Search

This paper discusses the digital automation workflows and co-design methods that made possible the comprehensive robotic prefabrication of the BUGA Wood Pavilion - a large-scale production case study of robotic timber construction. Latest research in architectural robotics often focuses on the advancement of singular aspects of integrated digital fabrication and computational design techniques. Few researchers discuss how a multitude of different robotic processes can come together into seamless, collaborative robotic fabrication workflows and how a high level of interaction within larger teams of computational design and robotic fabrication experts can be achieved. It will be increasingly important to discuss suitable methods for the management of robotics and computational design in construction for the successful implementation of robotic fabrication systems in the context of the industry. We present here how a co-design approach enabled the organization of computational design decisions in reciprocal feedback with the fabrication planning, simulation and robotic code generation. We demonstrate how this approach can implement direct and curated reciprocal feedback between all planning domains - paving the way for fast-paced integrative project development. Furthermore, we discuss how the modularization of computational routines simplify the management and computational control of complex robotic construction efforts on a per-project basis and open the door for the flexible reutilization of developed digital technologies across projects and building systems., European Regional Development Fund, Deutsche Forschungsgemeinschaft, Ministerium für Wissenschaft, Forschung und Kunst Baden-Württemberg, Projekt DEAL, Bundesgartenschau Heilbronn 2019 GmbH, GETTYLAB

Edge computing is projected to become the dominant form of cloud computing in the future because of the significant advantages it brings to both users (less latency, higher throughput) and telecom operators (less Internet traffic, more local management). However, to fully unlock its potential at scale, system designers and automated optimization systems alike will have to monitor closely the dynamics of both processing and communication facilities. Especially the latter is often neglected in current systems since network performance in cloud computing plays only a minor role. In this paper, we propose the architecture of MECPerf, which is a solution to collect network measurements in a live edge computing domain, to be collected for offline provisioning analysis and simulations, or to be provided in real-time for on-line system optimization. MECPerf has been validated in a realistic testbed funded by the European Commission (Fed4Fire+), and we describe here a summary of the results, which are fully available as open data and through a Python library to expedite their utilization. This is demonstrated via a use case involving the optimization of a system parameter for migrating clients in a federated edge computing system adopting the GSMA platform operator concept.

The wide availability of embedded sensor platforms and lowcost cameras—together with the developments in wireless communication—make it now possible the conception of pervasive intelligent systems based on vision. Such systems may be understood as distributed and collaborative sensor networks, able to produce, aggregate and process images in order to understand the observed scene and communicate the relevant information found about it. In this paper, we investigate the peculiarities of visual sensor networks with respect to standard vision systems and we identify possible strategies to accomplish image processing and analysis tasks over them. Although the rather strong constraints in computational and transmission power of embedded platforms that may prevent the use of state of the art computer vision and pattern recognition methods, we argue that multinode processing methods may be envisaged to decompose a complex task into a hierarchy of computationally simpler problems to be solved over the nodes of the network. These ideas are illustrated by describing an application of visual sensor network to infomobility. In particular, we consider an experimental setting in which several views of a parking lot are acquired by the sensor nodes in the network. By integrating the various views, the network is capable to provide a description of the scene in terms of the available spaces in the parking lot.

none 12 si In this paper we present D.A.V.I.D.E. (Development for an Added Value Infrastructure Designed in Europe), an innovative and energy efficient High Performance Computing cluster designed by E4 Computer Engineering for PRACE (Partnership for Advanced Computing in Europe). D.A.V.I.D.E. is built using best-in-class components (IBM’s POWER8-NVLink CPUs, NVIDIA TESLA P100 GPUs, Mellanox InfiniBand EDR 100 Gb/s networking) plus custom hardware and an innovative system middleware software. D.A.V.I.D.E. features (i) a dedicated power monitor interface, built around the BeagleBone Black Board that allows high frequency sampling directly from the power backplane and scalable integration with the internal node telemetry and system level power management software; (ii) a custom-built chassis, based on OpenRack form factor, and liquid cooling that allows the system to be used in modern, energy efficient, datacenter; (iii) software components designed for enabling fine grain power monitoring, power management (i.e. power capping and energy aware job scheduling) and application power profiling, based on dedicated machine learning components. Software APIs are offered to developers and users to tune the computing node performance and power consumption around on the application requirements. The first pilot system that we will deploy at the beginning of 2017, will demonstrate key HPC applications from different fields ported and optimized for this innovative platform. open Abu Ahmad, Wissam; Bartolini, Andrea; Beneventi, Francesco; Benini, Luca; Borghesi, Andrea; Cicala, Marco; Forestieri, Privato; Gianfreda, Cosimo; Gregori, Daniele; Libri, Antonio; Spiga, Filippo; Tinti, Simone Abu Ahmad, Wissam; Bartolini, Andrea; Beneventi, Francesco; Benini, Luca; Borghesi, Andrea; Cicala, Marco; Forestieri, Privato; Gianfreda, Cosimo; Gregori, Daniele; Libri, Antonio; Spiga, Filippo; Tinti, Simone

A major drawback of nonlinear dimensionality reduction (DR) techniques is their inability to preserve some authentic information from the source domain, leading to projections that are often hard to interpret when it comes to observing anything other than the topological structure of the data. In this paper, we propose a nonlinear DR approach enforcing projection constraints resulting from an a priori knowledge about the structure of the data in multivariate periodical time series. We then propose several ways of exploiting this constrained projection to extract user-relevant information, such as the nominal behavior of a periodical dynamical system or the deviant behaviors which may occur at different time scales. The techniques are demonstrated on both a synthetic dataset composed of simulated multivariate data exhibiting a periodical behavior, and a real dataset corresponding to six months of sensor data acquisitions and recordings inside experimental buildings. 1 We would like to thank the Institut National de l'Energie Solaire (INES) and the CEA, LITEN, Laboratoire Energetique du Bâtiment for providing the data.

As the development of autonomous vehicles rapidly advances, the use of convoying/platooning becomes a more widely explored technology option for saving fuel and increasing the efficiency of traffic. In cooperative adaptive cruise control (CACC), the vehicles in a convoy follow each other under adaptive cruise control (ACC) that is augmented by the sharing of preceding vehicle acceleration through the vehicle to vehicle communication in a feedforward control path. In general, the desired velocity optimization for vehicles in the convoy is based on fuel economy optimization, rather than driveability. This paper is a preliminary study on the impact of the desired velocity profile on the driveability characteristics of a convoy of vehicles and the controller gain impact on the driveability. A simple low-level longitudinal model of the vehicle has been used along with a PD type cruise controller and a generic spacing policy for ACC/CACC. The acceleration of the previous vehicle is available to the next vehicle as input, and the simulations are performed as Cooperative Adaptive Cruise Control of a convoy of vehicles. Individual vehicle acceleration profiles have been analyzed for driveability for two different velocity profiles that are followed in a stretch of 720 m between stop signs. The controller gains have been re-tuned based on the parameter space robust control PID approach for driveability and compared with the original gains. The US06 SFTP drive cycle has also been used for the comparison of the two different controller gain sets.

In this paper, we propose to tackle egocentric action recognition by suppressing background distractors and enhancing action-relevant interactions. The existing approaches usually utilize two independent branches to recognize egocentric actions, i.e., a verb branch and a noun branch. However, the mechanism to suppress distracting objects and exploit local human-object correlations is missing. To this end, we introduce two extra sources of information, i.e., the candidate objects' spatial location and their discriminative features, to enable concentration on the occurring interactions. We design a Symbiotic Attention withObject-centric featureAlignmentframework (SAOA) to provide meticulous reasoning between the actor and the environment. First, we introduce an object-centric feature alignment method to inject the local object features to the verb branch and noun branch. Second, we propose a symbiotic attention mechanism to encourage the mutual interaction between the two branches and select the most action-relevant candidates for classification. The framework benefits from the communication among the verb branch, the noun branch, and the local object information. Experiments based on different backbones and modalities demonstrate the effectiveness of our method. Notably, our framework achieves the state-of-the-art on the largest egocentric video dataset.

This paper presents an unsupervised and semi-automatic image segmentation approach where we formulate the segmentation as an inference problem based on unary and pairwise assignment probabilities computed using low-level image cues. The inference is solved via a probabilistic graph matching scheme, which allows rigorous incorporation of low-level image cues and automatic tuning of parameters. The proposed scheme is experimentally shown to compare favorably with contemporary semi-supervised and unsupervised image segmentation schemes, when applied to contemporary state-of-the-art image sets.

The paper proposes a technique for Human Action Recognition (HAR) that uses a Convolutional Neural Network (CNN). Depth data sequences from the motion sensing devices are converted into images and fed into a CNN rather than using any conventional or statistical method. The initial data was obtained from 10 actions performed by six subjects captured by the Kinect v2 sensor as well as 20 actions performed by 7 subjects from the MSR 3D Action data set. A custom CNN architecture consisting of three convolutional and three max pooling layers followed by a fully connected layer was used. Training, validation, and testing was carried out on a total of 39715 images. An accuracy of 97.23% was achieved on the Kinect data set. On the MSR data set the accuracy was 87.1%.

Detection of Alzheimer's Disease (AD) from neuroimaging data such as MRI through machine learning have been a subject of intense research in recent years. Recent success of deep learning in computer vision have progressed such research further. However, common limitations with such algorithms are reliance on a large number of training images, and requirement of careful optimization of the architecture of deep networks. In this paper, we attempt solving these issues with transfer learning, where state-of-the-art architectures such as VGG and Inception are initialized with pre-trained weights from large benchmark datasets consisting of natural images, and the fully-connected layer is re-trained with only a small number of MRI images. We employ image entropy to select the most informative slices for training. Through experimentation on the OASIS MRI dataset, we show that with training size almost 10 times smaller than the state-of-the-art, we reach comparable or even better performance than current deep-learning based methods., Comment: Presented at IEEE BIBM 2017

This paper attempts at improving the accuracy of Human Action Recognition (HAR) by fusion of depth and inertial sensor data. Firstly, we transform the depth data into Sequential Front view Images(SFI) and fine-tune the pre-trained AlexNet on these images. Then, inertial data is converted into Signal Images (SI) and another convolutional neural network (CNN) is trained on these images. Finally, learned features are extracted from both CNN, fused together to make a shared feature layer, and these features are fed to the classifier. We experiment with two classifiers, namely Support Vector Machines (SVM) and softmax classifier and compare their performances. The recognition accuracies of each modality, depth data alone and sensor data alone are also calculated and compared with fusion based accuracies to highlight the fact that fusion of modalities yields better results than individual modalities. Experimental results on UTD-MHAD and Kinect 2D datasets show that proposed method achieves state of the art results when compared to other recently proposed visual-inertial action recognition methods.

Detection of Alzheimer's Disease (AD) from neuroimaging data such as MRI through machine learning has been a subject of intense research in recent years. Recent success of deep learning in computer vision has progressed such research further. However, common limitations with such algorithms are reliance on a large number of training images, and requirement of careful optimization of the architecture of deep networks. In this paper, we attempt solving these issues with transfer learning, where the state-of-the-art VGG architecture is initialized with pre-trained weights from large benchmark datasets consisting of natural images. The network is then fine-tuned with layer-wise tuning, where only a pre-defined group of layers are trained on MRI images. To shrink the training data size, we employ image entropy to select the most informative slices. Through experimentation on the ADNI dataset, we show that with training size of 10 to 20 times smaller than the other contemporary methods, we reach state-of-the-art performance in AD vs. NC, AD vs. MCI, and MCI vs. NC classification problems, with a 4% and a 7% increase in accuracy over the state-of-the-art for AD vs. MCI and MCI vs. NC, respectively. We also provide detailed analysis of the effect of the intelligent training data selection method, changing the training size, and changing the number of layers to be fine-tuned. Finally, we provide Class Activation Maps (CAM) that demonstrate how the proposed model focuses on discriminative image regions that are neuropathologically relevant, and can help the healthcare practitioner in interpreting the model's decision making process.

In the last decades, several studies have revealed how critical the urban heat island (UHI) effect can be in cities located in cold climates, such as the Canadian one. Meanwhile, many researchers have looked at the impact of the city design over the urban microclimate, and have raised concerns about the development of too dense cities. Under the effect of the “Places to Growth” plan, the city of Toronto is experiencing one of the highest rates of building development in North America. Over 48,000 and 33,000 new home permits were issued in 2012 and 2013 respectively, and at the beginning of 2015, almost 500 high-rise proposals across the Greater Toronto Area were released. In this context, it is important to investigate how new constructions will affect the urban microclimate, and to propose strategies to mitigate possible UHI effects. Using the software ENVI-met, microclimate simulations for the Church-Yonge corridor both in the current situation and with the new constructions are reported in this paper. The outdoor air temperature and the wind speed are the parameters used to assess the outdoor microclimate changes. The results show that the new constructions could increase the wind speed around the buildings. However, high-rise buildings will somewhat reduce the air temperature during day-time, as they will create large shadow areas, with lower average mean radiant temperature.

Mobile Edge Computing (MEC) has emerged as a promising paradigm catering to overwhelming explosions of mobile applications, by offloading the compute-intensive tasks to an MEC network for processing. The surging of deep learning brings new vigor and vitality to shape the prospect of intelligent Internet of Things (IoT), and edge intelligence arises to provision real-time deep neural network (DNN) inference services for users. In this paper, we study a novel delay-aware DNN inference throughput maximization problem by accelerating each DNN inference through jointly exploring DNN partitioning and multi-thread parallelism. Specifically, we consider the problem under both offline and online request arrival settings: a set of DNN inference requests is given in advance, and a sequence of DNN inference requests arrives one by one without the knowledge of future arrivals, respectively. We first show that the defined problems are NP-hard. We then devise a novel constant approximation algorithm for the problem under the offline setting. We also propose an online algorithm with a provable competitive ratio for the problem under the online setting. We finally evaluate the performance of the proposed algorithms through experimental simulations. Experimental results demonstrate that the proposed algorithms are promising.

In this paper, a long-term workload management problem for multi-server edge computing with server collaboration is studied. In the considered model, mobile users computation-intensive tasks are generated dynamically over the time and offloaded to associated edge servers according to pre-determined subscription agreements. Upon receiving the subscribed workload, each edge server can then decide to whether participate in server collaboration for enabling workload re-allocation (i.e., workload exchange) with other heterogeneously configured edge servers. Unlike most of the existing work, this paper takes into account both competitions and collaborations among strategic edge servers in sharing their computing capacities. To achieve the equilibrium for each edge server in minimizing its expected cost (including energy consumption, delay, transmission, configuration and pricing costs), a joint optimization is formulated for determining i) its amount of workload to undertake, ii) compensation price charged from peers, and iii) computing speed to adopt. To efficiently solve this problem, we propose a novel cooperative queueing game approach, which integrates a convex optimization, a core cost sharing scheme and a mapping rule. Theoretical analyses and extensive simulations are conducted to evaluate the performance of the proposed solution, and demonstrate its superiority over counterparts.

This paper studies the coordinated use of smart inverters with legacy voltage regulating devices to help increase the energy savings from conservation voltage reduction (CVR) in distribution systems with high photovoltaic penetration. Two voltage optimization algorithms are developed to evaluate the CVR benefit by considering two types of smart inverter functions: aggregated reactive power control and autonomous volt/VAR control. In each algorithm, smart inverters are coordinately controlled with the operation of legacy voltage regulating devices including load tap changers and capacitor banks. Both algorithms are tested on representative utility distribution system models. Simulation results demonstrate that the proposed algorithms can achieve around 1.8-3.6% energy savings when only using legacy voltage regulating devices and an additional 0.3-0.9% when adding smart inverters.

An increasing number of companies aim to enable their development teams to work in an agile manner. When introducing agile teams, companies face several challenges. This paper explores the kind of leadership needed to support teams to work in an agile way. One theoretical agile leadership concept describes a Scrum Master who is supposed to empower the team to lead itself. Empirical findings on such a leadership role are controversial. We still have not understood how leadership unfolds in a team that is by definition self-organizing. Further exploration is needed to better understand leadership in agile teams. Our goal is to explore how leadership changes while the team matures using the example of the Scrum Master. Through a grounded theory study containing 75 practitioners from 11 divisions at the Robert Bosch GmbH we identified a set of nine leadership roles that are transferred from the Scrum Master to the Development Team while it matures. We uncovered that a leadership gap and a supportive internal team climate are enablers of the role transfer process, whereas role conflicts may diminish the role transfer. To make the Scrum Master change in a mature team, team members need to receive trust and freedom to take on a leadership role which was previously filled by the Scrum Master. We conclude with practical implications for managers, Product Owners, Development Teams and Scrum Masters which they can apply in real settings., Robert Bosch Automotive Steering GmbH, Projekt DEAL

Solar energy is widely available in nature and electricity can be easily extracted using solar PV cells. A fuel cell being reliable and environment friendly becomes a good choice for the backup so as to compensate for continuously varying solar irradiation. This paper presents simple control schemes for power management of the DC microgrid consisting of PV modules and fuel cell as energy sources and a hydrogen electrolyzer system for storing the excess power generated. The supercapacitor bank is used as a short term energy storage device for providing the energy buffer whenever sudden fluctuations occur in the input power and the load demand. A new power control strategy is developed for a hydrogen storage system. The performance of the system is assessed with and without the supercapacitor bank and the results are compared. A comparative study of the voltage regulation of the microgrid is presented with the controller of the supercapacitor bank, realized using a traditional PI controller and an intelligent fuzzy logic controller.

A domestic water heating system that combines photovoltaic thermal (PVT) solar collectors with two heat pumps, in a novel cascade arrangement, is presented and analyzed in this paper. The goal of this analysis is to determine and compare the annual thermal energy output of the PVT cascade heat pump system with an evacuated tube and simultaneous consumption PVT single heat pump water heating system. The computational technique that was developed to analyze the PVT cascade heat pump system, which determines solar panel energy outputs, and heat pump operating characteristics, is described in detail. Case study simulation results are also presented, which include transient power output profiles, temperature profiles, and yearly energy output results. Hourly weather data, including air dry-bulb temperatures and solar flux values, from locations with a range of climates was used in these simulations. The results of this study show that the PVT cascade heat pump system has an annual thermal energy output improvement over the evacuated tube heating system ranging from 37% to 68%, depending on the selected simulation location.

Online recognition of gestures is critical for intuitive human-robot interaction (HRI) and further push collaborative robotics into the market, making robots accessible to more people. The problem is that it is difficult to achieve accurate gesture recognition in real unstructured environments, often using distorted and incomplete multisensory data. This paper introduces an HRI framework to classify large vocabularies of interwoven static gestures (SGs) and dynamic gestures (DGs) captured with wearable sensors. DG features are obtained by applying data dimensionality reduction to raw data from sensors (resampling with cubic interpolation and principal component analysis). Experimental tests were conducted using the UC2017 hand gesture dataset with samples from eight different subjects. The classification models show an accuracy of 95.6% for a library of 24 SGs with a random forest and 99.3% for 10 DGs using artificial neural networks. These results compare equally or favorably with different commonly used classifiers. Long short-term memory deep networks achieved similar performance in online frame-by-frame classification using raw incomplete data, performing better in terms of accuracy than static models with specially crafted features, but worse in training and inference time. The recognized gestures are used to teleoperate a robot in a collaborative process that consists in preparing a breakfast meal.

Deep latent generative models have attracted increasing attention due to the capacity of combining the strengths of deep learning and probabilistic models in an elegant way. The data representations learned with the models are often continuous and dense. However in many applications, sparse representations are expected, such as learning sparse high dimensional embedding of data in an unsupervised setting, and learning multi-labels from thousands of candidate tags in a supervised setting. In some scenarios, there could be further restriction on degree of sparsity: the number of non-zero features of a representation cannot be larger than a pre-defined threshold $L_{0}$ . In this paper we propose a sparse deep latent generative model SDLGM to explicitly model degree of sparsity and thus enable to learn the sparse structure of the data with the quantified sparsity constraint. The resulting sparsity of a representation is not fixed, but fits to the observation itself under the pre-defined restriction. In particular, we introduce to each observation $i$ an auxiliary random variable $L_{i}$ , which models the sparsity of its representation. The sparse representations are then generated with a two-step sampling process via two Gumbel-Softmax distributions. For inference and learning, we develop an amortized variational method based on MC gradient estimator. The resulting sparse representations are differentiable with backpropagation. The experimental evaluation on multiple datasets for unsupervised and supervised learning problems shows the benefits of the proposed method.

The proliferation of enterprise social media generates an ever-growing record of digital traces that provides ample opportunities to study the social making of organisations. Subsequently, we present the social fabric framework, which comprises a structured five-step approach for eliciting, interpreting, and representing the situated social idiosyncrasies and underlying patterns of the social making of organisations. The paper focuses on the application of the social fabric framework as a research method. However, the framework also lends itself to practice as a diagnostic tool that can detect emergent changes in the social fabric of an organisation as well as support organisational development and change. Moreover, by providing a vocabulary for articulating the social making of organisations, the framework can help organisation members reify their dispositions, make sense of the social dynamics, and enable a constructive discussion at the grassroots level about any controversy or aspiration.

International audience; In this paper we enhance the EasyCrypt proof assistant to reason about computational complexity of adversaries. The key technical tool is a Hoare logic for reasoning about computational complexity (execution time and oracle calls) of adversarial computations. Our Hoare logic is built on top of the module system used by EasyCrypt for modeling adversaries. We prove that our logic is sound w.r.t. the semantics of EasyCrypt programs-we also provide full semantics for the EasyCrypt module system, which was previously lacking. We showcase (for the first time in EasyCrypt and in other computer-aided cryptographic tools) how our approach can express precise relationships between the probability of adversarial success and their execution time. In particular, we can quantify existentially over adversaries in a complexity class, and express general composition statements in simulation-based frameworks. Moreover, such statements can be composed to derive standard concrete security bounds for cryptographic constructions whose security is proved in a modular way. As a main benefit of our approach, we revisit security proofs of some well-known cryptographic constructions and we present a new formalization of Universal Composability (UC).

Introduction. To represent our national goods at the Western market it is necessary to ensure, first of all, the competitiveness of local products through complex mechanization of technological processes, labour costs reduction, increasing yields and quality of received products. The aim of the research is to provide the comparative analysis of technology and machines for potato harvesting, to determine the main factors that influence the agricultural technical indicators of harvesting equipment, to develop technological process patterns and to examine the strategies for improving the potato root-and-harvest machines. Methods and methodology. The research was carried out on the basis of technological and constructional analysis of technology and machines for potato harvesting. The methods of comparison and mathematical modelling of technological processes were used in the study. The research studies of Ukrainian and foreign scientists on technology and machines for potato harvesting were used as information base of our paper. Results. A comparative analysis of technology and machines for potato harvesting made it possible to determine the main factors that influence the agricultural performance of harvesting machinery and to develop the technological process for a digger, a double-loader digger and a harvester (harvesting machines). A theoretical model of the technological processes of harvesting machines includes both uncontrolled and controlled factors that influence the choice of a potato harvesting technology of a digger, a double-loader digger and a harvester. Nevertheless, the first factors are connected, primarily, with the conditions of potato growth and its biological properties, and the second factors deal with the organizational and technical measures, including the improvement of the working bodies of machines (cutting, dirt digging through, top separation, longitudinal hump with cut roller and other constructive and kinematic parameters), quality of received products, length and terms of potato storage, available farming human resources, free vehicle in the period of harvesting, farm potato storage, farm equipment for potato cleaning and sorting.

Nowadays, embedded systems are provided with cache memories that are large enough to influence in both performance and energy consumption as never occurred before in this kind of systems. In addition, the cache memory system has been identified as a component that improves those metrics by adapting its configuration according to the memory access patterns of the applications being run. However, given that cache memories have many parameters which may be set to a high number of different values, designers are faced with a wide and time-consuming exploration space. In this paper, we propose an optimization framework based on Grammatical Evolution (GE) which is able to efficiently find the best cache configurations for a given set of benchmark applications. This metaheuristic allows an important reduction of the optimization runtime obtaining good results in a low number of generations. Besides, this reduction is also increased due to the efficient storage of evaluated caches. Moreover, we selected GE because the plasticity of the grammar eases the creation of phenotypes that form the call to the cache simulator required for the evaluation of the different configurations. Experimental results for the Mediabench suite show that our proposal is able to find cache configurations that obtain an average improvement of 62 % versus a real world baseline configuration.

This paper proposes a comprehensive steady-state analysis for a front-end Modular Multi-Parallel Rectifiers (MMR) system with a shared DC-link. A generalised mathematical representation for n number of parallel rectifiers is proposed. The MMR is analysed for both Continuous Conduction Mode (CCM) and Discontinuous Conduction Mode (DCM). In addition, the CCM and DCM boundary of the MMR is identified mathematically. A 60kW Simulink model for the MMR is utilised to confirm the proposed steady-state mathematical modelling equations.

Today there is a rapid development taking place in phenotyping of plants using non-destructive image based machine vision techniques. Machine vision based plant phenotyping ranges from single plant trait estimation to broad assessment of crop canopy for thousands of plants in the field. Plant phenotyping systems either use single imaging method or integrative approach signifying simultaneous use of some of the imaging techniques like visible red, green and blue (RGB) imaging, thermal imaging, chlorophyll fluorescence imaging (CFIM), hyperspectral imaging, 3-dimensional (3-D) imaging or high resolution volumetric imaging. This paper provides an overview of imaging techniques and their applications in the field of plant phenotyping. This paper presents a comprehensive survey on recent machine vision methods for plant trait estimation and classification. In this paper, information about publicly available datasets is provided for uniform comparison among the state-of-the-art phenotyping methods. This paper also presents future research directions related to the use of deep learning based machine vision algorithms for structural (2-D and 3-D), physiological and temporal trait estimation, and classification studies in plants.

Surveying wide areas with only one camera is a typical scenario in surveillance and automotive applications. Ultra wide-angle fisheye cameras employed to that end produce video data with characteristics that differ significantly from conventional rectilinear imagery as obtained by perspective pinhole cameras. Those characteristics are not considered in typical image and video processing algorithms such as motion estimation, where translation is assumed to be the predominant kind of motion. This contribution introduces an adapted technique for use in block-based motion estimation that takes into the account the projection function of fisheye cameras and thus compensates for the non-perspective properties of fisheye videos. By including suitable projections, the translational motion model that would otherwise only hold for perspective material is exploited, leading to improved motion estimation results without altering the source material. In addition, we discuss extensions that allow for a better prediction of the peripheral image areas, where motion estimation falters due to spatial constraints, and further include calibration information to account for lens properties deviating from the theoretical function. Simulations and experiments are conducted on synthetic as well as real-world fisheye video sequences that are part of a data set created in the context of this paper. Average synthetic and real-world gains of 1.45 and 1.51 dB in luminance PSNR are achieved compared against conventional block matching. Furthermore, the proposed fisheye motion estimation method is successfully applied to motion compensated temporal resolution enhancement, where average gains amount to 0.79 and 0.76 dB.

Component Based Software Engineering has one main sole motive of making the development process of software systems as easy as possible and to achieve this objective work needs to be done in previous systems to identify the concerns and limitations which can be overcome using this software engineering based approach. In this paper to support concept of component based system a domain is chosen that covers the GIS systems. GIS (Geographic Information Systems) are commonly used for development of map based applications these systems are widely used across the web and in various organizations. With the development and deepening of GIS, traditional GIS systems showed the challenges on isolation, sealing, interoperability and the limitations, thereby hindering further development and application of GIS technology. In this paper framework for component based GIS system is proposed. This framework is having rich graphical interface and user data can be easily retrieved from the connected database and displayed in the browser.

This paper presents DistRDF2ML, the generic, scalable, and distributed framework for creating in-memory data preprocessing pipelines for Spark-based machine learning on RDF knowledge graphs. This framework introduces software modules that transform large-scale RDF data into ML-ready fixed-length numeric feature vectors. The developed modules are optimized to the multimodal nature of knowledge graphs. DistRDF2ML provides aligned software design and usage principles as common data science stacks that offer an easy-to-use package for creating machine learning pipelines. The modules used in the pipeline, the hyper-parameters and the results are exported as a semantic structure that can be used to enrich the original knowledge graph. The semantic representation of metadata and machine learning results offers the advantage of increasing the machine learning pipelines’ reusability, explainability, and reproducibility. The entire framework of DistRDF2ML is open source, integrated into the holistic SANSA stack, documented in scala-docs, and covered by unit tests. DistRDF2ML demonstrates its scalable design across different processing power configurations and (hyper-)parameter setups within various experiments. The framework brings the three worlds of knowledge graph engineers, distributed computation developers, and data scientists closer together and offers all of them the creation of explainable ML pipelines using a few lines of code.

In this paper, a novel robotic grasping system is established to automatically pick up objects in cluttered scenes. A composite robotic hand composed of a suction cup and a gripper is designed for grasping the object stably. The suction cup is used for lifting the object from the clutter first and the gripper for grasping the object accordingly. We utilize the affordance map to provide pixel-wise lifting point candidates for the suction cup. To obtain a good affordance map, the active exploration mechanism is introduced to the system. An effective metric is designed to calculate the reward for the current affordance map, and a deep Q-Network (DQN) is employed to guide the robotic hand to actively explore the environment until the generated affordance map is suitable for grasping. Experimental results have demonstrated that the proposed robotic grasping system is able to greatly increase the success rate of the robotic grasping in cluttered scenes., Comment: has been accepted by IEEE/RSJ International Conference on Intelligent Robots and Systems 2019

This paper considers the problem of tracking the players in handball videos using a single video source. Tracking of handball players in the video is a difficult task as they can frequently leave and re-enter the camera field of view, often change directions quickly and occlude each other. Players wear similar team uniforms, play indoor under artificial illumination, with the background than can vary significantly as the handball court is often painted in various colors. The continually improving accuracy of CNN-based object detectors makes tracking-by-detection methods an attractive choice for tracking players in sports videos as they can perform online and with low computational requirements on top of object detection. Here we consider the use of three tracking-by-detection methods in conjunction with the YOLO object detector, namely the standard Hungarian assignment algorithm, the Simple Online, and Real-time Tracking (SORT) algorithm that adds a motion model, and its extension Deep SORT. The methods are tested on a custom dataset of handball video scenes.

With the rapid progress of wireless communication technologies along with their digital revolutions, the quantity of Internet of Things (IoT) has been increased by manifolds resulting in a huge increase in data volume and network traffic. It became easier for an intruder to pretend as a valid service provider, and generate different types of network attacks. This becomes even more severe when the service involves digital financial transactions. This paper proposes an intrusion detection system (IDS) based on a stacked autoencoder (AE) and a deep neural network (DNN). The stacked AE learns the features of the input network record in an unsupervised manner to decrease the feature width. Then, the DNN is trained in a supervised manner to extract deep-learned features for the classifier. In the proposed system, the stacked AE has two latent layers and the DNN has two or three layers, where each layer has a fully-connected layer, a batch normalization, and a dropout. The system was evaluated on three publicly available datasets: KDDCup99, NSL-KDD, and AWID. Experimental results exhibited that the proposed IDS achieved 94.2%, 99.7%, 99.9% accuracy, respectively, for multiclass classification.

The assets in Industry 4.0 are categorised into physical, virtual and human. The innovation and popularisation of ubiquitous computing enhance the usage of smart devices: RFID tags, QR codes, LoRa tags, etc. for assets identification and tracking. The generated data from Industrial Internet of Things (IIoT) eases information visibility and process automation in Industry 4.0. Virtual assets include the data produced from IIoT. One of the applications of the industrial big data is to predict the failure of manufacturing equipment. Predictive maintenance enables the business owner to decide such as repairing or replacing the component before an actual failure which affects the whole production line. Therefore, Industry 4.0 requires an effective asset management to optimise the tasks distributions and predictive maintenance model. This paper presents the Genetic Algorithm (GA) based resource management integrating with machine learning for predictive maintenance in fog computing. The time, cost and energy performance of GA along with MinMin, MaxMin, FCFS, RoundRobin are simulated in the FogWorkflowsim. The predictive maintenance model is built in two-class logistic regression using real-time datasets. The results demonstrate that the proposed technique outperforms MinMin, MaxMin, FCFS, RoundRobin in execution time, cost and energy usage. The execution time is 0.48% faster, 5.43% lower cost and energy usage is 28.10% lower in comparison with second-best results. The training and testing accuracy of the prediction model is 95.1% and 94.5%, respectively.

This paper aims to predict a set of apps a user will open on her mobile device in the next time slot. Such an information is essential for many smartphone operations, e.g., app pre-loading and content pre-caching, to improve user experience. However, it is hard to build an explicit model that accurately captures the complex environment context and predicts a set of apps at one time. This paper presents a deep reinforcement learning framework, named as DeepAPP, which learns a model-free predictive neural network from historical app usage data. Meanwhile, an online updating strategy is designed to adapt the predictive network to the time-varying app usage behavior. To transform DeepAPP into a practical deep reinforcement learning system, several challenges are addressed by developing a context representation method for complex contextual environment, a general agent for overcoming data sparsity and a lightweight personalized agent for minimizing the prediction time. Extensive experiments on a large-scale anonymized app usage dataset reveal that DeepAPP provides high accuracy (precision 70.6% and recall of 62.4%) and reduces the prediction time of the state-of-the-art by 6.58 times. A field experiment of 29 participants demonstrates DeepAPP can effectively reduce launch time of apps.

Projection techniques are often used to visualize high-dimensional data, allowing users to better understand the overall structure of multi-dimensional spaces on a 2D screen. Although many such methods exist, comparably little work has been done on generalizable methods of inverse-projection -- the process of mapping the projected points, or more generally, the projection space back to the original high-dimensional space. In this paper we present NNInv, a deep learning technique with the ability to approximate the inverse of any projection or mapping. NNInv learns to reconstruct high-dimensional data from any arbitrary point on a 2D projection space, giving users the ability to interact with the learned high-dimensional representation in a visual analytics system. We provide an analysis of the parameter space of NNInv, and offer guidance in selecting these parameters. We extend validation of the effectiveness of NNInv through a series of quantitative and qualitative analyses. We then demonstrate the method's utility by applying it to three visualization tasks: interactive instance interpolation, classifier agreement, and gradient visualization.

To date, the majority of positioning systems have been designed to operate within environments that have a long-term stable macro-structure with potential small-scale dynamics. These assumptions allow the existing positioning systems to produce and utilize stable maps. However, in highly dynamic industrial settings these assumptions are no longer valid and the task of tracking people is more challenging due to the rapid large-scale changes in structure. In this paper, we propose a novel positioning system for tracking people in highly dynamic industrial environments, such as construction sites. The proposed system leverages the existing CCTV camera infrastructure found in many industrial settings along with radio and inertial sensors within each worker’s mobile phone to accurately track multiple people. This multi-target multi-sensor tracking framework also allows our system to use cross-modality training in order to deal with the environment dynamics. In particular, we show how our system uses cross-modality training in order to automatically keep track environmental changes (i.e., new walls) by utilizing occlusion maps. In addition, we show how these maps can be used in conjunction with social forces to accurately predict human motion and increase the tracking accuracy. We have conducted extensive real-world experiments in a construction site showing significant accuracy improvement via cross-modality training and the use of social forces.

An efficient scalable data representation is an important task especially in the medical area, e.g. for volumes from Computed Tomography (CT) or Magnetic Resonance Tomography (MRT), when a downscaled version of the original signal is needed. Image and video coders based on wavelet transforms provide an adequate way to naturally achieve scalability. This paper presents a new approach for improving the visual quality of the lowpass band by using a novel graph-based method for motion compensation, which is an important step considering data compression. We compare different kinds of neighborhoods for graph construction and demonstrate that a higher amount of referenced nodes increases the quality of the lowpass band while the mean energy of the highpass band decreases. We show that for cardiac CT data the proposed method outperforms a traditional mesh-based approach of motion compensation by approximately 11 dB in terms of PSNR of the lowpass band. Also the mean energy of the highpass band decreases by around 30%.

Medical applications like Computed Tomography (CT) or Magnetic Resonance Tomography (MRT) often require an efficient scalable representation of their huge output volumes in the further processing chain of medical routine. A downscaled version of such a signal can be obtained by using image and video coders based on wavelet transforms. The visual quality of the resulting lowpass band, which shall be used as a representative, can be improved by applying motion compensation methods during the transform. This paper presents a new approach of using the distorted edge lengths of a mesh-based compensated grid instead of the approximated intensity values of the underlying frame to perform a motion compensation. We will show that an edge adaptive graph-based compensation and its usage for compensated wavelet lifting improves the visual quality of the lowpass band by approximately 2.5 dB compared to the traditional mesh-based compensation, while the additional filesize required for coding the motion information doesn't change.

In this paper, we describe our work-in-progress for developing Collaborative Discovering Tool (CoDi tool) that is meant for enhancing knowledge building discourse in the Future Learning Environment 2 (Fle2) system. Knowledge building discourse in the Fle2 type of systems usually leads to gradual accumulation of notes. We have found that users experience difficulties to get an overall picture of the knowledge produced and synthesize its advancement. By providing means for the participants to highlight key ideas, that they find particularly useful, the CoDi tool was designed to facilitate collective management of knowledge and inquiry and provide various visual representations of the database. We report results of a pilot experiment carried out with the CoDi prototype that appears to be a promising tool. However there are certain open questions concerning what are the social and pedagogical effects of highlighting ideas in different educational setting, how highlighting should be organized so that it would provide strongest support of knowledge advancement, and whether the results should always be shared not only by tutors but also by students. Regardless of the challenges, the development of the CoDi tool appears to open up an interesting line of inquiry that we would like to share with the CSCL community.

In 1996 Koschmann (1996) suggested computer-supported collaborative learning (CSCL) as an emerging paradigm of educational technology. After six years, how has the field developed? What does research say about CSCL to date? What is the state of the art? The aim of the present paper is to explore the foundations for CSCL, and in doing so, to contribute to the theoretical as well as empirical understanding and development of CSCL research.

We consider robot learning in the context of shared autonomy, where control of the system can switch between a human teleoperator and autonomous control. In this setting we address reinforcement learning, and learning from demonstration, where there is a cost associated with human time. This cost represents the human time required to teleoperate the robot, or recover the robot from failures. For each episode, the agent must choose between requesting human teleoperation, or using one of its autonomous controllers. In our approach, we learn to predict the success probability for each controller, given the initial state of an episode. This is used in a contextual multi-armed bandit algorithm to choose the controller for the episode. A controller is learnt online from demonstrations and reinforcement learning so that autonomous performance improves, and the system becomes less reliant on the teleoperator with more experience. We show that our approach to controller selection reduces the human cost to perform two simulated tasks and a single real-world task., Comment: Preprint version of IEEE Robotics and Automation Letters paper

Recently, Ivanov et al. proposed a new approach to construct code-based cryptosystems, namely the \begin{document}$ {\sf IKKR} $\end{document} public-key encryptions (PKE) in the International Workshop on Code-Based Cryptography (CBCrypto 2020) [ 9 ]. Unlike the usual construction in code-based encryption schemes which has restrictions on the Hamming weight of the error introduced into the ciphertext, the \begin{document}$ {\sf IKKR} $\end{document} approach allows error vectors of arbitrary weight being introduced into the ciphertext. Using this new approach, Ivanov et al. constructed two cryptosystems, namely the modified and the upgraded \begin{document}$ {\sf IKKR} $\end{document} -PKE. This paper aims to discuss the practical security of the \begin{document}$ {\sf IKKR} $\end{document} -PKE. In particular, we describe the weaknesses in the design of the public key used in the \begin{document}$ {\sf IKKR} $\end{document} -PKE. We exploit such weaknesses and propose two attacks to recover the plaintext in the \begin{document}$ {\sf IKKR} $\end{document} -PKE. The approach of our first attack is similar to the LCKN attack [ 12 ], whilst our second attack is more efficient than the LCKN attack. Our experimental results show that we can recover the plaintext from a given ciphertext in less than 176 milliseconds for schemes based on random Goppa codes and BCH codes.

Key assignment and key maintenance in encrypted networks of resource-limited devices may be a challenging task, due to the permanent need of replacing out-of-service devices with new ones and to the consequent need of updating the key information. Recently, Aragona et al. proposed a new cryptographic scheme, ECTAKS, which provides a solution to this design problem by means of a Diffie-Hellman-like key establishment protocol based on elliptic curves and on a prime field. Even if the authors proved some results related to the security of the scheme, the latter still lacks a formal security analysis. In this paper, we address this issue by providing a security proof for ECTAKS in the setting of computational security, assuming that no adversary can solve the underlying discrete logarithm problems with non-negligible success probability.

A tweakable enciphering scheme (TES) is a length preserving (tweakable) encryption scheme that provides (tweakable) strong pseudorandom permutation security on arbitrarily long messages. TES is traditionally built using block ciphers and the security of the mode depends on the strong pseudorandom permutation security of the underlying block cipher. In this paper, we construct TESs using public random permutations. Public random permutations are being considered as a replacement of block cipher in several cryptographic schemes including AEs, MACs, etc. However, to our knowledge, a systematic study of constructing TES using public random permutations is missing. In this paper, we give a generic construction of a TES which uses a public random permutation, a length expanding public permutation based PRF and a hash function which is both almost xor universal and almost regular. Further, we propose a concrete length expanding public permutation based PRF construction. We also propose a single keyed TES using a public random permutation and an AXU and almost regular hash function.

In a thought-provoking paper published in EJIS more than a decade ago, Lyytinen and colleagues asked the question, why does the “old world” perform poorly in high academic impact publishing? This triggered a lively debate on the epistemological and methodological traditions, preferences, and research practices of Europeans versus North Americans that has lasted until today. Is it still true, we asked ourselves, that European scholars generate less academic impact than their North American colleagues? Is the European research context indeed disadvantageous for developing high academic impact research? In this paper, we set out to explore these questions by analyzing the Google Scholar profiles of 1713 IS researchers from all over the world. Our findings show that Northern and Western European scholars no longer seem to differ significantly from their North American peers, even though the different research contexts still exercise a certain level of influence. However, is this a development the “old world" desires? We provide an assessment and some suggestions for the future of European IS research.

Building Information Modeling (BIM) and Virtual reality (VR) have attracted growing attention within the architecture, engineering, and construction (AEC) industry in recent years. Integration of BIM and VR technology can develop workflow efficiency through enhanced common understanding and prepare students in architecture and engineering programs to become leaders of the AEC industry. However, the current shortage of AEC professionals trained in BIM and VR is still a barrier to collaborative working practice in this industry. This paper reviews previous work on the BIM, VR, and BIM-into-VR in AEC education/training to bridge this gap. It also presents an advanced framework to clarify creating and using the BIM model into VR workflow in the AEC industry through the integrated definition function (IDEF0) model. The authors further evaluated the BIM-into-VR applications in literature and real-life by surveying students’ learning performance in terms of eight characteristics relevant to the VR environment and students’ performance within two projects, one involving the “NASA Mars Habitat Project” and the other involving the “Norris Center Project” at Northwestern University. The results confirmed that BIM-into-VR usability and efficiency in improving students’ main learning performance characteristics: Learnability, Interoperability, Visualization, Real-world, Interaction, Creativity, Motivation, and Comfort. This study addresses the advantages of using BIM-into-VR in AEC programs. It also offers suggestions to AEC educators and students in implementing BIM-into-VR in different courses and creating a roadmap for their future as professionals in the AEC industry.

Most clustering algorithms rely in some fundamental way on a measure of either similarity or distance — either between objects themselves, or between objects and cluster centroids. When the dataset contains mixed attributes, defining a suitable measure can be problematic. This paper presents a general graph-based method for clustering mixed-attribute datasets that does not require any explicit measure of similarity or distance. Empirical results on a range of well-known datasets using a range of evaluation measures show that the method achieves performance competitive with traditional clustering algorithms that require explicit calculation of distance or similarity, as well as with more recently proposed clustering algorithms based on matrix factorization.

PurposeThe best algorithm that was implemented on this Brazilian dataset was artificial immune system (AIS) algorithm. But the time and cost of this algorithm are high. Using asexual reproduction optimization (ARO) algorithm, the authors achieved better results in less time. So the authors achieved less cost in a shorter time. Their framework addressed the problems such as high costs and training time in credit card fraud detection. This simple and effective approach has achieved better results than the best techniques implemented on our dataset so far. The purpose of this paper is to detect credit card fraud using ARO.Design/methodology/approachIn this paper, the authors used ARO algorithm to classify the bank transactions into fraud and legitimate. ARO is taken from asexual reproduction. Asexual reproduction refers to a kind of production in which one parent produces offspring identical to herself. In ARO algorithm, an individual is shown by a vector of variables. Each variable is considered as a chromosome. A binary string represents a chromosome consisted of genes. It is supposed that every generated answer exists in the environment, and because of limited resources, only the best solution can remain alive. The algorithm starts with a random individual in the answer scope. This parent reproduces the offspring named bud. Either the parent or the offspring can survive. In this competition, the one which outperforms in fitness function remains alive. If the offspring has suitable performance, it will be the next parent, and the current parent becomes obsolete. Otherwise, the offspring perishes, and the present parent survives. The algorithm recurs until the stop condition occurs.FindingsResults showed that ARO had increased the AUC (i.e. area under a receiver operating characteristic (ROC) curve), sensitivity, precision, specificity and accuracy by 13%, 25%, 56%, 3% and 3%, in comparison with AIS, respectively. The authors achieved a high precision value indicating that if ARO detects a record as a fraud, with a high probability, it is a fraud one. Supporting a real-time fraud detection system is another vital issue. ARO outperforms AIS not only in the mentioned criteria, but also decreases the training time by 75% in comparison with the AIS, which is a significant figure.Originality/valueIn this paper, the authors implemented the ARO in credit card fraud detection. The authors compared the results with those of the AIS, which was one of the best methods ever implemented on the benchmark dataset. The chief focus of the fraud detection studies is finding the algorithms that can detect legal transactions from the fraudulent ones with high detection accuracy in the shortest time and at a low cost. That ARO meets all these demands.

Automatic blood vessel segmentation from retinal images plays an important role in the diagnosis of many systemic and eye diseases, including retinopathy of prematurity. Current state-of-the-art research in blood vessel segmentation from retinal images is based on convolutional neural networks. The solutions proposed so far are trained and tested on images from few available retinal blood vessel segmentation datasets, which might limit their performance when given an image with retinopathy of prematurity signs. In this paper, the performance of three high-performing convolutional neural networks for retinal blood vessel segmentation is evaluated in the context of blood vessel segmentation on retinal images exhibiting retinopathy of prematurity. The main motive behind the study is to test if existing public datasets suffice to develop a high performing predictor that could assist an ophthalmologist in retinopathy of prematurity diagnosis. To do so, the authors created a dataset consisting solely of retinopathy of prematurity images. Retinal blood vessels are manually labeled in the images by two observers, including an ophthalmologist experienced in retinopathy of prematurity treatment. Experimental results show that all three solutions have difficulties in detecting the retinal blood vessels of infants due to a lower contrast compared to images from public datasets as demonstrated by significant drop in classification sensitivity. All three solutions segment alongside retinal also choroidal blood vessels which are not used to diagnose retinopathy of prematurity, but instead represent noise and are confused with retinal blood vessels. Through observations and numerical analysis of experimental data, it is concluded that existing solutions for retinal blood vessel segmentation need improvement oriented toward using more detailed datasets or deeper models in order to assist the ophthalmologist in retinopathy of prematurity diagnosis.