End-to-End 2D Convolutional Neural Network Architecture for Lung Nodule Identification and Abnormal Detection in Cloud

The extent of the peril associated with cancer can be perceived from the lack of treatment, ineffective early diagnosis techniques, and most importantly its fatality rate. Globally, cancer is the second leading cause of death and among over a hundred types of cancer; lung cancer is the second most common type of cancer as well as the leading cause of cancer-related deaths. Anyhow, an accurate lung cancer diagnosis in a timely manner can elevate the likelihood of survival by a noticeable margin and medical imaging is a prevalent manner of cancer diagnosis since it is easily accessible to people around the globe. Nonetheless, this is not eminently efficacious considering human inspection of medical images can yield a high false positive rate. Ineffective and inefficient diagnosis is a crucial reason for such a high mortality rate for this malady. However, the conspicuous advancements in deep learning and artificial intelligence have stimulated the development of exceedingly precise diagnosis systems. The development and performance of these systems rely prominently on the data that is used to train these systems. A standard problem witnessed in publicly available medical image datasets is the severe imbalance of data between different classes. This grave imbalance of data can make a deep learning model biased towards the dominant class and unable to generalize. This study aims to present an end-to-end convolutional neural network that can accurately differentiate lung nodules from non-nodules and reduce the false positive rate to a bare minimum. To tackle the problem of data imbalance, we oversampled the data by transforming available images in the minority class. The average false positive rate in the proposed method is a mere 1.5 percent. However, the average false negative rate is 31.76 percent. The proposed neural network has 68.66 percent sensitivity and 98.42 percent specificity.     

Geometry and topology optimization of geodesic domes using charged system search

Dome structures provide cost-effective solutions for covering large areas without intermediate supports. In this article, simple procedures are developed to reach the configuration of the geodesic domes. A new definition of dome optimization problems is given which consists of finding optimal sections for elements (size optimization), optimal height for the crown (geometry optimization) and the optimum number of elements (topology optimization) under determined loading conditions. In order to find the optimum design, the recently developed meta-heuristic algorithm, known as the Charged System Search (CSS), is applied to the optimum design of geodesic domes. The CSS takes into account the nonlinear response of the domes. Using CSS, the optimum design of the geodesic domes is efficiently performed.     

Determining malicious executable distinguishing attributes and low-complexity detection

Detection of rapidly evolving malware requires classification techniques that can effectively and efficiently detect zero-day attacks. Such detection is based on a robust model of benign behavior and deviations from that model are used to detect malicious behavior. In this paper we propose a low-complexity host-based technique that uses deviations in static file attributes to detect malicious executables. We first develop simple statistical models of static file attributes derived from the empirical data of thousands of benign executables. Deviations among the attribute models of benign and malware executables are then quantified using information-theoretic (Kullback-Leibler-based) divergence measures. This quantification reveals distinguishing attributes that are considerably divergent between benign and malware executables and therefore can be used for detection. We use the benign models of divergent attributes in cross-correlation and log-likelihood frameworks to classify malicious executables. Our results, using over 4,000 malicious file samples, indicate that the proposed detector provides reasonably high detection accuracy, while having significantly lower complexity than existing detectors.     

Improving minimax disparity model to determine the OWA operator weights

Determining the Ordered Weighted Averaging (OWA) operator weights is important in decision making applications. Several approaches have been proposed in the literature to obtain the associated weights. This paper provides an alternative disparity model to identify the OWA operator weights. The proposed mathematical model extends the existing disparity approaches by minimizing the sum of the deviation between two distinct OWA weights. The proposed disparity model can be used for a preference ranking aggregation. A numerical example in preference ranking and an application in search engines prove the usefulness of the generated OWA weights.     

Congestion prevention in broadband wireless access systems: An economic approach

While the demand for mobile broadband wireless services continues to increase, radio resources remain scarce. Even with the substantial increase in the supported bandwidth in the next generation broadband wireless access systems (BWASs), it is expected that these systems will severely suffer from congestion, due to the rapid increase in demand of bandwidth-intensive multimedia services. Without efficient bandwidth management and congestion control schemes, network operators may not be able to meet the increasing demand of users for multimedia services, and hence they may suffer an immense revenue loss. In this paper, we propose an admission-level bandwidth management scheme consisting of call admission control (CAC) and dynamic pricing. The main aim of our proposed scheme is to provide monetary incentives to users to use the wireless resources efficiently and rationally, hence, allowing efficient bandwidth management at the admission level. By dynamically determining the prices of units of bandwidth, the proposed scheme can guarantee that the number of connection requests to the system are less than or equal to certain optimal values computed dynamically, hence, ensuring a congestion-free system. The proposed scheme is general and can accommodate different objective functions for the admission control as well as different pricing functions. Comprehensive simulation results with accurate and inaccurate demand modeling are provided to show the effectiveness and strengths of our proposed approach.     

Role-based access to facilities lifecycle information on RFID tags

Radio Frequency Identification (RFID) based systems have been used in different applications in the Architecture, Engineering, Construction, Owner and Operator (AECOO) industry. Applications are mainly designed for specific lifecycle stage of the facility and serve the needs of only one of the stakeholders. This would increase the cost and the labor for adding and removing tags and eliminate the chance of using shared resources. In this paper, the usage of tags permanently attached to components is proposed where the memory of the tags is used during the lifecycle by different stakeholders for data storage and handover. A Building Information Model (BIM) database is used for tackling the interoperability issues allowing different users to access and share the data. To securely and efficiently store data on RFID tags in ifcXML format, multi-level encryption together with role-based access control is applied on the data stored on RFID tags. Each user is assigned a certain role and can only access the part of data for which he has authorization according to a predefined role and the Access Control Policy. To explore the technical feasibility of the proposed approach, a case study considering both facilities management and emergency management has been implemented and tested at Concordia University.     

Dynamic routing of real-time jobs among parallel EDF queues: A performance study

This paper introduces an analytical method for approximating the performance of a firm real-time system consisting of a number of parallel infinite-capacity single-server queues. The service discipline for the individual queues is earliest-deadline-first (EDF). Real-time jobs with exponentially distributed relative deadlines arrive according to a Poisson process. Jobs either all have deadlines until the beginning of service or deadlines until the end of service. Upon arrival, a job joins a queue according to a state-dependent stationary policy, where the state of the system is the number of jobs in each queue. Migration among the queues is not allowed. An important performance measure to consider is the overall loss probability of the system. The system is approximated by a Markovian model in the long run. The resulting model can then be solved analytically using standard Markovian solution techniques. Comparing numerical and simulation results for at least three different stationary policies, we find that the existing errors are relatively small.     

Online learning of task-driven object-based visual attention control

We propose a biologically-motivated computational model for learning task-driven and object-based visual attention control in interactive environments. In this model, top-down attention is learned interactively and is used to search for a desired object in the scene through biasing the bottom-up attention in order to form a need-based and object-driven state representation of the environment. Our model consists of three layers. First, in the early visual processing layer, most salient location of a scene is derived using the biased saliency-based bottom-up model of visual attention. Then a cognitive component in the higher visual processing layer performs an application specific operation like object recognition at the focus of attention. From this information, a state is derived in the decision making and learning layer. Top-down attention is learned by the U-TREE algorithm which successively grows an object-based binary tree. Internal nodes in this tree check the existence of a specific object in the scene by biasing the early vision and the object recognition parts. Its leaves point to states in the action value table. Motor actions are associated with the leaves. After performing a motor action, the agent receives a reinforcement signal from the critic. This signal is alternately used for modifying the tree or updating the action selection policy. The proposed model is evaluated on visual navigation tasks, where obtained results lend support to the applicability and usefulness of the developed method for robotics.     

Data envelopment analysis with classification and regression tree – a case of banking efficiency

Abstract: Data envelopment analysis (DEA) is a non‐parametric method for measuring the efficiency and productivity of decision‐making units (DMUs). On the other hand data mining techniques allow DMUs to explore and discover meaningful, previously hidden information from large databases. Classification and regression (C&R) is the commonly used decision tree in data mining. DEA determines the efficiency scores but cannot give details of factors related to inefficiency, especially if these factors are in the form of non‐numeric variables such as operational style in the banking sector. This paper proposes a framework to combine DEA with C&R for assessing the efficiency and productivity of DMUs. The result of the combined model is a set of rules that can be used by policy makers to discover reasons behind efficient and inefficient DMUs. As a case study, we use the proposed methodology to investigate factors associated with the efficiency of the banking sector in the Gulf Cooperation Council countries.