scholarly journals Theft Prediction Model Based on Spatial Clustering to Reflect Spatial Characteristics of Adjacent Lands

2021 ◽  
Vol 13 (14) ◽  
pp. 7715
Author(s):  
Dongyoung Kim ◽  
Sungwon Jung ◽  
Yongwook Jeong
Keyword(s):  
Spatial Clustering ◽  
Spatial Characteristics ◽  
Crime Prediction ◽  
Spatial Features ◽  
Machine Learning Model ◽  
Detailed Method ◽  
Event Location ◽  
Region Model ◽  
Model Training ◽  
Physical Environmental Factors

Previous studies have shown that when a crime occurs, the risk of crime in adjacent areas increases. To reflect this, previous grid-based crime prediction studies combined all the cells surrounding the event location to be predicted for use in model training. However, the actual land is continuous rather than a set of independent cells as in a geographic information system. Because the patterns that occur according to the detailed method of crime vary, it is necessary to reflect the spatial characteristics of the adjacent land in crime prediction. In this study, cells with similar spatial characteristics were classified using the Max-p region model (a spatial clustering technique), and the performance was compared to the existing method using random forest (a tree-based machine learning model). According to the results, the F1 score of the model using spatial clustering increased by approximately 2%. Accordingly, there are differences in the physical environmental factors influenced by the detailed method of crime. The findings reveal that crime involving the same offender is likely to occur around the area of the original crime, indicating that a repeated crime is likely in areas with similar spatial features to the area where the crime occurred.

Skeleton Network Extraction and Analysis on Bicycle Sharing Networks

2020 ◽  
Vol 16 (3) ◽  
pp. 146-167
Author(s):  
Kanokwan Malang ◽  
Shuliang Wang ◽  
Yuanyuan Lv ◽  
Aniwat Phaphuangwittayakul
Keyword(s):  
Spatial Distribution ◽  
Extraction Method ◽  
Spatial Information ◽  
Spatial Clustering ◽  
Transportation Networks ◽  
Network Size ◽  
Network Characteristics ◽  
Spatial Features

Skeleton network extraction has been adopted unevenly in transportation networks whose nodes are always represented as spatial units. In this article, the TPks skeleton network extraction method is proposed and applied to bicycle sharing networks. The method aims to reduce the network size while preserving key topologies and spatial features. The authors quantified the importance of nodes by an improved topology potential algorithm. The spatial clustering allows to detect high traffic concentrations and allocate the nodes of each cluster according to their spatial distribution. Then, the skeleton network is constructed by aggregating the most important indicated skeleton nodes. The authors examine the skeleton network characteristics and different spatial information using the original networks as a benchmark. The results show that the skeleton networks can preserve the topological and spatial information similar to the original networks while reducing their size and complexity.

scholarly journals SPATIAL NARRATIVE AND PERCEPTION OF SPACE IN HISTORICAL AND CONTEMPORARY ARCHITECTURAL COMPOSITIONS / ERDVINIS NARATYVAS IR FORMOS PERCEPCIJA ISTORINĖS IR ŠIUOLAIKINĖS ARCHITEKTŪROS KOMPOZICIJOSE

2013 ◽  
Vol 5 (3) ◽  
pp. 289-295
Author(s):  
Gytis Oržikauskas
Keyword(s):  
Modern Architecture ◽  
Cultural Meanings ◽  
Spatial Characteristics ◽  
Spatial Features ◽  
Architectural Feature ◽  
Spatial Narrative

highlighted in terms of architecture of Modernism. According to the theory of modern architecture and Geschtalt Psychology, elementary geometrical forms and main spatial features were underlined and accepted as anthropomorphic principle of architecture. Even today main spatial characteristics are accepted as a key principle of architectural composition. However, architects and critics of contemporary – post-modern and deconstructive – architecture emphasize the value of architectural narrative achieved not only through perception of space, but also by its relationship to social and cultural meanings and subtext of architecture. A narrative, as architectural feature, is realized in some compositions of the deconstructivist and postmodern architecture, both worldwide and in Lithuania. Santrauka Vienas svarbiausių istorinės architektūros bruožų – geometriškumas – buvo išryškintas modernizmo architektūros teorijoje. Remiantis geštaltpsichologijos teorija, elementarios geometrinės formos ir pagrindinės erdvinės charakteristikos suvoktos kaip antropomorfinis architektūros aspektas: net ir šiandien jos laikomos architektūros kompozicijos pagrindu. Nepaisant to, šiuolaikinės postmodernizmo ir dekonstruktyvizmo architektūros kūrėjai bei kritikai akcentuoja erdvinio naratyvo, kuriamo ne tik erdvės percepcijos, bet ir erdvės santykio su socialinėmis ir kultūrinėmis reikšmėmis, svarbą. Naratyvo, kaip architektūros kompozicinės ypatybės, naudojamos dekonstruktyvizmo ir postmodernizmo architektūros kompozicijose, pavyzdžių galime aptikti tiek užsienyje, tiek Lietuvoje.

scholarly journals ON THE RELATIONSHIPS BETWEEN CLUSTERING AND SPATIAL CO-LOCATION PATTERN MINING

2008 ◽  
Vol 17 (01) ◽  
pp. 55-70 ◽  
Author(s):  
YAN HUANG ◽  
PUSHENG ZHANG ◽  
CHENGYANG ZHANG
Keyword(s):  
Pattern Mining ◽  
Spatial Clustering ◽  
Spatial Proximity ◽  
Location Pattern ◽  
Continuous Space ◽  
Clustering Techniques ◽  
Spatial Objects ◽  
Spatial Features ◽  
Statistical Measures ◽  
Location Patterns

The goal of spatial co-location pattern mining is to find subsets of spatial features frequently located together in spatial proximity. Example co-location patterns include services requested frequently and located together from mobile devices (e.g., PDAs and cellular phones) and symbiotic species in ecology (e.g., Nile crocodile and Egyptian plover). Spatial clustering groups similar spatial objects together. Reusing research results in clustering, e.g. algorithms and visualization techniques, by mapping co-location mining problem into a clustering problem would be very useful. However, directly clustering spatial objects from various spatial features may not yield well-defined co-location patterns. Clustering spatial objects in each layer followed by overlaying the layers of clusters may not applicable to many application domains where the spatial objects in some layers are not clustered. In this paper, we propose a new approach to the problem of mining co-location patterns using clustering techniques. First, we propose a novel framework for co-location mining using clustering techniques. We show that the proximity of two spatial features can be captured by summarizing their spatial objects embedded in a continuous space via various techniques. We define the desired properties of proximity functions compared to similarity functions in clustering. Furthermore, we summarize the properties of a list of popular spatial statistical measures as the proximity functions. Finally, we show that clustering techniques can be applied to reveal the rich structure formed by co-located spatial features. A case study on real datasets shows that our method is effective for mining co-locations from large spatial datasets.

scholarly journals Hindsight logging for model training

2020 ◽  
Vol 14 (4) ◽  
pp. 682-693
Author(s):  
Rolando Garcia ◽  
Eric Liu ◽  
Vikram Sreekanti ◽  
Bobby Yan ◽  
Anusha Dandamudi ◽  
...  
Keyword(s):  
Training Model ◽  
Database Systems ◽  
Slowing Down ◽  
Machine Learning Model ◽  
Experimental Process ◽  
Free Mode ◽  
Model Training ◽  
Post Hoc ◽  
Multiple Variants ◽  
Modern Machine

In modern Machine Learning, model training is an iterative, experimental process that can consume enormous computation resources and developer time. To aid in that process, experienced model developers log and visualize program variables during training runs. Exhaustive logging of all variables is infeasible, so developers are left to choose between slowing down training via extensive conservative logging, or letting training run fast via minimalist optimistic logging that may omit key information. As a compromise, optimistic logging can be accompanied by program checkpoints; this allows developers to add log statements post-hoc, and "replay" desired log statements from checkpoint---a process we refer to as hindsight logging. Unfortunately, hindsight logging raises tricky problems in data management and software engineering. Done poorly, hindsight logging can waste resources and generate technical debt embodied in multiple variants of training code. In this paper, we present methodologies for efficient and effective logging practices for model training, with a focus on techniques for hindsight logging. Our goal is for experienced model developers to learn and adopt these practices. To make this easier, we provide an open-source suite of tools for Fast Low-Overhead Recovery (flor) that embodies our design across three tasks: (i) efficient background logging in Python, (ii) adaptive periodic checkpointing, and (iii) an instrumentation library that codifies hindsight logging for efficient and automatic record-replay of model-training. Model developers can use each flor tool separately as they see fit, or they can use flor in hands-free mode, entrusting it to instrument their code end-to-end for efficient record-replay. Our solutions leverage techniques from physiological transaction logs and recovery in database systems. Evaluations on modern ML benchmarks demonstrate that flor can produce fast checkpointing with small user-specifiable overheads (e.g. 7%), and still provide hindsight log replay times orders of magnitude faster than restarting training from scratch.

scholarly journals OSNR Prediction Based on Federal Learning in Multi-Domain Optical Networks

2021 ◽  
Author(s):  
Junhua Huang ◽  
Bohan Zhu ◽  
Hongxi Zhou ◽  
Qiwei Zheng ◽  
Zhuo Chen ◽  
...  
Keyword(s):  
Machine Learning ◽  
Optical Networks ◽  
Low Cost ◽  
Optical Network ◽  
Main Idea ◽  
Learning Model ◽  
Important Indicator ◽  
Machine Learning Model ◽  
Network Operation ◽  
Model Training

With the continuous expansion of the scale of optical communication network and the rapid increase of network traffic demand, the management form of multi-domain optical network has widely existed. OSNR is an important indicator to judge the quality of communication. It is very important to predict OSNR more accurately in a low-cost and energy-saving way in multi-domain optical networks. In this paper, a scheme of federal learning in multi-domain optical networks is proposed to improve the accuracy of the OSNR prediction. The main idea is to train hybrid machine learning model in each single domain, then the strategy of federal learning is used for optimization it in multi-domains. The performance of the proposed scheme is verified by simulation experiments. The strategy can alleviate the problems of data silos and model training set caused by multi-domain optical network. According to simulation result, when the amount of data reaches 5×103, adding this strategy will reduce the mean square error of the prediction model by about 18%. It can improve the performance of machine learning model, the ability of OSNR prediction and the reliability of network operation.

Quantifying identifiability to choose and audit ϵ in differentially private deep learning

2021 ◽  
Vol 14 (13) ◽  
pp. 3335-3347
Author(s):  
Daniel Bernau ◽  
Günther Eibl ◽  
Philip W. Grassal ◽  
Hannah Keller ◽  
Florian Kerschbaum
Keyword(s):  
Machine Learning ◽  
Differential Privacy ◽  
Training Data ◽  
Training Dataset ◽  
Privacy Leakage ◽  
Societal Norms ◽  
Machine Learning Model ◽  
Model Training ◽  
Parameter Values ◽  
Learning Data

Differential privacy allows bounding the influence that training data records have on a machine learning model. To use differential privacy in machine learning, data scientists must choose privacy parameters (ϵ, δ ). Choosing meaningful privacy parameters is key, since models trained with weak privacy parameters might result in excessive privacy leakage, while strong privacy parameters might overly degrade model utility. However, privacy parameter values are difficult to choose for two main reasons. First, the theoretical upper bound on privacy loss (ϵ, δ) might be loose, depending on the chosen sensitivity and data distribution of practical datasets. Second, legal requirements and societal norms for anonymization often refer to individual identifiability, to which (ϵ, δ ) are only indirectly related. We transform (ϵ, δ ) to a bound on the Bayesian posterior belief of the adversary assumed by differential privacy concerning the presence of any record in the training dataset. The bound holds for multidimensional queries under composition, and we show that it can be tight in practice. Furthermore, we derive an identifiability bound, which relates the adversary assumed in differential privacy to previous work on membership inference adversaries. We formulate an implementation of this differential privacy adversary that allows data scientists to audit model training and compute empirical identifiability scores and empirical (ϵ, δ ).

scholarly journals Enumeration of de novo inorganic complexes for chemical discovery and machine learning

2020 ◽  
Vol 5 (1) ◽  
pp. 139-152 ◽  
Author(s):  
Stefan Gugler ◽  
Jon Paul Janet ◽  
Heather J. Kulik
Keyword(s):  
Machine Learning ◽  
Transition Metal ◽  
Metal Complexes ◽  
Transition Metal Complexes ◽  
Spin State ◽  
De Novo ◽  
Machine Learning Model ◽  
Inorganic Complexes ◽  
Model Training ◽  
Unique Spin

Enumerated, de novo transition metal complexes have unique spin state properties and accelerate machine learning model training.

scholarly journals Semantic Components of the Russian Preposition “Через” in Combination With Different Locums and its Expression in the Persian Language

2021 ◽  
Vol 7 (3) ◽  
pp. 43-52
Author(s):  
M. Estiri ◽  
Kh. Torkashvand
Keyword(s):  
Russian Language ◽  
Spatial Characteristics ◽  
Spatial Prepositions ◽  
Persian Language ◽  
Spatial Features ◽  
Iranian Students ◽  
And Function ◽  
Meaning And Function ◽  
The Russian Language

In the Russian language the preposition “cherez (through)” is used in its typical contexts to refer to spatial characteristics in which an action or movement takes place. However, there are cases in the Persian language when there is no clear boundary among the spatial prepositions corresponding to the preposition “cherez (through)”, which causes difculty for Iranian learners to choose the correct one. At the same time one and the same Persian preposition can be expressed by different Russian prepositions which lead to regular mistakes in the speech of Iranian students. Tus, for instance, Iranian students use the preposition “az miyan-e” / (among) in the meaning of the Russian prepositions “cherez” (through), “mezhdu”, “ckvoz” (within) and “iz” (from), although these prepositions are different in meaning and function. In this article, the locations used in combination with the preposition “through” are systematically classifed to explain their specifc features. In addition, the ways of expressing the spatial meanings of the preposition “through” in the Persian language are addressed in order to raise Iranian learners’ awareness of possible mistakes. Te novelty of the article is in the attempt to compare semantic and spatial features of the Russian preposition “cherez (through)” with its correlates in the Persian language. Te fndings of this study can be of interest to RFL teachers, in particular in Iran, as they will highlight common mistakes in the speech of Iranian learners when using the preposition “through”, and to RFL textbook developers.

Sign in / Sign up

Export Citation Format

Share Document