Delta Learning Rule Research Articles

Application of Improved Class of Weighted Averaging Operators in Intuitionistic Fuzzy Ann Guided MAGDM E-Commerce Problems

Objectives: To propose a novel and improvised Artificial Neural Network (ANN) technique to solve Multiple Attribute Group Decision Making (MAGDM) problems and an improved class of Aggregation operators for combining Intuitionistic Fuzzy Set (IFS) matrices for the ANN algorithm. Methods: A novel class of improved aggregation operators namely the Improved Intuitionistic Fuzzy Weighted Arithmetic Averaging (IM-IFWAA) operator and the Improved Intuitionistic Fuzzy Ordered Weighted Averaging (IM-IFOWA) operator are proposed in this work. The proposed improved class of aggregation operators will aggregate the IFS matrix data sets appearing in the form of matrices and then the revised input vectors which is then fed into the ANN algorithm following Delta, Perceptron, and Hebb Learning Rule for the next phase. Findings: Aggregating the Intuitionistic Fuzzy set information or data in today’s digital world is a tedious task in the field of MAGDM problem-solving. In this work, two new classes of operators for aggregating the data sets are proposed namely the IM-IFWAA operator and the IM-IFOWA operator which will improve the performance of the ANN. Necessary theorems for the proposed operators are proved to provide consistency of the same. The input created using the aforementioned operators is then fed into the novel ANN algorithm for further computations. Varieties of learning rules are then engaged for ranking of the best alternative for the decision problem. The developed theory is supported by a numerical example which is computed using all the proposed techniques. Novelty: Most of the research done on Intuitionistic Fuzzy Artificial Neural Network models are based on learning rules or using some other calculations. The proposed methods of using novel and improvised aggregation operators for ANN are used to find the inputs for ANN where varieties of learning rules for ANN are employed for effective decision analysis. Keywords: ANN, Learning Rules, MAGDM, Intuitionistic Fuzzy Sets, Weighted Aggregation Operator

Intuitionistic Fuzzy Gram-Schmidt Orthogonalized Artificial Neural Network for Solving MAGDM Problems

Objectives: To propose a suitable decision-making model based on Intuitionistic Fuzzy sets (IFSs) and Gram-Schmidt orthogonalization process for Artificial Neural Network (ANN). Methods: The IFS data sets appearing in the form of matrices are aggregated using the available aggregation operators in the literature and then the collective aggregated information is processed through Gram-Schmidt orthogonalization for the revised input vectors which is then fed into the ANN algorithm following Delta Learning Rule for the next phase. The weight updation is performed through the ANN and the output is improvised. Findings: The proposed Gram-Scmidt Orthogonalization process is utilized in Intuitionistic Fuzzy Artificial Neural Network model. The Delta learning rule is utilized in the process of the Neural Network, where the Intuitionistic Fuzzy nature of the input data is transformed into a fuzzy data and then the ranking of the alternatives is done based on the weights updation through the learning phase of the ANN. Once the vector is trained out of the learning phase, it is then processed through the activation function for the final selection of the best alternative required of the Multiple Attribute Group Decision Making (MAGDM) problem posed in this work. To demonstrate the usefulness and applicability of this new method with the Gram-Schmidt process, the numerical example also adds more insight to the proposed methodology of ANN with the application of some Linear Space techniques. Novelty: Most of the research done on Intuitionistic Fuzzy Artificial Neural Network model are based on learning rules or using some other calculations. The proposed Gram-Schmidt Orthogonalization process is used to find the orthogonal basis that are used as input training vectors in the Delta learning rule for ANN. Keywords: MAGDM, ANN, Aggregation operators, Learning Rules, Intuitionistic Fuzzy sets, Gram-Scmidt Orthogonalization

Lateral Connections Improve Generalizability of Learning in a Simple Neural Network.

To navigate the world around us, neural circuits rapidly adapt to their environment learning generalizable strategies to decode information. When modeling these learning strategies, network models find the optimal solution to satisfy one task condition but fail when introduced to a novel task or even a different stimulus in the same space. In the experiments described in this letter, I investigate the role of lateral gap junctions in learning generalizable strategies to process information. Lateral gap junctions are formed by connexin proteins creating an open pore that allows for direct electrical signaling between two neurons. During neural development, the rate of gap junctions is high, and daughter cells that share similar tuning properties are more likely to be connected by these junctions. Gap junctions are highly plastic and get heavily pruned throughout development. I hypothesize that they mediate generalized learning by imprinting the weighting structure within a layer to avoid overfitting to one task condition. To test this hypothesis, I implemented a feedforward probabilistic neural network mimicking a cortical fast spiking neuron circuit that is heavily involved in movement. Many of these cells are tuned to speeds that I used as the input stimulus for the network to estimate. When training this network using a delta learning rule, both a laterally connected network and an unconnected network can estimate a single speed. However, when asking the network to estimate two or more speeds, alternated in training, an unconnected network either cannot learn speed or optimizes to a singular speed, while the laterally connected network learns the generalizable strategy and can estimate both speeds. These results suggest that lateral gap junctions between neurons enable generalized learning, which may help explain learning differences across life span.

Further perceptions of probability: In defence of associative models.

Extensive research in the behavioral sciences has addressed people's ability to learn stationary probabilities, which stay constant over time, but only recently have there been attempts to model the cognitive processes whereby people learn-and track-nonstationary probabilities. In this context, the old debate on whether learning occurs by the gradual formation of associations or by occasional shifts between hypotheses representing beliefs about distal states of the world has resurfaced. Gallistel et al. (2014) pitched the two theories against each other in a nonstationary probability learning task. They concluded that various qualitative patterns in their data were incompatible with trial-by-trial associative learning and could only be explained by a hypothesis-testing model. Here, we contest that claim and demonstrate that it was premature. First, we argue that their experimental paradigm consisted of two distinct tasks: probability tracking (an estimation task) and change detection (a decision-making task). Next, we present a model that uses the (associative) delta learning rule for the probability tracking task and bounded evidence accumulation for the change detection task. We find that this combination of two highly established theories accounts well for all qualitative phenomena and outperforms the alternative model proposed by Gallistel et al. (2014) in a quantitative model comparison. In the spirit of cumulative science, we conclude that current experimental data on human learning of nonstationary probabilities can be explained as a combination of associative learning and bounded evidence accumulation and does not require a new model. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Age-dependent statistical learning trajectories reveal differences in information weighting.

Statistical learning (SL) is the ability to generate predictions based on probabilistic dependencies in the environment, an ability that is present throughout life. The effect of aging on SL is still unclear. Here, we explore statistical learning in healthy adults (40 younger and 40 older). The novel paradigm tracks learning trajectories and shows age-related differences in overall performance, yet similarities in learning rates. Bayesian models reveal further differences between younger and older adults in dealing with uncertainty in this probabilistic SL task. We test computational models of 3 different learning strategies: (a) Win-Stay, Lose-Shift, (b) Delta Rule Learning, (c) Information Weights to explore whether they capture age-related differences in performance and learning in the present task. A likely candidate mechanism emerges in the form of age-dependent differences in information weights, in which young adults more readily change their behavior, but also show disproportionally strong reactions toward erroneous predictions. With lower but more balanced information weights, older adults show slower behavioral adaptation but eventually arrive at more stable and accurate representations of the underlying transitional probability matrix. (PsycInfo Database Record (c) 2020 APA, all rights reserved).

Application of artificial neural network for optimal operation of a multi-purpose multi-reservoir system, II: optimal solution and performance evaluation

This papers forms the second part of series on application of artificial neural network (ANN) for optimal operation of a multi-purpose multi-reservoir system. Optimal operating policies of a reservoir system are derived using Discrete differential dynamic programming (DDDP)-based ANN model. In ANN model development a feed-forward network with delta learning rule and back propagation algorithm is used. Neural networks have been trained using supervised learning approach. Water supply for irrigation, municipal and industrial use have been selected as objective of operation and other purposes are treated as binding constraints. Minimization of the sum of square of penalties incurred due to deviation of release from the target, is selected as the objective function. Damodar Valley (DV), a multi-purpose four reservoir system in India is used for this study. With different combination of input data, five types of ANN models are developed. Simulation has been done with 5 years (out of 1000 years) generated monthly inflow sequence as well as three types of observed historical monthly inflow sequences: maximum annual inflow year, 75% dependable inflow year and minimum annual inflow year. For simulation, total 360 monthly networks are trained and stored. ANN model: in which initial storage, current period’s inflow and previous period’s inflow are considered as input and optimal final state as output, yields lowest objective function value. Performances of the said model is computed based on modern reliability parameters, i.e., reliability, resiliency and vulnerability.

Causal effect analysis of logistics processes risks in manufacturing industries using sequential multi-stage fuzzy cognitive map: a case study

ABSTRACT Any shortage and deviation in the implementation of logistics processes can lead to a poor performance and losing the market share of the manufacturer. To overcome this problem, the identification of existing risks in all logistics sub-processes, and taking corrective/preventive measures, is of great importance. In this study, a risk prioritization approach is presented based on a sequential multi-stage fuzzy cognitive map (SMFCM) and process failure mode and effects analysis (PFMEA) to prioritize logistics processes risks. This approach, in addition to considering a process-oriented view, prioritizes the logistics risks according to the amount of each risk’s impact on other risks through the internal and external-stage causal relationships as well as the values of risk factors. The score obtained from this approach can create enough distinction among the priorities of different risks in comparison with conventional risk priority number (RPN). Also, the results based on this score have a lower dependency on experts’ opinions by applying the Extended Delta Rule (EDR) learning algorithm. In fact, the intelligent nature of this approach enables decision-makers to identify critical risks and examine the status of the system at any time. The results of the implementation of the SMFCM-PFMEA approach in a manufacturing company active in the automotive spare parts industry confirm the superiority of this compared with the conventional score.

Evaluating strategies for environmental sustainability in a supply chain of an emerging economy

Due to an increased pressure to be environmentally sustainable, many manufacturing organizations, especially from developing countries like Bangladesh, are attempting to make necessary changes in practices and supply chains. However, those attempts need to be applied strategically with the objective to be both environmentally sustainable and economically viable. This paper offers a decision-making methodology by integrating a fuzzy cognitive map (FCM) and data envelopment analysis (DEA) for evaluating strategies for environmental sustainability based on their impact on the overall supply chain network of an organization. This paper first identifies 18 generic strategies for environmental sustainability and three supply chain performance measurement (PM) factors. Afterwards, the cause-effect relationships among these strategies and PM factors are utilized to capture the complicated relationships by FCM. The extended delta rule (EDR) learning algorithm was used in association with FCM to quantify the impact of those strategies on supply chain PM factors. Finally, DEA is used to prioritize strategies using these impact values. A real-life case using a fast-moving consumer goods (FMCG) manufacturer from Bangladesh is presented to justify the applicability of the proposed methodology. The results reflect the usefulness of this methodology for evaluating strategies for environmental sustainability in a supply chain (SC), specifically in the FMCG sector of an emerging economy. Thus, other manufacturing organizations from any industry can use this methodology to evaluate strategies for environmental sustainability.

Backpropagation – Artificial Neural Network (BP-ANN): Understanding gender characteristics of older driver accidents in West Midlands of United Kingdom

Older people are vulnerable road users with higher rate of casualties in traffic accidents. The commonly cited causes of accidents for older people are poor attention and decision making at critical locations of road, poor visibility in extreme weather, poor road surface condition and unpredictability of other road users, particularly young drivers. Female drivers are often labelled as being precarious drivers and having higher accident risk comparing to male drivers. This paper applies Backpropagation - Artificial Neural Network (BP-ANN) with a Generalized Delta Rule (GDR) learning algorithm to model the factors affecting traffic accidents of both older female and male drivers. The BP-ANN can construct the causation model of traffic accidents with greater accuracy and define the proportion of errors contributed by each factor to traffic accidents. This paper studies a total of 95,092 accident records in West Midlands of the United Kingdom during the period of 2006 to 2016. This paper determines journey purpose, lighting condition, pedestrian crossing with physical interventions, complex roadway geometry, extreme weather and time severity as the most significant factors of older driver accidents. The accident risk of older drivers can be improved by providing accessible routes, affordable, reliable and convenient public transport, timely warning of unexpected situations and changes in roadway geometry; increasing use of assistive technology in cars, driverless cars and encouraging active transports into sociable activities. The findings help the transport authorities and city councils to develop strategies and measures promoting public and active transports to ensuring the safety of older drivers.

Testing learning mechanisms of rule-based judgment.

Weighing the importance of different pieces of information is a key determinant of making accurate judgments. In social judgment theory, these weighting processes have been successfully described with linear models. How people learn to make judgments has received less attention. Although the hitherto proposed delta learning rule can perfectly learn to solve linear problems, reanalyzing a previous experiment showed that it does not adequately describe human learning. To provide a more accurate description of learning processes we amended the delta learning rule with three learning mechanisms—a decay, an attentional learning mechanism, and a capacity limitation. An additional study tested the different learning mechanisms in predicting learning in linear judgment tasks. In this study, participants first learned to predict a continuous criterion based on four cues. To test the three learning mechanisms rigorously against each other, we changed the importance of the cues after 200 trials so that the mechanisms make different predictions with regard to how fast people adapt to the new environment. On average, judgment accuracy improved from Trial 1 to Trial 200, dropped when the task environment changed, but improved again until the end of the task. The capacity-restricted learning model, restricting how much people update the cue weights on a single trial, best described and predicted the learning curve of the majority of participants. Taken together, these results suggest that considering cognitive constraints within learning models may help to understand how humans learn when making inferences.

MLP modeling for search advertising price prediction

As the use of online and various smart devices spread, the use of online search engines became more active. As Internet shopping has evolved through online search engines, competition is under way to launch its link at the top of search engines to expose its links to prospective shoppers. This trend has contributed to the increase in advertising costs in the search advertising market. In this case, the value of the search keyword is generally calculated based on the frequency of the search keyword, however the search engine configures the price of the search keyword through the private auction method without disclosing the price in real time. Finally, it is difficult to reach the exact price and position by passive statistical method in order to predict the price of the search keyword. There is a growing demand for automation methodologies to perform this process quickly and efficiently. In this paper, we propose a Multi-Layer Perceptron (MLP) Neural Network modeling method that estimates bid prices of search keywords by collecting search keywords. MLP is used because it uses generalized delta learning rules and easily gets trained in less number of iterations. In this paper, we propose a MLP based prediction modeling to predict optimal bidding price of the keyword in a specific ranking of search engine.

Machine Learning Approaches for Face Identification Feed Forward Algorithms

Face identification using feed forward technique is a very important technique to use in computer vision, machine learning, biometrics, pattern recognition, pattern analysis and digital image processing. It is a systematic method for training multi-layer convolutional neural network. It is a mathematical technique that is strong but not highly used in practical. Feed forward technique is using for extend gradient descent based delta learning rules. Feed forward technique are provides a computationally efficient method for changing the weight and bias. Face learning problem is to search for all hypothesis space defined to all weight values for all units in the networks. The error is replaced by P and the other category of the space corresponding to all of the associated weight with all of the units in the network. In this equation in the case of training a single unit the output attempts to find a hypothesis to minimize P. In face identification algorithm the automatically determined location of the different feature. This alignment is refined by optical view. Identification is performing by computing normalized correlation scores in many face identification scenarios the pose of the probe and registered database image are different.

Adaptive Home Automation System by Using Smart Phone Based Artificial Intelligent

This paper proposes an advanced intelligent home automation system to control the mainhome functions such as heating, ventilation, air conditioning, shading, lighting, security and food’spreparation. The proposed system designed to detect motion or fire and to make decisionsindependently. Information about motion, heating, and lightning were collected from three nodes usingspecial sensors that micro-controlled through Arduino with WIFI shield and Xbee to be sent to theSmart Phone for manipulation through Java-based Android application. Delta Learning Rule algorithmwas used for decisions making as it is able to distinguish whether it is a dangerous situation or not.Furthermore, the proposed system has a property of generating an alert signal and sends it to the policeor fire station through GMS messages.

Computationally efficient generic adaptive filter (CEGAF)

Enhancement to clean speech from noisy speech has always been a challenging issue for the researcher’s community. Various researchers have used different techniques to resolve this problem. These techniques can be classified into the unsupervised and supervised approaches. Amongst the unsupervised approaches, Spectral Subtraction and Wiener Filter are commonly exploited. However, such approaches do not yield significant enhancement in the speech quality as well as intelligibility. As compared to unsupervised, supervised approaches such as Hidden Markov Model produces enhanced speech signals with better quality. However, supervised approaches need prior knowledge about the type of noise which is considered their major drawback. Moreover, for each noise type, separate models need to be trained. In this paper, a novel hybrid approach for the enhancement of speech is presented to overcome the limitations of both supervised and unsupervised approaches. The filter weights adjustment on the basis of Delta Learning Rule makes it a supervised approach. To address the issue of construction of new model for each noise type, the filter adjusts its weights automatically through minimum mean square error. It is unsupervised as there is no need of estimation of noise power spectral density. Various experiments are performed to test the performance of proposed filter with respect to different parameters. Moreover, the performance of the proposed filter is compared with state-of-the-art approaches using objective and subjective measures. The results indicate that CEGAF outperforms the algorithms such as Wiener Filter, supervised NMF and online NMF.

Investigating the Impact of Physiological Aspect on Cow Milk Production Using Artificial Intelligence

The purpose of the paper is to investigate the impact of physiological and environmental factors on milk productivity by using artificial intelligence (AI). The model will be useful for the user to decide the best cow treatment in order to gain the best milk production. The research starts with a literature review and an early survey of cattle physiological, environment factors and milk productivity. The next step is measuring the environment data (temperature, wind speed, noise level and relative humidity) and measuring the physiological aspect (heart rate, body temperature) correlated with the milk productivity in 500 pairs of data. All the data are collected and stored into the database and then trained and validated using Back Propagation Neural Network (BPNN) with Genetic Algorithm (GA) optimization. The initial BPNN architectures are selected in 2 hidden layers, delta bar delta learning rule, sigmoid transfer function and epoch 10000. The sensitivity analysis of all independent factors with temperature, relative humidity, core body temperature and heart rate in milk production are successfully presented. Finally, the research successfully increases cow milk production at an average = 0.96 kg/day.

Geometrical Modification of Learning Vector Quantization Method for Solving Classification Problems

In this paper, a geometrical scheme is presented to show how to overcome an encountered problem arising from the use of generalized delta learning rule within competitive learning model. It is introduced a theoretical methodology for describing the quantization of data via rotating prototype vectors on hyper-spheres. The proposed learning algorithm is tested and verified on different multidimensional datasets including a binary class dataset and two multiclass datasets from the UCI repository, and a multiclass dataset constructed by us. The proposed method is compared with some baseline learning vector quantization variants in literature for all domains. Large number of experiments verify the performance of our proposed algorithm with acceptable accuracy and macro f1 scores.

Backpropagation Neural Network to estimate pavement performance: dealing with measurement errors

The objective of this study is to apply the Backpropagation Neural (BPN) network with Generalised Delta Rule learning algorithm for reducing the measurement errors of pavement performance modelling. The Multi-Layer Perceptron network and sigmoid activation function are applied to build the BPN network of Pavement Condition Index (PCI). Collector and arterial roads of both flexible and rigid pavements in Montreal City are taken as a case study. The input variables of the PCI are Average Annual Daily Traffic (AADT), Equivalent Single Axle Loads (ESALs), Structural Number (SN), pavement age, slab thickness and difference in the PCI between the current and preceding year (ΔPCI). The BPN networks estimate that the PCI has inverse relationships with AADT, ESALs and pavement age. The PCI has positive relationships with these variables for roads that have recent treatment operations. The PCI has positive relationships with SN and slab thickness that imply the increase in pavement condition with increasing structural strength and slab thickness. The ΔPCI significantly influences the estimation of PCI values. The AADT and ESALs have considerable importance; however, pavement age and structural characteristics of the pavement have an insignificant influence in determining the PCI values, except in the case of flexible arterial roads.

Pavement management with dynamic traffic and artificial neural network: a case study of Montreal

This study improves the pavement management system by developing a linear programming optimization for the road network of the City of Montreal with simulated traffic for a period of 50 years and deals with the uncertainty of pavement performance modeling. Travel demand models are applied to simulate annual average daily traffic (AADT) every 5 years. A backpropagation neural network (BPN) with a generalized delta rule learning algorithm is applied to develop pavement performance models without uncertainties. Linear programming of life-cycle optimization is applied to develop maintenance and rehabilitation strategies to ensure the achievement of good levels of pavement condition subject to a given maintenance budget. The BPN network estimated that PCI values were predominantly determined by the differences in pavement condition index, AADT, and equivalent single axle loads. Dynamic linear programming optimization estimated that CAD$150 million is the minimum annual budget required to keep most of the arterial and local roads in good condition in Montreal.

The role of cognitive abilities in decisions from experience: Age differences emerge as a function of choice set size

People seldom enjoy access to summarized information about risky options before making a decision. Instead, they may search for information and learn about environmental contingencies—thus making decisions from experience. Aging is associated with notable deficits in learning and memory—but do these translate into poorer decisions from experience? We report three studies that used a sampling paradigm to investigate younger (M=24years) and older (M=71years) adults’ decisions from experience. In Study 1 (N=121) participants made 12 decisions between pairs of payoff distributions in the lab. Study 2 (N=70) implemented the same paradigm using portable devices, collecting 84 decisions per individual over a week. Study 3 (N=84) extended the sampling paradigm by asking participants to make 12 decisions between two, four, and eight payoff distributions (in the lab). Overall, the behavioral results suggest that younger and older adults are relatively similar in how they search and what they choose when facing two payoff distributions (Studies 1 and 2). With an increasing number of payoff distributions, however, age differences emerged (Study 3). A modeling analysis on the level of individual participants showed that a simple delta-learning rule model best described the learning processes of most participants. To the extent that ongoing updating processes unfold relatively automatically and effortlessly, older adults may be liberated from the detrimental consequences of cognitive aging in the case of decisions from experience with few decision options. We discuss implications for research on decisions from experience and choice performance over the lifespan.

Quality of Services Provisioning in Wireless Sensor Networks using Artificial Neural Network: A Survey

Wireless sensor network (WSN) is one of emerging trends in networking technologies being used for communication purpose in modern life. It has mainly comprised of small sensor nodes (SNs) with limited resources. Individual SNs are connected with each other and make the communication possible. Enhancement in the communication among sensor nodes or Sensor-to-Sink nodes is today’s most prominent objective. In this paper we have surveyed artificial neural network for different QOS parameters of WSN. Artificial neural network (ANN) is very prominent emerging area for WSN applications. Generally, artificial neural networks are classified in supervised learning and unsupervised learning. Unsupervised learning includes algorithms like Hebbian, Winner-take-all, ART, ART1, ART2, counter propagation network etc., while supervised learning includes perceptron model, delta learning rule, error back-propagation etc. ANN helps to achieve the better quality of services for communication in wireless sensor networks at the greater extent. We have summarized the survey of neural networks’ techniques applied for WSN applications so far.