Machine learning (ML) has proven to be a useful technology for data analysis and modeling in a wide variety of domains, including food science and engineering. The use of ML models for the monitoring and prediction of food safety is growing in recent years. Currently, several studies have reviewed ML applications on foodborne disease and deep learning applications on food. This article presents a literature review on ML applications for monitoring and predicting food safety. The paper summarizes and categorizes ML applications in this domain, categorizes and discusses data types used for ML modeling, and provides suggestions for data sources and input variables for future ML applications. The review is based on three scientific literature databases: Scopus, CAB Abstracts, and IEEE. It includes studies that were published in English in the period from January 1, 2011 to April 1, 2021. Results show that most studies applied Bayesian networks, Neural networks, or Support vector machines. Of the various ML models reviewed, all relevant studies showed high prediction accuracy by the validation process. Based on the ML applications, this article identifies several avenues for future studies applying ML models for the monitoring and prediction of food safety, in addition to providing suggestions for data sources and input variables.

Diabetes is a metabolic disorder comprising of high glucose level in blood over a prolonged period in the body as it is not capable of using it properly. The severe complications associated with diabetes include diabetic ketoacidosis, nonketotic hypersmolar coma, cardiovascular disease, stroke, chronic renal failure, retinal damage and foot ulcers. There is a huge increase in the number of patients with diabetes globally and it is considered a major health problem worldwide. Early diagnosis of diabetes is helpful for treatment and reduces the chance of severe complications associated with it. Machine learning algorithms (such as ANN, SVM, Naive Bayes, PLS-DA and deep learning) and data mining techniques are used for detecting interesting patterns for diagnosing and treatment of disease. Current computational methods for diabetes diagnosis have some limitations and are not tested on different datasets or peoples from different countries which limits the practical use of prediction methods. This paper is an effort to summarize the majority of the literature concerned with machine learning and data mining techniques applied for the prediction of diabetes and associated challenges. This report would be helpful for better prediction of disease and improve in understanding the pattern of diabetes. Consequently, the report would be helpful for treatment and reduce risk of other complications of diabetes.

In the broad sense, the Bayesian networks (BN) are probabilistic graphical models that possess unique methodical features to model dependencies in complex networks, such as forward and backward propagation (inference) of disruptions. BNs have transitioned from an emerging topic to a growing research area in supply chain (SC) resilience and risk analysis. As a result, there is an acute need to review existing literature to ascertain recent developments and uncover future areas of research. Despite the increasing number of publications on BNs in the domain of SC uncertainty, an extensive review on their application to SC risk and resilience is lacking. To address this gap, we analyzed research articles published in peer-reviewed academic journals from 2007 to 2019 using network analysis, visualization-based scientometric analysis, and clustering analysis. Through this study, we contribute to literature by discussing the challenges of current research, and, more importantly, identifying and proposing future research directions. The results of our survey show that further debate on the theory and application of BNs to SC resilience and risk management is a significant area of interest for both academics and practitioners. The applications of BNs, and their conjunction with machine learning algorithms to solve big data SC problems relating to uncertainty and risk, are also discussed.

Climate change has already led to a wide range of impacts on our society, the economy and the environment. According to future scenarios, mountain regions are highly vulnerable to climate impacts, including changes in the water cycle (e.g. rainfall extremes, melting of glaciers, river runoff), loss of biodiversity and ecosystems services, damages to local economy (drinking water supply, hydropower generation, agricultural suitability) and human safety (risks of natural hazards). This is due to their exposure to recent climate warming (e.g. temperature regime changes, thawing of permafrost) and the high degree of specialization of both natural and human systems (e.g. mountain species, valley population density, tourism-based economy). These characteristics call for the application of risk assessment methodologies able to describe the complex interactions among multiple hazards, biophysical and socio-economic systems, towards climate change adaptation. Current approaches used to assess climate change risks often address individual risks separately and do not fulfil a comprehensive representation of cumulative effects associated to different hazards (i.e. compound events). Moreover, pioneering multi-layer single risk assessment (i.e. overlapping of single-risk assessments addressing different hazards) is still widely used, causing misleading evaluations of multi-risk processes. This raises key questions about the distinctive features of multi-risk assessments and the available tools and methods to address them. Here we present a review of five cutting-edge modelling approaches (Bayesian networks, agent-based models, system dynamic models, event and fault trees, and hybrid models), exploring their potential applications for multi-risk assessment and climate change adaptation in mountain regions. The comparative analysis sheds light on advantages and limitations of each approach, providing a roadmap for methodological and technical implementation of multi-risk assessment according to distinguished criteria (e.g. spatial and temporal dynamics, uncertainty management, cross-sectoral assessment, adaptation measures integration, data required and level of complexity). The results show limited applications of the selected methodologies in addressing the climate and risks challenge in mountain environments. In particular, system dynamic and hybrid models demonstrate higher potential for further applications to represent climate change effects on multi-risk processes for an effective implementation of climate adaptation strategies.

Many biological research areas such as drug design require gene regulatory networks to provide clear insight and understanding of the cellular process in living cells. This is because interactions among the genes and their products play an important role in many molecular processes. A gene regulatory network can act as a blueprint for the researchers to observe the relationships among genes. Due to its importance, several computational approaches have been proposed to infer gene regulatory networks from gene expression data. In this review, six inference approaches are discussed: Boolean network, probabilistic Boolean network, ordinary differential equation, neural network, Bayesian network, and dynamic Bayesian network. These approaches are discussed in terms of introduction, methodology and recent applications of these approaches in gene regulatory network construction. These approaches are also compared in the discussion section. Furthermore, the strengths and weaknesses of these computational approaches are described.