Artificial Neural Network Module Research Articles

Landscape pattern prediction method based on ANN-CA-Markov coupling model

The simulation and prediction of landscape patterns can provide a reference for the formulation of ecological space security policies and management and control measures. Therefore, it is necessary to use objective and accurate scientific methods to make accurate simulation predictions. In this study, the quantitative prediction of the Markov model is combined with the advantages of the space-time simulation of the CA model, and the artificial neural network (ANN) module is used for calculation and coupling correction. The Kappa coefficient and the FoM (figure of merit) index are used to test the simulation accuracy. Based on this process, the changes of the landscape pattern in Mudanjiang City at three time points in 2000, 2010 and 2020 were analyzed, and the simulation prediction was made based on this. The experimental results show that the CA-Markov model using the ANN module for coupling correction can be tested for accuracy in the study area, and its Kappa coefficient is 0.834 and the FoM index is 0.001. The model meets the requirements of the landscape pattern for the accuracy of simulation and prediction, and the prediction and analysis of the study area is carried out, and the accurate prediction results are obtained.The results of the study were: Looking at the change in landscape pattern over the 20 years from 2000 to 2020, significant changes occurred in the areas of arable land and artificial surface. The total area of arable land decreased by nearly 130 km2, while the area of artificial surface (i.e., built-up land) increased by about 167 km2. The forest area initially decreased and then increased, with an overall increase of approximately 56 km2, while the water and grassland areas first increased and then decreased. In terms of spatial distribution, the changes in agricultural and forest land are mainly concentrated in the central area where urban development is intensive and in the northern forest area. The results of this study are quite important for policy formulation, according to which it was found that human activities, especially urbanization, have led to a decrease in the area of forested land, and therefore the implementation of the natural forest protection policy can lead to a sustained increase in the area of forested land.

Optimized Fault Detector Based Pattern Recognition Technique to Classify and Localize Electrical Faults in Modern Distribution Systems

This research presents a method that integrates artificial neural networks (ANN) and discrete wavelet transform (DWT) to identify and classify faults in large power networks, as well as to pinpoint the zones where these faults occur. The objective is to enhance reliability and safety by accurately detecting and categorizing electrical faults. To manage the computational demands of processing the extensive and complex data from the power system, the network is divided into optimal zones, each made visible for fault detection. Niche Binary particle swarm optimization (NBPSO) is employed to place the fault detectors (FD) in each zone. This allows for precise measurement of fault voltage and current phasors without significant cost. The ANN module is tasked with identifying the fault area and locating the exact fault within that zone, as well as classifying the specific type of fault. Discrete Wavelet Transform is used for feature extraction, and a phase locked loop (PLL) is used for load angle computation. The proposed method's validity has been tested on the IEEE-33 bus distribution network.

A prediction method for blade deformations of large-scale FVAWTs using dynamics theory and machine learning techniques

There is renewed interest in floating vertical axis wind turbines (FVAWTs) as offshore wind turbines progressively increase in size and move into deeper waters. To explore the potential of large-scale FVAWTs for future commercialization, it is crucial to investigate blade deformations using an accurate and effective method. In this study, we developed a hybrid model, namely, the SVST-ANN, which integrates dynamic theory and machine learning techniques to predict blade deformations. Specifically, an artificial neural network (ANN) module is incorporated into the slack coupled vertical axis wind turbine simulation tool (SVST), which significantly reduces the total computational time. A comparative study was conducted between the SVST-ANN model and the traditional SVST model, employing a 10 MW helical-type FVAWT as an example. The results show that the SVST-ANN model can accurately and efficiently predict blade deformations. The maximum errors for the maximum value, average value, and standard deviation across all nodes are minimal, with a corresponding computational time reduction of approximately 60 %. This study provides a novel method for investigating the dynamic behavior of the FVAWTs, which is more effective for calculating the elastic deformations of blades than traditional numerical methods.

Intelligent stability monitoring and improvement of grid‐connected converter under weighted average control

AbstractThis article presents an intelligent stability monitoring and improvement method for the grid‐connected converter system. The model of grid‐connected converter, based on the weighted average current feedback (WACF) and weighted average voltage feedforward (WAVF) control, is first established. Then, the time‐varying grid impedance and parameter perturbation of LCL‐filter are precisely identified by artificial neural network (ANN) module in real time. Furthermore, the control parameters are adaptively tuned by certain rules based on the predicted parameters to increase the high‐frequency stability margin of converter system. Simulation and experimental results are given to validate the proposed identification and parameter tuning method. The proposed method is able to monitor the real‐time operation state of the grid‐connected converter and improve the self‐adaptivity of the grid‐connected converter system against parameter perturbation.

Machine-Learning-Based Ground-Level Mobile Network Coverage Prediction Using UAV Measurements

Future mobile network operators and telecommunications authorities aim to provide reliable network coverage. Signal strength, normally assessed using standard drive tests over targeted areas, is an important factor strongly linked to user satisfaction. Drive tests are, however, time-consuming, expensive, and can be dangerous in hard-to-reach areas. An alternative safe method involves using drones or unmanned aerial vehicles (UAVs). The objective of this study was to use a drone to measure signal strength at discrete points a few meters above the ground and an artificial neural network (ANN) for processing the measured data and predicting signal strength at ground level. The drone was equipped with low-cost data logging equipment. The ANN was also used to classify specific ground locations in terms of signal coverage into poor, fair, good, and excellent. The data used in training and testing the ANN were collected by a measurement unit attached to a drone in different areas of Sultan Qaboos University campus in Muscat, Oman. A total of 12 locations with different topologies were scanned. The proposed method achieved an accuracy of 97% in predicting the ground level coverage based on measurements taken at higher altitudes. In addition, the performance of the ANN in predicting signal strength at ground level was evaluated using several test scenarios, achieving less than 3% mean square error (MSE). Additionally, data taken at different angles with respect to the vertical were also tested, and the prediction MSE was found to be less than approximately 3% for an angle of 68 degrees. Additionally, outdoor measurements were used to predict indoor coverage with an MSE of less than approximately 6%. Furthermore, in an attempt to find a globally accurate ANN module for the targeted area, all zones’ measurements were cross-tested on ANN modules trained for different zones. It was evaluated that, within the tested scenarios, an MSE of less than approximately 10% can be achieved with an ANN module trained on data from only one zone.

Public transport demand estimation by frequency adjustments

This article addresses the problem of estimating the demand for public transport from two approaches. First, we propose a bilevel optimization problem that allows estimating the demand using historical data and the observed bus frequencies. This model has been applied to small theoretical networks and the transit network of Tandil (a medium-sized city in Buenos Aires, Argentina), showing good results. However, from a practical point of view, the computation time of the algorithm used to solve the bilevel problem is long, reducing its applicability by traffic authorities. To solve this, we propose to use an artificial neural network module that allows to quickly detect if the change in demand is significant enough (for example, beyond a predefined threshold). If it is substantial, the operator can decide to run the algorithm to estimate the demand and take action to adapt the system to the new reality, for example, adapting vehicle frequencies or incorporating more vehicles into the system so that the current demand can be served. The machine learning approach allows it to be used as a fast change detection tool, avoiding running the expensive algorithm for false positives.

Cell outage compensation scheme based on hybrid genetic algorithms and neural networks

In this paper, a system for LTE Cell Outage Compensation (COC) based on hybrid Genetic Algorithms (GA) and Artificial Neural Networks (ANN) has been proposed. COC aims to minimize the impact of cell outage which leads to decrease in operator revenue and/or the customer satisfaction. The proposed system adopts an optimization module to search for an optimal setting of a set of LTE operational parameters to achieve a targeted set of key performance indicators. The optimization process always leads to good enough solutions, but it also requires a huge number of trials. So, in the proposed system, a huge set of outage scenarios is collected along with their optimal argument settings that are acquired by the optimization module and they are used to train an artificial neural network (ANN) module, which acts as an expert that can optimally act on the different situations in real-time mode. Simulation environment is set to evaluate different LTE measures and Key Performance Indicators (KPIs) on different outage scenarios. Simulation results proved the capability and robustness of the proposed system to minimize the number of users experiencing outage. Simulation results also show that the proposed system achieves optimal parameter settings without violating the overall system performance and with minimal processing time, while introducing significant impact on the performance of LTE.

Подход к проектированию нейронной сети для формирования индивидуальной траектории тестирования знаний

The paper discusses the issues of implementing an adaptive testing system based on the use of artificial neural network (INS) modules, which should solve the problem of intelligent choice of the next question, forming an individual testing trajectory. The aim of the work is to increase the accuracy of the INS to form the level of complexity of the next test question for two types of architectures – direct propagation (FNN – Feedforward Neural Network) and recurrent with long-term short-term memory (LSTM – Long-Short Term Memory). The data affecting the quality of training are analyzed, the architectures of the input layer of the direct propagation INS are considered, which have significantly improved the quality of neural networks. To solve the problem of choosing the thematic block of the question, a hybrid module structure is proposed, including the INS itself and a software module for algorithmic processing of the results obtained from the INS. A study of the feasibility of using direct propagation ANNs in comparison with the LSTM architecture was carried out, the input parameters of the network were identified, various architectures and parameters of the ANN training were compared (algorithms for updating weights, loss functions, the number of training epochs, packet sizes). The substantiation of the choice of a direct distribution network in the structure of the hybrid module for selecting a thematic block is given. The above results were obtained using the Keras high-level library, which allows you to quickly start at the initial stages of research and get the first results. Traditionally, learning has taken place over a large number of eras.

Система мониторинга параметров распределительной сети с корректирующим управлением на основе нейронной сети

Background. As a rule, the control of compensating devices is carried out in the automatic control system with sensors of network parameters and control system included in a specific node of the electrical network. However, the general state of the electrical network in terms of reactive power flows is not considered. At present, static VAR compensators are mostly spread. They are designed on the principle of an indirect compensation system, which has several disadvantages. In this regard, to optimize reactive power flows and maintain the specified voltage values in the network nodes with an abruptly variable nature of reactive power consumption, it is necessary to stabilize the required network parameters and minimize the loss of electrical energy due to the flow of reactive power. Materials and methods. To improve the energy efficiency of corrective devices, it is proposed to use static VAR compensators based on magnetic valve elements. To generate control actions, an artificial neural network (ANN) module is introduced into the monitoring to predict the capacities of consumers. Such a neural network is based on an electrical network model described by the combined matrix method. The main processor generates control signals for corrective devices. Results. The authors have proposed to generate control signals for corrective devices by processing information received from remote voltage sensors and current sensors of the distribution grid. The proposed system for monitoring the distribution grid makes it possible to stabilize the required parameters of the network for consumers, to minimize the loss of electrical energy due to the flow of reactive power. Conclusions. The block of neural networks minimizes the emergency situations and accidents. The use of the static VAR compensators based on magnetic valve elements will additionally improve the energy efficiency of the distribution network monitoring system. The use of matrix analysis of network parameters in the distribution network of monitoring system to generate control signals for corrective devices allows optimizing networks in such a way as to minimize reactive power losses to select and install reactive power compensation devices and control them. The use of SVC based on magnetic valve elements as a corrective device improves the efficiency of reactive power compensation in networks with an abruptly variable nature of electrical energy consumption.

Development of Adaptive Testing Method Based on Neurotechnologies

Purpose of the study. The aim of the study is to create neural network models of modules in an adaptive testing system to design an individual testing trajectory.The research article discusses the implementation of an adaptive testing system in terms of introducing artificial neural network modules into its composition, which should solve the problem of choosing a topic and the complexity of the next question, taking into account previous answers and the complexity of previously asked questions, as well as the connectivity of topics and response time as a factor guessing or searching for an answer, thereby forming an individual testing trajectory.Materials and methods. In the course of the study, the data that affect the quality of the solution of the problem was analyzed, the general modular structure of the system was proposed, and the main data flows entering the input of an artificial neural network (ANN) were described. To solve the problem of choosing the complexity of a question, it is proposed to use a feed-forward network, a comparison of various ANN architectures and training parameters (weight update algorithms, loss functions, number of training epochs, packet sizes) is carried out. As an alternative, the possibility of using a recurrent ANN LSTM (Long-Short Term Memory) network is considered. All results were obtained using the high-level Keras library, which allows you to quickly start at the initial stages of research and get the first results. SGD, Adam, NAdam and RMSprop implemented in Keras were compared as optimizers to achieve faster convergence. Adam showed the best results in terms of accuracy, while the MSE loss function (mean square error) was used together with the optimizer. Traditionally, training was carried out for a large number of epochs; graphs of dependences of accuracy on the number of epochs for a different number of neurons in the hidden layer were experimentally obtained.Results. Based on the study, we can conclude that the obtained accuracy of the direct propagation network of 80-85% is quite sufficient for its use in the adaptive testing system. However, it remains to answer the question of the need to improve the efficiency of an already implemented network, and, therefore, to conduct research on methods to improve the efficiency of networks, including finer tuning of parameters and learning algorithms, as well as architecture.A well-known and obvious drawback of using LSTMs is their exactingness in terms of equipment and resources, both during training (the training process takes a significant amount of time) and during startup, in our case, it is supplemented by increased requirements for the training sample and casts doubt on the advisability of further study of LSTM networks when solving this task.Conclusion. The introduction of the proposed tools will allow implementing an adaptive testing system, with an intelligent selection of questions depending on the demonstrated level of knowledge of the test person to form an individual testing trajectory in order to determine the reliable level of knowledge of the test subject for the optimal number of questions asked.

Integrated Regression Approach for Prediction of Solar Irradiance Based on Multiple Weather Factors

Solar irradiance is the most vital aspect in estimating the solar energy collection at any location. Renewable energy setup at any location is dependent on it and other ambient weather parameters. However, it is hard to predict due to unstable nature and dependence on variations in weather conditions. The correlation of ambient weather factors on the performance of solar irradiance is analysed, by collecting the data using weather API, over the year for a particular location of central India. The training of this non-linear data is carried out with hybrid regression model integrating decision tree regression with Artificial Neural Network (ANN) module. Experimentation is performed using real data of different days from different seasons of the year, also by considering different irradiance conditions. The results demonstrated significant weather factors with moderate positive and negative correlation with solar irradiance, which can be used as a helpful tool to predict it before deployment of solar energy setup.

Multi-Component Fusion Temporal Networks to Predict Vehicle Exhaust Based on Remote Monitoring Data

Vehicle exhaust prediction is of great importance for exhaust emissions control and public environment protection, and very challenging because it is influenced by various complex factors, including multi-component temporal dependencies (closeness, period, trend) and external factors, e.g., meteorological data and workday information. To address these issues, we propose a novel deep-learning-based framework, called multi-component fusion temporal networks (MCFT-Net), to collectively forecast emission concentration of carbon monoxide (CO). The proposed MCFT-Net consists of three parts, 1) a one-dimensional Convolution Neural Networks (1D-CNNs) module to capture temporal dependencies of vehicle emissions by merging closeness, period, and trend time sequences; 2) an artificial neural network (ANN) module to capture features of external factors, such as wind direction, weekday and weekend; and 3) a cascade fusion component to merge the temporal patterns, which are derived from temporal dependencies processed by multiple 1D-CNNs, and then assigned different weights according to an attention mechanism after fusion. The output of the attention operation is further combined with external features through sum and average operations to predict the final emission concentration. We evaluate the proposed MCFT-Net using two real-world vehicle exhaust datasets, ExhaustBMS and ExhaustHMS, which were collected from Beijing monitoring station (BMS) and Hefei monitoring station (HMS). The results demonstrate that our MCFT-Net outperforms 8 baseline methods, such as ARIMA, RNN, GRU, BiLSTM.

Factors Predicting the Utilization of Center-Based Cardiac Rehabilitation Program.

Although cardiac rehabilitation (CR) is clearly beneficial to improving patients’ physical functioning and reducing heart disease progression, significant proportions of patients do not complete CR programs. To evaluate the prevalence and predictors of completion of a center-based CR program in eligible cardiac patients, existing data collected from electronic medical records were used. To identify the predictors of CR completion, we used principal components analysis (PCA) and an artificial neural network (ANN) module. Among 685 patients, 61.4% (n = 421) completed the program, 31.7% (n = 217) dropped out, and 6.9% (n = 47) were referred but failed to initiate the program. PCA was conducted to consolidate baseline data into three factors—(1) psychosocial factors (depression, anxiety, and quality of life), (2) age, and (3) BMI, which explained 66.8% of the total variance. The ANN model produced similar results as the PCA. Patients who completed CR sessions had greater extremity strength and flexibility, longer six-minute walk distance, more CR knowledge, and a better quality of life. The present study demonstrated that patients who were older, obese, and who had depression, anxiety, or a low quality of life were less likely to complete the CR program.

Predicting Excavation-Induced Tunnel Response by Process-Based Modelling

Potential damages to existing tunnels represent a major concern for constructing deep excavations in urban areas. The uncertainty of subsurface conditions and the nonlinear interactions between multiple agents (e.g., soils, excavation support structures, and tunnel structures) make the prediction of the response of tunnel induced by adjacent excavations a rather difficult and complex task. This paper proposes an initiative to solve this problem by using process-based modelling, where information generated from the interaction processes between soils, structures, and excavation activities is utilized to gradually reduce uncertainty related to soil properties and to learn the interaction patterns through machine learning techniques. To illustrate such a concept, this paper presents a simple process-based model consisting of artificial neural network (ANN) module, inverse modelling module, and mechanistic module. The ANN module is trained to learn and recognize the patterns of the complex interactions between excavation deformations, its geometries and support structures, and soil properties. The inverse modelling module enables a gradual reduction of uncertainty associated with soil characterizations by accumulating field observations during the construction processes. Based on the inputs provided by the former two modules, the mechanistic module computes the response of tunnel. The effectiveness of the proposed process-based model is evaluated against high-fidelity numerical simulations and field measurements. These evaluations suggest that the strategy of combining artificial intelligence techniques with information generated during interaction processes can represent a promising approach to solve complex engineering problems in conventional industries.

A Novel Load Scheduling Mechanism Using Artificial Neural Network Based Customer Profiles in Smart Grid

In most demand response (DR) based residential load management systems, shifting a considerable amount of load in low price intervals reduces end user cost, however, it may create rebound peaks and user dissatisfaction. To overcome these problems, this work presents a novel approach to optimizing load demand and storage management in response to dynamic pricing using machine learning and optimization algorithms. Unlike traditional load scheduling mechanisms, the proposed algorithm is based on finding suggested low tariff area using artificial neural network (ANN). Where the historical load demand individualized power consumption profiles of all users and real time pricing (RTP) signal are used as input parameters for a forecasting module for training and validating the network. In a response, the ANN module provides a suggested low tariff area to all users such that the electricity tariff below the low tariff area is market based. While the users are charged high prices on the basis of a proposed load based pricing policy (LBPP) if they violate low tariff area, which is based on RTP and inclining block rate (IBR). However, we first developed the mathematical models of load, pricing and energy storage systems (ESS), which are an integral part of the optimization problem. Then, based on suggested low tariff area, the problem is formulated as a linear programming (LP) optimization problem and is solved by using both deterministic and heuristic algorithms. The proposed mechanism is validated via extensive simulations and results show the effectiveness in terms of minimizing the electricity bill as well as intercepting the creation of minimal-price peaks. Therefore, the proposed energy management scheme is beneficial to both end user and utility company.

Multi-Objective Optimization of Pulsed Nd: YAG Laser Cutting Process Using Entropy-Based ANN-PSO Model

The paper investigated the efficacy of entropy-based ANN-PSO model combining Artificial Neural Networks (ANN) and Particle Swarm Optimization (PSO) for estimation and optimization of quality characteristics associated with pulsed Nd:YAG laser cutting of aluminium alloy. In the ANN-PSO model, ANN trained using backpropagation with the Bayesian regularization algorithm is employed for estimation and computation of objective function value during optimization with PSO. The entropy method is used to compute the real weight of different output quality characteristics during formulation of the combined objective function. An experiment has been conducted based on full factorial experimental design, where cutting speed, pulse energy, and pulse width are considered as controllable input parameters while kerf width, kerf deviation, surface roughness, and material removal rate are measured as output parameters. Further, the experimental dataset has been used in the ANN-PSO model for prediction and optimization. The prediction accuracy of the ANN module is indicated by a low mean absolute error of 1.74%. Experimental validation of optimized output also results in less than 2% error only. ANOVA study suggests cutting speed as the most influencing factor.

The application of artificial neural networks (ANN) for the denaturation of meat proteins – the kinetic analysis method.

Artificial neural networks (ANN) are a common mathematical tool widely used in many research fields. Since they are applicable to non-linear relationships and do not require preliminary assumptions, they are a particularly promising tool in relation to meat processing. Thermal denaturation contains    a lot of information concerning the quality of meats. The aim was to create a methodology of kinetic analysis to obtain a quick and accurate tool for meat protein denaturation in non-isothermal conditions based on   The Coats-Redfern equation with the use of ANN. The analyses were carried out on samples of minced samples of Longissimus dorsi (pork). Thermal properties were determined using the differential scanning calorimetry (DSC) method with a Q100 TA Instruments apparatus. The data obtained was processed using the artificial neural network module in Statistica 13.0 software. The following models fit well with experimental data: F1 and F2 (r = 0.99, F Snedecor’s F statistics 836943.20 and 971947.41 respectively). Deviations from experimental conversion degrees were higher for model F2, while for F1, good conformity was obtained across the whole range of α(T). This preliminary study confirmed that methods of traditional kinetics of processes in non-isothermal conditions based on the Coats-Redfern equation can be successfully applied to meat protein denaturation. The method of kinetic analysis allows a high level of accuracy to be achieved and meets the requirements of an efficient engineering tool. &nbsp.

Optimization of the Process for Producing Biomass and Exopolysaccharide from the King Tuber Oyster Mushroom, Pleurotus tuber-regium (Agaricomycetes), for Biotechnological Applications.

The optimization of microbial growth for biotechnological purposes traditionally requires an approach that uses only one variable at a time, which has many drawbacks. This research used a completely randomized approach to optimize carbon and nitrogen nutrient requirements and growth factors (pH and temperature) for Pleurotus tuber-regium in order to optimally produce biomass and extracellular polysaccharide (EPS) in shake-flask cultures. An artificial neural network (ANN) module was used to simulate the fungus-growing process and hence determine optimal conditions. The experiments demonstrated the effectiveness of the EPS fraction from P. tuber-regium in preserving hepatic cells against paracetamol-induced damage. Totals of 0.699 g biomass and 0.291 g EPS per 100 mL medium were obtained, whereas the ANN predicted 0.750 g biomass and 0.300 g EPS per 100 mL medium, thereby achieving 93.20% predictability for biomass and 73.00% predictability for EPS. Conditions for optimal EPS and biomass production for P. tuber-regium were quite different. Rat hepatic cells that had been fortified with the EPS fraction from P. tuber-regium were effectively preserved against liver damage. By using a mathematical approach, this study established optimal fermentation conditions for mycelia biomass and EPS production by P. tuber-regium and the relevant biotechnological implications.

Mobile cloud computing based stroke healthcare system

Information technology has recently seen a huge progress in innovative healthcare technologies that rendered healthcare data bigger. Connectivity on 7/24 basis between human to device and device to device have a crucial role in individuals’ lives. Therefore, Mobile Cloud System (MCC) has become an indispensable tool. Parallel with the rapid developments in the Internet of Things, convergence has become an important issue. Our proposed method, accordingly, can be converged with mobile-cloud environments with cloud computing in handling healthcare information. This study uses Virtual Dedicated Server (VDS) as 4 VCPU and 8 GB RAM and proposes a model based on the Android based mobile phones for stroke patients with cardioembolic (689) and cryptogenic (528) subtypes. The system set up through this study has two basic application elements which are mobile application and server application. Artificial Neural Network (ANN) module is beneficial for classifying the two stroke subtypes while server application is used for saving the data from the patients. Accordingly, our model guarantees availability, security, and scalability as a system for stroke patients applying Stroke dataset for ANN algorithm, Multilayer Perceptron Algorithm (MLP), which has been done for the first time in literature with big data in this scope. The main contributions are: (1) The outcomes will display an individual unique social insurance framework. (2) The outcomes will be utilized for the distinguishing proof of stroke-related data to be gathered by cell phones that are Android based. (3) Stroke patients will find out about their condition of well-being through an ANN application programming interface, which will provide a sort of organization for the patients. Overall, an efficient and user-friendly stroke determination human services framework has been presented through this Healthcare System for patients.

A novel modular ANN architecture for efficient monitoring of gases/odours in real-time

Data pre-processing is tremendously used for enhanced classification of gases. However, it suppresses the concentration variances of different gas samples. A classical solution of using single artificial neural network (ANN) architecture is also inefficient and renders degraded quantification. In this paper, a novel modular ANN design has been proposed to provide an efficient and scalable solution in real–time. Here, two separate ANN blocks viz. classifier block and quantifier block have been used to provide efficient and scalable gas monitoring in real—time. The classifier ANN consists of two stages. In the first stage, the Net1-NDSRT has been trained to transform raw sensor responses into corresponding virtual multi-sensor responses using normalized difference sensor response transformation (NDSRT). These responses have been fed to the second stage (i.e., Net2-classifier). The Net2-classifier has been trained to classify various gas samples to their respective class. Further, the quantifier block has parallel ANN modules, multiplexed to quantify each gas. Therefore, the classifier ANN decides class and quantifier ANN decides the exact quantity of the gas/odor present in the respective sample of that class.