scholarly journals Understanding memories of the Holocaust—A new approach to neural networks in the digital humanities

2019 ◽  
Vol 35 (1) ◽  
pp. 17-33
Author(s):  
Tobias Blanke ◽  
Michael Bryant ◽  
Mark Hedges
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Sentiment Analysis ◽  
Digital Humanities ◽  
Research Question ◽  
Real Life ◽  
Computational Modelling ◽  
The United States ◽  
New Approach ◽  
Distant Supervision

Abstract This article addresses an important challenge in artificial intelligence research in the humanities, which has impeded progress with supervised methods. It introduces a novel method to creating test collections from smaller subsets. This method is based on what we will introduce as distant supervision’ and will allow us to improve computational modelling in the digital humanities by including new methods of supervised learning. Using recurrent neural networks, we generated a training corpus and were able to train a highly accurate model that qualitatively and quantitatively improved a baseline model. To demonstrate our new approach experimentally, we employ a real-life research question based on existing humanities collections. We use neural network based sentiment analysis to decode Holocaust memories and present a methodology to combine supervised and unsupervised sentiment analysis to analyse the oral history interviews of the United States Holocaust Memorial Museum. Finally, we employed three advanced methods of computational semantics. These helped us decipher the decisions by the neural network and understand, for instance, the complex sentiments around family memories in the testimonies.

scholarly journals Use of Neural Networks to Identify Safety Prevention Priorities in Agro-Manufacturing Operations within Commercial Grain Elevators

2019 ◽  
Vol 9 (21) ◽  
pp. 4690 ◽  
Author(s):  
Fatemeh Davoudi Kakhki ◽  
Steven A. Freeman ◽  
Gretchen A. Mosher
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
The United States ◽  
Work Environments ◽  
Safety Risk ◽  
Grain Elevators ◽  
Manufacturing Operations ◽  
Safety Risks ◽  
Artificial Neural

The grain handling industry plays a significant role in U.S. agriculture by storing, distributing, and processing a variety of agricultural commodities. Commercial grain elevators are hazardous agro-manufacturing work environments where workers are prone to severe injuries, due to the nature of the activities and workplace. Safety incidents in agro-manufacturing operations generally arise from a combination of factors, rather than a single cause, therefore, research on occupational incidents must look deeper into identifying the underlying causes, through the application of advanced analyses methods. In occupational safety, it is possible to estimate and predict probability of safety risks through developing artificial neural network predictive models. Due to the significance of safety risk assessment in the design and prioritization of effective prevention measures, this study aimed at classifying and predicting causes of occupational incidents in grain elevator agro-manufacturing operations in the Midwest region of the United States. Workers’ compensation claims data, from 2008 to 2016, were utilized for training multilayer perceptron (MLP) and radial basis function (RBF) neural networks. Both MLP and RBF models could predict the probability of safety risks with a high overall accuracy of 60%, 61%. Based on values of AUC (area under the curve) from the ROC (receiving operating charts), both models predicted the probability of individual safety risks with a high accuracy rate of between 71.5% and 99.2%. In addition, sensitivity analysis showed that nature of injury is the most significant determinant of safety risks probability, along with type of injury. The novelty of this study is the use of the artificial neural network methodology to analyze multi-level causes of occupational incidents as the sources of safety risks in bulk storage facilities. The results confirm that artificial neural networks are useful in safety risk estimation, and identifying the incidents’ risk factors. The implementation of safety measures in grain elevators can help in preventing occupational injuries, saving lives, and reducing the occurrence and severity of such incidents in industrial work environments.

Efficiency testing of artificial neural networks in predicting the properties of carbon nanomaterials as potential systems for nervous tissue stimulation and regeneration

2017 ◽  
Vol 13 (1) ◽  
Author(s):  
Martyna Sasiada ◽  
Aneta Fraczek-Szczypta ◽  
Ryszard Tadeusiewicz
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Nervous Tissue ◽  
Carbon Nanomaterials ◽  
Real Life ◽  
Neural Model ◽  
Carbon Nanomaterial ◽  
Neural Models ◽  
Predictive Learning ◽  
The Many

AbstractA new method of predicting the properties of carbon nanomaterials from carbon nanotubes and graphene oxide, using electrophoretic deposition (EPD) on a metal surface, was investigated. The main goal is to obtain the basis for nervous tissue stimulation and regeneration. Because of the many variations of the EPD method, costly and time-consuming experiments are necessary for optimization of the produced systems. To limit such costs and workload, we propose a neural network-based model that can predict the properties of selected carbon nanomaterial systems before they are produced. The choice of neural networks as predictive learning models is based on many studies in the literature that report neural models as good interpretations of real-life processes. The use of a neural network model can reduce experimentation with unpromising methods of systems processing and preparation. Instead, it allows a focus on experiments with these systems, which are promising according to the prediction given by the neural model. The performed tests showed that the proposed method of predictive learning of carbon nanomaterial properties is easy and effective. The experiments showed that the prediction results were consistent with those obtained in the real system.

scholarly journals Fuzzy Matrix Game: A Fast Approach using Artificial Hybrid Neural-Net Logic-Gate Switching Circuit

2022 ◽  
Author(s):  
Ankan Bhaumik ◽  
Sankar Kumar Roy
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Decision Making ◽  
Artificial Neural Network ◽  
Logic Gate ◽  
Real Life ◽  
Neural Nets ◽  
Matrix Game ◽  
Switching Circuit ◽  
Artificial Neural

Abstract Introducing neuro -fuzzy concept in decision making problems, makes a new way in artificial intelligence and expert systems. Sometimes, neural networks are used to optimize certain performances. In general, knowledge acquisition becomes difficult when problem's variables, constraints, environment, decision maker's attitude and complex behavior are encountered with. A sense of fuzziness prevails in these situations; sometimes numerically and sometimes linguistically. Neural networks (or neural nets) help to overcome this problem. Neural networks are explicitly and implicitly hyped to draw out fuzzy rules from numerical information and linguistic information. Logic-gate and switching circuit mobilize the fuzzy data in crisp environment and can be used in artificial neural network, also. Game theory has a tremendous scope in decision making; and consequently decision makers' hesitant characters play an important role in it. In this paper, a game situation is clarified under artificial neural network through logic-gate switching circuit in hesitant fuzzy environment with a suitable example; and this concept can be applied in future for real-life situations.

Performance of Multi-Layer Feedforward Neural Networks to Predict Liver Transplantation Outcome

1996 ◽  
Vol 35 (01) ◽  
pp. 12-18 ◽  
Author(s):  
M. Subotin ◽  
W. Marsh ◽  
J. McMichael ◽  
J. J. Fung ◽  
I. Dvorchik
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Liver Transplantation ◽  
Missing Data ◽  
Network Performance ◽  
Missing Values ◽  
Feedforward Neural Networks ◽  
Linear Scaling ◽  
Data Set ◽  
New Approach

AbstractA novel multisolutional clustering and quantization (MCO) algorithm has been developed that provides a flexible way to preprocess data. It was tested whether it would impact the neural network’s performance favorably and whether the employment of the proposed algorithm would enable neural networks to handle missing data. This was assessed by comparing the performance of neural networks using a well-documented data set to predict outcome following liver transplantation. This new approach to data preprocessing leads to a statistically significant improvement in network performance when compared to simple linear scaling. The obtained results also showed that coding missing data as zeroes in combination with the MCO algorithm, leads to a significant improvement in neural network performance on a data set containing missing values in 59.4% of cases when compared to replacement of missing values with either series means or medians.

NEURAL NETWORK RULE EXTRACTION BY A NEW ENSEMBLE CONCEPT AND ITS THEORETICAL AND HISTORICAL BACKGROUND: A REVIEW

2013 ◽  
Vol 12 (04) ◽  
pp. 1340006 ◽  
Author(s):  
YOICHI HAYASHI
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
High Performance ◽  
Real Life ◽  
Rule Extraction ◽  
Historical Background ◽  
Neural Network Ensemble ◽  
Extraction Algorithm ◽  
Neural Network Ensembles ◽  
Network Ensembles

This paper presents theoretical and historical backgrounds related to neural network rule extraction. It also investigates approaches for neural network rule extraction by ensemble concepts. Bologna pointed out that although many authors had generated comprehensive models from individual networks, much less work had been done to explain ensembles of neural networks. This paper carefully surveyed the previous work on rule extraction from neural network ensembles since 1988. We are aware of three major research groups i.e., Bologna' group, Zhou' group and Hayashi' group. The reason of these situations is obvious. Since the structures of previous neural network ensembles were quite complicated, the research on the efficient rule extraction algorithm from neural network ensembles was few although their learning capability was extremely high. Thus, these issues make rule extraction algorithm for neural network ensemble difficult task. However, there is a practical need for new ideas for neural network ensembles in order to realize the extremely high-performance needs of various rule extraction problems in real life. This paper successively explain nature of artificial neural networks, origin of neural network rule extraction, incorporating fuzziness in neural network rule extraction, theoretical foundation of neural network rule extraction, computational complexity of neural network rule extraction, neuro-fuzzy hybridization, previous rule extraction from neural network ensembles and difficulties of previous neural network ensembles. Next, this paper address three principles of proposed neural network rule extraction: to increase recognition rates, to extract rules from neural network ensembles, and to minimize the use of computing resources. We also propose an ensemble-recursive-rule extraction (E-Re-RX) by two or three standard backpropagation to train multi-layer perceptrons (MLPs), which enabled extremely high recognition accuracy and the extraction of comprehensible rules. Furthermore, this enabled rule extraction that resulted in fewer rules than those in previously proposed methods. This paper summarizes experimental results of rule extraction using E-Re-RX by multiple standard backpropagation MLPs and provides deep discussions. The results make it possible for the output from a neural network ensemble to be in the form of rules, thus open the "black box" of trained neural networks ensembles. Finally, we provide valuable conclusions and as future work, three open questions on the E-Re-RX algorithm.

A New Approach Hybrid Based in Artificial Neural Networks to Detection and Classification of Failures in Aeronautical Structures

2015 ◽  
Vol 763 ◽  
pp. 175-181
Author(s):  
Simone Silva Frutuoso Souza ◽  
Fernando Parra dos Anjos Lima ◽  
Fábio Roberto Chavarette
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
New Approach ◽  
Inspection Process ◽  
Artificial Neural ◽  
Aluminum Beam ◽  
First Time ◽  
Hybrid Methodology

In this paper presents a new hybrid methodology to perform fault detection and classification of aircraft structures using the tool as ARTMAP-Fuzzyand Perceptron multi-layer artificial neural networks. This method is divided into two steps, the first step performed by the multi-layer Perceptron neural network, which consists in the detection of abnormalities in the structure. The second step is performed by ARTMAP-Fuzzyneural network and consists of the classification of faults structural detected in the first time. The main application of this hybrid methodology is to assist in the inspection process of aeronautical structures in order to identify and characterize flaws as well, make decision-making in order to avoid accidents or air crashes. To evaluate this method, the modeling and simulation was carried out signals from a numerical model of an aluminum beam. The results obtained by the methodology demonstrating robustness and accuracy structural flaws.

scholarly journals Economic analysis of data protection in systems with complex architecture using neural network methods

2020 ◽  
Vol 185 (9-10) ◽  
pp. 178-188
Author(s):  
Vladimir Nelub ◽  
◽  
Andrey Gantimurov ◽  
Alexey Borodulin ◽  
◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Economic Analysis ◽  
Data Protection ◽  
Preventive Measure ◽  
The United States ◽  
Cyber Attacks ◽  
Data Loss ◽  
Network Methods ◽  
Complex Architecture

Introduction. In the United States, Europe, and Asia, there have been spikes in cyber attacks on protected and confidential information (including bank data, personal data, and confidential business information) over the period 2000-2020. Data protection in systems with complex architectures is a complex and non-trivial solution, which is suitable for flexible self-tuning and self-learning tools, such as neural networks as state modern studies. The described above state of things stipulates the importance and topicality of the direction of our research. Our research raises the question about the economic study of the data but attempts to create a mathematical apparatus to cause a loss of data in digital form, not made before The purpose of the study is to propose and test the calculation of the economic value of the data loss and economic benefit from data protection with multi-level neural networks. Results. Nowadays, almost every business that has access to the Internet has a threat of losing protected data, including banking data. To prevent this, the company must comply with the data protection management regulations. As an example, we studied the process of neural network reaction to an attack and its detection, when two types of attacks are threatened: botnet and UDP flood. Due to the result of a quick response to detect suspicious activity, neural network methods are excellent for use in economic analysis, because the neural network logs every event for every millisecond. Conclusions. As a result of using neural network tools for economic analysis of data protection in modern systems with complex architecture, we were able to obtain stable results of responding to an emerging attack in order to obtain protected data. Such protection is a preventive measure for the possibility of reducing business losses in the event of data loss. As we can see, the management of protection of systems with complex architecture is necessary for each company with the specified data level.

scholarly journals Database security: combining neural networks and classification approach

2020 ◽  
pp. 95-115
Author(s):  
Jarosław Skaruz
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Detection System ◽  
Time Series Prediction ◽  
Database Security ◽  
Prediction Problem ◽  
New Approach ◽  
Classification Approach ◽  
Backpropagation Through Time ◽  
The Relationship

In the paper we present a new approach based on application of neural networks to detect SQL attacks. SQL attacks are those attacks that take the advantage of using SQL statements to be performed. The problem of detection of this class of attacks is transformed to time series prediction problem. SQL queries are used as a source of events in a protected environment. To differentiate between normal SQL queries and those sent by an attacker, we divide SQL statements into tokens and pass them to our detection system, which predicts the next token, taking into account previously seen tokens. In the learning phase tokens are passed to a recurrent neural network (RNN) trained by backpropagation through time (BPTT) algorithm. Then, two coefficients of the rule are evaluated. The rule is used to interpret RNN output. In the testing phase RNN with the rule is examined against attacks and legal data to find out how evaluated rule affects efficiency of detecting attacks. All experiments were conducted on Jordan network. Experimental results show the relationship between the rule and a length of SQL queries.

Fatigue Damage Diagnostics of Composites Using Data Fusion and Data Augmentation with Deep Neural Networks

2021 ◽  
pp. 1-38
Author(s):  
Shweta Dabetwar ◽  
Stephen Ekwaro-Osire ◽  
Joao Paulo Dias
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Data Fusion ◽  
Damage Detection ◽  
Deep Neural Networks ◽  
Data Augmentation ◽  
Research Question ◽  
Complex Nature ◽  
Fault Diagnostics ◽  
Damage Diagnostics

Abstract Composite materials can be modified according to the requirements of applications and hence their applications are increasing significantly with time. Due to the complex nature of the aging of composites, it is equally challenging to establish structural health monitoring techniques. One of the most applied non-destructive techniques for this class of materials is using Lamb waves to quantify the damage. Another important advancement in damage detection is the application of deep neural networks. The data-driven methods have proven to be most efficient for damage detection in composites. For both of these advanced methods, the burning question always has been the requirement of data and quality of data. In this paper, these measurements were used to create a framework based on a deep neural network for efficient fault diagnostics. The research question developed for this paper was: can data fusion techniques used along with data augmentation improve the damage diagnostics using the convolutional neural network? The specific aims developed to answer this research question were (1) highlighting the importance of data fusion methods, (2) underlining the importance of data augmentation techniques, (3) generalization abilities of the proposed framework, and (4) sensitivity of the size of the dataset. The results obtained through the analysis concluded that the artificial intelligence techniques along with the Lamb wave measurements can efficiently improve the fault diagnostics of complex materials such as composites.

Evolutionary Algorithm Training of Higher Order Neural Networks

2010 ◽  
pp. 57-85
Author(s):  
M. G. Epitropakis ◽  
V. P. Plagianakos ◽  
Michael N. Vrahatis
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Real Life ◽  
Higher Order ◽  
Neural Network Training ◽  
Activation Functions ◽  
Swarm Optimization ◽  
Network Training ◽  
Higher Order Neural Networks ◽  
Distributed Evolutionary Algorithms

This chapter aims to further explore the capabilities of the Higher Order Neural Networks class and especially the Pi-Sigma Neural Networks. The performance of Pi-Sigma Networks is evaluated through several well known neural network training benchmarks. In the experiments reported here, Distributed Evolutionary Algorithms are implemented for Pi-Sigma neural networks training. More specifically, the distributed versions of the Differential Evolution and the Particle Swarm Optimization algorithms have been employed. To this end, each processor of a distributed computing environment is assigned a subpopulation of potential solutions. The subpopulations are independently evolved in parallel and occasional migration is allowed to facilitate the cooperation between them. The novelty of the proposed approach is that it is applied to train Pi-Sigma networks using threshold activation functions, while the weights and biases were confined in a narrow band of integers (constrained in the range [-32, 32]). Thus, the trained Pi-Sigma neural networks can be represented by using only 6 bits. Such networks are better suited for hardware implementation than the real weight ones and this property is very important in real-life applications. Experimental results suggest that the proposed training process is fast, stable and reliable and the distributed trained Pi-Sigma networks exhibit good generalization capabilities.

Sign in / Sign up

Export Citation Format

Share Document