4466 research outputs found
Sort by
Customer Churn Analytics Using Monotonic Rules
No full textUsing bank customer churn data, we demonstrate the explanatory
and predictive capacity of monotonic decision rules. Since the data
are partially ordinal, they are structured by a new version of the Variable
Consistency Dominance-based Rough Set Approach before the induction of
monotonic decision rules. The induced rules characterize loyal customers
and the ones who left the bank. Such an approach is in line with explainable
AI, aiming to obtain a transparent and understandable decision model. In
the course of a computational experiment, we compare the predictive performance
of monotonic rules with several well-known machine learning models
Lessons Learned from a Smart City Project with Citizen Engagement
No full textThe paper discusses the experiences gained in a joint research
project by AGH and the commune of Siechnice. Two main areas are discussed:
collecting data from heterogenous sensor devices as well as input
from citizens, and development of analytic procedures in a way which guarantees
integration between day-to-day and research operations. The most
prominent outcomes of the project include the development of a living lab as
well as automation of multi-aspect inference, which would normally have to
be carried out by a team of experts
Badanie szybkości reakcji dwutlenku węgla z roztworami n-metylodietanoloaminy i anhydrazy węglanowej w reaktorze z płaską powierzchnią kontaktu
No full textUrban Corners in Guangzhou: Desing, Morphology and Everyday Life, 1757–1949
No full textUrban corners are a distinct form of public space, yet little has been written about how this type of space has emerged and developed from a historical perspective. Addressing this gap, this paper presents a historical study of the spatial forms of urban corners in China. We reframe the Everyday Urbanism paradigm as an analytical framework to investigate the dynamics of the corners through three particular dimensions: design governance, morphological characteristics and everyday use. Drawing on historical sources such as maps, planning documents, old photographs and drawings, private written records and existing studies, we apply the framework to examine the transformation process of urban corners in the historic city core, Guangzhou, from 1757 to 1949. Findings suggest that urban corners have the potential to become an important cultural heritage in China’s historic cities. It concludes by discussing the implications of these findings for culture-led regeneration in contemporary China
Transformers Neural Networks Applications in Different Computer Vision Tasks
No full textTransformers architectures are one of the latest inventions in the
field of deep learning. Originally dedicated to NLP, they begin to find use
in computer vision too. In this paper, we briefly describe the idea behind
vision transformers and present a few examples, where we utilised them in
our research, focusing on the field of medical images and autonomous driving.
We show, that vision transformers can be used in various tasks, such as
detection or classification, as well as explain how some of their drawbacks
can be mitigated with a transfer learning approach
Improving RGB-D Visual Odometry with Depth Learned from a Better Sensor’s Output
No full textThis paper compares the results obtained from an indoor Visual
Odometry (VO) system with RGB-D images provided by a Kinect v1 camera
against those achieved by a VO with enhanced depth channel. For this
purpose, we have used two classic image inpainting methods and a deeplearning
approach for scene depth estimation employing Kinect v2 depth
maps as reference data. The ability to enhance lower-quality data is crucial
to reduce the cost of VO applications because higher-quality information
can be infused through deep learning in systems using budget sensors
Chinese Economic Transition and the Evolution of Liuhua Clothing Wholesale District in Guangzhou, China
No full textCommunist country China’s post-1978 radical economic transition led to extraordinary morphological and functional changes in urban space. Dramatic changes resulting from the economic transition from centralized administrative allocation to the commercialization of land, suddenly endow space with distinct capital values; accordingly, spaces are linked to different functions. The Liuhua Clothing Wholesale District in Guangzhou offers the researcher an opportunity for the re-examination of morphological changes in accordance with these dramatic urban renewal processes under economic transition. It is the Liuhua District’s position on the south of the large transportation hub Guangzhou Railway Station that started the rapid growth of a brand-new clothing wholesale district. The deficiency of urban planning (Yeh 2004) created the local conditions for the development of an re-articulated, efficiently integrated, organic commercial district. This research aims to unravel the impact of economic and functional changes related to Liuhua District’s urban renewal processes with Actor-network-theory.
For research design, grounded theory makes it possible to build up arguments on research data. Research data are obtained through methods including archive research, semi-structured interview and mapping. Archives including policies and historical maps enable the investigation of the Liuhua District’s evolving processes and morphological changes. Semi-structured interview is adopted to collect information about experience and memories on economic and functional changes; the interviews were conducted with 40 people of distinct professions in Liuhua District. Mapping is adopted for recording and representing spatial changes. For data analysis, graphic and nongraphic materials are coded to draw themes. This research will contribute to a critical understanding on how economic and functional changes impact urban renewal processes in Chinese context
