Search

We have proposed earlier the incremental internode communication method to reduce the communication cost as well as the time of the learning process in artificial neural networks (ANNs). In this paper, the limited precision incremental communication method is applied to a class of recurrent neural networks, the adaptive resonance theory 2 (ART2) networks. Simulation studies are carried out to examine the effects of the incremental communication method on the convergence behavior of ART2 networks. We have found that, 7-13-b precision is sufficient to obtain almost the same results as those with full (32-b) precision conventional communication. A theoretical error analysis is also carried out to analyze the effects of the limited precision incremental communication. The simulation and analytical results show that the limited precision errors are bounded and do not seriously degrade the convergence of ART2 networks. Therefore, the incremental communication can be incorporated in parallel and special-purpose very large scale integration (VLSI) implementations of the ART2 networks.

As the Internet of Things (IoT) landscape expands, new devices with various functionalities are continuously being integrated into the IoT ecosystem. When traditional systems, which involve human interaction, are replaced by devices, it becomes crucial to upgrade the conventional authorization and authentication systems. This is essential to establish a new access control system designed to manage accessibility of multiple devices. Traditional device identification approaches often struggle to accommodate the dynamic behaviors exhibited by IoT devices. In response, this paper introduces an innovative approach that leverages enhanced behavioral features to generate a representation of device behavior. This representation is then employed to train machine learning models for classifying devices based on their behaviors. Furthermore, this paper also considers special scenarios where the access management system lacks access to full network traffic data. In such cases, device identification is achieved based on HTTPS features and user agent information. We conducted experimental analyses using real data from state-of-the-art IoT device profiling datasets. The performance results indicate that the extracted behavioral-based features have the capability to identify multiple IoT devices with various functionalities and vendors. [ABSTRACT FROM AUTHOR]

Self-Compacting Concrete (SCC) is a unique type of concrete that can flow and fill spaces without the need for vibrating compaction, resulting in a dense and uniform material. This article focuses on estimating the compressive strength of SCC utilizing Artificial Neural Networks. Specifically, the study employs multilayer perceptrons with back-propagation learning algorithms, which are commonly used in various problem-solving scenarios. The study covers essential components such as structure, algorithm, data preprocessing, over-fitting prevention, and sensitivity analysis in MLPs. The input variables considered in the research include water, fine aggregate, super-plasticizer, fly ash, coarse aggregate, ground granulated blast furnace slag, limestone powder, viscosity-modifying admixtures, cement, silica fume, and rice husk ash. The target variable is the compressive strength. Through a sensitivity analysis, the study evaluates the relative importance of each parameter. The results indicate that the AI-based model accurately predicts the compressive strength of self-compacting concrete. [ABSTRACT FROM AUTHOR]

With the advances in computing powers and increasing volumes of data, deep learning's emergence has helped revitalize artificial intelligence research. There is a growing trend of applying deep learning techniques to image processing, speech recognition, self-driving cars, and even health-care. Recently, several deep learning models have been employed to detect a cyber threat such as network attack, malware infiltration, or phishing website; nevertheless, they suffer from not being explainable to security experts. Security experts not only do need to detect the incoming threat but also need to know the incorporating features that cause that particular security incident. To address this issue, in this paper, we propose a deep embedded neural network expert system (DeNNeS) that extracts refined rules from a trained deep neural network (DNN) architecture to substitute the knowledge base of an expert system. The knowledge base later is used to classify an unseen security incident and inform the final user of the corresponding rule that made that inference. We consider different rule extraction scenarios, and to prove the robustness of DeNNeS, we evaluate it on two cybersecurity datasets including UCI phishing websites dataset and Android malware dataset comprising more than 4000 Android APKs from several sources. The comparison results of DeNNeS with standalone DNN, JRip, and common machine learning algorithms show that DeNNeS with the retraining uncovered samples scenario outperforms other algorithms on both datasets. Furthermore, the extracted rules approximately reproduce the accuracy of the neural network from which they are derived. DeNNeS achieves an outstanding accuracy of 97.5 % and a negligible false positive rate of 1.8 % about 2.4 % higher and 3.5 % lower than the rule learner JRip on the phishing dataset. Moreover, DeNNeS outperforms random forest (RF), which produces the highest results among decision tree (DT), support vector machine, k-nearest neighbor, and Gaussian naive Bayes. Despite smaller training data in the malware dataset, DeNNeS achieves an accuracy of 95.8 % and F 1 s c o r e of 91.1 % , much higher than JRip and RF. [ABSTRACT FROM AUTHOR]