomez ◽

Sebastián Matías Pazos ◽

Félix Palumbo ◽

Jordi Suñé ◽

...

Keyword(s):

Pattern Recognition ◽

Ex Situ ◽

Multilayer Perceptrons ◽

Spice Simulation ◽

Large Dataset ◽

High Line ◽

Calibration Algorithm ◽

The Impact ◽

Line Resistance

In this paper, we extend the application of the Quasi-Static Memdiode model to the realistic SPICE simulation of memristor-based single (SLPs) and multilayer perceptrons (MLPs) intended for large dataset pattern recognition. By considering ex-situ training and the classification of the hand-written characters of the MNIST database, we evaluate the degradation of the inference accuracy due to the interconnection resistances for MLPs involving up to three hidden neural layers. Two approaches to reduce the impact of the line resistance are considered and implemented in our simulations, they are the inclusion of an iterative calibration algorithm and the partitioning of the synaptic layers into smaller blocks. The obtained results indicate that MLPs are more sensitive to the line resistance effect than SLPs and that partitioning is the most effective way to minimize the impact of high line resistance values.

Download Full-text

Estimation of electrical resistivity using artificial neural networks: a case study from Lublin Basin, SE Poland

Acta Geophysica ◽

10.1007/s11600-021-00554-0 ◽

2021 ◽

Author(s):

Jakub Ważny ◽

Michał Stefaniuk ◽

Adam Cygal

Keyword(s):

Neural Networks ◽

Artificial Neural Networks ◽

Training Data ◽

Multilayer Perceptrons ◽

Borehole Data ◽

Geological Interpretation ◽

Se Poland ◽

Geological Conditions ◽

Artificial Neural ◽

Reliable Solution

AbstractArtificial neural networks method (ANNs) is a common estimation tool used for geophysical applications. Considering borehole data, when the need arises to supplement a missing well log interval or whole logging—ANNs provide a reliable solution. Supervised training of the network on a reliable set of borehole data values with further application of this network on unknown wells allows creation of synthetic values of missing geophysical parameters, e.g., resistivity. The main assumptions for boreholes are: representation of similar geological conditions and the use of similar techniques of well data collection. In the analyzed case, a set of Multilayer Perceptrons were trained on five separate chronostratigraphic intervals of borehole, considered as training data. The task was to predict missing deep laterolog (LLD) logging in a borehole representing the same sequence of layers within the Lublin Basin area. Correlation between well logs data exceeded 0.8. Subsequently, magnetotelluric parametric soundings were modeled and inverted on both boreholes. Analysis showed that congenial Occam 1D models had better fitting of TM mode of MT data in each case. Ipso facto, synthetic LLD log could be considered as a basis for geophysical and geological interpretation. ANNs provided solution for supplementing datasets based on this analytical approach.

Download Full-text

Sensor Validation and Diagnostic Potential of Smartwatches in Movement Disorders

Sensors ◽

10.3390/s21093139 ◽

2021 ◽

Vol 21 (9) ◽

pp. 3139

Author(s):

Julian Varghese ◽

Catharina Marie van Alen ◽

Michael Fujarski ◽

Georg Stefan Schlake ◽

Julitta Sucker ◽

...

Keyword(s):

Low Noise ◽

Disease Classification ◽

Multilayer Perceptrons ◽

Sensor Validation ◽

Diagnostic Potential ◽

A Prospective Study ◽

Learning Architectures ◽

Diagnosis Classification ◽

Healthy Participants ◽

Digital Biomarkers

Smartwatches provide technology-based assessments in Parkinson’s Disease (PD). It is necessary to evaluate their reliability and accuracy in order to include those devices in an assessment. We present unique results for sensor validation and disease classification via machine learning (ML). A comparison setup was designed with two different series of Apple smartwatches, one Nanometrics seismometer and a high-precision shaker to measure tremor-like amplitudes and frequencies. Clinical smartwatch measurements were acquired from a prospective study including 450 participants with PD, differential diagnoses (DD) and healthy participants. All participants wore two smartwatches throughout a 15-min examination. Symptoms and medical history were captured on the paired smartphone. The amplitude error of both smartwatches reaches up to 0.005 g, and for the measured frequencies, up to 0.01 Hz. A broad range of different ML classifiers were cross-validated. The most advanced task of distinguishing PD vs. DD was evaluated with 74.1% balanced accuracy, 86.5% precision and 90.5% recall by Multilayer Perceptrons. Deep-learning architectures significantly underperformed in all classification tasks. Smartwatches are capable of capturing subtle tremor signs with low noise. Amplitude and frequency differences between smartwatches and the seismometer were under the level of clinical significance. This study provided the largest PD sample size of two-hand smartwatch measurements and our preliminary ML-evaluation shows that such a system provides powerful means for diagnosis classification and new digital biomarkers, but it remains challenging for distinguishing similar disorders.

Download Full-text

A supervised machine learning approach to characterize spinal network function

Journal of Neurophysiology ◽

10.1152/jn.00763.2018 ◽

2019 ◽

Vol 121 (6) ◽

pp. 2001-2012 ◽

Cited By ~ 4

Author(s):

A. N. Dalrymple ◽

S. A. Sharples ◽

N. Osachoff ◽

A. P. Lognon ◽

P. J. Whelan

Keyword(s):

Machine Learning ◽

Spinal Cord ◽

Nervous System ◽

Spontaneous Activity ◽

Machine Learning Algorithms ◽

Supervised Machine Learning ◽

Network Activity ◽

Multilayer Perceptrons ◽

Network Development ◽

Newborn Mice

Spontaneous activity is a common feature of immature neuronal networks throughout the central nervous system and plays an important role in network development and consolidation. In postnatal rodents, spontaneous activity in the spinal cord exhibits complex, stochastic patterns that have historically proven challenging to characterize. We developed a software tool for quickly and automatically characterizing and classifying episodes of spontaneous activity generated from developing spinal networks. We recorded spontaneous activity from in vitro lumbar ventral roots of 16 neonatal [postnatal day (P)0–P3] mice. Recordings were DC coupled and detrended, and episodes were separated for analysis. Amplitude-, duration-, and frequency-related features were extracted from each episode and organized into five classes. Paired classes and features were used to train and test supervised machine learning algorithms. Multilayer perceptrons were used to classify episodes as rhythmic or multiburst. We increased network excitability with potassium chloride and tested the utility of the tool to detect changes in features and episode class. We also demonstrate usability by having a novel experimenter use the program to classify episodes collected at a later time point (P5). Supervised machine learning-based classification of episodes accounted for changes that traditional approaches cannot detect. Our tool, named SpontaneousClassification, advances the detail in which we can study not only developing spinal networks, but also spontaneous networks in other areas of the nervous system.NEW & NOTEWORTHY Spontaneous activity is important for nervous system network development and consolidation. Our software uses machine learning to automatically and quickly characterize and classify episodes of spontaneous activity in the spinal cord of newborn mice. It detected changes in network activity following KCl-enhanced excitation. Using our software to classify spontaneous activity throughout development, in pathological models, or with neuromodulation, may offer insight into the development and organization of spinal circuits.

Download Full-text

Chaotic Liquid State Machine

International Journal of Cognitive Informatics and Natural Intelligence ◽

10.4018/ijcini.2015100101 ◽

2015 ◽

Vol 9 (4) ◽

pp. 1-20

Author(s):

Mario Antoine Aoun ◽

Mounir Boukadoum

Keyword(s):

Liquid State ◽

State Machine ◽

Spiking Neurons ◽

Signature Verification ◽

Time Varying ◽

Plasticity Mechanism ◽

Online Signature ◽

Online Signature Verification ◽

One Class Classifier ◽

Classification Capability

The authors implement a Liquid State Machine composed from a pool of chaotic spiking neurons. Furthermore, a synaptic plasticity mechanism operates on the connection weights between the neurons inside the pool. A special feature of the system's classification capability is that it can learn the class of a set of time varying inputs when trained from positive examples only, thus, it is a one class classifier. To demonstrate the applicability of this novel neurocomputing architecture, the authors apply it for Online Signature Verification.

Download Full-text