Artificial Neural Network-based Classification Research Articles

Classifier Model using Artificial Neural Network

When it comes to AI and ML, precision in categorization is of the utmost importance. In this research, the use of supervised instance selection (SIS) to improve the performance of artificial neural networks (ANNs) in classification is investigated. The goal of SIS is to enhance the accuracy of future classification tasks by identifying and selecting a subset of examples from the original dataset. The purpose of this research is to provide light on how useful SIS is as a preprocessing tool for artificial neural network-based classification. The work aims to improve the input dataset to ANNs by using SIS, which may help with problems caused by noisy or redundant data. The ultimate goal is to improve ANNs' ability to identify data points properly across a wide range of application areas.

A Novel Deep Reinforcement Learning Based Relay Selection for Broadcasting in Vehicular Ad Hoc Networks

VANETs (Vehicular Ad hoc NETworks) are considered among the world’s largest networks. These networks are providing multiple services like infotainment applications, safety services, driver assistance, and even video on demand. On one hand, VANETs are characterized by their random topology and dynamic behavior that varies in urban context, and which highly changes in highways. On the other hand, diffusing information is a fundamental task to deliver multiple services. Thus, the broadcasting task is a challenging problem and need more investigation. In fact, to achieve this task, artificial intelligence and learning based computing seem to be one of the most appropriate options that best fits the dynamic behavior of VANETs. Accordingly, in this paper we propose a novel hybrid relay selection technique to perform the broadcasting task based on a reinforcement learning method. Our proposition is initially to combine an artificial neural network-based classification applied to select forwarding nodes, and in the second phase, we apply the Viterbi algorithm as a reinforcement tool to refine the first classification. To measure the performance of our contribution, we adopt a grid map scenario with varied traffic densities. Afterwards, we analyze and compare the simulation results with other methods in the literature based on different parameters such as the success rate, the data loss, the saved rebroadcasts, and the delay. We conclude by proving that the proposed technique combining deep learning along with reinforcement learning outperforms other recently proposed broadcasting schemes based on the results which show that the new solution increased the success rate by 16%, the saved rebroadcasts by 20%, and reduced the delay by 23%.

Multi-Sensor Feature Integration for Assessment of Endotracheal Intubation

Traditionally, proficiency in endotracheal intubation (ETI) has been assessed by human supervisors in a subjective manner during training sessions; however, recent advances in sensor and computing technology have made it possible to obtain objective measures to evaluate the practitioner's performance. This study presents an automated and objective ETI assessment system based on multi-sensor integration which aims at discriminating experienced from novice providers accurately. To this end, four different types of sensors were used to collect data, including hand motion of the provider, and tongue force, incisor force and head angle of the training mannequin. Features were extracted from the datasets, and relevant ones were identified by applying feature selection algorithms to create individual and integrated feature sets. An artificial neural network-based classification model was developed for each feature set. The results show that a classifier based on a small number of integrated features achieves the best accuracy (96.4%), significantly higher than the best obtained by any individual feature sets (91.17% by hand motion). This study demonstrated the feasibility of a multi-sensor based ETI assessment system that can provide practitioners with objective and timely feedback about their performance.

Development of Classification Models for Assessment of Endotracheal Intubation Training by a Cyber-Physical System

Endotracheal intubation (ETI) is one of the most staple skills in prehospital medicine that is performed to prevent suffocation of an unconscious person. To evaluate ETI skills of medical practitioners, an effective and reliable assessment system is required; however, the current assessment method relies on subjective evaluation by supervisors during training sessions that may be inaccurate and biased. To provide objective and immediate feedback to trainees, this paper proposes a cyber physical system (CPS)-based ETI assessment system. The CPS is composed of wearable gloves with embedded sensors to capture hand motion data and software to discriminate between two groups: experienced and novice. To this end, we collected hand motion data from the two groups and extracted 18 features. Furthermore, we identified reduced sets of 8 and 10 based on their statistical significance. To discriminate the two groups, artificial neural network-based classification models were developed with the three feature sets. Experimental results show that the classifiers with 18, 8, and 10 features achieved an accuracy of 90.94%, 87.87% and 89.60%, respectively. This work corroborates that wearable gloves with embedded motion sensors can be effective in assisting self-training of ETI on a CPS.

Evaluation of the Accuracy of ADAS Module Readings Based on an Analysis of the Transient Supply Current and Neural Network Application

The following paper presents advanced methods for evaluating the reliability of ADAS module readings, based on an analysis of the transient supply current. Changes in the transient current waveform occur due to environmental conditions and damage to a module's inner circuitry. Specific deviations in the waveforms may indicate a certain event – either internal or external. This paper presents how to successfully distinguish certain anomalies using artificial neural network-based classification algorithms without having to interfere with the module's internal circuitry.DOI: http://dx.doi.org/10.5755/j01.eie.24.3.20944

Oppositional Gravitational Search Algorithm and Artificial Neural Network-based Classification of Kidney Images

Abstract Ultrasound (US) imaging has been broadly utilized as part of kidney diagnosis because of its ability to show structural abnormalities like cysts, stones, and infections as well as information about kidney function. The main aim of this research is to effectively classify normal and abnormal kidney images through US based on the selection of relevant features. In this study, abnormal kidney images were classified through gray-scale conversion, region-of-interest generation, multi-scale wavelet-based Gabor feature extraction, probabilistic principal component analysis-based feature selection and adaptive artificial neural network technique. The anticipated method is executed in the working platform of MATLAB, and the results were analyzed and contrasted. Results show that the proposed approach had 94% accuracy and 100% specificity. In addition, its false-acceptance rate is 0%, whereas that of existing methods is not <27%. This shows the precise prediction level of the proposed approach, compared with that of existing methods.

Spectrum sensing for 4G LTE OFDM signals in heterogeneous network using neural network

Spectrum sensing is an important requirement in cognitive radios deployed in advanced 4G wireless communication systems. The cognitive radio has to classify the signal of interest from many such signals in its vicinity. There has been wide spread acceptance of multicarrier signal like orthogonal frequency division multiplexed (OFDM) due to its better protection characteristics against channel degradations. Many recent and upcoming wireless standards thus employ OFDM signal, and a CR radio has to classify the OFDM signal operating in a heterogeneous operating environment. In this paper, we have used artificial neural network-based classification of OFDM signal of third-generation partnership project long term evolution (3GPP LTE) signals that is used on 4G wireless networks. We used reference signal-induced cyclostationarity and cyclic prefix property as feature for classification. The 3GPP LTE OFDM signal classification is done in a heterogeneous network environment, in which other OFDM signal from IEEE WiMAX network and other single-carrier digital modulation signal presence are considered. Comparison of classification performance for multilayer perceptron and radial basis function neural network is presented. Effect of two training algorithms, Levenberg - Marquardt (LM) and Back Propagation with momentum, on the convergence rate for training the neural network is presented.

Spectrum sensing for 4G LTE OFDM signals in heterogeneous network using neural network

Spectrum sensing is an important requirement in cognitive radios deployed in advanced 4G wireless communication systems. The cognitive radio has to classify the signal of interest from many such signals in its vicinity. There has been wide spread acceptance of multicarrier signal like orthogonal frequency division multiplexed (OFDM) due to its better protection characteristics against channel degradations. Many recent and upcoming wireless standards thus employ OFDM signal, and a CR radio has to classify the OFDM signal operating in a heterogeneous operating environment. In this paper, we have used artificial neural network-based classification of OFDM signal of third-generation partnership project long term evolution (3GPP LTE) signals that is used on 4G wireless networks. We used reference signal-induced cyclostationarity and cyclic prefix property as feature for classification. The 3GPP LTE OFDM signal classification is done in a heterogeneous network environment, in which other OFDM signal from IEEE WiMAX network and other single-carrier digital modulation signal presence are considered. Comparison of classification performance for multilayer perceptron and radial basis function neural network is presented. Effect of two training algorithms, Levenberg - Marquardt (LM) and Back Propagation with momentum, on the convergence rate for training the neural network is presented.

Artificial neural network-based classification of body movements in ambulatory ECG signal

Ambulatory ECG monitoring provides electrical activity of the heart when a person is involved in doing normal routine activities. Thus, the recorded ECG signal consists of cardiac signal along with motion artifacts introduced due to a person’s body movements during routine activities. Detection of motion artifacts due to different physical activities might help in further cardiac diagnosis. Ambulatory ECG signal analysis for detection of various motion artifacts using adaptive filtering approach is addressed in this paper. We have used BIOPAC MP 36 system for acquiring ECG signal. The ECG signals of five healthy subjects (aged between 22–30 years) were recorded while the person performed various body movements like up and down movement of the left hand, up and down movement of the right hand, waist twisting movement while standing and change from sitting down on a chair to standing up movement in lead I configuration. An adaptive filter-based approach has been used to extract the motion artifact component from the ambulatory ECG signal. The features of motion artifact signal, extracted using Gabor transform, have been used to train the artificial neural network (ANN) for classifying body movements.

Artificial Neural Network-based Classification to Screen for Dysphonia Using Psychoacoustic Scaling of Acoustic Voice Features

For diagnosis and classification of dysphonia, voice specialists can choose from an array of diagnostic tools like perceptual tests or acoustic voice analysis. These methods have in common that they require a high level of specialized training and experience, and therefore are mostly reserved to specialized centers. We aimed at developing an acoustic voice analysis system that could be used as a screening device to monitor, document, and diagnose voice problems that are also encountered by non-voice specialists, such as anesthesiologists, head and neck surgeons, and general surgeons before surgery of the thyroid gland and the upper thoracic aperture. An acoustical feature extraction paradigm that focused on jitter, shimmer, standard deviation of fundamental frequency, and the glottal-to-noise excitation ratio was used to reanalyse 120 voice samples previously analyzed by Schönweiler et al (A Novel Approach to Acoustical Voice Analysis Using Artificial Neural Networks. JARO. 2000:1;270-282). An improved artificial neural network (ANN) was used for classification. Building on this preliminary work, we modified the mathematical algorithm to further improve classification accuracy. Eighty percent of all voice samples could be classified correctly as either healthy or hoarse (sensitivity: 63.0%; specificity: 93.9%; area under the curve: 0.854). The adaptation of the ANN-voice analysis system for mobile use may facilitate its use and acceptance by non-voice specialists for the discovery and documentation of preexisting voice disorders, and may thereby lead to a timely initiation of further diagnosis and therapy by voice specialists.