Search

Safe and efficient navigation is critical for a mobile robot in a highly constrained workspace. Autonomous navigation is to be performed safely and robustly in the environment map with obstacles of various geometric shapes, sizes and colors positioned at random locations. In this paper, we present an approach to perform autonomous navigation by detecting the obstacles in the map and by generating auxiliary collision-free waypoints in obstacle-free space map. In achieving this, the object detection is done using SSDMobileNetV2 model and auxiliary collision-free navigation waypoints are generated using the Deepway neural network model. Further, the RRT path planner is applied to analyze the waypoints generated and to find the a global path between start and goal locations. An optimal local path is achieved using the A* path planner. Extensive simulations of various scenarios are performed and the proposed model is evaluated. The results reveal that the proposed model achieves significant improvements in terms of time, distance and F1-score. [ABSTRACT FROM AUTHOR]

Email phishing is a social engineering scheme that uses spoofed emails intended to trick the user into disclosing legitimate business and personal credentials. Many phishing email detection techniques exist based on machine learning, deep learning, and word embedding. In this paper, we propose a new technique for the detection of phishing emails using word embedding (Word2Vec, FastText, and TF-IDF) and deep learning techniques (DNN and BiLSTM network). Our proposed technique makes use of only four header based (From, Returnpath, Subject, Message-ID) features of the emails for the email classification. We applied several word embeddings for the evaluation of our models. From the experimental evaluation, we observed that the DNN model with FastText-SkipGram achieved an accuracy of 99.52% and BiLSTM model with FastText-SkipGram achieved an accuracy of 99.42%. Among these two techniques, DNN outperformed BiLSTM using the same word embedding (FastText-SkipGram) techniques with an accuracy of 99.52%. [ABSTRACT FROM AUTHOR]

Blasting has been one of the most important contributors of mining since the start of mineral extraction and excavation. Along with fragmentation of the rocks, blasting also produces an excess of energy in the form of heat and vibration. Due to the spread of the vibration, the surrounding environment gets affected. Therefore, this paper aims to minimize the vibration to reduce the impact of ground vibration happening due to the mine blasting. In order to optimize the blasting parameters, a good predictor of such vibration is to be created. Hence, the paper compares a lot of predictors including empirical formulas and ANNs (Artificial Neural Networks). The best performing predictor has been used as the objective function for the optimization of parameters. Among the various optimization methods, the firefly algorithm proved to be a very good optimizer. Therefore, it was used to optimize the field parameters and implemented. The resulting optimized parameters showed a significant reduction in the ground vibration of 14.58%. [ABSTRACT FROM AUTHOR]

Ejectors are implemented in energy conservation applications such as power and refrigeration systems and fuel cell stacks due to their passive nature and geometrical simplicity. Ejectors work on the principle of thermal compression that utilizes low-grade energy to produce a compression effect. A low-enthalpy secondary fluid gets compressed through gasdynamic interactions with a co-flowing high-enthalpy primary flow in ejectors. The aerodynamic choking of the secondary flow within an ejector leads to two modes of ejector operation: (a) critical flow regime and (b) mixed flow regime. Several low-fidelity models for analyzing ejectors have been proposed in the literature. These models are adequate for the rapid design of specific categories of ejectors. However, they yield notable deviations of 20-25% with experimental measurements for different operating conditions. On the other hand, computational fluid dynamics (CFD) simulations for ejectors are computationally expensive. Furthermore, they require a careful selection of numerical solvers and turbulence models to predict performance and flow characteristics accurately. This paper presents a data-driven artificial neural network (ANN) model to predict the critical parameters of supersonic ejectors. The model is trained using experimental measurement for air ejectors at various operating and geometrical parameters. The ANN model consists of five input parameters, representing operating and geometrical parameters of ejectors to estimate two output parameters: (a) entrainment ratio and (b) operating regime. The trained ANN model predicts the entrainment ratio with a maximum deviation of about 7% and classifies the ejector operational mode with an accuracy of 100%. [ABSTRACT FROM AUTHOR]

This paper develops an artificial neural network (ANN) model for predicting the speed limit of cars moving on corroded steel girder bridges. A total of 311 datasets, which are created from the proposed analytical model, are used to construct the ANN model. The input parameters of the proposed ANN model include the car's weight, diameter of tires, and the dimensions of girder bridges, which are the top flange width, top flange thickness, bottom flange width, bottom flange thickness, girder height, web thickness, and the span of girder. Meanwhile, the speed limit of cars is the output variable of the ANN model. The results show that the speed limitation of cars on the corrosive steel girder bridge is reduced pronounced after 100 years. Sensitivity analyses reveal that the influential parameters with respect to the maximum speed are the girder height and tire diameter, whereas the girder weigh and girder span have negative effects on the speed limit of cars. Moreover, a mathematical formula and a graphical user interface program are developed to calculate the speed limits of cars on the corrosive steel girder bridge. These practical tools are very helpful for practitioners in determining the speed limit of cars moving on steel girder bridges subjected to corrosion. [ABSTRACT FROM AUTHOR]

This paper presents the modeling of tensile properties of cast duplex stainless steel using the artificial neural network model, exclusively developed for this work. For this research, melts of varying chemical composition were poured, heat treated and tested for the tensile properties. The artificial neural network model was developed using the composition as input and tensile properties as the targets. The prediction performances of the models were evaluated by the mean absolute error (MAE), and the model with less MAE was considered for predicting the properties. Multilayer feed forward back propagation models with two hidden layers were implemented to predict the tensile properties of cast duplex stainless steel. The ANN model developed and validated shows a reliable correlation between chemical compositions and tensile properties. [ABSTRACT FROM AUTHOR]

Mechanical power transmission systems are an indispensable part of the industrial process. The most complex equipment of these processes is the gear systems. Among the gear systems the worm gearboxes are used in various applications, especially those that need high transmission ratios in one reduction stage. However, worm wheel manifests defects easily because it is made of soft material, in comparison with the worm. The stress on each tooth surface may increase because of overload, shock load, cyclic load change, gear misalignment, etc. This often causes pitting faults in worm gearboxes. This paper focuses on the detection of localized pitting damages in a worm gearbox by a vibration visualization method and artificial neural networks (ANNs). For this purpose, the vibration signals are converted into an image to display and detect pitting defects on the worm wheel tooth surface. In addition, statistical parameters of vibration signals in the time and frequency domains are used as an input to ANN for multi-class recognition. Later, the results obtained from ANN are compared for both axial and radial vibration. It is found that the ANN can classify with high accuracy for any sample of the vibration data obtained from the radial direction according to fault severity levels. [ABSTRACT FROM AUTHOR]

Dual fuel engines are being used these days to overcome shortage of fossil fuels and fulfill stringent exhaust gas emission regulations. They have several advantages over conventional diesel engines. In this context, this paper makes use of experimental results obtained from a dual fuel engine for developing models to predict performance and emission parameters. Conventional modelling efforts to understand the relationships between the input and the output variables, requires thermodynamic analysis which is complex and time consuming. As a result, efforts have been made to use artificial intelligence modelling techniques like fuzzy logic, Artificial Neural Network (ANN), Genetic Algorithm (GA), etc. This paper uses a neuro fuzzy modelling technique, Adaptive Neuro Fuzzy Inference System (ANFIS) for developing prediction models for performance and emission parameter of a dual fuel engine. Percentage load, percentage Liquefied Petroleum Gas (LPG) and Injection Timing (IT) have been used as input parameters, whereas output parameters include Brake Specific Energy Consumption (BSEC), Brake Thermal Efficiency (BTE), Exhaust Gas Temperature (EGT) and smoke. In order to further improve the prediction accuracy of the model, GA has been used to optimize ANFIS. GA optimized ANFIS gives higher prediction accuracy of more than 90% for all parameters except for smoke, where there is a substantial improvement from 46.67% to 73.33%, when compared to conventional ANFIS model. [ABSTRACT FROM AUTHOR]

Content-based video retrieval system aims at assisting a user to retrieve targeted video sequence in a large database. Most of the search engines use textual annotations to retrieve videos. These types of engines offer a low-level abstraction while the user seeks high-level semantics. Bridging this type of semantic gap in video retrieval remains an important challenge. In this paper, colour, texture and shapes are considered to be low-level features and motion is a high-level feature. Colour histograms convert the RGB colour space into YcbCr and extract hue and saturation values from frames. After colour extraction, filter mask is applied and gradient value is computed. Gradient and threshold values are compared to draw the edge map. Edges are smoothed for sharpening to remove the unnecessary connected components. These diverse shapes are then extracted and stored in shape feature vectors. Finally, an SVM classifier is used for classification of low-level features. For high-level features, depth images are extracted for motion feature identification and classification is done via echo state neural networks (ESN). ESN are a supervised learning technique and follow the principle of recurrent neural networks. ESN are well known for time series classification and also proved their effective performance in gesture detection. By combining the existing algorithms, a high-performance multimedia event detection system is constructed. The effectiveness and efficiency of proposed event detection mechanism is validated using MSR 3D action pair dataset. Experimental results show that the detection accuracy of proposed combination is better than those of other algorithms [ABSTRACT FROM AUTHOR]

In this paper, a quantum based binary neural network algorithm is proposed, named as novel quantum binary neural network algorithm (NQ-BNN). It forms a neural network structure by deciding weights and separability parameter in quantum based manner. Quantum computing concept represents solution probabilistically and gives large search space to find optimal value of required parameters using Gaussian random number generator. The neural network structure forms constructively having three number of layers input layer: hidden layer and output layer. A constructive way of deciding the network eliminates the unnecessary training of neural network. A new parameter that is a quantum separability parameter (QSP) is introduced here, which finds an optimal separability plane to classify input samples. During learning, it searches for an optimal separability plane. This parameter is taken as the threshold of neuron for learning of neural network. This algorithm is tested with three benchmark datasets and produces improved results than existing quantum inspired and other classification approaches. [ABSTRACT FROM AUTHOR]

This paper discusses the application of neural networks for developing different speech systems. Prosodic parameters of speech at syllable level depend on positional, contextual and phonological features of the syllables. In this paper, neural networks are explored to model the prosodic parameters of the syllables from their positional, contextual and phonological features. The prosodic parameters considered in this work are duration and sequence of pitch ( F) values of the syllables. These prosody models are further examined for applications such as text to speech synthesis, speech recognition, speaker recognition and language identification. Neural network models in voice conversion system are explored for capturing the mapping functions between source and target speakers at source, system and prosodic levels. We have also used neural network models for characterizing the emotions present in speech. For identification of dialects in Hindi, neural network models are used to capture the dialect specific information from spectral and prosodic features of speech. [ABSTRACT FROM AUTHOR]

There is no direct method for design of beams. In general the dimensions of the beam and reinforcement are initially assumed and then the interaction formula is used to verify the suitability of chosen dimensions. This approach necessitates few trials for coming up with an economical and safe design. This paper demonstrates the applicability of Artificial Neural Networks (ANN) and Genetic Algorithms (GA) for the design of beams subjected to moment and shear. A hybrid neural network model which combines the features of feed forward neural networks and genetic algorithms has been developed for the design of beam subjected to moment and shear. The network has been trained with design data obtained from design experts in the field. The hybrid neural network model learned the design of beam in just 1000 training cycles. After successful learning, the model predicted the depth of the beam, area of steel, spacing of stirrups required for new problems with accuracy satisfying all design constraints. The various stages involved in the development of a genetic algorithm based neural network model are addressed at length in this paper. [ABSTRACT FROM AUTHOR]

This paper investigates the application of induction motor stator current signature analysis (MCSA) using Park's transform for the detection of rolling element bearing damages in three-phase induction motor. The paper first discusses bearing faults and Park's transform, and then gives a brief overview of the radial basis function (RBF) neural networks algorithm. Finally, system information and the experimental results are presented. Data acquisition and Park's transform algorithm are achieved by using LabVIEW and the neural network algorithm is achieved by using MATLAB programming language. Experimental results show that it is possible to detect bearing damage in induction motors using an ANN algorithm. [ABSTRACT FROM AUTHOR]

Time series data (TSD) originating from different applications have dissimilar characteristics. Hence for prediction of TSD, diversified varieties of prediction models exist. In many applications, hybrid models provide more accurate predictions than individual models. One such hybrid model, namely auto regressive integrated moving average - artificial neural network (ARIMA-ANN) is devised in many different ways in the literature. However, the prediction accuracy of hybrid ARIMA-ANN model can be further improved by devising suitable processing techniques. In this paper, a hybrid ARIMA-ANN model is proposed, which combines the concepts of the recently developed moving average (MA) filter based hybrid ARIMA-ANN model, with a processing technique involving a partitioning-interpolation (PI) step. The improved prediction accuracy of the proposed PI based hybrid ARIMA-ANN model is justified using a simulation experiment. Further, on different experimental TSD like sunspots TSD and electricity price TSD, the proposed hybrid model is applied along with four existing state-of-the-art models and it is found that the proposed model outperforms all the others, and hence is a promising model for TSD prediction. [ABSTRACT FROM AUTHOR]

Weld bead plays an important role in determining the quality of welding particularly in high heat input processes. This research paper presents the development of multiple regression analysis (MRA) and artificial neural network (ANN) models to predict weld bead geometry and HAZ width in submerged arc welding process. Design of experiments is based on Taguchi's L16 orthogonal array by varying wire feed rate, transverse speed and stick out to develop a multiple regression model, which has been checked for adequacy and significance. Also, ANN model was accomplished with the back propagation approach in MATLAB program to predict bead geometry and HAZ width. Finally, the results of two prediction models were compared and analyzed. It is found that the error related to the prediction of bead geometry and HAZ width is smaller in ANN than MRA. [ABSTRACT FROM AUTHOR]

Intermediate band solar cells (IBSCS) is a relatively new solar cell concept. The theoretical conversion efficiency limit for IBSCS is predicted to be 63.2% with blackbody illumination and 65.1% with AM1.5 spectrum, comparable to the theoretical efficiency for optimized triple junction solar cells with efficiencies of 63.8% and 67.0% under blackbody and AM1.5 illumination, respectively. This paper presents a structure of IBSC based on ZnTe:O. The proposed model uses irradiance and temperature as input parameters and the output characteristics of the structure are used as a prototypical example. So, in this work the artificial neural networks (ANNs) and the analog behavior modeling (ABM) of PSpice are implemented in order to model the IBSC. In addition, we have used the bias matrix and the weights matrix obtained by training to establish the IBSCS model on PSPICE simulator. This method represents an advantage by using a small representative database. Therefore, the obtained results of our model can be used in an electrical simulator. Thus, this method can be extended to other solar cells for motivating experimental efforts to realize these promising photovoltaic devices for low cost and high efficiency. [ABSTRACT FROM AUTHOR]

The network of solar power plants in distributed power system (in India) is growing exponentially. Since tilt angle affects the energy collection by solar panels, the conduction of experiments to find optimum tilt angle is expensive and time consuming in each location. Although different non-linear, empirical models have been proposed by different researchers in India, they have too many constraints and needs complex and rigorous computational effort each time. In this paper, a data driven approach such as ANN estimator has been proposed to estimate βopt at which solar energy collection of Photo-Voltaic Array (PVA) will be maximum at selected cities of India. The latitude (φ) elevation (EL) from sea level and monthly mean hourly and daily global solar irradiance (Hg) of location are taken into account for this study. The ANN estimator takes Hg, φ and EL of site as inputs which are easily available and estimate optimum tilt angle almost instantaneously while testing. The proposed ANN estimator results are compared with analytical results. To validate the performance of ANN estimator results, statistical analysis study is carried out. Where, two statistical approaches such as descriptive method and Altman-Bland methods are applied. The ANA estimator results are found much close to ANA results at 95% confidence interval under statistical study. [ABSTRACT FROM AUTHOR]

This paper presents a particle swarm optimization (PSO) technique to train an artificial neural network (ANN) for prediction of flank wear in drilling, and compares the network performance with that of the back propagation neural network (BPNN). This analysis is carried out following a series of experiments employing high speed steel (HSS) drills for drilling on mild steel workpieces, under different sets of cutting conditions and noting the root mean square (RMS) value of spindle motor current as well as the average flank wear in each case. The results show that the PSO trained ANN not only gives better prediction results and reduced computational times compared to the BPNN, it is also a more robust model, being free of getting trapped in local optimum solutions unlike the latter. Besides, it offers the advantages of a straight-forward logic, simple realization and underlying intelligence. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new pattern classification system by combining Temporal features with Fuzzy Min-Max (TFMM) neural network based classifier for effective decision support in medical diagnosis. Moreover, a Particle Swarm Optimization (PSO) algorithm based rule extractor is also proposed in this work for improving the detection accuracy. Intelligent fuzzy rules are extracted from the temporal features with Fuzzy Min-Max neural network based classifier, and then PSO rule extractor is used to minimize the number of features in the extracted rules. We empirically evaluated the effectiveness of the proposed TFMM-PSO system using the UCI Machine Learning Repository Data Set. The results are analysed and compared with other published results. In addition, the detection accuracy is validated by using the ten-fold cross validation. [ABSTRACT FROM AUTHOR]

An attempt is made in this paper to report how a supervised methodology has been adopted for the task of Word Sense Disambiguation (WSD) in Bengali with necessary modifications. At the initial stage, four commonly used supervised methods, Decision Tree (DT), Support Vector Machine (SVM), Artificial Neural Network (ANN) and Naïve Bayes (NB), are developed at the baseline. These algorithms are applied individually on a data set of 13 most frequently used Bengali ambiguous words. On experimental basis, the baseline strategy is modified with two extensions: (a) inclusion of lemmatization process into the system and (b) bootstrapping of the operational process. As a result, the levels of accuracy of the baseline methods are slightly improved, which is a positive signal for the whole process of disambiguation as it opens scope for further modification of the existing method for better result. In this experiment, the data sets are prepared from the Bengali corpus, developed in the Technology Development for Indian Languages (TDIL) project of the Government of India and from the Bengali WordNet, which is developed at the Indian Statistical Institute, Kolkata. The paper reports the challenges and pitfalls of the work that have been closely observed during the experiment. [ABSTRACT FROM AUTHOR]

This paper reports the design and implementation of an intelligent system for detection of microcalcification from digital mammograms. A neuron based thresholding strategy has been developed to reduce the number of candidate pixels. A back propagation neural network (BPNN) classifier has been used to classify the pixels into positive (affected) and normal ones. The false positives generated in the process are eliminated using the connected component analysis and the elongated component removal algorithms in succession. Suspected areas of microcalcification are detected and marked on the mammogram. The system was rigorously tested for the available images and was found to be quite robust, consistent and fast in detection. The output image with prompts generated by the system can form an important input to a radiologist for the final diagnosis. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new H synchronization strategy, called a Radial Basis Function Neural Network H synchronization (RBFNNHS) strategy, for unknown chaotic systems in the presence of external disturbance. In the proposed framework, a radial basis function neural network (RBFNN) is constructed as an alternative to approximate the unknown nonlinear function of the chaotic system. Based on this neural network and linear matrix inequality (LMI) formulation, the RBFNNHS controller and the learning laws are presented to reduce the effect of disturbance to an H norm constraint. It is shown that finding the RBFNNHS controller and the learning laws can be transformed into the LMI problem and solved using the convex optimization method. A numerical example is presented to demonstrate the validity of the proposed RBFNNHS scheme. [ABSTRACT FROM AUTHOR]

Optical Character Recognition (OCR) systems have been effectively developed for the recognition of printed characters of non-Indian languages. Efforts are on the way for the development of efficient OCR systems for Indian languages, especially for Kannada, a popular South Indian language. We present in this paper an OCR system developed for the recognition of basic characters (vowels and consonants) in printed Kannada text, which can handle different font sizes and font types. Hu's invariant moments and Zernike moments that have been progressively used in pattern recognition are used in our system to extract the features of printed Kannada characters. Neural classifiers have been effectively used for the classification of characters based on moment features. An encouraging recognition rate of 96⋅8% has been obtained. The system methodology can be extended for the recognition of other south Indian languages, especially for Telugu. [ABSTRACT FROM AUTHOR]

Automatic identification of a meaning of a word in a context is termed as Word Sense Disambiguation (WSD). It is a vital and hard artificial intelligence problem used in several natural language processing applications like machine translation, question answering, information retrieval, etc. In this paper, an explicit WSD system for Punjabi language using supervised techniques has been analysed. The sense tagged corpus of 150 ambiguous Punjabi noun words has been manually prepared. The six supervised machine learning techniques Decision List, Decision Tree, Naive Bayes, K-Nearest Neighbour (K-NN), Random Forest and Support Vector Machines (SVM) have been investigated in this proposed work. Every classifier has used same feature space encompassing lexical (unigram, bigram, collocations, and co-occurrence) and syntactic (part of speech) count based features. The semantic features of Punjabi language have been devised from the unlabelled Punjabi Wikipedia text using word2vec continuous bag of word and skip gram shallow neural network models. Two deep learning neural network classifiers multilayer perceptron and long short term memory have also been applied for WSD of Punjabi words. The word embedding features have experimented on six classifiers for the Punjabi WSD task. It has been observed that the performance of the supervised classifiers applied for the WSD task of Punjabi language has been enhanced with the application of word embedding features. In this work, an accuracy of 84% has been achieved by LSTM classifier using word embedding feature. [ABSTRACT FROM AUTHOR]

Detection and reading of the text from natural images is a difficult computer vision task, which is essential in a variety of emerging applications. Document character recognition is one such problem, which has been widely studied and documented by many machine learning and computer vision researchers, which is practically used for solving applications like recognizing handwritten digits. In this paper, a new approach for efficiently extracting cognition out of a total of 56 different classes of Handwritten Manipuri Meetei-Mayek (HMMM) (an Indian language) is described. Although character recognition algorithms have been researched and developed for other Indian scripts, no research work has been reported so far for recognizing all the characters of the Manipuri Meetei-Mayek (MMM). The work begins with a thorough analysis of the recognition task using a single hidden layer type Multilayer Perceptron Feedforward Artificial Neural Network with Histogram of Oriented Gradient (HOG) feature descriptors. After reviewing the level of accuracy and time it takes to train the network, the limitations are experimentally removed using multiple-sized cell grids using HOG descriptors. HOG, being a gradient-based descriptor, is very efficient in data discrimination and very stable with illumination variation. For efficient classification of the HOG features of the MMM, a linear multiclass support vector machine (SVM) classifier has been proposed for classifying the different offline characters because of its simplicity and speed. The classification based on linear multiclass SVM yielded a very high overall accuracy of 96.928% [ABSTRACT FROM AUTHOR]

This paper reports a new approach for clustering melodies in audio music collections of both western as well as Indian background and its application to genre classification. A simple yet effective new classification technique called mean centred clustering (MCC) is discussed. The proposed technique maximizes the distance between different clusters and reduces the spread of data in individual clusters. The use of MCC as a preprocessing technique for conventional classifiers like artificial neural network (ANN) and support vector machine (SVM) is also demonstrated. It is observed that the MCC-based classifier outperforms the classifiers based on conventional techniques such as Principal Component Analysis (PCA) and discrete cosine transform (DCT). Extensive simulation results obtained on different data sets of western genre (ISMIR) and classical Indian ragas are used to validate the efficiency of proposed MCC-based clustering algorithm and ANN/SVM classifiers based on MCC. As an additional endeavour, the performance of MCC on preprocessed data from PCA and DCT is studied. Based on simulation results, it is concluded that the application of MCC on DCT coefficients resulted in the highest overall classification success rate over different architectures of the classifiers. [ABSTRACT FROM AUTHOR]

Biometric systems have gained considerable significance as they are highly employed in the security applications. Achieving human recognition is easier and cheaper and the single modality employed for the recognition faces a lot of challenges due to the environmental factors. Thus, the paper proposes a multimodal recognition system based on the Multi-Support Vector Neural Network (MSVNN). The algorithm proposed is the Glowworm Penguin Search Optimization Algorithm (GwPeSOA), which is a modification of the Glowworm Optimization Algorithm (GOA) with the Penguin Search Optimization Algorithm (PeSOA). The proposed method employs two modalities: the ear and the finger vein modalities; the features of the ear image are obtained using the proposed BiComp masking method of feature extraction, whereas the features from the finger vein are extracted using the Repeated Line Tracking (RLT) method. The features obtained are applied to the MSVNN classifier to recognize the person with good accuracy and the proposed BiComp Mask offers robust features for the extraction. The experimentation using the proposed method attained a better accuracy, specificity and sensitivity at a rate of 0.95, 0.95 and 0.9868, respectively. [ABSTRACT FROM AUTHOR]

Pulsating heat pipe (PHP) is one of the prominent research areas in the family of heat pipes. Heat transfer and fluid flow mechanism associated with PHP are quite involved. The analytical models are simple in nature and limited in scope and applicability. The regression models and Artificial Neural Network (ANN) are also limited to a number of input parameters, their ranges and accuracy. The present paper discusses the thermal performance prediction models of a PHP based on ANN and RCA approach. Totally 1652 experimental data are collected from the literature (2003-2017). Nine major influencing input variables are considered for the first time to develop the prediction models. Feed-forward back-propagation neural network is developed and verified. Backward regression analysis is used in RCA-based regression model. Linear and power-law regression correlations are developed for input heat flux in terms of dimensionless Kutateladze (Ku) number, which is a function of Jakob number (Ja), Morton number (Mo), Bond number (Bo), Prandtl number (Pr) and geometry of a PHP. The prediction accuracy of present regression models (R2 = 0.95) is observed to be better as compared with literature-based correlations. [ABSTRACT FROM AUTHOR]