One approach to determining whether an automated system is performing correctly is to monitor its performance, signaling when the performance is not acceptable; another approach is to automatically analyze the possible behaviors of the system a-priori and determine performance guarantees. Thea authors have applied this second approach to automatically derive performance guarantees for behavior-based, multi-robot critical mission software using an innovative approach to formal verification for robotic software. Localization and mapping algorithms can allow a robot to navigate well in an unknown environment. However, whether such algorithms enhance any specific robot mission is currently a matter for empirical validation. Several approaches to incorporating pre-existing software into the authors' probabilistic verification framework are presented, and one used to include Monte-Carlo based localization software. Verification and experimental validation results are discussed for real localization missions with this software, showing that the proposed approach accurately predicts performance.
This article describes how transfer subspace learning has recently gained popularity for its ability to perform cross-dataset and cross-domain object recognition. The ability to leverage existing data without the need for additional data collections is attractive for monitoring and surveillance technology, specifically for aided target recognition applications. Transfer subspace learning enables the incorporation of sparse and dynamically collected data into existing systems that utilize large databases. Manifold learning has also gained popularity for its success at dimensionality reduction. In this contribution, Manifold learning and transfer subspace learning are combined to create a new system capable of achieving high target recognition rates. The manifold learning technique used in this contribution is diffusion maps, a nonlinear dimensionality reduction technique based on a heat diffusion analogy. The transfer subspace learning technique used is Transfer Fisher's Linear Discriminative Analysis. The new system, manifold transfer subspace learning, sequentially integrates manifold learning and transfer subspace learning. In this article, the ability of the new techniques to achieve high target recognition rates for cross-dataset and cross-domain applications is illustrated using a variety of diverse datasets.
The monitoring and the surveillance of industrial and agricultural sites have become first order tasks mainly for security or the safety reasons. The main issues of this activity is tied to the size of the sites and to their accessibility. Thus, it seems nowadays relevant to tackle with this problem with robots, which can detect potential issues with a low operational cost. To that purpose, in addition to individual patrolling behavior, robots need coordination schemes. The goal of this paper is to explore the possibility of using interference fringes and waves properties in a virtual environment to tackle with the longitudinal distance regulation in the platoon control issue. The proposed model, based on a multi-agent paradigm, is considering each vehicle as an agent wave generator in the virtual environment.
This article describes how the integration of renewable energy in the power grid is a critical issue in order to realize a smart grid infrastructure. To that end, intelligent methods that monitor and currently predict the values of critical variables of renewable energy are essential. With respect to wind power, such variable is the wind speed given that it is of great interest to efficient schedule operation of a wind farm. In this article, a new methodology for predicting wind speed is presented for very short-term prediction horizons. The methodology integrates multiple Gaussian process regressors GPR via the adoption of an optimization problem whose solution is given by the particle swarm optimization algorithm. The optimized framework is utilized for the average hourly wind speed prediction for a prediction horizon of six hours ahead. Results demonstrate the ability of the methodology in accurately forecasting the wind speed. Furthermore, obtained forecasts are compared with those taken from single Gaussian process regressors as well from the integration of the same multiple GPR using a genetic algorithm.
Understanding diseases and human activities, and constructing highly accurate classifiers are two important tasks in bio-medicine, healthcare, and wearable sensor technology. Being able to mine high-quality patterns is useful here, as such patterns can help improve understanding and build accurate classifiers. However, most pattern mining algorithms only operate on discrete data; applying them often requires a binning step to discretize continuous attributes. This article presents a new discretization technique, called Class Distribution Curve based Binning CDC Binning; the main idea is to use a so-called class distribution curve, which measures the class purity in sliding windows over an attribute's range, to construct binning intervals. Experiments show that 1 CDC Binning outperforms existing binning methods in discovering high-quality patterns, especially when the class distribution curve is complicated e.g. when the two classes are two fairly similar human activities, and 2 it can outperform other binning methods by 10% in classification accuracy when using discovered patterns as features. CDC Binning is particularly useful for applications where the classes/activities to be distinguished are similar to each other. This is especially important in wearable sensor technology where detection of behavioral or activity changes in a person e.g. fall detection could indicate a significant medical event.
Cloud computing has been massively adopted in healthcare, where it attracts economic, operational, and functional advantages beneficial to insurance providers. However, according to Identity Theft Resource Centre, over twenty-five percent of data breaches in the US targeted healthcare. The HIPAA Journal reported an increase in healthcare data breaches in the US in 2016, exposing over 16 million health records. The growing incidents of cyberattacks in healthcare are compelling insurance providers to implement mitigating controls. Addressing data security and privacy issues before cloud adoption protects from monetary and reputation losses. This article provides an assessment tool for health insurance providers when adopting cloud vendor solutions. The final deliverable is a proposed framework derived from prominent cloud computing and governance sources, such as the Cloud Security Alliance, Cloud Control Matrix CSA, CCM v 3.0.1 and COBIT 5 Cloud Assurance.
A cyber physical system approach for a utility-scale photovoltaic (PV) array monitoring and control is presented in this article. This system consists of sensors that capture voltage, current, temperature, and irradiance parameters for each solar panel which are then used to detect, predict and control the performance of the array. More specifically the article describes a customized machine-learning method for remote fault detection and a computer vision framework for cloud movement prediction. In addition, a consensus-based distributed approach is proposed for resource optimization, and a secure authentication protocol that can detect intrusions and cyber threats is presented. The proposed system leverages video analysis of skyline imagery that is used along with other measured parameters to reconfigure the solar panel connection topology and optimize power output. Additional benefits of this cyber physical approach are associated with the control of inverter transients. Preliminary results demonstrate improved efficiency and robustness in renewable energy systems using advanced cyber enabled sensory analysis and fusion devices and algorithms.
The evolution of Internet of Things (IoT) has significantly contributed to the development of the sensing enterprise concept and to the use of appropriate information systems for real-time processing of sensor data that are able to provide meaningful insights about potential problems in a proactive way. In the current article, the authors outline a conceptual architecture and describe the system design requirements for deciding and acting ahead of time with the aim to address the Decide and the Act phases of the “Detect-Predict-Decide-Act” proactive principle, which are still underexplored areas. The associated developed information system is capable of being integrated with systems addressing the Detect and the Predict phases in an Event Driven Architecture (EDA).
Rapid diagnosis of symptoms caused by pest attack, diseases and nutritional or physiological disorders in apple orchards is essential to avoid greater losses. This paper aimed to evaluate the efficiency of Convolutional Neural Networks CNN to automatically detect and classify symptoms of diseases, nutritional deficiencies and damage caused by herbicides in apple trees from images of their leaves and fruits. A novel data set was developed containing labeled examples consisting of approximately 10,000 images of leaves and apple fruits divided into 12 classes, which were classified by algorithms of machine learning, with emphasis on models of deep learning. The results showed trained CNNs can overcome the performance of experts and other algorithms of machine learning in the classification of symptoms in apple trees from leaves images, with an accuracy of 97.3% and obtain 91.1% accuracy with fruit images. In this way, the use of Convolutional Neural Networks may enable the diagnosis of symptoms in apple trees in a fast, precise and usual way.
Ample evidence shows that the Qwerty layout is inefficient for one-finger typing on virtual keyboards: letters in common digrams are placed on opposite sides of the keyboard, resulting in an unnecessarily long finger-travel distance. In this paper, we report on using simulated annealing for modifying keyboard layout to reduce finger-travel distance for entering letters of the English alphabet. Our investigation led to improved 3 X 10, 4 X 7, and 5 X 6 layouts, all of which reduced the weighted sum of finger-travel distances for all digrams (denoted by d) by about 40% over Qwerty. The most improved layout is the 5 X 6 layout, which reduces d from 3.31 key widths (the value of d for Qwerty) to 1.78 key widths. These layouts also outperform the best layout reported in the literature.
Monitoring people's health is useful for enhancing the care provided to them by others or self-management of health. This article is a survey of the latest research on monitoring parameters indicating a person's current health or having potential to affect the person's health in future, using various physical sensors. These sensors include accelerometers, gyroscopes, electromyography sensors, fiber optic sensors, textile electrodes, thermistors, infrared sensors, force sensors, and photo diodes. The health parameters monitored include heart rate, respiration rate, weight, body mass index, calories burnt, pressure distribution, diet, blood pressure, blood glucose, oxygen saturation, posture, duration of sleep, quality of sleep, hand movement, body temperature, skin conductance, exposure to ultraviolet light, adherence to medication-intake schedule, gait characteristics, and steps taken. The population monitored includes elderly people, miners, stroke survivors, osteoarthritis patients, people suffering from anorexia nervosa, obese people, people with Parkinson's disease, people having panic attacks, and wheelchair users.
In this paper, the authors consider the planning problem for a system represented as a set of interacting agents evolving along time according to explicit timing constraints. Given a goal, the planning problem is to find the sequence of actions such that the system reaches the goal state in a limited time and in an optimal manner, assuming actions have a cost. In their approach, the planning problem is based on model-checking and controller synthesis techniques while the goal is defined using temporal logic. Each agent of the system is represented using the formalism of Priced Timed Game Automata (PTGA). PTGA is an extension of Timed Automata that allows the representation of cost on actions and the definition of uncontrollable actions. The authors define a planning algorithm that computes the best strategy to achieve a goal. To experiment their approach, they extend the classical Transport Domain with timing constraints, cost on actions and uncontrollable actions. The planning algorithm is finally presented on a marine ecosystem management problem.
In the domain of E&P petroleum chain, the authors have developed a study and proposed a conceptual framework for inserting direct rock data into reservoir models, through calibration of well logs. This type of data is often ignored or manual processed in actual petroleum reservoir modeling activities, due to its high cost of acquisition, or due to the high complexity for its modeling, interpretation and extrapolation. Direct rock data is the data that is acquired by direct observation of the rock, like descriptions of well cores, instead of indirect data, like seismic, well logs, etc. Directly observed data is important because it allows calibration of indirect interpretation methods, detection of errors in their evaluations and also to verify rock properties that is not possible when using indirect data. The authors claim that a well defined ontology can help in describing reservoir petrofacies, which are aggregates of rock data that can be detected through a special signature in the registers of indirectly collected rock data and, therefore, they can use to integrate rock data in reservoir models.
Multi-agent multi-team systems are commonly seen in environments where hierarchical layers of goals are at play. For example, theater-wide combat scenarios where multiple levels of command and control are required for proper execution of goals from the general to the foot soldier. Additionally, similar structures can be seen in game environments, where agents work together as teams to compete with other teams. The different agents within the same team must, while maintaining their own "personality", work together and coordinate with each other to achieve a common team goal. This paper develops strategy-based multi-agent multi-team systems, where strategy is framed as an instrument at the team level to coordinate the multiple agents of a team in a cohesive way. The authors present SiMAMT, a framework for strategy-based multi-agent multi-team systems. The different components of the framework, including strategy simulation, strategy inference, strategy evaluation, and strategy selection are described. A formal specification of strategy and strategy-based multi-agent multi-team systems is provided. An example and experimental results are given to illustrate the proposed framework and its efficacy.
Much effort has gone into improving the performance of evolutionary algorithms that augment traditional control in a Flapping Wing Micro Air Vehicle. An EA applied to such a vehicle in flight is expected to evolve solutions quickly to prevent disruptions in following the desired flight trajectory. Time to evolve solutions therefore is a major criterion by which performance of an algorithm is evaluated. This paper presents results of applying an assortment of different evolutionary algorithms to the problem. This paper also presents some discussion on which choices for representation and algorithm parameters would be optimal for the flight control problem and the rationale behind it. The authors also present a guided sampling approach of the search space to make use of the redundancy of workable solutions found in the search space. This approach has been demonstrated to improve learning times when applied to the problem.
Detection and identification of special nuclear materials (SNMs) are an essential part of the US nonproliferation effort. Modern cutting-edge SNM detection methodologies rely more and more on modeling and simulation techniques. Experiments with radiological samples in realistic configurations, is the ultimate tool that establishes the minimum detection limits of SNMs in a host of different geometries. Modern modeling and simulation approaches have the potential to significantly reduce the number of experiments with radioactive sources needed to determine these detection limits and reduce the financial barrier to SNM detection. Unreliable nuclear data is one of the principal causes of uncertainty in modeling and simulating nuclear systems. In particular, nuclear cross sections introduce a significant uncertainty in the nuclear data. The goal of this research is to develop a methodology that will autonomously extract the correct nuclear resonance characteristics of experimental data in a reliable way, a task previously left to expert judgement. Accurate nuclear data will in turn allow contemporary modeling and simulation to become far more reliable, de-escalating the extent of experimental testing. Consequently, modeling and simulation techniques reduce the use and distribution of radiological sources, while at the same time increase the reliability of the currently used methods for the detection and identification of SNMs.
Many-to-one wireless sensor networks suffer from an extreme variation of traffic load between nodes. Sensor nodes near the sink consume much more energy than distant ones, resulting in the energy hole problem (global variation of load). In addition, even nodes located at the same distance from the sink experience very different traffic load with each other (local variation). This uneven distribution of traffic load, both globally and locally, results in a severe shortening of the time until first node runs out of battery. This work focuses on balancing the load of equally-distant nodes from the sink by sharing each one's load among its next-hop neighbors. Eventually, packets are travelling from node to sink by following interlaced paths. The proposed routing mechanism, called braided routing, is a simple one and can be applied over any cost-based routing, incurring a negligible overhead. Simulation results show that the local variance of load is reduced nearly 20-60% on average while the time until first death can be prolonged more than twice in many cases and the lifetime about 15%.
The increasing demand for electricity the last decades leads towards the more frequent use of Combined Cycle Power Plants (CCPPs) because of the quite efficient way these units are capable to produce electricity. Hence, the prediction of the output of these units is of significant interest and constitutes the cornerstone towards the attainment of economic power production and a reliable power generation system as a whole. To that end, the aim of this paper is the development of a hierarchical predictive method based on Artificial Neural Networks (ANNs) in order to efficiently predict the power plant's output. The under consideration features are the hourly average ambient variables of Temperature (T), Ambient Pressure (AP), Relative Humidity (RH) and Exhaust Vacuum (V) for predicting the hourly power output of a CCPP. A parellel, but equally important, aim of this study is to assess the effectiveness of ANNs in this type of applications.
The main idea of this paper is to provide an insight to the reader and create awareness on some of the basic Curve Fitting techniques that have evolved and existed over the past few decades. A critical survey has been done on the various Curve Fitting methodologies proposed by various Mathematicians and Researchers who had been working in the fields of Computer Graphics, Image Processing and Pattern Recognition etc. to name a few over the past. Most of the methodologies that have evolved over time have their core structure derived from few significantly basic concepts and it is these basic concepts that have been tried to grasp through this survey and its tried to present the same as the essence of the survey. Note that the same physical variables may be named differently under different methodologies. The purpose was to maintain the originality of the work published by the original authors and this survey to only report their work as it is.
In this paper, a new descriptor based on phase congruency concept and LUV color space features is presented. Since the phase of the signal conveys more information regarding signal structure than the magnitude and the indispensable quality of the color in describing the world around us, the proposed descriptor can precisely identify and localize image features over the gradient based techniques, especially in the regions affected by illumination changes. The proposed features can be formed by extracting the phase congruency information for each pixel in the three-color image channels. The maximum phase congruency values are selected from the corresponding color channels. Histograms of the phase congruency values of the local regions in the image are computed with respect to its orientation. These histograms are concatenated to construct the proposed descriptor. Results of the experiments performed on the proposed descriptor show that it has better detection performance and lower error rates than a set of the state of the art feature extraction methodologies.
