Human-Centric AI for Trustworthy IoT Systems With Explainable Multilayer Perceptrons

García‐Magariño, Iván; Rajarajan, Muttukrishnan; Lloret, Jaime

doi:10.1109/access.2019.2937521

Cited by 59 publications

(32 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such neural networks can be used to solve various issues in the domain of cybersecurity. For instance, building an intrusion detection model [36], malware analysis [57], security threat analysis [50], detecting malicious botnet traffic [54] as well as for building trustworthy IoT systems [39] MLP based network are used. MLP is sensitive to feature scaling and needs a range of hyperparameters such as the number of hidden layers, neurons and iterations to be tuned, which may lead the model computationally expensive to solve a complex security model.…”

Section: Multi-layer Perceptron (Mlp)mentioning

confidence: 99%

Deep Cybersecurity: A Comprehensive Overview from Neural Network and Deep Learning Perspective

Sarker¹

2021

Preprint

View full text Add to dashboard Cite

Deep learning (DL), which is originated from an artificial neural network (ANN), is one of the major technologies of today's smart cybersecurity systems or policies to function in an intelligent manner. Popular deep learning techniques, such as Multi-layer Perceptron (MLP), Convolutional Neural Network (CNN or ConvNet), Recurrent Neural Network (RNN) or Long Short-Term Memory (LSTM), Self-organizing Map (SOM), Auto-Encoder (AE), Restricted Boltzmann Machine (RBM), Deep Belief Networks (DBN), Generative Adversarial Network (GAN), Deep Transfer Learning (DTL or Deep TL), Deep Reinforcement Learning (DRL or Deep RL), or their ensembles and hybrid approaches can be used to intelligently tackle the diverse cybersecurity issues. In this paper, we aim to present a comprehensive overview from the perspective of these neural networks and deep learning techniques according to today's diverse needs. We also discuss the applicability of these techniques in various cybersecurity tasks such as intrusion detection, identification of malware or botnets, phishing, predicting cyber-attacks, e.g. denial of service (DoS), fraud detection or cyber-anomalies, etc. Finally, we highlight several research issues and future directions within the scope of our study in the field. Overall, the ultimate goal of this paper is to serve as a reference point and guidelines for the academia and professionals in the cyber industries, especially from the deep learning point of view.

show abstract

Section: Multi-layer Perceptron (Mlp)mentioning

confidence: 99%

Deep Cybersecurity: A Comprehensive Overview from Neural Network and Deep Learning Perspective

Sarker¹

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…AI systems should be designed and developed to be human centric and serve people. A significant approach is to apply humancentric AI (HAI) in IoT systems, so that IoT systems cannot only learn from users but also provide easy-tounderstand explanations about decisions or estimations [18]. 4 AI4People, an Atomium-EISMD initiative designed to lay the foundations for a "Good AI Society", [1] 5 Figure 6 Beneficent AI systems can contribute to wellbeing by seeking achievement of a fair, inclusive and peaceful society by helping to increase citizen's mental autonomy, with equal distribution of economic, social and political opportunity.…”

Section: ) the Principle Of Beneficence: "Do Good"mentioning

confidence: 99%

AI Ethics: Algorithmic Determinism or Self-Determination? The GPDR Approach

Milossi

Alexandropoulou-Egyptiadou

Psannis

2021

IEEE Access

View full text Add to dashboard Cite

Artificial Intelligence (AI) refers to systems designed by humans, interpreting the already collected data and deciding the best action to take, according to the pre-defined parameters, in order to achieve the given goal. Designing, trial and error while using AI, brought ethics to the center of the dialogue between tech giants, enterprises, academic institutions as well as policymakers. Ethical challenges in AI brought ethical AI framework in place in an attempt to regulate people's lives and interactions, used for the benefit of society, for the human rights' protection as well as for the respect of individual's privacy and autonomy. The paper aims to summarize and critically evaluate the basic principles for the use of AI, with emphasis to the General Data Protection Regulation's (GDPR) approach, concerning data subject's consent, data protection principles and data subject's rights in a context of 'privacy by design' architecture.

show abstract

“…The learning and selection of features in these models are non-trackable, where the resulting alarms are considered unexplained. This problem has prompted the rise of explainable AI research to reveal more details on their automatic learning and selection of features [22].…”

Section: B Challengesmentioning

confidence: 99%

“…LSTM, the most efficient recurrent neural network (RNN) algorithm, provides a classifier with the advantage of managing the set of features, and the observation window [14,[19][20][21]. It distinguishes LSTM from other neural artificial networks (ANNs) and deep learning classifiers, which are sometimes defined as inexplicable [22]. The proposed decision support system is applied to the data set of the observational study collected at the University Hospital of Oslo [30].…”

Section: Introductionmentioning

confidence: 99%

A New Real Time Clinical Decision Support System Using Machine Learning for Critical Care Units

et al. 2020

View full text Add to dashboard Cite

Mean arterial pressure (MAP) is an important clinical parameter to evaluate the health of critically ill patients in intensive care units. Thus, the real time clinical decision support systems detecting anomalies and deviations in MAP enable early interventions and prevent serious complications. The state-ofthe-art decision support systems are based on a three-phase method that applies offline training, transfer learning, and retraining at the bedside. Their applicability in critical care units is challenging with delay and inaccuracy. In this paper, we propose a real time clinical decision support system forecasting the MAP status at the bedside using a new machine learning structure. The proposed system works in real time at the bedside without requiring the offline phase for training using large datasets. It thereby enables timely interventions and improved healthcare services. The proposed machine learning structure includes two stages. Stage I applies online learning using hierarchical temporal memory (HTM) to enable real time stream processing and provides unsupervised predictions. To the best of our knowledge, this is the first time it is applied to medical signals. Stage II is a long short-term memory (LSTM) classifier that forecasts the status of the patient's MAP ahead of time based on Stage I stream predictions. We perform a thorough performance evaluation of the proposed system and compare it with the state-of-the-art systems employing logistic regression (LR). The comparison shows the proposed system outperforms LR in terms of the classification accuracy, recall, precision, and area under the receiver operation curve (AUROC). INDEX TERMS Clinical decision support, classification, hierarchical temporal memory (HTM), long shortterm memory (LSTM), machine learning, real time prediction.

show abstract

Human-Centric AI for Trustworthy IoT Systems With Explainable Multilayer Perceptrons

Cited by 59 publications

References 19 publications

Deep Cybersecurity: A Comprehensive Overview from Neural Network and Deep Learning Perspective

Deep Cybersecurity: A Comprehensive Overview from Neural Network and Deep Learning Perspective

AI Ethics: Algorithmic Determinism or Self-Determination? The GPDR Approach

A New Real Time Clinical Decision Support System Using Machine Learning for Critical Care Units

Contact Info

Product

Resources

About