Neural Network Based Prediction Model Research Articles

Neural network-based prognostic predictive tool for gastric cardiac cancer: the worldwide retrospective study

BackgroundsThe incidence of gastric cardiac cancer (GCC) has obviously increased recently with poor prognosis. It’s necessary to compare GCC prognosis with other gastric sites carcinoma and set up an effective prognostic model based on a neural network to predict the survival of GCC patients.MethodsIn the population-based cohort study, we first enrolled the clinical features from the Surveillance, Epidemiology and End Results (SEER) data (n = 31,397) as well as the public Chinese data from different hospitals (n = 1049). Then according to the diagnostic time, the SEER data were then divided into two cohorts, the train cohort (patients were diagnosed as GCC in 2010–2014, n = 4414) and the test cohort (diagnosed in 2015, n = 957). Age, sex, pathology, tumor, node, and metastasis (TNM) stage, tumor size, surgery or not, radiotherapy or not, chemotherapy or not and history of malignancy were chosen as the predictive clinical features. The train cohort was utilized to conduct the neural network-based prognostic predictive model which validated by itself and the test cohort. Area under the receiver operating characteristics curve (AUC) was used to evaluate model performance.ResultsThe prognosis of GCC patients in SEER database was worse than that of non GCC (NGCC) patients, while it was not worse in the Chinese data. The total of 5371 patients were used to conduct the model, following inclusion and exclusion criteria. Neural network-based prognostic predictive model had a satisfactory performance for GCC overall survival (OS) prediction, which owned 0.7431 AUC in the train cohort (95% confidence intervals, CI, 0.7423–0.7439) and 0.7419 in the test cohort (95% CI, 0.7411–0.7428).ConclusionsGCC patients indeed have different survival time compared with non GCC patients. And the neural network-based prognostic predictive tool developed in this study is a novel and promising software for the clinical outcome analysis of GCC patients.

Parametric analysis and prediction of energy consumption of electric vehicles using machine learning

Emission regulations for all automobiles have been introduced to reduce global warming caused by vehicles. Hybrid electric vehicles (HEVs) are being developed to address consumer demand for environmentally friendly automobiles with more power and better fuel efficiency. HEVs are propelled by a combination of an internal combustion engine (ICE) and one or more electric motors that draw power from a secondary battery, which is commonly a lithium-based battery. The fuel economy of such a hybrid drivetrain system can be enhanced above that of traditional ICE automobiles. Although the global world is now focussing on electric vehicles (EVs) over HEVs due to environmental pollution. In this study, a 1-dimensional model was developed for an electric vehicle (EV), and a parametric analysis was made for the eight different cycles using GT-Suite software. The parameters included motor power, state of charge of the battery, vehicle speed, distance travelled, and energy consumption. In light of the parametric analysis obtained using GT-Suite software, this paper also predicts the energy consumption of EV batteries using a neural network-based machine learning (ML) method. After selecting input parameters through a correlation coefficient index (CI) process, the proposed neural network-based prediction model has achieved 89% accuracy in predicting battery energy consumption which will help EV drivers to plan. It will also help automobile engineers to design more efficient and scalable EVs.

Convolutional neural network-based deep learning model for air quality prediction in October city of Egypt

Purpose Modern human society has continuous advancements that have a negative impact on the quality of the air. Daily transportation, industrial and residential operations churn up dangerous contaminants in our surroundings. Addressing air pollution issues is critical for human health and ecosystems, particularly in developing countries such as Egypt. Excessive levels of pollutants have been linked to a variety of circulatory, respiratory and nervous illnesses. To this end, the purpose of this research paper is to forecast air pollution concentrations in Egypt based on time series analysis. Design/methodology/approach Deep learning models are leveraged to analyze air quality time series in the 6th of October City, Egypt. In this regard, convolutional neural network (CNN), long short-term memory network and multilayer perceptron neural network models are used to forecast the overall concentrations of sulfur dioxide (SO2) and particulate matter 10 µm in diameter (PM10). The models are trained and validated by using monthly data available from the Egyptian Environmental Affairs Agency between December 2014 and July 2020. The performance measures such as determination coefficient, root mean square error and mean absolute error are used to evaluate the outcomes of models. Findings The CNN model exhibits the best performance in terms of forecasting pollutant concentrations 3, 6, 9 and 12 months ahead. Finally, using data from December 2014 to July 2021, the CNN model is used to anticipate the pollutant concentrations 12 months ahead. In July 2022, the overall concentrations of SO2 and PM10 are expected to reach 10 and 127 µg/m3, respectively. The developed model could aid decision-makers, practitioners and local authorities in planning and implementing various interventions to mitigate their negative influences on the population and environment. Originality/value This research introduces the development of an efficient time-series model that can project the future concentrations of particulate and gaseous air pollutants in Egypt. This research study offers the first time application of deep learning models to forecast the air quality in Egypt. This research study examines the performance of machine learning approaches and deep learning techniques to forecast sulfur dioxide and particular matter concentrations using standard performance metrics.

Psychotic Relapse Prediction in Schizophrenia Patients Using A Personalized Mobile Sensing-Based Supervised Deep Learning Model.

Mobile sensing-based modeling of behavioral changes could predict an oncoming psychotic relapse in schizophrenia patients for timely interventions. Deep learning models could complement existing non-deep learning models for relapse prediction by modeling the latent behavioral features relevant to prediction. However, given the inter-individual behavioral differences, model personalization might be required. In this work, we propose RelapsePredNet, a Long Short-Term Memory (LSTM) neural network-based model for relapse prediction. The model is personalized for a particular patient by using data from patients most similar to the given patient based on their demographics or baseline mental health scores. RelapsePredNet was compared with a deep learning-based anomaly detection model for relapse prediction. Additionally, we investigated if RelapsePredNet could complement ClusterRFModel (a random forest model leveraging clustering and template features proposed in prior work) in a fusion model. The CrossCheck dataset consisting of continuous mobile sensing data obtained from 63 schizophrenia patients, each monitored for up to a year, was used for our evaluations. RelapsePredNet outperformed the deep learning-based anomaly detection for relapse prediction with an F2 score of 0.21 and 0.52 in the full test set and the Relapse Test Set (consisting of data from patients who have had relapse only), respectively, representing a 29.4% and 38.8% improvement. Patients' social functioning scale (SFS) score was found to be the best personalization metric to define patient similarity. RelapsePredNet complemented the ClusterRFModel as it improved the F2 score by 26.1% with a fusion model, resulting in an F2 score of 0.30 in the full test set.

A time-varying acoustic channel-aware topology control mechanism for cooperative underwater sonar detection network

Topology control plays a vital role in cooperative underwater sonar detection networks (USDNs) to ensure detection applications. By incorporating spatio-temporal uncertainties in acoustic channel and limited resources in underwater networks, a large number of node deployment schemes have been proposed to overcome these difficulties through topology control. However, the channel uncertainty has not been solved fundamentally. In order to effectively deal with the time-space-frequency uncertainty of the acoustic channel, this paper proposes a time-varying acoustic channel-aware (TVAC) topology control mechanism to deploy sonar nodes in USDNs. Initially, a time-varying acoustic channel state information (CSI) estimation algorithm and a prediction algorithm are proposed by applying three sub-modules: a feature stitching deep neural network-based temperature prediction model that we designed, a deep neural network-based sound velocity estimation model, and a BELLHOP-based propagation loss calculation model. After that, a TVAC topology control mechanism is adopted to adaptively deploy nodes based on the CSI estimation and prediction results. Using the improved weighted set covering algorithm, the current CSI is adopted to determine the working modes of sonar nodes, and the predicted CSI is adopted to obtain the cycle of topology update. What is more, we develop an offline–online CSI prediction model to improve the accuracy and stability of node working modes management. Simulation results show that compared with other topology control schemes, TVAC can obtain superior coverage performance, full connectivity, and prolong the network lifetime with guaranteed coverage and connectivity.

DNN-based error level prediction for reducing read latency in 3D NAND flash memory

3D NAND Flash memory still suffers from many reliability issues in practice, such as endurance and data retention errors. Meanwhile, due to process variation, pages with different layers show different error characteristics even in the same block. In this paper, we firstly propose a deep neural network-based codeword error level prediction model that can effectively predict the level of codeword errors, and we consider all the main factors that affect the codeword errors, including the P/E cycles and retention time, the location information of the codeword. The new network structure can effectively reduce the weight size by approximately 27% without loss of accuracy compared to traditional neural network. Based on this prediction model, we further propose an optimized scheme to reduce the read latency of the system. The results of the model prediction can help the controller to choose a suitable decoding scheme, thus reducing the overall read latency. Experiments show that the proposed network can predict the error level of the codeword to over 97% accuracy, and also significantly help to improve the average read performance with a maximum latency reduction of 45.3%.

An artificial neural network-based radiomics model for predicting the radiotherapy response of advanced esophageal squamous cell carcinoma patients: a multicenter study

Radiotherapy benefits patients with advanced esophageal squamous cell carcinoma (ESCC) in terms of symptom relief and long-term survival. In contrast, a substantial proportion of ESCC patients have not benefited from radiotherapy. This study aimed to establish and validate an artificial neural network-based radiomics model for the pretreatment prediction of the radiotherapy response of advanced ESCC by using integrated data combined with feasible baseline characteristics of computed tomography. A total of 248 patients with advanced ESCC who underwent baseline CT and received radiotherapy were enrolled in this study and were analyzed by two types of radiomics models, machine learning and deep learning. As a result, the Att. Resnet50 pretrained network model indicated superior performance, with AUCs of 0.876, 0.802 and 0.732 in the training, internal validation, and external validation cohorts, respectively. Similarly, our Att. Resnet50 pretrained network model showed excellent calibration and significant clinical benefit according to the C index and decision curve analysis. Herein, a novel pretreatment radiomics model was established based on deep learning methods and could be used for radiotherapy response prediction in advanced ESCC patients, thus providing reliable evidence for therapeutic decision-making.

Time series prediction with granular neural networks

Conventional artificial neural networks are inherently equipped with an ambiguous (uncertain) structure which is hard to be quantified and explained. Time series forecasting using neural networks thus becomes a highly challenging task also due to the fact that time series data are always nonlinear and uncertain (because of some disturbances). Considering this, we propose a granular neural network-based time series prediction model connecting the uncertainty of models and data with the concept of information granularity. We aim to provide an explainable time series prediction model to resist the disturbance inner time series data and reduce the vagueness of the model. The functionalities of the granular neural network model are threefold: (1) It reveals the uncertainty of a time series data set through the level of granularity, coverage and specificity and possesses high prediction accuracy; (2) It provides an optimized interval output endowed with enough specificity and sufficient coverage and this interval is more robust than a single value; (3) It owns an interpretable and flexible structure that reflects the uncertainty of the initial numeric neural network and the generalization and robustness of connections while being faced with disturbances. The experimental studies elaborate on each function of our model in detail and show that the developed method performed better than the existing approaches present in the literature when experimenting on several time series data sets.

Artificial Neural Network-Based Predictive Model for Finite Element Analysis of Additive-Manufactured Components

Additive manufacturing is becoming one of the most utilized tools in an increasing number of fields from Industry 4.0 concepts, engineering, and manufacturing to aerospace and medical applications. One important issue with additive-manufactured components is their orthotropic behaviour where mechanical properties are concerned. This behaviour is due to the layer-by-layer manufacturing process and is particularly hard to predict since it depends on a number of factors, including the manufacturing parameters used during the manufacturing process (speed, temperature, etc.). This study aimed to create and train an artificial neural network-based predictive model using empirical tensile strength data obtained from additive manufactured test parts using the FDM method and PLA material. The predictive model was designed to predict mechanical characteristics for different orientation axis, which were used to set the material properties for finite element analysis. Results indicate a strong correlation between predicted finite element analysis behaviour and real-world tests on additive-manufactured components. The neural network model was trained to an accuracy of ~93% for predicting the mechanical characteristics of 3D-printed PLA material. Using the predicted mechanical characteristics for defining a custom orthotropic material profile in finite element analysis, the simulated failure mode and the behaviour of a complex geometry component agreed with the real-world test.

Removing artefacts and periodically retraining improve performance of neural network-based seizure prediction models

The development of seizure prediction models is often based on long-term scalp electroencephalograms (EEGs) since they capture brain electrical activity, are non-invasive, and come at a relatively low-cost. However, they suffer from major shortcomings. First, long-term EEG is usually highly contaminated with artefacts. Second, changes in the EEG signal over long intervals, known as concept drift, are often neglected. We evaluate the influence of these problems on deep neural networks using EEG time series and on shallow neural networks using widely-used EEG features. Our patient-specific prediction models were tested in 1577 hours of continuous EEG, containing 91 seizures from 41 patients with temporal lobe epilepsy who were undergoing pre-surgical monitoring. Our results showed that cleaning EEG data, using a previously developed artefact removal method based on deep convolutional neural networks, improved prediction performance. We also found that retraining the models over time reduced false predictions. Furthermore, the results show that although deep neural networks processing EEG time series are less susceptible to false alarms, they may need more data to surpass feature-based methods. These findings highlight the importance of robust data denoising and periodic adaptation of seizure prediction models.

A prediction model based on an adaptive genetic algorithm and optimized Elman neural network for PV power

Due to the high volatility and randomness of PV power generation, fast change frequency, limited data samples and poor data conditions, the reliability, stability and economy of grid operation are affected seriously. Therefore, the accurate prediction of PV power generation can mitigate the impact of its volatility on the stability of national grid power operations. And it improves PV consumption capacity and enhances the security of microgrid and distribution grid interconnection. This paper first proposed a PV power prediction method. Secondly, through the introduction and analysis of three types of prediction methods, the first type of prediction is selected using statistical analysis and modeling methods. Thirdly, an optimized Elman neural network-based PV power prediction model is proposed to allow accurate prediction of PV power prediction. Finally, an example is given to verify the advantages of the algorithm.

Artificial neural network-based predictive model for output characteristics in drilling of quartz cyanate ester polymeric composite

Artificial neural network-based predictive model for output characteristics in drilling of quartz cyanate ester polymeric composite

Effective Molecular Dynamics from Neural Network-Based Structure Prediction Models.

Recent breakthroughs in neural network-based structure prediction methods, such as AlphaFold2 and RoseTTAFold, have dramatically improved the quality of computational protein structure prediction. These models also provide statistical confidence scores that can estimate uncertainties in the predicted structures, but it remains unclear to what extent these scores are related to the intrinsic conformational dynamics of proteins. Here, we compare AlphaFold2 prediction scores with explicit large-scale molecular dynamics simulations of 28 one- and two-domain proteins with varying degrees of flexibility. We demonstrate a strong correlation between the statistical prediction scores and the explicit motion derived from extensive atomistic molecular dynamics simulations and further derive an elastic network model based on the statistical scores of AlphFold2 (AF-ENM), which we benchmark in combination with coarse-grained molecular dynamics simulations. We show that our AF-ENM method reproduces the global protein dynamics with improved accuracy, providing a powerful way to derive effective molecular dynamics using neural network-based structure prediction models.

Short-Term Power Prediction of Wind Power Generation System Based on Logistic Chaos Atom Search Optimization BP Neural Network

Wind power generation is the major approach to wind energy utilization. However, due to the volatility, intermittent, and controllability of wind power, it is difficult to control and scheduling of wind power, which brings challenges to the grid-connected operation and dispatch of wind power. Therefore, accurate power prediction of the wind power generation system is worthy of in-depth study. And this paper proposes a wind power prediction model based on logistic chaos atom search optimization (LCASO) optimized back-propagation (BP) neural network, aiming to achieve accurate and efficient power prediction. Moreover, this work utilizes data preprocessing to obtain more precise prediction results and related prediction evaluation indexes to quantificationally compare the effect of the proposed one with other prediction models based on GA-BP neural network and PSO-BP neural network. In contrast with the BP neural network, GA-BP neural network, and PSO-BP neural network, the simulation tests verify the comprehensive prediction performance and wider applicability of LCASO-BP neural network-based power prediction model.

Methodological progress note: Machine learning methods in healthcare research.

Methodological progress note: Machine learning methods in healthcare research.

Exploring a general convolutional neural network-based prediction model for critical casting diameter of metallic glasses

Metallic glasses (MGs) as emerging amorphous materials have attracted considerable interest due to their excellent mechanical, physical, and chemical properties. However, the poor glass-forming ability (GFA) of MGs makes them difficult to produce large specimen sizes required by engineering applications. Traditional design on MGs mainly relies on empirical rules, thus being limited in the accuracy and generality, in turn leading to slow development of MGs. Motivated by the issue, we hope to utilize the powerful learning capability of deep learning to mine the relationship between the metallic glass structure and the critical casting diameter (Dmax) such that develop a universal and accurate tool to aid the experimental investigation. Based on a reliable metallic glass dataset of 1121 unique alloys collected from literature, we introduce a periodic table representation (PTR) strategy to characterize the MG structure, which only needs the information of alloy composition such that can avoid feature engineering involving domain knowledge. Based on the image representation, we accordingly construct a convolutional neural network to effectively extract the structure feature from PTR, and then follow a fully connected neural network to realize the Dmax prediction. In addition, two data augmentation strategies are introduced to address the dependence of deep learning on big data, through which the model performance is indeed improved. In particular, the pairwise difference regression (PADRE) strategy exhibits better performance than the Mixup augmentation way, as PADRE targets the difference between sample pairs such that can to some extent drop the systematic error of experimental determination. The principal component analysis (PCA) analysis further confirms the effectiveness of the PTR representation and the powerful capacity of CNN to extract structural information from PTR. Benefited from the technical advantages, our deep learning model achieves satisfactory performance with R2 of 0.822 for unseen samples in the independent test set, which outperforms two competitive models using traditional machine learning algorithms coupled with hand-selection features, further demonstrating the advantage of our model in the universality and accuracy.

DBoTPM: A Deep Neural Network-Based Botnet Prediction Model

Internet of things (IoT) devices’ evolution and growth have boosted system efficiency, reduced human labour, and improved operational efficiency; however, IoT devices pose substantial security and privacy risks, making them highly vulnerable to botnet attacks. Botnet attacks are capable of degrading the performance of an IoT system in a way that makes it difficult for IoT network users to identify them. Earlier studies mainly focused on the detection of IoT botnets, and there was a gap in predicting the botnet attack due to their complex behaviour, repetitive nature, uncertainty, and almost invisible presence in the compromised system. Based on the gaps, it is highly required to develop efficient and stable AI models that can reliably predict botnet attacks. The current study developed and implemented DBoTPM, a novel deep-neural-network-based model for botnet prediction. The DBoTPM was optimized for performance and less computational overhead by utilizing rigorous hyperparameter tuning. The consequences of overfitting and underfitting were mitigated through dropouts. The evaluation of the DBoTPM demonstrated that it is one of the most accurate and efficient models for botnet prediction. This investigation is unique in that it makes use of two real datasets to detect and predict botnet attacks with efficient performance and faster response. The results achieved through the DBoTPM model were assessed against prior research and found to be highly effective at predicting botnet attacks with a real dataset.

Neural Network-Based Prediction Model for Sites' Overhead in Commercial Projects

Construction companies need to improve the accuracy of their projects' budgeting to achieve the targeted profit. Site overheads are the expenses related to a project but are not allocated to a specific work package. The main objective of this research is to develop a neural network model for commercial projects to predict and estimate project site overhead costs as a percentage of the direct cost. The focal point of the research is focused on the main factors affecting site overhead costs for commercial projects in Egypt. These factors and their weights were identified by experts through the collected structured data. Cost data for 55 projects in the past seven years was collected with various conditions of company rank, direct cost, project duration, project location, contract type, and type of company ownership. The results have shown that the best model developed consists of six input neurons; two hidden layers with six and five neurons respectively, and one output layer representing the percentage of project site overhead. The model was tested on six projects with accuracy of 84%.

Spatiotemporal correlation modelling for machine learning-based traffic state predictions: state-of-the-art and beyond

ABSTRACT Predicting traffic states has gained more attention because of its practical significance. However, the existing literature lacks a critical review regarding how to address the spatiotemporal correlation in the ML-based traffic state prediction models from a traffic-oriented perspective. Therefore, this study aims to comprehensively and critically review the spatiotemporal correlation modelling (STCM) approaches adopted for developing ML-based traffic state prediction models and provide future research directions based on traffic-oriented characteristics and ML techniques. Concretely, we investigate the neural network-based traffic state prediction models and characterise the STCM of these models by a proposed systematic review framework including three components: (i) spatial feature representation that demonstrates how the spatial information regarding road network is formulated, (ii) temporal feature representation that illustrates a variety of approaches to extract the temporal features, and (iii) model structure analyses the model layout to address the spatial correlations and temporal correlations simultaneously. Finally, several open challenges regarding incorporating traffic-oriented characteristics such as signal effects with ML techniques are put up with future research directions provided and discussed.

Micromagnetic and Robust Evaluation of Surface Hardness in Cr12MoV Steel Considering Repeatability of the Instrument.

The combination of multifunctional micromagnetic testing and neural network-based prediction models is a promising way of nondestructive and quantitative measurement of steel surface hardness. Current studies mainly focused on improving the prediction accuracy of intelligent models, but the unavoidable and random uncertainties related to instruments were seldom explored. The robustness of the prediction model considering the repeatability of instruments was seldom discussed. In this work, a self-developed multifunctional micromagnetic instrument was employed to perform the repeatability test with Cr12MoV steel. The repeatability of the instrument in measuring multiple magnetic features under both static and dynamic conditions was evaluated. The magnetic features for establishing the prediction model were selected based on the consideration of both the repeatability of the instrument and the ability of magnetic features in surface hardness evaluation. To improve the robustness of the model in surface hardness prediction, a modelling strategy considering the repeatability of the instrument was proposed. Through removing partial magnetic features with higher mean impact values from input nodes, robust evaluation of surface hardness in Cr12MoV steel was realized with the multifunctional micromagnetic instrument.