Abstract: The sensory stimuli from the urban environment are often distinguished as subtle structures that derive from experiencing the city. The experience of the urban environment is also related to the social relationships and memories that complete the 'urban eyescapes' and the way individuals can recall them. Despite the fact that the consideration of urban sensory stimuli is part of urban design, currently the account of visual experience in urban studies is hard to be identified. This article explores ways of recording how the senses mediate one's engagement with the urban environment. This study involves an experiment in the urban environment of the Copenhagen city centre, with 20 subjects performing a walking task. The aim of the experiment is to categorize the visual 'Bold Headlined Stimuli’ (BHS) of the examined environment, using eye-tracking techniques. The analysis allows us to identify the Headlining Stimuli Process, (HSP) in the select urban environment. HSP is significantly mediated by body mobility and perceptual memories and has shown how urban stimuli influence the intelligibility and the recalling patterns of the urban characteristics. The results have yielded a 'Bold Headline list' of stimuli related to: the spatial characteristics of higher preference; the stimuli that are relevant to livability; and the spatial dimensions easier to recall. The data of BHS will be used in cross-disciplinary city analysis. In the future, these results could be useful in urban design, to provide information on how urban space affects the human activities.
Abstract: Robotic assistance in nursing care is an increasingly
important area of research and development. Facing a shortage of
labor and an increasing number of people in need of care, the
German Nursing Care Innovation Center (Pflegeinnovationszentrum,
PIZ) aims to address these challenges from the side of technology.
Little is known about nurses experiences with existing robotic
assistance systems. Especially nurses perspectives on starting points
for the development of robotic solutions, that target recurring
burdensome tasks in everyday nursing care, are of interest. This
paper presents findings focusing on robotics resulting from an
explanatory mixed-methods study on nurses experiences with and
their expectations for innovative technologies in nursing care in
stationary and ambulant care facilities and hospitals in Germany.
Based on the findings, eight scenarios for robotic assistance are
identified based on the real needs of practitioners. An initial system
addressing a single use-case is described to show perspectives for the
use of robots in nursing care.
Abstract: This paper presents and benchmarks a number of
end-to-end Deep Learning based models for metaphor detection in
Greek. We combine Convolutional Neural Networks and Recurrent
Neural Networks with representation learning to bear on the metaphor
detection problem for the Greek language. The models presented
achieve exceptional accuracy scores, significantly improving the
previous state-of-the-art results, which had already achieved accuracy
0.82. Furthermore, no special preprocessing, feature engineering or
linguistic knowledge is used in this work. The methods presented
achieve accuracy of 0.92 and F-score 0.92 with Convolutional
Neural Networks (CNNs) and bidirectional Long Short Term Memory
networks (LSTMs). Comparable results of 0.91 accuracy and 0.91
F-score are also achieved with bidirectional Gated Recurrent Units
(GRUs) and Convolutional Recurrent Neural Nets (CRNNs). The
models are trained and evaluated only on the basis of training tuples,
the related sentences and their labels. The outcome is a state-of-the-art
collection of metaphor detection models, trained on limited labelled
resources, which can be extended to other languages and similar
tasks.
Abstract: Expert sight readers rely on their ability to recognize patterns in scores, their inner hearing and prediction skills in order to perform complex sight reading exercises. They also have the ability to observe deviations from expected patterns in musical scores. This increases the “Eye-hand span” (reading ahead of the point of playing) in order to process the elements in the score. The study aims to investigate the gaze patterns of expert and non-expert sight readers focusing on key and time signatures. 20 musicians were tasked with playing 12 sight reading examples composed for one hand and five examples composed for two hands to be performed on a piano keyboard. These examples were composed in different keys and time signatures and included accidentals and changes of time signature to test this theory. Results showed that the experts fixate more and for longer on key and time signatures as well as deviations in examples for two hands than the non-expert group. The inverse was true for the examples for one hand, where expert sight readers showed fewer and shorter fixations on key and time signatures as well as deviations. This seems to suggest that experts focus more on the key and time signatures as well as deviations in complex scores to facilitate sight reading. The examples written for one appeared to be too easy for the expert sight readers, compromising gaze patterns.
Abstract: This paper presents a taxonomy of non-technical skills, communicative intentions, and behavior for an individual acting as a medical coordinator. In medical emergency situations, a leader among the group is imperative to both patient health and team emotional and mental health. Situational Leadership is used to make clear and easy-to-follow guidelines for behavior depending on circumstantial factors. Low-level leadership behaviors belonging to two different styles, directive and supporting, are identified from literature and are included in the proposed taxonomy. The high-level information in the taxonomy consists of the necessary non-technical skills belonging to a medical coordinator: situation awareness, decision making, task management, and teamwork. Finally, communicative intentions, dimensions, and functions are included. Thus this work brings high-level and low-level information - medical non-technical skills, communication capabilities, and leadership behavior - into a single versatile taxonomy of behavior.
Abstract: Many designers are asking for an automated path from an abstract mathematical MATLAB model to a high-quality Register-Transfer Level (RTL) hardware description. Manual transformations of MATLAB or intermediate code are needed, when the design abstraction is changed. Design conversion is problematic as it is multidimensional and it requires many different design steps to translate the mathematical representation of the desired functionality to an efficient hardware description with the same behavior and configurability. Yet, a manual model conversion is not an insurmountable task. Using currently available design tools and an appropriate design methodology, converting a MATLAB model to efficient hardware is a reasonable effort. This paper describes a simple and flexible design methodology that was developed together with several design teams.
Abstract: Task Assignment and Scheduling is a challenging Operations Research problem when there is a limited number of resources and comparatively higher number of tasks. The Cost Management team at Cummins needs to assign tasks based on a deadline and must prioritize some of the tasks as per business requirements. Moreover, there is a constraint on the resources that assignment of tasks should be done based on an individual skill level, that may vary for different tasks. Another constraint is for scheduling the tasks that should be evenly distributed in terms of number of working hours, which adds further complexity to this problem. The proposed greedy approach to solve assignment and scheduling problem first assigns the task based on management priority and then by the closest deadline. This is followed by an iterative selection of an available resource with the least allocated total working hours for a task, i.e. finding the local optimal choice for each task with the goal of determining the global optimum. The greedy approach task allocation is compared with a variant of Hungarian Algorithm, and it is observed that the proposed approach gives an equal allocation of working hours among the resources. The comparative study of the proposed approach is also done with manual task allocation and it is noted that the visibility of the task timeline has increased from 2 months to 6 months. An interactive dashboard app is created for the greedy assignment and scheduling approach and the tasks with more than 2 months horizon that were waiting in a queue without a delivery date initially are now analyzed effectively by the business with expected timelines for completion.
Abstract: In this article, the collection and analysis of drawings are implemented and discussed as a methodological approach to reconstruct children's perspective on horse-assisted interventions. For this purpose, drawings of three children (8-10 years old) were included in the research process in order to clarify the question of what insights can be derived from the drawings about the child's perspective on the intervention. The children were asked to draw a picture of themselves at the horse stable. Practical implementation considerations are disclosed. The developed analysis steps consider the work of two art historians (Erwin Panofsky and Max Imdahl) to capture the visual sense and to interpret the children's drawings. Relevant topics about the children's perspective can be inferred from the drawings. In the drawings, the following topics are important for the children: Overcoming challenges and fears in handling the horse, support from an adult in handling the horse and feeling self-confident and competent to act after completing tasks with the horse. The drawings show the main topics which are relevant for the children and can be used as a basis for conversation. All in all, the child's drawing offers a useful addition to other survey methods in order to gain further insights into the experiences of children in a horse-assisted setting.
Abstract: Multimodal image registration is a profoundly complex
task which is why deep learning has been used widely to address it in
recent years. However, two main challenges remain: Firstly, the lack
of ground truth data calls for an unsupervised learning approach,
which leads to the second challenge of defining a feasible loss
function that can compare two images of different modalities to judge
their level of alignment. To avoid this issue altogether we implement a
generative adversarial network consisting of two registration networks
GAB, GBA and two discrimination networks DA, DB connected by
spatial transformation layers. GAB learns to generate a deformation
field which registers an image of the modality B to an image of the
modality A. To do that, it uses the feedback of the discriminator DB
which is learning to judge the quality of alignment of the registered
image B. GBA and DA learn a mapping from modality A to modality
B. Additionally, a cycle-consistency loss is implemented. For this,
both registration networks are employed twice, therefore resulting in
images ˆA, ˆB which were registered to ˜B, ˜A which were registered
to the initial image pair A, B. Thus the resulting and initial images
of the same modality can be easily compared. A dataset of liver
CT and MRI was used to evaluate the quality of our approach and
to compare it against learning and non-learning based registration
algorithms. Our approach leads to dice scores of up to 0.80 ± 0.01
and is therefore comparable to and slightly more successful than
algorithms like SimpleElastix and VoxelMorph.
Abstract: Since the vision system application in industrial environment for autonomous purposes is required intensely, the image recognition technique becomes an important research topic. Here, deep learning algorithm is employed in image system to recognize the industrial object and integrate with a 7A6 Series Manipulator for object automatic gripping task. PC and Graphic Processing Unit (GPU) are chosen to construct the 3D Vision Recognition System. Depth Camera (Intel RealSense SR300) is employed to extract the image for object recognition and coordinate derivation. The YOLOv2 scheme is adopted in Convolution neural network (CNN) structure for object classification and center point prediction. Additionally, image processing strategy is used to find the object contour for calculating the object orientation angle. Then, the specified object location and orientation information are sent to robotic controller. Finally, a six-axis manipulator can grasp the specific object in a random environment based on the user command and the extracted image information. The experimental results show that YOLOv2 has been successfully employed to detect the object location and category with confidence near 0.9 and 3D position error less than 0.4 mm. It is useful for future intelligent robotic application in industrial 4.0 environment.
Abstract: The Nigeria Police Force bears the constitutional mandate as the primary policing agency for the protection of life and property within Nigeria; however, the police have an historical ill-reputation for corruption, ineptitude and impunity. Using the institutional theory of police as the framework of analysis, the paper argues that the performance of the police in Nigeria mirrors the dominant political, social and economic institutions and the structural environment of the Nigerian state. The article puts in perspective the deliberate political decision to underfund the police, leaving officers of the force the extra task of foraging for funds to undertake the duty that the Nigeria state primarily exists for; the article further explores the nexus between corruption in the police in Nigeria and the issue of funding. The article finds that the Nigerian state, by deliberately under-funding the police, while expecting the agency to perform its duties, has indirectly sanctioned the corruption of the force and approved the cooption of the institution of police and policing for private use in Nigeria.
Abstract: Electric Vehicles (EV) appear to be gaining increasing patronage as a feasible alternative to Internal Combustion Engine Vehicles (ICEVs) for having low emission and high operation efficiency. The EV energy storage systems are required to handle high energy and power density capacity constrained by limited space, operating temperature, weight and cost. The choice of strategies for energy storage evaluation, monitoring and control remains a challenging task. This paper presents review of various energy storage technologies and recent researches in battery evaluation techniques used in EV applications. It also underscores strategies for the hybrid energy storage management and control schemes for the improvement of EV stability and reliability. The study reveals that despite the advances recorded in battery technologies there is still no cell which possess both the optimum power and energy densities among other requirements, for EV application. However combination of two or more energy storages as hybrid and allowing the advantageous attributes from each device to be utilized is a promising solution. The review also reveals that State-of-Charge (SoC) is the most crucial method for battery estimation. The conventional method of SoC measurement is however questioned in the literature and adaptive algorithms that include all model of disturbances are being proposed. The review further suggests that heuristic-based approach is commonly adopted in the development of strategies for hybrid energy storage system management. The alternative approach which is optimization-based is found to be more accurate but is memory and computational intensive and as such not recommended in most real-time applications.
Abstract: Level 3 autonomous vehicles are able to take full responsibility over the control of the vehicle unless a system boundary is reached or a system failure occurs, in which case, the driver is expected to take-over the control of the vehicle. While this happens, the driver is often not aware of the traffic situation or is engaged in a secondary task. Factors affecting the duration and quality of take-overs in these situations have included secondary task type and nature, traffic density, take-over request (TOR) time, and TOR warning type and modality. However, to the best of the authors’ knowledge, no prior study examined time buffer for TORs when a system failure occurs immediately before intersections. The first objective of this study is to investigate the effect of time buffer (3 and 7 seconds) on the duration and quality of take-overs when a system failure occurs just prior to intersections. In addition, eye-tracking has become one of the most popular methods to report what individuals view, in what order, for how long, and how often, and it has been utilized in driving simulations with various objectives. However, to the extent of authors’ knowledge, none has compared drivers’ eye gaze behavior in the two different time buffers in order to examine drivers’ attention and comprehension of salient information. The second objective is to understand the driver’s attentional focus on comprehension of salient traffic-related information presented on different parts of the dashboard and on the roads.
Abstract: To claim the ownership for an executable program is a non-trivial task. An emerging direction is to add a watermark to the program such that the watermarked program preserves the original program’s functionality and removing the watermark would heavily destroy the functionality of the watermarked program. In this paper, the first watermarking signature scheme with the watermark and the constraint function hidden in the symmetric key setting is constructed. The scheme uses well-known techniques of lattice trapdoors and a lattice evaluation. The watermarking signature scheme is unforgeable under the Short Integer Solution (SIS) assumption and satisfies other security requirements such as the unremovability security property.
Abstract: With the recent advance of the deep neural network, we observe new applications of NLP (natural language processing) and CV (computer vision) powered by deep neural networks for processing business documents. However, creating a real-world document processing system needs to integrate several NLP and CV tasks, rather than treating them separately. There is a need to have a unified approach for processing documents containing textual and graphical elements with rich formats, diverse layout arrangement, and distinct semantics. In this paper, a framework that fulfills this unified approach is presented. The framework includes a representation model definition for holding the information generated by various tasks and specifications defining the coordination between these tasks. The framework is a blueprint for building a system that can process documents with rich formats, styles, and multiple types of elements. The flexible and lightweight design of the framework can help build a system for diverse business scenarios, such as contract monitoring and reviewing.
Abstract: Program synthesis is the task to automatically generate
programs based on user specification. In this paper, we present a
framework that synthesizes programs from flow charts that serve as
accurate and intuitive specification. In order doing so, we propose a
deep neural network called GRCNN that recognizes graph structure
from its image. GRCNN is trained end-to-end, which can predict edge
and node information of the flow chart simultaneously. Experiments
show that the accuracy rate to synthesize a program is 66.4%, and
the accuracy rates to recognize edge and node are 94.1% and 67.9%,
respectively. On average, it takes about 60 milliseconds to synthesize
a program.
Abstract: Airborne Laser Scanning (ALS) is one of the main technologies for generating high-resolution digital terrain models (DTMs). DTMs are crucial to several applications, such as topographic mapping, flood zone delineation, geographic information systems (GIS), hydrological modelling, spatial analysis, etc. Laser scanning system generates irregularly spaced three-dimensional cloud of points. Raw ALS data are mainly ground points (that represent the bare earth) and non-ground points (that represent buildings, trees, cars, etc.). Removing all the non-ground points from the raw data is referred to as filtering. Filtering heavily forested areas is considered a difficult and challenging task as the canopy stops laser pulses from reaching the terrain surface. This research presents an approach for removing non-ground points from raw ALS data in densely forested areas. Smoothing splines are exploited to interpolate and fit the noisy ALS data. The presented filter utilizes a weight function to allocate weights for each point of the data. Furthermore, unlike most of the methods, the presented filtering algorithm is designed to be automatic. Three different forested areas in the United Kingdom are used to assess the performance of the algorithm. The results show that the generated DTMs from the filtered data are accurate (when compared against reference terrain data) and the performance of the method is stable for all the heavily forested data samples. The average root mean square error (RMSE) value is 0.35 m.
Abstract: Forecasting the stock market is a very challenging task. Various economic indicators such as GDP, exchange rates, interest rates, and unemployment have a substantial impact on the stock market. Time series models are the traditional methods used to predict stock market changes. In this paper, a machine learning method, Bayesian Additive Regression Tree (BART) is used in predicting stock market indexes based on multiple economic indicators. BART can be used to model heterogeneous treatment effects, and thereby works well when models are misspecified. It also has the capability to handle non-linear main effects and multi-way interactions without much input from financial analysts. In this research, BART is proposed to provide a reliable prediction on day-to-day stock market activities. By comparing the analysis results from BART and with time series method, BART can perform well and has better prediction capability than the traditional methods.
Abstract: This paper presents a wearable reconfigurable supernumerary robotic limb with differential actuated joints, which is lightweight, compact and comfortable for the wearers. Compared to the existing supernumerary robotic limbs which mostly adopted series structure with large movement space but poor carrying capacity, a prototype with the series-parallel configuration to better adapt to different task requirements has been developed in this design. To achieve a compact structure, two kinds of cable-driven mechanical structures based on guide pulleys and differential actuated joints were designed. Moreover, two different tension devices were also designed to ensure the reliability and accuracy of the cable-driven transmission. The proposed device also employed self-designed bearings which greatly simplified the structure and reduced the cost.
Abstract: Motion planning is a common task required to be fulfilled by robots. A strategy combining Ant Colony Optimization (ACO) and gravity gradient inversion algorithm is proposed for motion planning of mobile robots. In this paper, in order to realize optimal motion planning strategy, the cost function in ACO is designed based on gravity gradient inversion algorithm. The obstacles around mobile robot can cause gravity gradient anomalies; the gradiometer is installed on the mobile robot to detect the gravity gradient anomalies. After obtaining the anomalies, gravity gradient inversion algorithm is employed to calculate relative distance and orientation between mobile robot and obstacles. The relative distance and orientation deduced from gravity gradient inversion algorithm is employed as cost function in ACO algorithm to realize motion planning. The proposed strategy is validated by the simulation and experiment results.