Neural networks: An overview of early research, current frameworks and new challenges

Brain-computer interfaces inspired spiking neural network model for depression stage identification

BACKGROUND

Depression is a global mental disorder, and traditional diagnostic methods mainly rely on scales and subjective evaluations by doctors, which cannot effectively identify symptoms and even carry the risk of misdiagnosis. Brain-Computer Interfaces inspired deep learning-assisted diagnosis based on physiological signals holds promise for improving traditional methods lacking physiological basis and leads next generation neuro-technologies. However, traditional deep learning methods rely on immense computational power and mostly involve end-to-end network learning. These learning methods also lack physiological interpretability, limiting their clinical application in assisted diagnosis.

METHODOLOGY

A brain-like learning model for diagnosing depression using electroencephalogram (EEG) is proposed. The study collects EEG data using 128-channel electrodes, producing a 128×128 brain adjacency matrix. Given the assumption of undirected connectivity, the upper half of the 128×128 matrix is chosen in order to minimise the input parameter size, producing 8,128-dimensional data. After eliminating 28 components derived from irrelevant or reference electrodes, a 90×90 matrix is produced, which can be used as an input for a single-channel brain-computer interface image.

RESULT

At the functional level, a spiking neural network is constructed to classify individuals with depression and healthy individuals, achieving an accuracy exceeding 97.5 %.

COMPARISON WITH EXISTING METHODS

Compared to deep convolutional methods, the spiking method reduces energy consumption.

CONCLUSION

At the structural level, complex networks are utilized to establish spatial topology of brain connections and analyse their graph features, identifying potential abnormal brain functional connections in individuals with depression.

Buzzing with Intelligence: Current Issues in Apiculture and the Role of Artificial Intelligence (AI) to Tackle It

Honeybees (Apis mellifera L.) are important for agriculture and ecosystems; however, they are threatened by the changing climate. In order to adapt and respond to emerging difficulties, beekeepers require the ability to continuously monitor their beehives. To carry out this, the utilization of advanced machine learning techniques proves to be an exceptional tool. This review provides a comprehensive analysis of the available research on the different applications of artificial intelligence (AI) in beekeeping that are relevant to climate change. Presented studies have shown that AI can be used in various scientific aspects of beekeeping and can work with several data types (e.g., sound, sensor readings, images) to investigate, model, predict, and help make decisions in apiaries. Research articles related to various aspects of apiculture, e.g., managing hives, maintaining their health, detecting pests and diseases, and climate and habitat management, were analyzed. It was found that several environmental, behavioral, and physical attributes needed to be monitored in real-time to be able to understand and fully predict the state of the hives. Finally, it could be concluded that even if there is not yet a full-scale monitoring method for apiculture, the already available approaches (even with their identified shortcomings) can help maintain sustainability in the changing apiculture.

Classification of musical intervals by spiking neural networks: Perfect student in solfége classes

We investigate a spike activity of a network of excitable FitzHugh-Nagumo neurons, which is under constant two-frequency auditory signals. The neurons are supplemented with linear frequency filters and nonlinear input signal converters. We show that it is possible to configure the network to recognize a specific frequency ratio (musical interval) by selecting the parameters of the neurons, input filters, and coupling between neurons. A set of appropriately configured subnetworks with different topologies and coupling strengths can serve as a classifier for musical intervals. We have found that the selective properties of the classifier are due to the presence of a specific topology of coupling between the neurons of the network.

Glu-Ensemble: An ensemble deep learning framework for blood glucose forecasting in type 2 diabetes patients

Diabetes is a chronic metabolic disorder characterized by elevated blood glucose levels, posing significant health risks such as cardiovascular disease, and nerve, kidney, and eye damage. Effective management of blood glucose is essential for individuals with diabetes to mitigate these risks. This study introduces the Glu-Ensemble, a deep learning framework designed for precise blood glucose forecasting in patients with type 2 diabetes. Unlike other predictive models, Glu-Ensemble addresses challenges related to small sample sizes, data quality issues, reliance on strict statistical assumptions, and the complexity of models. It enhances prediction accuracy and model generalizability by utilizing larger datasets and reduces bias inherent in many predictive models. The framework's unified approach, as opposed to patient-specific models, eliminates the need for initial calibration time, facilitating immediate blood glucose predictions for new patients. The obtained results indicate that Glu-Ensemble surpasses traditional methods in accuracy, as measured by root mean square error, mean absolute error, and error grid analysis. The Glu-Ensemble framework emerges as a promising tool for blood glucose level prediction in type 2 diabetes patients, warranting further investigation in clinical settings for its practical application.

Innovative applications of artificial intelligence during the COVID-19 pandemic

The COVID-19 pandemic has created unprecedented challenges worldwide. Artificial intelligence (AI) technologies hold tremendous potential for tackling key aspects of pandemic management and response. In the present review, we discuss the tremendous possibilities of AI technology in addressing the global challenges posed by the COVID-19 pandemic. First, we outline the multiple impacts of the current pandemic on public health, the economy, and society. Next, we focus on the innovative applications of advanced AI technologies in key areas such as COVID-19 prediction, detection, control, and drug discovery for treatment. Specifically, AI-based predictive analytics models can use clinical, epidemiological, and omics data to forecast disease spread and patient outcomes. Additionally, deep neural networks enable rapid diagnosis through medical imaging. Intelligent systems can support risk assessment, decision-making, and social sensing, thereby improving epidemic control and public health policies. Furthermore, high-throughput virtual screening enables AI to accelerate the identification of therapeutic drug candidates and opportunities for drug repurposing. Finally, we discuss future research directions for AI technology in combating COVID-19, emphasizing the importance of interdisciplinary collaboration. Though promising, barriers related to model generalization, data quality, infrastructure readiness, and ethical risks must be addressed to fully translate these innovations into real-world impacts. Multidisciplinary collaboration engaging diverse expertise and stakeholders is imperative for developing robust, responsible, and human-centered AI solutions against COVID-19 and future public health emergencies.

Artificial intelligence-driven diagnosis of β-thalassemia minor & iron deficiency anemia using machine learning models

Background

Iron deficiency anemia (IDA) and b-thalassemia minor (BTM) are the two most common causes of microcytic anemia, and although these conditions do not share many symptoms, differential diagnosis by blood tests is a time-consuming and expensive process. CBC can be used to diagnose anemia, but without advanced techniques, it cannot differentiate between iron deficiency anemia and BTM. This makes the differential diagnosis of IDA and BTM costly, as it requires advanced techniques to differentiate between the two conditions. This study aims to develop a model to differentiate IDA from BTM using an automated machine-learning method using only CBC data.

Methods

This retrospective study included 396 individuals, consisting of 216 IDAs and 180 BTMs. The work was divided into three parts. The first section focused on the individual effects of hematological parameters on the differentiation of IDA and BTM. The second part discusses traditional methods and discriminant indices used in diagnosis. In the third section, models developed using artificial neural networks (ANN) and decision trees are analysed and compared with the methods used in the first two sections.

SHIP: a computational framework for simulating and validating novel technologies in hardware spiking neural networks

Investigations in the field of spiking neural networks (SNNs) encompass diverse, yet overlapping, scientific disciplines. Examples range from purely neuroscientific investigations, researches on computational aspects of neuroscience, or applicative-oriented studies aiming to improve SNNs performance or to develop artificial hardware counterparts. However, the simulation of SNNs is a complex task that can not be adequately addressed with a single platform applicable to all scenarios. The optimization of a simulation environment to meet specific metrics often entails compromises in other aspects. This computational challenge has led to an apparent dichotomy of approaches, with model-driven algorithms dedicated to the detailed simulation of biological networks, and data-driven algorithms designed for efficient processing of large input datasets. Nevertheless, material scientists, device physicists, and neuromorphic engineers who develop new technologies for spiking neuromorphic hardware solutions would find benefit in a simulation environment that borrows aspects from both approaches, thus facilitating modeling, analysis, and training of prospective SNN systems. This manuscript explores the numerical challenges deriving from the simulation of spiking neural networks, and introduces SHIP, Spiking (neural network) Hardware In PyTorch, a numerical tool that supports the investigation and/or validation of materials, devices, small circuit blocks within SNN architectures. SHIP facilitates the algorithmic definition of the models for the components of a network, the monitoring of states and output of the modeled systems, and the training of the synaptic weights of the network, by way of user-defined unsupervised learning rules or supervised training techniques derived from conventional machine learning. SHIP offers a valuable tool for researchers and developers in the field of hardware-based spiking neural networks, enabling efficient simulation and validation of novel technologies.

Development and application of random forest regression soft sensor model for treating domestic wastewater in a sequencing batch reactor

Small-scale distributed water treatment equipment such as sequencing batch reactor (SBR) is widely used in the field of rural domestic sewage treatment because of its advantages of rapid installation and construction, low operation cost and strong adaptability. However, due to the characteristics of non-linearity and hysteresis in SBR process, it is difficult to construct the simulation model of wastewater treatment. In this study, a methodology was developed using artificial intelligence and automatic control system that can save energy corresponding to reduce carbon emissions. The methodology leverages random forest model to determine a suitable soft sensor for the prediction of COD trends. This study uses pH and temperature sensors as premises for COD sensors. In the proposed method, data were pre-processed into 12 input variables and top 7 variables were selected as the variables of the optimized model. Cycle ended by the artificial intelligence and automatic control system instead of by fixed time control that was an uncontrolled scenario. In 12 test cases, percentage of COD removal is about 91. 075% while 24. 25% time or energy was saved from an average perspective. This proposed soft sensor selection methodology can be applied in field of rural domestic sewage treatment with advantages of time and energy saving. Time-saving results in increasing treatment capacity and energy-saving represents low carbon technology. The proposed methodology provides a framework for investigating ways to reduce costs associated with data collection by replacing costly and unreliable sensors with affordable and reliable alternatives. By adopting this approach, energy conservation can be maintained while meeting emission standards.

Fully Complex-Valued Dendritic Neuron Model

A single dendritic neuron model (DNM) that owns the nonlinear information processing ability of dendrites has been widely used for classification and prediction. Complex-valued neural networks that consist of a number of multiple/deep-layer McCulloch-Pitts neurons have achieved great successes so far since neural computing was utilized for signal processing. Yet no complex value representations appear in single neuron architectures. In this article, we first extend DNM from a real-value domain to a complex-valued one. Performance of complex-valued DNM (CDNM) is evaluated through a complex XOR problem, a non-minimum phase equalization problem, and a real-world wind prediction task. Also, a comparative analysis on a set of elementary transcendental functions as an activation function is implemented and preparatory experiments are carried out for determining hyperparameters. The experimental results indicate that the proposed CDNM significantly outperforms real-valued DNM, complex-valued multi-layer perceptron, and other complex-valued neuron models.

Optical Computing: Status and Perspectives

For many years, optics has been employed in computing, although the major focus has been and remains to be on connecting parts of computers, for communications, or more fundamentally in systems that have some optical function or element (optical pattern recognition, etc.). Optical digital computers are still evolving; however, a variety of components that can eventually lead to true optical computers, such as optical logic gates, optical switches, neural networks, and spatial light modulators have previously been developed and are discussed in this paper. High-performance off-the-shelf computers can accurately simulate and construct more complicated photonic devices and systems. These advancements have developed under unusual circumstances: photonics is an emerging tool for the next generation of computing hardware, while recent advances in digital computers have empowered the design, modeling, and creation of a new class of photonic devices and systems with unparalleled challenges. Thus, the review of the status and perspectives shows that optical technology offers incredible developments in computational efficiency; however, only separately implemented optical operations are known so far, and the launch of the world's first commercial optical processing system was only recently announced. Most likely, the optical computer has not been put into mass production because there are still no good solutions for optical transistors, optical memory, and much more that acceptance to break the huge inertia of many proven technologies in electronics.

Deep Learning-Based Frameworks for Semantic Segmentation of Road Scenes

Semantic segmentation using machine learning and computer vision techniques is one of the most popular topics in autonomous driving-related research. With the revolution of deep learning, the need for more efficient and accurate segmentation systems has increased. This paper presents a detailed review of deep learning-based frameworks used for semantic segmentation of road scenes, highlighting their architectures and tasks. It also discusses well-known standard datasets that evaluate semantic segmentation systems in addition to new datasets in the field. To overcome a lack of enough data required for the training process, data augmentation techniques and their experimental results are reviewed. Moreover, domain adaptation methods that have been deployed to transfer knowledge between different domains in order to reduce the domain gap are presented. Finally, this paper provides quantitative analysis and performance evaluation and discusses the results of different frameworks on the reviewed datasets and highlights future research directions in the field of semantic segmentation using deep learning.

Feedforward–Feedback Controller Based on a Trained Quaternion Neural Network Using a Generalised HR Calculus with Application to Trajectory Control of a Three-Link Robot Manipulator

This study derives a learning algorithm for a quaternion neural network using the steepest descent method extended to quaternion numbers. This applies the generalised Hamiltonian–Real calculus to obtain derivatives of a real–valued cost function concerning quaternion variables and designs a feedback–feedforward controller as a control system application using such a network. The quaternion neural network is trained in real-time by introducing a feedback error learning framework to the controller. Thus, the quaternion neural network-based controller functions as an adaptive-type controller. The designed controller is applied to the control problem of a three-link robot manipulator, with the control task of making the robot manipulator’s end effector follow a desired trajectory in the Cartesian space. Computational experiments are conducted to investigate the learning capability and the characteristics of the quaternion neural network used in the controller. The experimental results confirm the feasibility of using the derived learning algorithm based on the generalised Hamiltonian–Real calculus to train the quaternion neural network and the availability of such a network for a control systems application.

The role of neural artificial intelligence for diagnosis and treatment planning in endodontics: A qualitative review

Introduction

The role of artificial intelligence (AI) is currently increasing in terms of diagnosing diseases and planning treatment in endodontics. However, findings from individual research studies are not systematically reviewed and compiled together. Hence, this study aimed to systematically review, appraise, and evaluate neural AI algorithms employed and their comparative efficacy to conventional methods in endodontic diagnosis and treatment planning.

Methods

The present research question focused on the literature search about different AI algorithms and models of AI assisted endodontic diagnosis and treatment planning. The search engine included databases such as Google Scholar, PubMed, and Science Direct with search criteria of primary research paper, published in English, and analyzed data on AI and its role in the field of endodontics.

Results

The initial search resulted in 785 articles, exclusion based on abstract relevance, animal studies, grey literature and letter to editors narrowed down the scope of selected articles to 11 accepted for review. The review data supported the findings that AI can play a crucial role in the area of endodontics, such as identification of apical lesions, classifying and numbering teeth, detecting dental caries, periodontitis and periapical disease, diagnosing different dental problems, helping dentists make referrals, and also helping them make plans for treatment of dental disorders in a timely and effective manner with greater accuracy.

Conclusion

AI with different models or frameworks and algorithms can help dentists to diagnose and manage endodontic problems with greater accuracy. However, endodontic fraternity needs to provide more emphasis on the utilization of AI, provision of evidence based guidelines and implementation of the AI models.

Building 2D Model of Compound Eye Vision for Machine Learning

This paper presents a two-dimensional mathematical model of compound eye vision. Such a model is useful for solving navigation issues for autonomous mobile robots on the ground plane. The model is inspired by the insect compound eye that consists of ommatidia, which are tiny independent photoreception units, each of which combines a cornea, lens, and rhabdom. The model describes the planar binocular compound eye vision, focusing on measuring distance and azimuth to a circular feature with an arbitrary size. The model provides a necessary and sufficient condition for the visibility of a circular feature by each ommatidium. On this basis, an algorithm is built for generating a training data set to create two deep neural networks (DNN): the first detects the distance, and the second detects the azimuth to a circular feature. The hyperparameter tuning and the configurations of both networks are described. Experimental results showed that the proposed method could effectively and accurately detect the distance and azimuth to objects.

Predictive Coding, Variational Autoencoders, and Biological Connections

We present a review of predictive coding, from theoretical neuroscience, and variational autoencoders, from machine learning, identifying the common origin and mathematical framework underlying both areas. As each area is prominent within its respective field, more firmly connecting these areas could prove useful in the dialogue between neuroscience and machine learning. After reviewing each area, we discuss two possible correspondences implied by this perspective: cortical pyramidal dendrites as analogous to (nonlinear) deep networks and lateral inhibition as analogous to normalizing flows. These connections may provide new directions for further investigations in each field.

Soft Sensor Model for Estimating the POI Displacement Based on a Dynamic Neural Network

To satisfy the increasingly demanding requirements in throughput and accuracy, more lightweight structures and a higher control bandwidth are highly desirable in next-generation motion stages. However, these requirements lead to a more flexible deformation, causing the estimation accuracy of the point of interest (POI) displacement to be guaranteed under the rigid-body assumption. In this study, a soft sensor model is constructed using a dynamic neural network (DNN) to estimate the POI displacement. This model can reflect the dynamic characteristics of the POI and realize accurate estimations. Moreover, a method combining stepwise and weight methods is proposed to analyze the influence of different DNNs, and a performance measure is presented to evaluate the soft sensor model. In the simulation, the DNN with the hidden feedbacks is proved to be the most suitable soft sensor model. The relative error and correlation coefficient obtained were less than 2% and 0.9998, respectively, during training and 5% and 0.9989, respectively, during testing. Compared with the data-driven model using the least-squares method, the proposed method exhibits a higher precision, and the relative error is within the setting range using the proposed performance measure.

Application of Artificial Neural Networks in Construction Management: Current Status and Future Directions

Artificial neural networks (ANN) exhibit excellent performance in complex problems and have been increasingly applied in the research field of construction management (CM) over the last few decades. However, few papers draw up a systematic review to evaluate the state-of-the-art research on ANN in CM. In this paper, content analysis is performed to comprehensively analyze 112 related bibliographic records retrieved from seven selected top journals published between 2000 and 2020. The results indicate that the applications of ANN of interest in CM research have been significantly increasing since 2015. Back-propagation was the most widely used algorithm in training ANN. Integrated ANN with fuzzy logic/genetic algorithm was the most commonly employed way of addressing the CM problem. In addition, 11 application fields and 31 research topics were identified, with the primary research interests focusing on cost, performance, and safety. Lastly, challenges and future directions for ANN in CM were put forward from four main areas of input data, modeling, application fields, and emerging technologies. This paper provides a comprehensive understanding of the application of ANN in CM research and useful reference for the future.

Optimization of vector convolutional deep neural network using binary real cumulative incarnation for detection of distributed denial of service attacks

In today’s technological world, distributed denial of service (DDoS) attacks threaten Internet users by flooding huge network traffic to make critical Internet services unavailable to genuine users. Therefore, design of DDoS attack detection system is on urge to mitigate these attacks for protecting the critical services. Nowadays, deep learning techniques are extensively used to detect these attacks. The existing deep feature learning approaches face the lacuna of designing an appropriate deep neural network structure for detection of DDoS attacks which leads to poor performance in terms of accuracy and false alarm. In this article, a tuned vector convolutional deep neural network (TVCDNN) is proposed by optimizing the structure and parameters of the deep neural network using binary and real cumulative incarnation (CuI), respectively. The CuI is a genetic-based optimization technique which optimizes the tuning process by providing values generated from best-fit parents. The TVCDNN is tested with publicly available benchmark network traffic datasets and compared with existing classifiers and optimization techniques. It is evident that the proposed optimization approach yields promising results compared to the existing optimization techniques. Further, the proposed approach achieves significant improvement in performance over the state-of-the-art attack detection systems.

An optical neural chip for implementing complex-valued neural network

Complex-valued neural networks have many advantages over their real-valued counterparts. Conventional digital electronic computing platforms are incapable of executing truly complex-valued representations and operations. In contrast, optical computing platforms that encode information in both phase and magnitude can execute complex arithmetic by optical interference, offering significantly enhanced computational speed and energy efficiency. However, to date, most demonstrations of optical neural networks still only utilize conventional real-valued frameworks that are designed for digital computers, forfeiting many of the advantages of optical computing such as efficient complex-valued operations. In this article, we highlight an optical neural chip (ONC) that implements truly complex-valued neural networks. We benchmark the performance of our complex-valued ONC in four settings: simple Boolean tasks, species classification of an Iris dataset, classifying nonlinear datasets (Circle and Spiral), and handwriting recognition. Strong learning capabilities (i.e., high accuracy, fast convergence and the capability to construct nonlinear decision boundaries) are achieved by our complex-valued ONC compared to its real-valued counterpart.

Hybrid Neural Network Cerebellar Model Articulation Controller Design for Non-linear Dynamic Time-Varying Plants

This study proposes a hybrid method to control dynamic time-varying plants that comprises a neural network controller and a cerebellar model articulation controller (CMAC). The neural-network controller reduces the range and quantity of the input. The cerebellar-model articulation controller is the main controller and is used to compute the final control output. The parameters for the structure of the proposed network are adjusted using adaptive laws, which are derived using the steepest-descent gradient approach and back-propagation algorithm. The Lyapunov stability theory is applied to guarantee system convergence. By using the proposed combination architecture, the designed CMAC structure is reduced, and it makes it easy to design the network size and the initial membership functions. Finally, numerical-simulation results demonstrate the effectiveness of the proposed method.

Objective Video Quality Assessment Combining Transfer Learning With CNN

Nowadays, video quality assessment (VQA) is essential to video compression technology applied to video transmission and storage. However, small-scale video quality databases with imbalanced samples and low-level feature representations for distorted videos impede the development of VQA methods. In this paper, we propose a full-reference (FR) VQA metric integrating transfer learning with a convolutional neural network (CNN). First, we imitate the feature-based transfer learning framework to transfer the distorted images as the related domain, which enriches the distorted samples. Second, to extract high-level spatiotemporal features of the distorted videos, a six-layer CNN with the acknowledged learning ability is pretrained and finetuned by the common features of the distorted image blocks (IBs) and video blocks (VBs), respectively. Notably, the labels of the distorted IBs and VBs are predicted by the classic FR metrics. Finally, based on saliency maps and the entropy function, we conduct a pooling stage to obtain the quality scores of the distorted videos by weighting the block-level scores predicted by the trained CNN. In particular, we introduce a preprocessing and a postprocessing to reduce the impact of inaccurate labels predicted by the FR-VQA metric. Due to feature learning in the proposed framework, two kinds of experimental schemes including train-test iterative procedures on one database and tests on one database with training other databases are carried out. The experimental results demonstrate that the proposed method has high expansibility and is on a par with some state-of-the-art VQA metrics on two widely used VQA databases with various compression distortions.

Post-combustion artificial neural network modeling of nickel-producing multiple hearth furnace

In a nickel-producing multiple hearth furnace, there is a problem associated to the automatic operation of the temperature control loops in two of the hearths, since the same flow of air is split into two branches. A neural model of the post-combustion sub-process is built and served to increase the process efficiency of the industrial furnace. Data was taken for a three-months operating time period to identify the main variables characterizing the process and a model of multilayer perceptron type is built. For the validation of this model, process data from a four-months operating time period in 2018 was used and prediction errors based on a measure of closeness in terms of a mean square error criterion measured through its weights for the temperature of two of the hearths (four and six) versus the air flow to these hearths. Based on a rigorous testing and analysis of the process, the model is capable of predicting the temperature of hearth four and six with errors of 0.6 and 0.3 °C, respectively. In addition, the emissions by high concentration of carbon monoxide in the exhaust gases are reduced, thus contributing to the health of the ecosystem.

Use of deep learning to detect cardiomegaly on thoracic radiographs in dogs

The purpose of this study was to develop a computer-aided detection (CAD) device based on convolutional neural networks (CNNs) to detect cardiomegaly from plain radiographs in dogs. Right lateral chest radiographs (n = 1465) were retrospectively selected from archives. The radiographs were classified as having a normal cardiac silhouette (No-vertebral heart scale [VHS]-Cardiomegaly) or an enlarged cardiac silhouette (VHS-Cardiomegaly) based on the breed-specific VHS. The database was divided into a training set (1153 images) and a test set (315 images). The diagnostic accuracy of four different CNN models in the detection of cardiomegaly was calculated using the test set. All tested models had an area under the curve >0.9, demonstrating high diagnostic accuracy. There was a statistically significant difference between Model C and the remainder models (Model A vs. Model C, P = 0.0298; Model B vs. Model C, P = 0.003; Model C vs. Model D, P = 0.0018), but there were no significant differences between other combinations of models (Model A vs. Model B, P = 0.395; Model A vs. Model D, P = 0.128; Model B vs. Model D, P = 0.373). Convolutional neural networks could therefore assist veterinarians in detecting cardiomegaly in dogs from plain radiographs.

Transcriptomics in Toxicogenomics, Part III: Data Modelling for Risk Assessment

Transcriptomics data are relevant to address a number of challenges in Toxicogenomics (TGx). After careful planning of exposure conditions and data preprocessing, the TGx data can be used in predictive toxicology, where more advanced modelling techniques are applied. The large volume of molecular profiles produced by omics-based technologies allows the development and application of artificial intelligence (AI) methods in TGx. Indeed, the publicly available omics datasets are constantly increasing together with a plethora of different methods that are made available to facilitate their analysis, interpretation and the generation of accurate and stable predictive models. In this review, we present the state-of-the-art of data modelling applied to transcriptomics data in TGx. We show how the benchmark dose (BMD) analysis can be applied to TGx data. We review read across and adverse outcome pathways (AOP) modelling methodologies. We discuss how network-based approaches can be successfully employed to clarify the mechanism of action (MOA) or specific biomarkers of exposure. We also describe the main AI methodologies applied to TGx data to create predictive classification and regression models and we address current challenges. Finally, we present a short description of deep learning (DL) and data integration methodologies applied in these contexts. Modelling of TGx data represents a valuable tool for more accurate chemical safety assessment. This review is the third part of a three-article series on Transcriptomics in Toxicogenomics.

Supervised learning in spiking neural networks: A review of algorithms and evaluations

As a new brain-inspired computational model of the artificial neural network, a spiking neural network encodes and processes neural information through precisely timed spike trains. Spiking neural networks are composed of biologically plausible spiking neurons, which have become suitable tools for processing complex temporal or spatiotemporal information. However, because of their intricately discontinuous and implicit nonlinear mechanisms, the formulation of efficient supervised learning algorithms for spiking neural networks is difficult, and has become an important problem in this research field. This article presents a comprehensive review of supervised learning algorithms for spiking neural networks and evaluates them qualitatively and quantitatively. First, a comparison between spiking neural networks and traditional artificial neural networks is provided. The general framework and some related theories of supervised learning for spiking neural networks are then introduced. Furthermore, the state-of-the-art supervised learning algorithms in recent years are reviewed from the perspectives of applicability to spiking neural network architecture and the inherent mechanisms of supervised learning algorithms. A performance comparison of spike train learning of some representative algorithms is also made. In addition, we provide five qualitative performance evaluation criteria for supervised learning algorithms for spiking neural networks and further present a new taxonomy for supervised learning algorithms depending on these five performance evaluation criteria. Finally, some future research directions in this research field are outlined.

ANN-Based Fatigue Strength of Concrete under Compression

When concrete is subjected to cycles of compression, its strength is lower than the statically determined concrete compressive strength. This reduction is typically expressed as a function of the number of cycles. In this work, we study the reduced capacity as a function of a given number of cycles by means of artificial neural networks. We used an input database with 203 datapoints gathered from the literature. To find the optimal neural network, 14 features of neural networks were studied and varied, resulting in the optimal neural net. This proposed model resulted in a maximum relative error of 5.1% and a mean relative error of 1.2% for the 203 datapoints. The proposed model resulted in a better prediction (mean tested to predicted value = 1.00 with a coefficient of variation 1.7%) as compared to the existing code expressions. The model we developed can thus be used for the design and the assessment of concrete structures and provides a more accurate assessment and design than the existing methods.

N2SkyC: User Friendly and Efficient Neural Network Simulation Fostering Cloud Containers

Sky computing is a new computing paradigm leveraging resources of multiple Cloud providers to create a large scale distributed infrastructure. N2Sky is a research initiative promising a framework for the utilization of Neural Networks as services across many Clouds. This involves a number of challenges ranging from the provision, discovery and utilization of services to the management, monitoring, metering and accounting of the infrastructure. Cloud Container technology offers fast deployment, good portability, and high resource efficiency to run large-scale and distributed systems. In recent years, container-based virtualization for applications has gained immense popularity. This paper presents the new N2SkyC system, a framework for the utilization of Neural Networks as services, aiming for higher flexibility, portability, dynamic orchestration, and performance by fostering microservices and Cloud container technology.

Accuracy of deep learning to differentiate the histopathological grading of meningiomas on MR images: A preliminary study

BACKGROUND

Grading of meningiomas is important in the choice of the most effective treatment for each patient.

PURPOSE

To determine the diagnostic accuracy of a deep convolutional neural network (DCNN) in the differentiation of the histopathological grading of meningiomas from MR images.

STUDY TYPE

Retrospective.

POPULATION

In all, 117 meningioma-affected patients, 79 World Health Organization [WHO] Grade I, 32 WHO Grade II, and 6 WHO Grade III.

FIELD STRENGTH/SEQUENCE

1.5 T, 3.0 T postcontrast enhanced T1 W (PCT1 W), apparent diffusion coefficient (ADC) maps (b values of 0, 500, and 1000 s/mm2 ).

ASSESSMENT

WHO Grade II and WHO Grade III meningiomas were considered a single category. The diagnostic accuracy of the pretrained Inception-V3 and AlexNet DCNNs was tested on ADC maps and PCT1 W images separately. Receiver operating characteristic curves (ROC) and area under the curve (AUC) were used to asses DCNN performance.

STATISTICAL TEST

Leave-one-out cross-validation.

RESULTS

The application of the Inception-V3 DCNN on ADC maps provided the best diagnostic accuracy results, with an AUC of 0.94 (95% confidence interval [CI], 0.88-0.98). Remarkably, only 1/38 WHO Grade II-III and 7/79 WHO Grade I lesions were misclassified by this model. The application of AlexNet on ADC maps had a low discriminating accuracy, with an AUC of 0.68 (95% CI, 0.59-0.76) and a high misclassification rate on both WHO Grade I and WHO Grade II-III cases. The discriminating accuracy of both DCNNs on postcontrast T1 W images was low, with Inception-V3 displaying an AUC of 0.68 (95% CI, 0.59-0.76) and AlexNet displaying an AUC of 0.55 (95% CI, 0.45-0.64).

DATA CONCLUSION

DCNNs can accurately discriminate between benign and atypical/anaplastic meningiomas from ADC maps but not from PCT1 W images.

LEVEL OF EVIDENCE

2 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;50:1152-1159.

A Review of Epidemic Forecasting Using Artificial Neural Networks

Background and aims: Since accurate forecasts help inform decisions for preventive health-care intervention and epidemic control, this goal can only be achieved by making use of appropriate techniques and methodologies. As much as forecast precision is important, methods and model selection procedures are critical to forecast precision. This study aimed at providing an overview of the selection of the right artificial neural network (ANN) methodology for the epidemic forecasts. It is necessary for forecasters to apply the right tools for the epidemic forecasts with high precision. Methods: It involved sampling and survey of epidemic forecasts based on ANN. A comparison of performance using ANN forecast and other methods was reviewed. Hybrids of a neural network with other classical methods or meta-heuristics that improved performance of epidemic forecasts were analysed. Results: Implementing hybrid ANN using data transformation techniques based on improved algorithms, combining forecast models, and using technological platforms enhance the learning and generalization of ANN in forecasting epidemics. Conclusion: The selection of forecasting tool is critical to the precision of epidemic forecast; hence, a working guide for the choice of appropriate tools will help reduce inconsistency and imprecision in forecasting epidemic size in populations. ANN hybrids that combined other algorithms and models, data transformation and technology should be used for an epidemic forecast.

Using Machine Learning for Enhancing the Understanding of Bullwhip Effect in the Oil and Gas Industry

Several suppliers of oil and gas (O & G) equipment and services have reported the necessity of making frequent resources planning adjustments due to the variability of demand, which originates in unbalanced production levels. The occurrence of these specific problems for the suppliers and operators is often related to the bullwhip effect. For studying such a problem, a research proposal is herein presented. Studying the bullwhip effect in the O & G industry requires collecting data from different levels of the supply chain, namely: services, upstream and midstream suppliers, and downstream clients. The first phase of the proposed research consists of gathering the available production and financial data. A second phase will be the statistical treatment of the data in order to evaluate the importance of the bullwhip effect in the oil and gas industry. The third phase of the program involves applying artificial neural networks (ANN) to forecast the demand. At this stage, ANN based on different training methods will be used. Further on, the attained mathematical model will be used to simulate the effects of demand fluctuations and assess the bullwhip effect in an oil and gas supply chain.

An approach on the implementation of full batch, online and mini-batch learning on a Mamdani based neuro-fuzzy system with center-of-sets defuzzification: Analysis and evaluation about its functionality, performance, and behavior

Due to the rapid technological evolution and communications accessibility, data generated from different sources of information show an exponential growth behavior. That is, volume of data samples that need to be analyzed are getting larger, so the methods for its processing have to adapt to this condition, focusing mainly on ensuring the computation is efficient, especially when the analysis tools are based on computational intelligence techniques. As we know, if you do not have a good control of the handling of the volume of the data, some techniques that are based on learning iterative processes could represent an excessive load of computation and could take a prohibitive time in trying to find a solution that could not come close to desired. There are learning methods known as full batch, online and mini-batch, and they represent a good strategy to this problem since they are oriented to the processing of data according to the size or volume of available data samples that require analysis. In this first approach, synthetic datasets with a small and medium volume were used, since the main objective is to define its implementation and in experimentation phase through regression analysis obtain information that allows us to assess the performance and behavior of different learning methods under distinct conditions. To carry out this study, a Mamdani based neuro-fuzzy system with center-of-sets defuzzification with support of multiple inputs and outputs was designed and implemented that had the flexibility to use any of the three learning methods, which were implemented within the training process. Finally, results show that the learning method with best performances was Mini-Batch when compared to full batch and online learning methods. The results obtained by mini-batch learning method are as follows; mean correlation coefficient R¯ with 0.8268 and coefficient of determination R2¯ with 0.7444, and is also the method with better control of the dispersion between the results obtained from the 30 experiments executed per each dataset processed.

High-Level Modeling and Simulation Tool for Sensor Conditioning Circuit Based on Artificial Neural Networks

For current microelectronic integrated systems, the design methodology involves different steps that end up in the full system simulation by means of electrical and physical models prior to its manufacture. However, the higher the circuit complexity, the more time is required to complete these simulations, jeopardizing the convergence of the numerical methods and, hence, meaning that the reliability of the results are not guaranteed. This paper shows the use of a high-level tool based on Matlab to simulate the operation of an artificial neural network implemented in a mixed analog-digital CMOS process, intended for sensor calibration purposes. The proposed standard tool enables modification of the neural model architecture to adapt its characteristics to those of the electronic system, resulting in accurate behavioral models that predict the complete microelectronic IC system behavior under different operation conditions before its physical implementation with a simple, time-efficient, and reliable solution.

Diagnostic performance of an artificial neural network to predict excess body fat in children

BACKGROUND

Waist circumference (WC) and z scores of body mass index (BMI) are commonly used to predict childhood obesity, although BMI and WC have a limited sensitivity.

OBJECTIVES

To generate an artificial neural network (ANN), using the input parameters age, height, weight, and WC, to predict excess body fat in children.

METHODS

As part of the National Health and Nutrition Examination Survey (NHANES) study, in the years 1999 to 2004, the body fat percentage of randomly selected Americans from 8 to 19 years were measured using whole-body dual energy X-ray absorptiometry (DXA) scans. Excess body fat was defined as a body fat percentage ≥ 85th centile.

RESULTS

The data of 1999 children (856 female) were eligible. In females, the sensitivity of the BMI, WC, and ANN approaches to predict excess body fat were 0.751 (95% CI, 0.730-0.771), 0.523 (0.487-0.559), and 0.782 (0.754-0.810), respectively. In males, the sensitivity of the BMI, WC, and ANN approaches to predict excess body fat were 0.721 (95% CI, 0.699-0.743), 0.572 (0.549-0.594), and 0.795 (0.768-0.821).

CONCLUSIONS

Only in boys, the diagnostic performance in identifying excess body fat was better by using an ANN than by applying BMI and WC z scores. In girls, the ANN and BMI z scores performed comparable and significantly better than WC z scores.

A survey of neural network-based cancer prediction models from microarray data

Neural networks are powerful tools used widely for building cancer prediction models from microarray data. We review the most recently proposed models to highlight the roles of neural networks in predicting cancer from gene expression data. We identified articles published between 2013-2018 in scientific databases using keywords such as cancer classification, cancer analysis, cancer prediction, cancer clustering and microarray data. Analyzing the studies reveals that neural network methods have been either used for filtering (data engineering) the gene expressions in a prior step to prediction; predicting the existence of cancer, cancer type or the survivability risk; or for clustering unlabeled samples. This paper also discusses some practical issues that can be considered when building a neural network-based cancer prediction model. Results indicate that the functionality of the neural network determines its general architecture. However, the decision on the number of hidden layers, neurons, hypermeters and learning algorithm is made using trail-and-error techniques.