Search

This technical paper explores the use of Google Trends data to estimate the growth rate of the information and communication technology (ICT) sector. It discusses the statistical and machine learning methods employed to extract relevant information and make accurate predictions. The paper addresses challenges such as sampling noise and downward trends in search indexes, and suggests strategies to mitigate these issues. The results of the nowcasting model indicate that the ICT sector remained resilient during the COVID-19 pandemic. The paper concludes by suggesting potential enhancements to the model, including the incorporation of additional data sources and the exploration of alternative machine learning techniques. [Extracted from the article]

Stats Perform reported that a research paper authored by the company's AI team has been shortlisted as a finalist in the research track at the 2020 MIT Sloan Sports Analytics [...]

Researchers at the University of Virginia have developed a computer vision software that can digitize handwritten data from paper anesthesia charts in low-middle income countries. The software uses deep neural networks to identify and assign values to handwritten blood pressure symbols and physiological data. The researchers achieved high levels of accuracy, with the software digitizing checkbox data with over 99% accuracy and blood pressure data with a mean average error of 1.0 and 1.36 mmHg for systolic and diastolic blood pressure respectively. This technology provides improved access to digital data for healthcare practitioners in low-middle income countries. [Extracted from the article]

Researchers at the University of Florida have developed a new technique using artificial neural networks to enhance pathogen identification in cheese. The method, called the artificial neural network-driven paper chromogenic array sensor (ANN-PCA), allows for the nondestructive and simultaneous detection of Salmonella Enteritidis and Escherichia coli O157:H7 in shredded cheddar cheese. The technique has shown promising potential for integration into a digitalized, smart, and resilient nondestructive surveillance system for real-time pathogen detection in food supply chains. The research was funded by the US Army and the University of Florida, among others. [Extracted from the article]

In this paper, we are concerned with the finite-time synchronization of a class of inertial neural networks with time delays. Without applying some finite-time stability theorems, which are widely applied to studying the finite-time synchronization for neural networks, by constructing two Lyapunov functions and using integral inequality method, two sufficient conditions on the finite-time synchronization for a class of inertial neural networks with time delays are derived. Considering that the method and research results of the finite-time synchronization are different from some existing works, this paper extends the works on the finite-time synchronization of neural networks. [ABSTRACT FROM AUTHOR]

This article discusses the increasing popularity of data-driven methods for predicting heat transfer and fluid flow behavior in complex physical systems. The special issue focuses on innovative research that expands the boundaries of this field, showcasing advancements in methodologies and their applications across various domains. The article introduces 16 papers featured in the special issue, highlighting their contributions and findings. The overall aim of this special issue is to highlight the potential of data-driven methods in heat transfer and fluid flow, paving the way for more efficient and accurate solutions in engineering and scientific applications. [Extracted from the article]

"Theoretical and Modeling Research on the Valuation of Data Assets" is a paper that explores the concepts and characteristics of data assets. The author examines various valuation methods, including the traditional market method, income method, and cost method, as well as the Chen model and artificial neural network model. The paper provides insights into measuring the value of data assets. This research could be valuable for library patrons interested in understanding the valuation of data assets. [Extracted from the article]

The paper discusses algorithmic priority inversion in mission-critical machine inference pipelines used in modern neural-network-based perception subsystems and describes a solution to mitigate its effect. In general, priority inversion occurs in computing systems when computations that are "less important" are performed together with or ahead of those that are "more important." Significant priority inversion occurs in existing machine inference pipelines when they do not differentiate between critical and less critical data. We describe a framework to resolve this problem and demonstrate that it improves a perception system's ability to react to critical inputs, while at the same time reducing platform cost. [ABSTRACT FROM AUTHOR]

A report from the Thapar Institute of Engineering & Technology in Punjab, India discusses the use of machine learning and deep learning techniques for the detection of epileptic seizures. The paper compares different algorithms and models, such as support vector machine classifiers, artificial neural network classifiers, convolutional neural network classifiers, and long-short term memory networks. The effectiveness of different physiological signals, including electroencephalogram (EEG) and electrocardiogram (ECG), is also explored. The paper concludes that sentiment analysis could be another dimension of seizure detection. This research provides a summary of previous techniques and offers direction for further research in the field. [Extracted from the article]

Purpose: With the growth of organizations and businesses, customer acquisition and retention processes have become more complex in the long run. That is why customer lifetime value (CLV) has become crucial to sales managers. Predicting the CLV is a strategic weapon and competitive advantage in increasing profitability and identifying customers with more splendid profitability and is one of the essential key performance indicators (KPI) used in customer segmentation. Thus, this paper proposes a stacked ensemble learning method, a combination of multiple machine learning methods, for CLV prediction. Design/methodology/approach: In order to utilize customers' behavioral features for predicting the value of each customer's CLV, the data of a textile sales company was used as a case study. The proposed stacked ensemble learning method is compared with several popular predictive methods named deep neural networks, bagging support vector regression, light gradient boosting machine, random forest and extreme gradient boosting. Findings: Empirical results indicate that the regression performance of the stacked ensemble learning method outperformed other methods in terms of normalized rooted mean squared error, normalized mean absolute error and coefficient of determination, at 0.248, 0.364 and 0.848, respectively. In addition, the prediction capability of the proposed method improved significantly after optimizing its hyperparameters. Originality/value: This paper proposes a stacked ensemble learning method as a new method for accurate CLV prediction. The results and comparisons support the robustness and efficiency of the proposed method for CLV prediction. [ABSTRACT FROM AUTHOR]

The article discusses the deployment of machine learning technology in production environments. The authors describe the algorithms which constitute and shape machine learning protocols with a focus on papers on subjects including the MauveDB project to integrate machine learning technology into relational databases, scalable response prediction for online advertising, and optimization of neural network queries for object detection in video streams.

It is my pleasure to report that we have a couple of very successful on-going special issues, including a Special Issue on neurodynamic systems for optimization and applications and a Special Issue on neural networks and learning systems applications in smart grid. They received 101 and 79 submissions, respectively. You can visit http://www.tnnls.org for the call for papers of other Special Issues. If you and your colleagues would like to propose a Special Issue for TNNLS, please follow the instructions posted at http://cis.ieee.org/tnnls to submit your proposals. Special Issue proposals are always welcome on timely and hot topics related to neural networks and learning systems. [ABSTRACT FROM AUTHOR]

A research paper from Hongik University in Seoul, South Korea explores the potential of Spiking Neural Networks (SNNs) in biomedical applications. The paper highlights the advantages of SNNs compared to other models like LSTM, as well as the limitations of SNN classifiers. The researchers discuss the applications of SNNs in analyzing biomedical signals such as EEG, EMG, and ECG data, as well as their potential in specific anatomical regions. The paper concludes by offering insights into the advantages, disadvantages, challenges, and opportunities of various SNN models in healthcare and biomedical domains. This research has been peer-reviewed and provides a nuanced perspective on the potential impact of SNNs in the biomedical field. [Extracted from the article]

These instructions give guidelines for preparing papers for this publication. Presents information for authors publishing in this journal. [ABSTRACT FROM AUTHOR]

Decentralized energy production, particularly from photovoltaic (PV) systems, is becoming increasingly prevalent, leading to a rise in the number of energy producers and consumers, or "prosumers". These prosumers, equipped with their own energy generation and storage systems, are not just passive consumers but active participants in the energy market. They generate their own electricity, often from renewable sources, and can feed excess power back into the grid, store it for later use, or share it within a local energy community. This evolving energy paradigm presents new opportunities and challenges in terms of energy management and optimization, necessitating innovative approaches to ensure efficient and sustainable use of energy resources. This paper introduces an innovative storage management method for grid-connected photovoltaic (PV) systems. The method is designed to minimize either the economic or ecological cost, or to find an optimal balance between the two, under various tariff scenarios. This is achieved while adhering to a full self-consumption constraint imposed by the distribution system operator. The control strategy is underpinned by forecasts of electrical consumption, production, and CO 2 emissions, which are developed using feedforward neural network models. These models are trained on data from a real-scale smart-grid demonstrator at the Catholic University of Lille, France. The results of the study offer a comparative analysis of the economic and ecological benefits of the three proposed strategies, demonstrating that the best compromise is achieved when considering the off-peak tariff option. Furthermore, a real-time controller was implemented on the Energy Management System (EMS) of the demonstrator and tested over a 24-hour period, yielding satisfactory results. This paper, therefore, presents a significant advancement in the field of storage management for grid-connected PV systems. [ABSTRACT FROM AUTHOR]

Purpose: Aerodynamic shape optimisation is a complex problem usually governed by transonic non-linear aerodynamics, a high dimensional design space and high computational cost. Consequently, the use of a numerical simulation approach can become prohibitive for some applications. This paper aims to propose a computationally efficient multi-fidelity method for the optimisation of two-dimensional axisymmetric aero-engine nacelles. Design/methodology/approach: The nacelle optimisation approach combines a gradient-free algorithm with a multi-fidelity surrogate model. Machine learning based on artificial neural networks (ANN) is used as the modelling technique because of its ability to handle non-linear behaviour. The multi-fidelity method combines Reynolds-averaged Navier Stokes and Euler CFD calculations as high- and low-fidelity, respectively. Findings: Ratios of low- and high-fidelity training samples to degrees of freedom of nLF/nDOFs = 50 and nHF/nDOFs = 12.5 provided a surrogate model with a root mean squared error less than 5% and a similar convergence to the optimal design space when compared with the equivalent CFD-in-the-loop optimisation. Similar nacelle geometries and aerodynamic flow topologies were obtained for down-selected designs with a reduction of 92% in the computational cost. This highlights the potential benefits of this multi-fidelity approach for aerodynamic optimisation within a preliminary design stage. Originality/value: The application of a multi-fidelity technique based on ANN to the aerodynamic shape optimisation problem of isolated nacelles is the key novelty of this work. The multi-fidelity aspect of the method advances current practices based on single-fidelity surrogate models and offers further reductions in computational cost to meet industrial design timescales. Additionally, guidelines in terms of low- and high-fidelity sample sizes relative to the number of design variables have been established. [ABSTRACT FROM AUTHOR]

The article discusses the use of Artificial Intelligence (AI) in Australian schools and the potential benefits and risks associated with it. The authors emphasize the need for ethical considerations, data security, and accountability in the implementation of AI. They also highlight the Framework for Generative AI in Schools, which outlines principles for responsible AI use in education. The article stresses the importance of teaching and assessing students' knowledge and skills in using and creating with AI, as well as the need for school leaders to prioritize equity, diversity, and transparency in their AI practices. Additionally, the article recommends the involvement of school leaders and teachers in AI advisory bodies to address ethical issues and ensure fair and beneficial AI use in schools. The text references various research papers and articles related to education technology and assessment, providing valuable insights and research findings for library patrons conducting research in these areas. [Extracted from the article]

Purpose: Brewer's spent grain (BSG) is the main by-product of the brewing industry, holding significant potential for biomass applications. The purpose of this paper was to determine the effective thermal conductivity (keff) of BSG and to develop an Artificial Neural Network (ANN) to predict keff, since this property is fundamental in the design and optimization of the thermochemical conversion processes toward the feasibility of bioenergy production. Design/methodology/approach: The experimental determination of keff as a function of BSG particle diameter and heating rate was performed using the line heat source method. The resulting values were used as a database for training the ANN and testing five multiple linear regression models to predict keff under different conditions. Findings: Experimental values of keff were in the range of 0.090–0.127 W m−1 K−1, typical for biomasses. The results showed that the reduction of the BSG particle diameter increases keff, and that the increase in the heating rate does not statistically affect this property. The developed neural model presented superior performance to the multiple linear regression models, accurately predicting the experimental values and new patterns not addressed in the training procedure. Originality/value: The empirical correlations and the developed ANN can be utilized in future work. This research conducted a discussion on the practical implications of the results for biomass valorization. This subject is very scarce in the literature, and no studies related to keff of BSG were found. [ABSTRACT FROM AUTHOR]

Purpose: This paper aims to analyze the performance of artificial neural networks with filling methods in predicting the minimum fluidization velocity of different biomass types for bioenergy applications. Design/methodology/approach: An extensive literature review was performed to create an efficient database for training purposes. The database consisted of experimental values of the minimum fluidization velocity, physical properties of the biomass particles (density, size and sphericity) and characteristics of the fluidization (monocomponent experiments or binary mixture). The neural models developed were divided into eight different cases, in which the main difference between them was the filling method type (K-nearest neighbors [KNN] or linear interpolation) and the number of input neurons. The results of the neural models were compared to the classical correlations proposed by the literature and empirical equations derived from multiple regression analysis. Findings: The performance of a given filling method depended on the characteristics and size of the database. The KNN method was superior for lower available data for training and specific fluidization experiments, like monocomponent or binary mixture. The linear interpolation method was superior for a wider and larger database, including monocomponent and binary mixture. The performance of the neural model was comparable with the predictions of the most well-known correlations from the literature. Originality/value: Techniques of machine learning, such as filling methods, were used to improve the performance of the neural models. Besides the typical comparisons with conventional correlations, comparisons with three main equations derived from multiple regression analysis were reported and discussed. [ABSTRACT FROM AUTHOR]

These instructions give guidelines for preparing papers for this publication. Presents information for authors publishing in this journal. [ABSTRACT FROM AUTHOR]

For a class of nontriangular nonlinear systems in presence of unknown disturbances, we propose a predictor-based neural dynamic surface control (PNDSC) strategy in this paper. This nontriangular system is transformed via the mean value theorem, and a predictor is then constructed. To avoid an algebraic loop problem, partial state vectors are employed as input signals of neural networks (NNs) for approximating unknown dynamics, and compensation items are designed to compensate for approximation errors from NNs. Different from the traditional NDSC, the PNDSC in this paper utilizes prediction errors to update learning parameters for improving NNs’ learning behaviors with overlarge adaptive gains. On the basis of improved NNs’ approximation behaviors, a predictor-based NNs disturbance observer (PNNDO) is constructed for compensation for external disturbances and approximation errors from NNs. Furthermore, with predictors, a normalization method of weights is developed to reduce the number of online learning parameters. On the basis of the aforementioned result, measurement noises are taken into account in our predictor-based neural control strategy. We employ predictor states, rather than measurement information paralyzed by noises, in design of our control strategy. This reduces high-frequency oscillations in control input. A Lyapunov-based stability analysis shows that all signals are ultimately bounded in the closed-loop system. Finally, the effectiveness of the proposed control strategy is verified by a numerical example and a permanent magnet brushless DC motor system. [ABSTRACT FROM AUTHOR]

Neural networks (NNs) with large scales of artificial neurons are increasingly used in recognition and classification tasks. In power-constrained scenarios, the tradeoff between performance and hardware consumptions must be carefully evaluated before silicon tape-out. In this paper, we proposed a systematic approach to design ultra-low power NN system. This work is motivated by the facts that NNs are resilient to approximation in many of the computations and NNs are outputting statistical tensors which are acceptable to less-than-perfect results. We resort to the front-back end approach with a twofold aim: (1) a fast and accurate design approach is proposed by estimating the computing quality of low-power approximate adder arrays, and it is adopted to evaluate the neural network system; (2) a quality configurable engine with different approximation degrees while processing NNs is implemented. The proposed work is demonstrated with a comprehensive keyword spotting (KWS) system as an ultra-low power NN engine. The experimental environment is setup with ten keywords from the google speech command dataset (GSCD) using an industrial 22-nm ultra-low-leakage (ULL) process. Comparing to the state-of-the-art KWS processors, the proposed approximate NN engine can demonstrate over 60% improvement in power efficiency and $1.1\times $ area efficiency while achieving similar recognition accuracy. [ABSTRACT FROM AUTHOR]

Provides instructions and guidelines to prospective authors who wish to submit manuscripts. [ABSTRACT FROM AUTHOR]

These instructions give guidelines for preparing papers for this publication. Presents information for authors publishing in this journal. [ABSTRACT FROM AUTHOR]

These instructions give guidelines for preparing papers for this publication. Presents information for authors publishing in this journal. [ABSTRACT FROM AUTHOR]

These instructions give guidelines for preparing papers for this publication. Presents information for authors publishing in this journal. [ABSTRACT FROM AUTHOR]

These instructions give guidelines for preparing papers for this publication. Presents information for authors publishing in this journal. [ABSTRACT FROM AUTHOR]

These instructions give guidelines for preparing papers for this publication. Presents information for authors publishing in this journal. [ABSTRACT FROM AUTHOR]

These instructions give guidelines for preparing papers for this publication. Presents information for authors publishing in this journal. [ABSTRACT FROM PUBLISHER]

These instructions give guidelines for preparing papers for this publication. Presents information for authors publishing in this journal. [ABSTRACT FROM PUBLISHER]

In this paper, we first address the dynamics of the elegant multivalued quaternionic Hopfield neural network (MV-QHNN) proposed by Minemoto et al. Contrary to what was expected, we show that the MV-QHNN, as well as one of its variation, does not always come to rest at an equilibrium state under the usual conditions. In fact, we provide simple examples in which the network yields a periodic sequence of quaternionic state vectors. Afterward, we turn our attention to the continuous-valued quaternionic Hopfield neural network (CV-QHNN), which can be derived from the MV-QHNN by means of a limit process. The CV-QHNN can be implemented more easily than the MV-QHNN model. Furthermore, the asynchronous CV-QHNN always settles down into an equilibrium state under the usual conditions. Theoretical issues are all illustrated by examples in this paper. [ABSTRACT FROM AUTHOR]

The article titled "The Impact of Labor on the Performance of Founder-Family Firms" explores the prevalence of founder-family firms in the United States and challenges the notion that such organizational structures reduce firm value. The study, conducted by Murali Jagannathan, Brett W. Myers, and Xu Niu, finds no evidence that founder-family successions decrease firm value. This research provides valuable insights into the performance of founder-family firms and contributes to the ongoing discussion surrounding shareholder activism and organizational structures. [Extracted from the article]

The article titled "Number of Numbers: Does Quantitative Textual Disclosure Reduce Information Risk?" by Dexin Zhou, Xin Zheng, and John L. Campbell explores the relationship between numerical disclosure and various financial indicators. The research finds that more extensive numerical disclosure is associated with higher earnings announcement returns and reduced volatility, bid-ask spread, and cost of capital. The study suggests that quantitative textual disclosure can potentially reduce information risk. This information may be useful for library patrons conducting research on financial disclosure and its impact on market outcomes. [Extracted from the article]

Purpose: The purpose of this paper is to present numerical simulations for magnetohydrodynamics natural convection of a nanofluid flow inside a cavity with an H-shaped obstacle based on combining artificial neural network (ANN) with the finite element method (FEM), and predict the heat transfer rate and system entropy. Design/methodology/approach: The enclosure is assumed to be inclined. Changing the inclination angle results in a different obstacle shape, which affects the buoyancy force. Hence, different configurations of the contours of the fluid flow, isotherms and the entropy of the system are obtained. The outer walls of the cavity as well as the central part of the obstacle are kept adiabatic. The left vertical portion of the hindrance is cooled, whereas the right vertical part of the obstacle is a heated wall. Using dimensionless variables allows obtaining a dimensionless version of the governing system of equations that is solved via the consistency FEM. The coupled problem of pressure and velocity is overcome via the Increment Pressure Correction Scheme, which is known for its accuracy and stability for similar simple problems. A numerical computation is performed across a broad range of the governing parameters. A total of 304 data sets were used in the development of an ANN model. That data set was conducted from the numerical simulations. The data set underwent optimization, with 70% sets used for training the model, 15% for validation and another 15% for the testing phase. The training of the network model used the Levenberg–Marquardt training algorithm. Findings: From the numerical simulations, it is concluded that the H-shaped obstacle boosts heat transfer rate in comparison with the I-shaped case. Also, raising the value of the inclination angle improves the entropy of the system presented by the Bejen number. Furthermore, strength heat transfer rate is obtained via decreasing the Hartmann number while this decrease decays the values of the Bejen number for both positive and negative amounts of the nonlinear Boussinesq parameter. Slower velocity and a better heat transfer rate characterize nanofluid compared with pure fluid. Leveraging the capabilities of the ANN, the developed model adeptly forecasts the values of both the average Nusselt and Bejen numbers with a high degree of accuracy. Originality/value: A novel fusion of FEM and ANN has been tailored to forecast the heat transfer rate and system entropy of MHD natural convective flow within an inclined cavity containing an H-shaped obstacle, amid various physical influences. [ABSTRACT FROM AUTHOR]

These instructions give guidelines for preparing papers for this publication. Presents information for authors publishing in this journal. [ABSTRACT FROM PUBLISHER]

These instructions give guidelines for preparing papers for this publication. Presents information for authors publishing in this journal. [ABSTRACT FROM AUTHOR]

In this paper, a novel class of quaternion-valued memristive neural networks (QVMNNs) that considers both the spatial factor and Markov jump phenomenon is proposed, the finite/fixed-time anti-synchronization (F/FTAS) of which is investigated. It is worth mentioning that the considered master and slave systems are assumed to jump along two inconsistent Markov chains, which is a first attempt at the issue of the anti-synchronization of Markovian systems and may be more realistic than most existing Markovian systems’ models. Then, a suitable feedback controller is designed, such that the error system can be finite/fixed-time stable. Moreover, by integrating algebraic inequality technologies and Lyapunov theory, a new F/FTAS theorem can be obtained for the proposed systems. Finally, this paper provides two examples, so that the rationality, superiority, and practical value of the main results can be illustrated. [ABSTRACT FROM AUTHOR]

Hyperdimensional (HD) computing is a promising paradigm for future intelligent electronic appliances operating at low power. This paper discusses tradeoffs of selecting parameters of binary HD representations when applied to pattern recognition tasks. Particular design choices include density of representations and strategies for mapping data from the original representation. It is demonstrated that for the considered pattern recognition tasks (using synthetic and real-world data) both sparse and dense representations behave nearly identically. This paper also discusses implementation peculiarities which may favor one type of representations over the other. Finally, the capacity of representations of various densities is discussed. [ABSTRACT FROM AUTHOR]

These instructions give guidelines for preparing papers for this publication. Presents information for authors publishing in this journal. [ABSTRACT FROM AUTHOR]

For 70 years, it was hard to imagine how a computer could pass the test without possessing what AI researchers now call artificial general intelligence, the entire range of human intellectual capacities. Then hand him a stack of research papers on artificial neural networks and LLMs, give him access to GPT's source code, open up a ChatGPT prompt window, and set him loose. OK, sure, a casual user might now admit with a shrug, GPT-4 could very well pass a Turing test if you asked it to impersonate a human. [Extracted from the article]

These instructions give guidelines for preparing papers for this publication. Presents information for authors publishing in this journal. [ABSTRACT FROM AUTHOR]

The article focuses on the format of the journal "IEEE Transactions on Neural Networks and Learning Systems" for the authors to submit research papers and mentions charges of the pages, manuscripts submission, and editing services offered by publication of the journal.

These instructions give guidelines for preparing papers for this publication. Presents information for authors publishing in this journal. [ABSTRACT FROM PUBLISHER]

An introduction to an article published in the journal about the topic of neural radiance fields (NeRF) is presented.

These instructions give guidelines for preparing papers for this publication. Presents information for authors publishing in this journal. [ABSTRACT FROM AUTHOR]

These instructions give guidelines for preparing papers for this publication. Presents information for authors publishing in this journal. [ABSTRACT FROM AUTHOR]