IoTracker: A probabilistic event tracking approach for data-intensive IoT Smart Applications
IoTracker: یک رویکرد ردیابی رویداد احتمالی برای برنامههای هوشمند اینترنت اشیا با داده های فشرده-2022
Smart Applications for cities, industry, farming and healthcare use Internet of Things (IoT) approaches to improve the general quality. A dependency on smart applications implies that any misbehavior may impact our society with varying criticality levels, from simple inconveniences to life-threatening dangers. One critical challenge in this area is to overcome the side effects caused by data loss due to failures in software, hardware, and communication systems, which may also affect data logging systems. Event traceability and auditing may be impaired when an application makes automated decisions and the operating log is incomplete. In an environment where many events happen automatically, an audit system must understand, validate, and find the root causes of eventual failures. This paper presents a probabilistic approach to track sequences of events even in the face of logging data loss using Bayesian networks. The results of the performance analysis with three smart application scenarios show that this approach is valid to track events in the face of incomplete data. Also, scenarios modeled with Bayesian subnets highlight a decreasing complexity due to this divide and conquer strategy that reduces the number of elements involved. Consequently, the results improve and also reveal the potential for further advancement.
Keywords: Smart applications | Event tracker | Probabilistic tracker | Bayesian networks
A Quantum-Like Model for Predicting Human Decisions in the Entangled Social Systems
یک مدل کوانتومی برای پیشبینی تصمیمات انسانی در سیستمهای اجتماعی درهم تنیده-2022
Human-centered systems of systems, such as social networks, the Internet of Things, or healthcare systems are growingly becoming significant facets of modern life. Realistic models of human behavior in such systems play an essential role in their accurate modeling and prediction. Nevertheless, human behavior under uncertainty often violates the predictions by the conventional probabilistic models. Recently, quantum-like decision theories have shown a considerable potential to explain the contradictions in human behavior by applying quantum probabilities. But providing a quantum-like decision theory that could predict rather than describe the current state of human behavior is still one of the unsolved challenges. The fundamental contribution of this work is introducing the concept of entanglement from quantum information theory to Bayesian networks (BNs). This concept leads to an entangled quantum-like BN (QBN), in which each human is a part of the entire society. Accordingly, society’s effect on the dynamic evolution of the decision-making process, which is less often considered in decision theories, is modeled by entanglement measures. To reach this aim, we introduce a quantum-like witness and find the relationship between this witness and the famous concurrence entanglement measure. The proposed predictive entangled QBN (PEQBN) is evaluated on 22 experimental tasks. Results confirm that PEQBN provides more realistic predictions of human decisions under uncertainty when compared with classical BNs and three recent quantum-like approaches.
Index Terms: Bayesian networks (BNs) | entanglement | human behavior | quantum physics | quantum-like decision making | social systems.
Ontology knowledge base combined with Bayesian networks for integrated corridor risk warning
پایگاه دانش هستی شناسی همراه با شبکه های بیزی برای هشدار خطر یکپارچه راهرو-2021
With the accelerated urbanization process, the emergence of urban underground integrated pipeline corridors is the trend for cities, especially large and medium-sized cities. However, due to the complexity of the internal system of the integrated corridor, there are various risks in the process of its construction and operation and maintenance, and the risk factors are complex and diverse. In this paper, we introduce ontology technology and knowledge base construction into the risk management of integrated pipeline corridor, build an ontology-based knowledge base of integrated pipeline corridor risk, and construct a Bayesian network based on the established risk knowledge base for risk evaluation of identified risk factors. The combination of ontology knowledge base construction and Bayesian network method of integrated pipeline corridor risk makes the risk identification system completer and more effective, and the method can effectively evaluate the disaster risk level of integrated pipeline corridor operation and maintenance, which can meet the practical needs of integrated pipeline corridor operation and maintenance risk management and disaster prevention and mitigation work.
Keywords: Integrated corridor | Risk warning | Ontology knowledge | Bayesian networks
An assessment of probabilistic disaster in the oil and gas supply chain leveraging Bayesian belief network
ارزیابی فاجعه احتمالی در زنجیره تأمین نفت و گاز با استفاده از شبکه اعتقادی بیزی-2021
The oil and gas supply chain (OGSC) is considered to have one of the most significant stakes in the U.S. economy because of its interconnectedness with supply chains in other sectors, such as health and medicine, food, heavy manufacturing, and services. While oil and gas development is expanding exponentially, various factors ranging from man-made to natural disasters can hinder OGSC processes, which, in turn, can result in inefficient and costly operations in other sectors. This study presents a Bayesian Network (BN) model to predict and assess disasters in the OGSC based on seven main factors: technical, economic, social, political, safety, environmental, and legal. BBN is a probabilistic graphical model that is predominantly used in risk analysis to illustrate and assess probabilistic relationships among different variables. To draw meaningful managerial insights into the proposed model, sensitivity analysis and belief propagation are used. The results indicate that of the seven factors responsible for OGSC disasters, technical factors have the highest impact while legal and political factors have the lowest.
Keywords: Oil and gas | Supply chain | Disaster assessment | Bayesian network | Resilience
Accounting for Safety Barriers Degradation in the Risk Assessment of Oil and Gas Systems by Multistate Bayesian Networks
حسابداری برای تخریب موانع ایمنی در ارزیابی ریسک سیستم های نفت و گاز توسط شبکه های چندگانه بیزی-2021
In this paper, a multistate Bayesian Network (BN) is proposed to model and evaluate the functional performance of safety barriers in Oil and Gas plants. The nodes of the BN represent the safety barriers Health States (HSs) and the corresponding conditional Failure Probability (FP) values are assigned. HSs are assessed on the basis of specific Key Performance Indicators (KPIs) related to the barrier characteristics (i.e., technical, procedural or organizational, continuously monitored or event-based characterized). FP values are estimated from failure datasets (for technical barriers), evaluated by Human Reliability Analysis (HRA) (for operational and organi- zational barriers) and assigned by expert elicitation (for barriers lacking data or information). For illustration, the multistate BN model is developed for preventive barriers and applied to a case study related to the potential release of flammable material in the slug catcher of a representative O&G Upstream plant which may lead to major accident scenarios (fire, explosion, toxic dispersion). The results from the case study demonstrate that the multistate BN model is able to account for the safety barriers HS and their associated functional performance.
keywords: ارزیابی ریسک کمی | ارزیابی خطر زندگی | شبکه بیزی | مانع ایمنی | شاخص عملکرد کلیدی | حاشیه ایمنی احتمالی | Quantitative Risk Assessment | Living Risk Assessment | Bayesian Network | Safety Barrier | Key Performance Indicator | Probabilistic Safety Margins
An Approach Based on Bayesian Network for Improving ProjectManagement Maturity: An Application to Reduce Cost Overrun Risksin Engineering Projects
رویکرد مبتنی بر شبکه بیزی برای بهبود بلوغ مدیریت پروژه: برنامه ای برای کاهش هزینه های پیشی گرفتن از پروژه های مهندسی ریسکین-2020
The project management field has the imperative to increase the success probability of projects. Expertshave developed several Project Management Maturity (PMM) models to assess project managementpractices and improve the project outcome. However, the current literature lacks models that allowexperts to correlate the measured maturity with the expected probability of success. The present paperdevelops a general framework and a method to estimate the impact of PMM on project performance. Ituses Bayesian networks to formalize project management experts’ knowledge and to extract knowledgefrom a database of past projects. An industrial case concerning large projects in the oil and gas industryis used to illustrate the application of the method to reduce the risk of project cost (or budget) overruns.
Keywords:Bayesian Networks | Cost Overrun | Knowledge Modeling | Maturity Model | Project Management
Bayesian networks + reinforcement learning: Controlling group emotion from sensory stimuli
شبکه های بیزی + یادگیری تقویتی : کنترل احساسات گروهی از محرک های حسی-2020
As communication technology develops, various sensory stimuli can be collected in service spaces. To enhance the service effectiveness, it is important to determine the optimal stimuli to induce group emo- tion in the service space to the target emotion. In this paper, we propose a stimuli control system to adjust the group emotion. It is a stand-alone system that can determine optimal stimuli by utility ta- ble and modular tree-structured Bayesian networks designed for emotion prediction model proposed in the previous study. To verify the proposed system, we collected data using several scenarios at a kinder- garten and a senior welfare center. Each space is equipped with sensors for collection and equipment for controlling stimuli. As a result, the system shows a performance of 78% in the kindergarten and 80% in the senior welfare center. The proposed method shows much better performance than other classifica- tion methods with lower complexity. Also, reinforcement learning is applied to improving the accuracy of stimuli decision for a positive effect on system performance.
Keywords: Adjusting emotion | Group emotion | Bayesian networks | Reinforcement Learning | IoT
A knowledge-based reasoning model for crime reconstruction and investigation
یک مدل استدلال دانش بنیان برای بازسازی و تحقیقات جرم-2020
Artificial intelligence has been successfully applied in many areas including forensic sciences. Perhaps all forensic works can be regarded as helping reconstruct crimes, i.e. clarify and sequence the events that took place in the commission of a crime through evidence. However, there are few researches on the crime reconstruction using artificial intelligence methods. In this paper, we present a model based on Bayesian networks to help solve crimes. The model, which is termed ‘case-type based model’, is based on the knowledge of a type of crimes. We use Bayesian networks to represent the knowledge and conduct the uncertainty reasoning. We propose a growth algorithm of Bayesian networks to adapt the model to different cases. The model was tested through a real case, and the results indicate that the model can provide effective investigation suggestions and achieve the crime reconstruction.
Keywords: Artificial intelligence | Forensic science | Bayesian networks | Criminal investigation | Uncertainty reasoning | Evidence
A novel approach to solve AI planning problems in graph transformations
یک رویکرد جدید برای حل مشکلات برنامه ریزی هوش مصنوعی در تحولات نمودار-2020
The aim of AI planning is to solve the problems with no exact solution available. These problems usually have a big search space, and planning may not find plans with the least actions and in the shortest time. Recent researches show that using suitable heuristics can help to find desired plans. In planning problems specified formally through graph transformation system (GTS), there are dependencies between applied rules (actions) in the search space. This fact motivates us to solve the planning problem for a small goal (instead of the main goal), extract dependencies from the searched space, and use these dependencies to solve the planning problem for the main goal. In GTS based systems, the nodes of a state (really is a graph) can be grouped due to their type. To create a small (refined) goal, we use a refinement technique to remove the predefined percent of nodes from each group of the main goal. Bayesian Optimization Algorithm (BOA) is then used to solve the planning problem for the refined goal. BOA is an Estimation of Distribution Algorithm (EDA) in which Bayesian networks are used to evolve the solution populations. Actually, a Bayesian network is learned from the current population, and then this network is employed to generate the next population. Since the last Bayesian network learned in BOA has the knowledge about dependencies between applied rules, this network can be used to solve the planning problem for the main goal. Experimental results on four well-known planning domains confirm that the proposed approach finds plans with the least actions and in the lower time compared with the state-of-the-art approaches.
Keywords: Bayesian Optimization Algorithm | AI planning | Graph transformation system | Bayesian network | Refinement
Deep learning model for end-to-end approximation of COSMIC functional size based on use-case names
مدل یادگیری عمیق برای تخمین پایان به پایان اندازه کاربردی COSMIC بر اساس نامهای مورد استفاده-2020
Context: COSMIC is a widely used functional size measurement (FSM) method that supports software development effort estimation. The FSM methods measure functional product size based on functional requirements. Unfortu- nately, when the description of the product’s functionality is often abstract or incomplete, the size of the product can only be approximated since the object to be measured is not yet fully described. Also, the measurement performed by human-experts can be time-consuming, therefore, it is worth considering automating it. Objective: Our objective is to design a new prediction model capable of approximating COSMIC-size of use cases based only on their names that is easier to train and more accurate than existing techniques. Method: Several neural-network architectures are investigated to build a COSMIC size approximation model. The accuracy of models is evaluated in a simulation study on the dataset of 437 use cases from 27 software develop- ment projects in the Management Information Systems (MIS) domain. The accuracy of the models is compared with the Average Use-Case approximation (AUC), and two recently proposed two-step models —Average Use-Case Goal-aware Approximation (AUCG) and Bayesian Network Use-Case Goal AproxImatioN (BN-UCGAIN). Results: The best prediction accuracy was obtained for a convolutional neural network using a word-embedding model trained on Wikipedia + Gigaworld. The accuracy of the model outperformed the baseline AUC model by ca. 20%, and the two-step models by ca. 5–7%. In the worst case, the improvement in the prediction accuracy is visible after estimating 10 use cases. Conclusions: The proposed deep learning model can be used to automatically approximate COSMIC size of software applications for which the requirements are documented in the form of use cases (or at least in the form of use- case names). The advantage of the model is that it does not require collecting historical data other than COSMIC size and names of use cases.
Keywords: Functional size approximation | Approximate software sizing methods | COSMIC | Deep learning | Word embeddings | Use cases