A real-time abnormality detection system for intensive care management

Detecting abnormalities from multiple correlated time series is valuable to those applications where a credible realtime event prediction system will minimize economic losses (e.g. stock market crash) and save lives (e.g. medical surveillance in the operating theatre). For example, in an intensive care scenario, anesthetists perform a vital role in monitoring the patient and adjusting the flow and type of anesthetics to the patient during an operation. An early awareness of possible complications is vital for an anesthetist to correctly react to a given situation. In this demonstration, we provide a comprehensive medical surveillance system to effectively detect abnormalities from multiple physiological data streams for assisting online intensive care management. Particularly, a novel online support vector regression (OSVR) algorithm is developed to approach the problem of discovering the abnormalities from multiple correlated time series for accuracy and real-time efficiency. We also utilize historical data streams to optimize the precision of the OSVR algorithm. Moreover, this system comprises a friendly user interface by integrating multiple physiological data streams and visualizing alarms of abnormalities. © 2013 IEEE.

Modified AHP for gene selection and cancer classification using type-2 fuzzy logic

This paper proposes a modification to the analytic hierarchy process (AHP) to select the most informative genes that serve as inputs to an interval type-2 fuzzy logic system (IT2FLS) for cancer classification. Unlike the conventional AHP, the modified AHP allows us to process quantitative factors that are ranking outcomes of individual gene selection methods including t-test, entropy, receiver operating characteristic curve, Wilcoxon test, and signal-to-noise ratio. The IT2FLS is introduced for the classification task due to its great ability for handling nonlinear, noisy, and outlier data, which are common problems in cancer microarray gene expression profiles. An unsupervised learning strategy using the fuzzy c-means clustering is employed to initialize parameters of the IT2FLS. Other classifiers such as multilayer perceptron network, support vector machine, and fuzzy ARTMAP are also implemented for comparisons. Experiments are carried out on three well-known microarray datasets: diffuse large B-cell lymphoma, leukemia cancer, and prostate. Rather than the traditional cross validation, leave-one-out cross-validation strategy is applied for the experiments. Results demonstrate the performance dominance of the IT2FLS against the competing classifiers. More noticeably, the modified AHP improves the classification performance not only of the IT2FLS but of all other classifiers as well. Accordingly, the proposed combination between the modified AHP and IT2FLS is a powerful tool for cancer classification and can be implemented as a real clinical decision support system that is useful for medical practitioners.

Detection and classification of anomaly intrusion using hierarchy clustering and SVM

Anomaly detection as a kind of intrusion detection is good at detecting the unknown attacks or new attacks, and it has attracted much attention during recent years. In this paper, a new hierarchy anomaly intrusion detection model that combines the fuzzy c-means (FCM) based on genetic algorithm and SVM is proposed. During the process of detecting intrusion, the membership function and the fuzzy interval are applied to it, and the process is extended to soft classification from the previous hard classification. Then a fuzzy error correction sub interval is introduced, so when the detection result of a data instance belongs to this range, the data will be re-detected in order to improve the effectiveness of intrusion detection. Experimental results show that the proposed model can effectively detect the vast majority of network attack types, which provides a feasible solution for solving the problems of false alarm rate and detection rate in anomaly intrusion detection model.

Forecasting daily patient outflow from a ward having no real-time clinical data

OBJECTIVE: Our study investigates different models to forecast the total number of next-day discharges from an open ward having no real-time clinical data.

METHODS: We compared 5 popular regression algorithms to model total next-day discharges: (1) autoregressive integrated moving average (ARIMA), (2) the autoregressive moving average with exogenous variables (ARMAX), (3) k-nearest neighbor regression, (4) random forest regression, and (5) support vector regression. Although the autoregressive integrated moving average model relied on past 3-month discharges, nearest neighbor forecasting used median of similar discharges in the past in estimating next-day discharge. In addition, the ARMAX model used the day of the week and number of patients currently in ward as exogenous variables. For the random forest and support vector regression models, we designed a predictor set of 20 patient features and 88 ward-level features.

RESULTS: Our data consisted of 12,141 patient visits over 1826 days. Forecasting quality was measured using mean forecast error, mean absolute error, symmetric mean absolute percentage error, and root mean square error. When compared with a moving average prediction model, all 5 models demonstrated superior performance with the random forests achieving 22.7% improvement in mean absolute error, for all days in the year 2014.

CONCLUSIONS: In the absence of clinical information, our study recommends using patient-level and ward-level data in predicting next-day discharges. Random forest and support vector regression models are able to use all available features from such data, resulting in superior performance over traditional autoregressive methods. An intelligent estimate of available beds in wards plays a crucial role in relieving access block in emergency departments.

A fast malware feature selection approach using a hybrid of multi-linear and stepwise binary logistic regression

Malware replicates itself and produces offspring with the same characteristics but different signatures by using code obfuscation techniques. Current generation anti-virus engines employ a signature-template type detection approach where malware can easily evade existing signatures in the database. This reduces the capability of current anti-virus engines in detecting malware. In this paper, we propose a stepwise binary logistic regression-based dimensionality reduction techniques for malware detection using application program interface (API) call statistics. Finding the most significant malware feature using traditional wrapper-based approaches takes an exponential complexity of the dimension (m) of the dataset with a brute-force search strategies and order of (m-1) complexity with a backward elimination filter heuristics. The novelty of the proposed approach is that it finds the worst case computational complexity which is less than order of (m-1). The proposed approach uses multi-linear regression and the p-value of each individual API feature for selection of the most uncorrelated and significant features in order to reduce the dimensionality of the large malware data and to ensure the absence of multi-collinearity. The stepwise logistic regression approach is then employed to test the significance of the individual malware feature based on their corresponding Wald statistic and to construct the binary decision the model. When the selected most significant APIs are used in a decision rule generation systems, this approach not only reduces the tree size but also improves classification performance. Exhaustive experiments on a large malware data set show that the proposed approach clearly exceeds the existing standard decision rule, support vector machine-based template approach with complete data and provides a better statistical fitness.

Simulation-based support tool for operator performance in batch manufacturing

In industry, the workload and utilization of shop floor operators is often misunderstood. In this paper, we will present several real case studies, using Discrete Event Simulation (DES) models, which allow us to better understand operators in a batch manufacturing environment. The first study investigates labour in a machining plant consisting of multiple identical CNC machines that batch produce parts. The second study investigates labour in an eight station, gravity die casting rotary table. The results from these studies have shown that there can be potential improvements made by the production planners in the current labour configuration. In the first case study, a matrix is produced that estimates what the operator's utilization levels will be for various configurations. From this, the preferred operator to machine ratio over a range of cycle times is presented. In the second study, the results have shown that by reducing the casting cycle time, the operator would be overloaded. A discrete event simulation of these two cases highlighted areas that were misunderstood by plant management, and provided them with a useful decision support tool for production planning.

A decision support tool for resource allocation in batch manufacturing

A decision support tool for production planning is discussed in this paper to perform the job of machine grouping and labour allocation within a machining line. The production plans within the industrial partner have been historically inefficient because the relationship between the cycle times, the machine group size, and the operator's utilisation hasn't been properly understood. Starting with a simulation model, a rule-base has been generated to predict the operator's utilisation for a range of production settings. The resource allocation problem is then solved by breaking the problem into a series of smaller sized tasks. The objective is to minimise the number of operators and the difference between the maximum and minimum cycle times of machines within each group. The results from this decision support tool is presented for the particular case study.

Using social software to support the teaching of IT professional practice

Social software has been used to support problem-based learning activities in a wholly online information technology (IT) professional practice course at Deakin University since 2006. When the course was first delivered, the authentic learning environment was a website, with an intranet and team forums created in Drupal, the open source content management system (CMS). Although this environment was suitable, feedback from students and teaching staff highlighted areas where improvements could be made. In the second year of the course, Joomla!, the open source CMS, in combination with Simple Machines Forum (SMF), the open source online discussion community software, was used to provide the website, as well as the intranet and team forums respectively. Feedback in 2007 was more positive, suggesting that the Joomla!-SMF social software combination and the features implemented, improved the learning and teaching experience in comparison to the 2006 version of the course.

Decision support tool for production planning of a machining line

A decision support tool for production planning was developed to perform the difficult and time consuming task of allocating resources within the industrial partner's machining line, consisting of identical Computerized Numerically Controlled machines. The production-planning tool identified significant labour savings in a number of the industrial partner's production plans.

Is psychotherapy a vector for isolation and anomie?

A key traditional question the client learns in the conventional psychotherapies is ‘Am I getting what I want?’. But can this question incite a mindset that does not align with the ‘give and take’ essence of sustainable everyday relations? Is it possible that the psychotherapies—if these practices can be bundled together—might teach clients to become more self-centred and relationally illiterate? MARK FURLONG suggests that well-intentioned practitioners can inadvertently de-empathise, ignore or even disrupt their clients’ intimate networks. Findings from his research support the proposition that the action of the mainstream therapies tends to undermine the service users’ prospects for sustainable personal relationships. Exceptions were found in the specialist settings of paediatric and aged care, and in narrative and family therapy practice.

Gaming maching addiction : the role of avoidance, accessibility and social support

Commonality in etiology and clinical expression plus high comorbidity between pathological gambling and substance use disorders suggest common underlying motives. It is important to understand common motivators and differentiating factors. An overarching framework of addiction was used to examine predictors of problem gambling in current electronic gaming machine (EGM) gamblers. Path analysis was used to examine the relationships between antecedent factors (stressors, coping habits, social support), gambling motivations (avoidance, accessibility, social) and gambling behavior. Three hundred and forty seven (229 females: M = 29.20 years, SD = 14.93; 118 males: M = 29.64 years, SD = 12.49) people participated. Consistent with stress, coping and addiction theory, situational life stressors and general avoidance coping were positively related to avoidance-motivated gambling. In turn, avoidance-motivated gambling was positively related to EGM gambling frequency and problems. Consistent with exposure theory, life stressors were positively related to accessibility-motivated gambling, and accessibility-motivated gambling was positively related to EGM gambling frequency and gambling problems. These findings are consistent with other addiction research and suggest avoidance-motivated gambling is part of a more generalized pattern of avoidance coping with relative accessibility to EGM gambling explaining its choice as a method of avoidance. Findings also showed social support acted as a direct protective factor in relation to gambling frequency and problems and indirectly via avoidance and accessibility gambling motivations. Finally, life stressors were positively related to socially motivated gambling but this motivation was not related to either social support or gambling behavior suggesting it has little direct influence on gambling problems.

Embedded restricted Boltzmann machines for fusion of mixed data types and applications in social measurements analysis

Analysis and fusion of social measurements is important to understand what shapes the public’s opinion and the sustainability of the global development. However, modeling data collected from social responses is challenging as the data is typically complex and heterogeneous, which might take the form of stated facts, subjective assessment, choices, preferences or any combination thereof. Model-wise, these responses are a mixture of data types including binary, categorical, multicategorical, continuous, ordinal, count and rank data. The challenge is therefore to effectively handle mixed data in the a unified fusion framework in order to perform inference and analysis. To that end, this paper introduces eRBM (Embedded Restricted Boltzmann Machine) – a probabilistic latent variable model that can represent mixed data using a layer of hidden variables transparent across different types of data. The proposed model can comfortably support largescale data analysis tasks, including distribution modelling, data completion, prediction and visualisation. We demonstrate these versatile features on several moderate and large-scale publicly available social survey datasets.

Cumulative restricted Boltzmann machines for ordinal matrix data analysis

Ordinal data is omnipresent in almost all multiuser-generated feedback - questionnaires, preferences etc. This paper investigates modelling of ordinal data with Gaussian restricted Boltzmann machines (RBMs). In particular, we present the model architecture, learning and inference procedures for both vector-variate and matrix-variate ordinal data. We show that our model is able to capture latent opinion profile of citizens around the world, and is competitive against state-of-art collaborative filtering techniques on large-scale public datasets. The model thus has the potential to extend application of RBMs to diverse domains such as recommendation systems, product reviews and expert assessments.

Tensor-variate restricted Boltzmann machines

Restricted Boltzmann Machines (RBMs) are an important class of latent variable models for representing vector data. An under-explored area is multimode data, where each data point is a matrix or a tensor. Standard RBMs applying to such data would require vectorizing matrices and tensors, thus resulting in unnecessarily high dimensionality and at the same time, destroying the inherent higher-order interaction structures. This paper introduces Tensor-variate Restricted Boltzmann Machines (TvRBMs) which generalize RBMs to capture the multiplicative interaction between data modes and the latent variables. TvRBMs are highly compact in that the number of free parameters grows only linear with the number of modes. We demonstrate the capacity of TvRBMs on three real-world applications: handwritten digit classification, face recognition and EEG-based alcoholic diagnosis. The learnt features of the model are more discriminative than the rivals, resulting in better classification performance.

Rise of the machines: a critical consideration of automated leadership decision making in organizations

Machines are increasingly becoming a substitute for human skills and intelligence in a number of fields where decisions that are crucial to group performance have to be taken under stringent constraints—for example, when an army contingent has to devise battlefield tactics or when a medical team has to diagnose and treat a life-threatening condition or illness. We hypothesize a scenario where similar machine-based intelligent technology is available to support, and even substitute human decision making in an organizational leadership context. We do not engage in any metaphysical debate on the plausibility of such a scenario. Rather, we contend that given what we observe in several other fields of human decision making, such a scenario may very well eventuate in the near future. We argue a number of “positives” that can be expected to emerge out of automated group and organizational leadership decision making. We also posit several anti-theses—“negatives” that can also potentially emerge from the hypothesized scenario and critically consider their implications. We aim to bring leadership and organization theorists, as well as researchers in machine intelligence, together at the discussion table for the first time and postulate that while leadership decision making in a group/organizational context could be effectively delegated to an artificial-intelligence (AI)-based decision system, this would need to be subject to the devising of crucial safeguarding conditions.