Classification of data on stacked autoencoder using modified sigmoid activation function

Mechanical sifting and manual grading have conventionally been utilised to assess the grade of aggregates. Nonetheless, such evaluations require a range of mechanical, chemical, and physical examinations, typically conducted manually, resulting in a process that is tedious, subjective, and labour-intensive. This research aims to provide an image-based classification system for the categorisation of aggregates. An artifi cial neural network (ANN) has been used to analyse the acquired images and categorise their shapes. The composite images are obtained and utilised as the input parameter for prediction prior to the thresholding step. The Log-sigmoid (Logsig) activation function, utilised in a Multilayer Perceptron (MLP) network, exhibits a lower mean square error (MSE) and superior regression performance relative to the Pureline activation functions. The Logsig-based network has a MSE of 1.7473 and a regression capability of 0.9521.

This paper presents the iris recognition system for biometric personal identification using neural network. Personal identification consists of localization of the iris region and generation of a data set of iris images followed by iris pattern recognition. In this paper, a fast algorithm is proposed for the localization of the inner and outer boundaries of the iris region. Located iris is extracted from an eye image, and, after normalization and enhancement, it is represented by a data set. Using this data set a Neural Network (NN) is used for the classification of iris patterns. The adaptive learning strategy is applied for training of the NN. The results of simulations illustrate the effectiveness of the neural system in personal identification.

The convolutional neural network (CNN) has been widely used in image recognition field due to its good performance. This paper proposes a facial expression recognition method based on the CNN model. Regarding the complexity of the hierarchic structure of the CNN model, the activation function is its core, because the nonlinear ability of the activation function really makes the deep neural network have authentic artificial intelligence. Among common activation functions, the ReLu function is one of the best of them, but it also has some shortcomings. Since the derivative of the ReLu function is always zero when the input value is negative, it is likely to appear as the phenomenon of neuronal necrosis. In order to solve the above problem, the influence of the activation function in the CNN model is studied in this paper. According to the design principle of the activation function in CNN model, a new piecewise activation function is proposed. Five common activation functions (i.e., sigmoid, tanh, ReLu, leaky ReLus and softplus–ReLu, plus the new activation function) have been analysed and compared in facial expression recognition tasks based on the Keras framework. The Experimental results on two public facial expression databases (i.e., JAFFE and FER2013) show that the convolutional neural network based on the improved activation function has a better performance than most-of-the-art activation functions.

This paper presents a deep-learning-based method for iris presentation attack detection (PAD) when iris images are obtained from deceased people. Post-mortem iris recognition, despite being a potentially useful method that could aid forensic identification, can also pose challenges when used inappropriately, i.e. utilizing a dead organ of a person in an unauthorized way. Our approach is based on the VGG-16 architecture fine-tuned with a database of 574 post-mortem, near-infrared iris images from the WarsawBioBase-PostMortem-Iris-v1 database, complemented by a dataset of 256 images of live irises, collected within the scope of this study. Experiments described in this paper show that our approach is able to correctly classify iris images as either representing a live or a dead eye in almost 99% of the trials, averaged over 20 subject-disjoint, train/test splits. We also show that the post-mortem iris detection accuracy increases as time since death elapses, and that we are able to construct a classification system with APCER=0%@BPCER≈1% (Attack Presentation and Bona Fide Presentation Classification Error Rates, respectively) when only post-mortem samples collected at least 16 hours post-mortem are considered. Since acquisitions of ante- and post-mortem samples differ significantly, we applied countermeasures to minimize bias in our classification methodology caused by image properties that are not related to the PAD. This included using the same iris sensor in collection of ante- and post-mortem samples, and analysis of class activation maps to ensure that discriminant iris regions utilized by our classifier are related to properties of the eye, and not to those of the acquisition protocol. This paper offers the first known to us PAD method in a postmortem setting, together with an explanation of the decisions made by the convolutional neural network. Along with the paper we offer source codes, weights of the trained network, and a dataset of live iris images to facilitate reproducibility and further research.

This research mainly based on multilayer perceptron (MLP) neural networks technique of data mining to forecast the wheat crop yield at the district level. There are many statistical and simulation models available, but the proposed algorithm with new activation function provides promising results in a shorter time with more accuracy. Sigmoid and hyperbolic tangent activation functions are widely used in the neural network. The activation functions play an important role in the neural network learning algorithm. The main objective of the proposed work is to develop an amended MLP neural network with new activation function and revised random weights and bias values for crop yield estimation by using the different weather parameter datasets. MLP model has been tested by existing activation functions and newly created activation functions with different cases including weights and bias values. In this research study, we evaluate the result of different activation functions and recommend some new simple activation functions, named DharaSig, DharaSigm and SHBSig, to improve the performance of neural networks and accurate results. Also, three new activation functions created with little variations in the DharaSig function named DharaSig1, DharaSig2 and DharaSig3. In this research study, variable numbers of hidden layers are tested with the variable number of neurons per hidden layer for the agriculture dataset. Variable values of momentum, seed and learning rate are also used in this study. Experiments show that newly created activation functions provide better results compared to ‘sigmoid’ default neural network activation function for agriculture datasets.

In this article, the artificial intelligence techniques have been used for the solution of Falkner–Skan (FS) equations based on neural networks optimized with three methods including active set technique, sequential quadratic programming and genetic algorithms (GA) hybridization. Log-sigmoid activation function is used in artificial neural network architecture. The proposed techniques are applied to a number of cases for Falkner–Skan problems, and results were compared with GA hybrid results in all cases and were found accurate. The level of accuracy is examined through statistical analyses based on a sufficiently large number of independent runs.

We describe and analyze the performance of a non-ideal iris recognition system. The system is designed to process non-ideal iris images in two steps: (i) estimation of the gaze direction and (ii) processing and encoding of the rotated iris image. We use two objective functions to estimate the gaze direction: Hamming distance and Daugman's integro-differential operator and determine an estimated angle by picking the value that optimizes the selected objective function. After the angle is estimated, the off-angle iris image undergoes geometric transformations involving the estimated angle and is further processed as if it were a frontal view image. The encoding technique developed in this work is based on application of the global independent component analysis (ICA) to masked iris images. We use two datasets: CASIA dataset and a special dataset of off-angle iris images collected at WVU to verify the performance of the encoding technique and angle estimator, respectively. A series of receiver operating characteristics (ROCs) demonstrates various effects on the performance of the non-ideal iris based recognition system implementing the global ICA encoding.

A number of ANN methods are used, but BP is the most commonly used algorithms to train ANNs by using the gradient descent method. Two main problems which exist in BP are slow convergence and local minima. To overcome these existing problems, global search techniques are used. This research work proposed new hybrid flower pollination based back propagation HFPBP with a modified activation function and FPBP algorithm with log-sigmoid activation function. The proposed HFPBP and FPBP algorithm search within the search space first and finds the best sub-search space. The exploration method followed in the proposed HFPBP and FPBP allows it to converge to a global optimum solution with more efficiency than the standard BPNN. The results obtained from proposed algorithms are evaluated and compared on three benchmark classification datasets, Thyroid, diabetes, and glass with standard BPNN, ABCNN, and ABC-BP algorithms. The simulation results obtained from the algorithms show that the proposed algorithm performance is better in terms of lowest MSE (0.0005) and high accuracy (99.97%).

An artificial neural network(ANN) is a type of computing system that mimics the functioning of the neural networks in a biological brain. In this paper, an ANN has been simulated on an Field Programmable Gate Array (FPGA) for the application of handwritten digit recognition using the sigmoid and hyperbolic tangent(tanh) activation functions. Both software and hardware simulations have been carried out, using python and Verilog HDL respectively. The two activation functions were implemented on an Artix-7 FPGA. A comparison has been made between the sigmoid and tanh activation functions based on speed, accuracy, and hardware required, and it has been inferred that the tanh function is best for the application of handwritten digit recognition as it has 3% higher accuracy and uses 5 less LUTs than the sigmoid activation function.

A neural network classifier is sought. Classical neural network neurons are aggregations of a weight multiplied by an input value and then controlled via an activation function. This paper learns everything within the neuron using a variant of Genetic Programming called Gene Expression Programming. That is, this paper does not explicitly use weights or activation functions within a neuron, nor bias nodes within a layer. Promising preliminary results are reported for a study of the detection of underground caves (a 1 class problem) and for a study of the interaction of water and minerals near a glacier in the Arctic (a 5 class problem).

On‐board training of artificial neural network (ANN) is important in instances where real time data are required for model training. Provision of on‐board intelligence enables the developed systems to self‐recalibrate and enhances their efficiencies. In this work, investigations have been performed to determine optimized parameters of ANN model for linear systems. The performance parameters that is, model parameters, memory requirements, accuracy and processing time are chosen by considering the model to be installed on commercially available microcontrollers that have very limited on‐board memory. Minimum data requirements for training ANN models of linear systems are also explored for better performance. All dataset ranges are normalized in order to exclude the effects of range differences. It is shown that for linear systems, 1–3–1 architecture produces best results against ≤100 data points when Bayesian Regularization (BR) training function is used along with Log Sigmoid Activation function. Simulations for 1–3–1 architecture are then performed for datasets having 10, 25, 50 and 100 data points. The results show that training with 25 data points produces over‐all better performance than other datasets. A large dataset utilizes more training time and memory whereas a smaller dataset produces relatively lesser accuracy. The effects of clustered data and uniformly distributed data are also explored. It is found that total epochs in case of clustered data are significantly higher than uniformly distributed data. The combination of these optimized parameters that is, 1–3–1 architecture, with BR and Log function, for ≤100 data points can be used for the development and implementation of linear components or systems in resource‐constrained embedded systems.

Prediction of multiple characteristics of Friction-Stir welded joints by Levenberg Marquardt algorithm based artificial neural network

Quantitation of thin-layer chromatography (TLC) using image analysis is attractive for its low cost and convenience. The image analysis is investigated by designing a digital imaging system with simple equipment, developing an image analysis software based on our algorithm, and validated the system in the TLC quantitative assay of cichoric acid present in Echinacea purpurea (L.) Moench. TLC used a polyamide thin-layer plate with chloroform-methanol formic acid-water (3:6:1:1) as the mobile phase and 3% (m/v) aqueous aluminum chloride solution as the visualization reagent. Images are acquired with a standard digital camera under a UV viewing lamp (365 nm) in a dark room. The three-dimensional gray scale digital image dataset (x, y, gray) is reduced to two-dimensional dataset (distance, accumulative gray) and then plotted as a curve. The area under the peak corresponding to the cichoric acid spot is integrated and used for quantitation. The whole method was validated by the assay tests of detection limit, calibration curve, repeatability, reproducibility, and recovery. The results showed that our digital imaging method and image analysis algorithm were applicable for the quantification of TLC. The whole method is convenient, efficient, and moderately accurate for the quantitative assay of cichoric acid present in Echinacea purpurea (L.) Moench.

Neural networks are a state-of-the-art approach that performs well for many tasks. The activation function (AF) is an important hyperparameter that creates an output against the coming inputs to the neural network model. AF significantly affects the training and performance of the neural network model. Therefore, selecting the most optimal AF for processing input data in neural networks is important. Determining the optimal AF is often a difficult task. To overcome this difficulty, studies on trainable AFs have been carried out in the literature in recent years. This study presents a different approach apart from fixed or trainable AF approaches. For this purpose, the activation function cyclically switchable convolutional neural network (AFCS-CNN) model structure is proposed. The AFCS-CNN model structure does not use a fixed AF value during training. It is designed in a self-regulating model structure by switching the AF during model training. The proposed model structure is based on the logic of starting training with the most optimal AF selection among many AFs and cyclically selecting the next most optimal AF depending on the performance decrease during neural network training. Any convolutional neural network (CNN) model can be easily used in the proposed model structure. In this way, a simple but effective perspective has been presented. In this study, first, ablation studies have been carried out using the Cifar-10 dataset to determine the CNN models to be used in the AFCS-CNN model structure and the specific hyperparameters of the proposed model structure. After the models and hyperparameters were determined, expansion experiments were carried out using different datasets with the proposed model structure. The results showed that the AFCS-CNN model structure achieved state-of-the-art success in many CNN models and different datasets.

Iris is claimed to be one of the best biometrics. We have collected a large data set of iris images, intentionally sampling a range of quality broader than that used by current commercial iris recognition systems. We have re-implemented the Daugman-like iris recognition algorithm developed by Masek. We have also developed and implemented an improved iris segmentation and eyelid detection stage of the algorithm, and experimentally verified the improvement in recognition performance using the collected dataset. Compared to Masek's original segmentation approach, our improved segmentation algorithm leads to an increase of over 6% in the rank-one recognition rate.