Irina Matijosaitiene - Academia.edu (original) (raw)
Papers by Irina Matijosaitiene
WIT Transactions on Ecology and the Environment, 2020
European Scientific Journal, ESJ, 2015
Five commercial objects (Soviet-time, fully reconstructed and newly built) located on one of the ... more Five commercial objects (Soviet-time, fully reconstructed and newly built) located on one of the most crime-ridden and problematic streets of Kaunas city, Lithuania, are researched according to crime prevention through environmental design (CPTED) strategies: natural surveillance, access control, territoriality, maintenance, and activity support. Theft from motor vehicle, robbery and intentional damage of property are analyzed. Research results reveal that CPTED is poorly implemented in all analyzed objects. Though, in Soviet-time commercial objects it is even harder to implement activity support strategy. Correlation analysis demonstrates significant strong relations between the analyzed crimes and some criteria from surveillance, access control, territoriality and activity support strategies. Recommendations for safety improvement in commercial objects are proposed based on CPTED strategies.
The paper represents analysis and modelling of urban spaces through their topological properties ... more The paper represents analysis and modelling of urban spaces through their topological properties in order to make them safer in terms of robberies, larceny and motor vehicle thefts, stolen properties, weapons and drugs. The research is performed on a macro-scale in the city of New Haven, Connecticut, USA. The topological properties of streets were calculated and analyzed by the application of space syntax method and DepthMap software, GIS and SPSS. The results are explained in the terms of people movement and presence on the main streets which are on the natural search paths of possible criminals, and which on the other hand have been assigned to a greater surveillance effect from movement.
Animals, 2020
Real-time identification of wildlife is an upcoming and promising tool for the preservation of wi... more Real-time identification of wildlife is an upcoming and promising tool for the preservation of wildlife. In this research project, we aimed to use object detection and image classification for the racer snakes of the Galápagos Islands, Ecuador. The final target of this project was to build an artificial intelligence (AI) platform, in terms of a web or mobile application, which would serve as a real-time decision making and supporting mechanism for the visitors and park rangers of the Galápagos Islands, to correctly identify a snake species from the user’s uploaded image. Using the deep learning and machine learning algorithms and libraries, we modified and successfully implemented four region-based convolutional neural network (R-CNN) architectures (models for image classification): Inception V2, ResNet, MobileNet, and VGG16. Inception V2, ResNet and VGG16 reached an overall accuracy of 75%.
Sustainability, 2019
This research aims to identify spatial and time patterns of theft in Manhattan, NY, to reveal urb... more This research aims to identify spatial and time patterns of theft in Manhattan, NY, to reveal urban factors that contribute to thefts from motor vehicles and to build a prediction model for thefts. Methods include time series and hot spot analysis, linear regression, elastic-net, Support vector machines SVM with radial and linear kernels, decision tree, bagged CART, random forest, and stochastic gradient boosting. Machine learning methods reveal that linear models perform better on our data (linear regression, elastic-net), specifying that a higher number of subway entrances, graffiti, and restaurants on streets contribute to higher theft rates from motor vehicles. Although the prediction model for thefts meets almost all assumptions (five of six), its accuracy is 77%, suggesting that there are other undiscovered factors making a contribution to the generation of thefts. As an output demonstrating final results, the application prototype for searching safer parking in Manhattan, NY ...
ISPRS International Journal of Geo-Information, 2018
Predicting the exact urban places where crime is most likely to occur is one of the greatest inte... more Predicting the exact urban places where crime is most likely to occur is one of the greatest interests for Police Departments. Therefore, the goal of the research presented in this paper is to identify specific urban areas where a crime could happen in Manhattan, NY for every hour of a day. The outputs from this research are the following: (i) predicted land uses that generates the top three most committed crimes in Manhattan, by using machine learning (random forest and logistic regression), (ii) identifying the exact hours when most of the assaults are committed, together with hot spots during these hours, by applying time series and hot spot analysis, (iii) built hourly prediction models for assaults based on the land use, by deploying logistic regression. Assault, as a physical attack on someone, according to criminal law, is identified as the third most committed crime in Manhattan. Land use (residential, commercial, recreational, mixed use etc.) is assigned to every area or lo...
Journal of Sustainable Architecture and Civil Engineering, 2017
Journal of Place Management and Development, 2016
Purpose The purpose of this paper is to respond to the need for comparative studies on methodolog... more Purpose The purpose of this paper is to respond to the need for comparative studies on methodologies for implementing Crime Prevention through Urban Design and Planning (CP-UDP) at the local level, particularly in peripheral Europe where CP-UDP’s top-down standards have poor dissemination and acceptance. This paper debates how local partnerships can help reduce crime and how a CP-UDP-based model can be introduced into municipal planning. Design/methodology/approach The paper discusses the challenge of CP-UDP in the framework of a post-crisis Europe and Europe 2020. Because there is a large gap between theory and practice, lack of a shared holistic approach, and scepticism, or lack of knowledge, of public authorities, at local-level planning professionals and the police have devised bottom-up initiatives based on interdisciplinary partnerships with the community. The paper describes, discusses and compares the implementation of such approaches in Lisbon (Portugal) and Vilnius (Lithua...
Journal of Sustainable Architecture and Civil Engineering, 2014
Safer Communities, 2016
Purpose – The purpose of this paper is to combine both Crime Prevention Through Environmental Des... more Purpose – The purpose of this paper is to combine both Crime Prevention Through Environmental Design (CPTED) and space syntax for the more detailed and overall analysis of built environment in terms of crime. The author is aiming to verify the designed research methodology by its application in cities that are similar in terms of size and population, and are very different in culture and location: New Haven (USA) and Kaunas (Lithuania). Design/methodology/approach – Based on CPTED strategies the factors of urban environment are analyzed, such as topological depth from private space to a public space, density of entrances and windows, street’s constitutedness, inter-visibility, land use, blind walls, segment’s accessibility, greenery, lighting, objects of small architecture, graffiti. Space syntax method is applied for the analysis of the following topological properties of urban spaces: integration, choice, depth, connectivity. Findings – The combination of both methods revels that ...
Journal of Sustainable Architecture and Civil Engineering, 2013
European Scientific Journal, Apr 30, 2015
The contemporary environment requires policy-makers to act responsible. However, in existing lite... more The contemporary environment requires policy-makers to act responsible. However, in existing literature, there is no explicit agreement on which aspects of institutional environment, including common law are more important than others for a country's prosperity, economic growth, entrepreneurship, or innovativeness. Therefore, the paper aims to reveal whether fair, transparent and effective policy-making fosters the emergence of competitive strategies for innovation, or instead limits the range of commonly-acceptable means of fair and legal competition. The empirical research covers 60 innovation variables across 127.674 organizations, 12 core and 19 additional industrial sectors, 16 European economies and 368 institutional variables, thus pointing to the impressive scope of the research. What makes the paper original is its focus on the responsible policy-making as a contributor to competitive practices for innovation.
Journal of Sustainable Architecture and Civil Engineering, 2016
European Scientific Journal, Mar 26, 2014
THE BALTIC JOURNAL OF ROAD AND BRIDGE ENGINEERING, 2014
The contemporary market laws and consumer society impose that road users are regarded to as consu... more The contemporary market laws and consumer society impose that road users are regarded to as consumers, and road landscape – as a product. In this context, consumers’ willingness to use the product is equivalent to road users’ willingness to drive on the road. Consumers’ fastidiousness induces to develop road landscape in a way which ensures satisfaction of drivers’ versatile needs, including the aesthetic ones. However, development of desirable-to-drive road landscape remains one of the challenges of land management. Hence, based on the analysis of aesthetic needs of road users, the paper proposes a framework for creation of desirable-to-drive road landscape. The research rests on photofixation, Kansei engineering, regression, correlation and descriptive analyses. The landscape of the main Lithuanian roads was investigated. The results show that the willingness to drive on a road depends on the level of tune of all the elements comprising the roadscape, the amount of positive impres...
Social Sciences, 2013
High rates of crime have always been considered a serious threat to city development. Crime and u... more High rates of crime have always been considered a serious threat to city development. Crime and urban development are strongly interconnected, therefore, local development policies cannot be successful without crime prevention strategies. One of the areas where local governments are characterized by quite a high degree of independence is that of urban planning, typically documented in a city master plan. In the light of the topic of safety in the urban space, one of the most notable measures of space evaluation is that of land use. The paper is aimed at identifying land uses, the most vulnerable to crime and the safest ones, and their permutations in the three largest cities of Lithuania: Vilnius, Kaunas, and Klaipeda, in accordance with both different types of criminal acts and crime as a whole. The findings have been based on the analysis of about 50 thousand incidents of antisocial behavior, committed in open public spaces, along 17 types of criminal acts and 14 types of land uses and their permutations. The underlying approach is that of space syntax, as it best integrates social and spatial elements of a city. The paper is novel in its attempt to access not only separate land uses, but also their clusters (i.e., permutations). In addition, the paper covers a broader range of antisocial behavior than most of the previously carried out research (i.e., the paper looks beyond theft, burglary, and robbery) used to. Therefore, the results might be of interest to a wider audience than the national one.
Journal of Sustainable Architecture and Civil Engineering, 2014
Journal of Sustainable Architecture and Civil Engineering, 2013
Landscape Research, 2010
Over time roads and their surroundings gained historic and cultural significance. This significan... more Over time roads and their surroundings gained historic and cultural significance. This significance is oftentimes acknowledged and numerous roads and road infrastructure objects with their surrounding environment are listed and protected. Notwithstanding this, it is necessary to note that the ways in which roads, their surrounding environment, and adjacent objects can manifest heritage values, can be complex, and are not
This paper analyzes the new method to create a safe living environment for a city. CPTED (Crime P... more This paper analyzes the new method to create a safe living environment for a city. CPTED (Crime Prevention Through Environmental Design) is an innovative interdisciplinary method for crime prevention in living environment implemented using environmental design and urban planning tools. This paper aims to investigate the possibilities of application of CPTEDstrategies in Lithuanian residential areas, and to identify elements of urban environment that affect crime. Calculation of crime risk and CPTED audit for determination of urban design was applied for the research of residential areas in Kaunas City, Lithuania. During the research unique database was created. For the identifications of relations and causations between crimes, id est. thefts from motor vehicles, robbery, intentional damage of property,and urban environmental factors correlation and linear regression analysis were applied. The results demonstrate that post-Soviet residential areas and the parking areas within them w...
WIT Transactions on Ecology and the Environment, 2020
European Scientific Journal, ESJ, 2015
Five commercial objects (Soviet-time, fully reconstructed and newly built) located on one of the ... more Five commercial objects (Soviet-time, fully reconstructed and newly built) located on one of the most crime-ridden and problematic streets of Kaunas city, Lithuania, are researched according to crime prevention through environmental design (CPTED) strategies: natural surveillance, access control, territoriality, maintenance, and activity support. Theft from motor vehicle, robbery and intentional damage of property are analyzed. Research results reveal that CPTED is poorly implemented in all analyzed objects. Though, in Soviet-time commercial objects it is even harder to implement activity support strategy. Correlation analysis demonstrates significant strong relations between the analyzed crimes and some criteria from surveillance, access control, territoriality and activity support strategies. Recommendations for safety improvement in commercial objects are proposed based on CPTED strategies.
The paper represents analysis and modelling of urban spaces through their topological properties ... more The paper represents analysis and modelling of urban spaces through their topological properties in order to make them safer in terms of robberies, larceny and motor vehicle thefts, stolen properties, weapons and drugs. The research is performed on a macro-scale in the city of New Haven, Connecticut, USA. The topological properties of streets were calculated and analyzed by the application of space syntax method and DepthMap software, GIS and SPSS. The results are explained in the terms of people movement and presence on the main streets which are on the natural search paths of possible criminals, and which on the other hand have been assigned to a greater surveillance effect from movement.
Animals, 2020
Real-time identification of wildlife is an upcoming and promising tool for the preservation of wi... more Real-time identification of wildlife is an upcoming and promising tool for the preservation of wildlife. In this research project, we aimed to use object detection and image classification for the racer snakes of the Galápagos Islands, Ecuador. The final target of this project was to build an artificial intelligence (AI) platform, in terms of a web or mobile application, which would serve as a real-time decision making and supporting mechanism for the visitors and park rangers of the Galápagos Islands, to correctly identify a snake species from the user’s uploaded image. Using the deep learning and machine learning algorithms and libraries, we modified and successfully implemented four region-based convolutional neural network (R-CNN) architectures (models for image classification): Inception V2, ResNet, MobileNet, and VGG16. Inception V2, ResNet and VGG16 reached an overall accuracy of 75%.
Sustainability, 2019
This research aims to identify spatial and time patterns of theft in Manhattan, NY, to reveal urb... more This research aims to identify spatial and time patterns of theft in Manhattan, NY, to reveal urban factors that contribute to thefts from motor vehicles and to build a prediction model for thefts. Methods include time series and hot spot analysis, linear regression, elastic-net, Support vector machines SVM with radial and linear kernels, decision tree, bagged CART, random forest, and stochastic gradient boosting. Machine learning methods reveal that linear models perform better on our data (linear regression, elastic-net), specifying that a higher number of subway entrances, graffiti, and restaurants on streets contribute to higher theft rates from motor vehicles. Although the prediction model for thefts meets almost all assumptions (five of six), its accuracy is 77%, suggesting that there are other undiscovered factors making a contribution to the generation of thefts. As an output demonstrating final results, the application prototype for searching safer parking in Manhattan, NY ...
ISPRS International Journal of Geo-Information, 2018
Predicting the exact urban places where crime is most likely to occur is one of the greatest inte... more Predicting the exact urban places where crime is most likely to occur is one of the greatest interests for Police Departments. Therefore, the goal of the research presented in this paper is to identify specific urban areas where a crime could happen in Manhattan, NY for every hour of a day. The outputs from this research are the following: (i) predicted land uses that generates the top three most committed crimes in Manhattan, by using machine learning (random forest and logistic regression), (ii) identifying the exact hours when most of the assaults are committed, together with hot spots during these hours, by applying time series and hot spot analysis, (iii) built hourly prediction models for assaults based on the land use, by deploying logistic regression. Assault, as a physical attack on someone, according to criminal law, is identified as the third most committed crime in Manhattan. Land use (residential, commercial, recreational, mixed use etc.) is assigned to every area or lo...
Journal of Sustainable Architecture and Civil Engineering, 2017
Journal of Place Management and Development, 2016
Purpose The purpose of this paper is to respond to the need for comparative studies on methodolog... more Purpose The purpose of this paper is to respond to the need for comparative studies on methodologies for implementing Crime Prevention through Urban Design and Planning (CP-UDP) at the local level, particularly in peripheral Europe where CP-UDP’s top-down standards have poor dissemination and acceptance. This paper debates how local partnerships can help reduce crime and how a CP-UDP-based model can be introduced into municipal planning. Design/methodology/approach The paper discusses the challenge of CP-UDP in the framework of a post-crisis Europe and Europe 2020. Because there is a large gap between theory and practice, lack of a shared holistic approach, and scepticism, or lack of knowledge, of public authorities, at local-level planning professionals and the police have devised bottom-up initiatives based on interdisciplinary partnerships with the community. The paper describes, discusses and compares the implementation of such approaches in Lisbon (Portugal) and Vilnius (Lithua...
Journal of Sustainable Architecture and Civil Engineering, 2014
Safer Communities, 2016
Purpose – The purpose of this paper is to combine both Crime Prevention Through Environmental Des... more Purpose – The purpose of this paper is to combine both Crime Prevention Through Environmental Design (CPTED) and space syntax for the more detailed and overall analysis of built environment in terms of crime. The author is aiming to verify the designed research methodology by its application in cities that are similar in terms of size and population, and are very different in culture and location: New Haven (USA) and Kaunas (Lithuania). Design/methodology/approach – Based on CPTED strategies the factors of urban environment are analyzed, such as topological depth from private space to a public space, density of entrances and windows, street’s constitutedness, inter-visibility, land use, blind walls, segment’s accessibility, greenery, lighting, objects of small architecture, graffiti. Space syntax method is applied for the analysis of the following topological properties of urban spaces: integration, choice, depth, connectivity. Findings – The combination of both methods revels that ...
Journal of Sustainable Architecture and Civil Engineering, 2013
European Scientific Journal, Apr 30, 2015
The contemporary environment requires policy-makers to act responsible. However, in existing lite... more The contemporary environment requires policy-makers to act responsible. However, in existing literature, there is no explicit agreement on which aspects of institutional environment, including common law are more important than others for a country's prosperity, economic growth, entrepreneurship, or innovativeness. Therefore, the paper aims to reveal whether fair, transparent and effective policy-making fosters the emergence of competitive strategies for innovation, or instead limits the range of commonly-acceptable means of fair and legal competition. The empirical research covers 60 innovation variables across 127.674 organizations, 12 core and 19 additional industrial sectors, 16 European economies and 368 institutional variables, thus pointing to the impressive scope of the research. What makes the paper original is its focus on the responsible policy-making as a contributor to competitive practices for innovation.
Journal of Sustainable Architecture and Civil Engineering, 2016
European Scientific Journal, Mar 26, 2014
THE BALTIC JOURNAL OF ROAD AND BRIDGE ENGINEERING, 2014
The contemporary market laws and consumer society impose that road users are regarded to as consu... more The contemporary market laws and consumer society impose that road users are regarded to as consumers, and road landscape – as a product. In this context, consumers’ willingness to use the product is equivalent to road users’ willingness to drive on the road. Consumers’ fastidiousness induces to develop road landscape in a way which ensures satisfaction of drivers’ versatile needs, including the aesthetic ones. However, development of desirable-to-drive road landscape remains one of the challenges of land management. Hence, based on the analysis of aesthetic needs of road users, the paper proposes a framework for creation of desirable-to-drive road landscape. The research rests on photofixation, Kansei engineering, regression, correlation and descriptive analyses. The landscape of the main Lithuanian roads was investigated. The results show that the willingness to drive on a road depends on the level of tune of all the elements comprising the roadscape, the amount of positive impres...
Social Sciences, 2013
High rates of crime have always been considered a serious threat to city development. Crime and u... more High rates of crime have always been considered a serious threat to city development. Crime and urban development are strongly interconnected, therefore, local development policies cannot be successful without crime prevention strategies. One of the areas where local governments are characterized by quite a high degree of independence is that of urban planning, typically documented in a city master plan. In the light of the topic of safety in the urban space, one of the most notable measures of space evaluation is that of land use. The paper is aimed at identifying land uses, the most vulnerable to crime and the safest ones, and their permutations in the three largest cities of Lithuania: Vilnius, Kaunas, and Klaipeda, in accordance with both different types of criminal acts and crime as a whole. The findings have been based on the analysis of about 50 thousand incidents of antisocial behavior, committed in open public spaces, along 17 types of criminal acts and 14 types of land uses and their permutations. The underlying approach is that of space syntax, as it best integrates social and spatial elements of a city. The paper is novel in its attempt to access not only separate land uses, but also their clusters (i.e., permutations). In addition, the paper covers a broader range of antisocial behavior than most of the previously carried out research (i.e., the paper looks beyond theft, burglary, and robbery) used to. Therefore, the results might be of interest to a wider audience than the national one.
Journal of Sustainable Architecture and Civil Engineering, 2014
Journal of Sustainable Architecture and Civil Engineering, 2013
Landscape Research, 2010
Over time roads and their surroundings gained historic and cultural significance. This significan... more Over time roads and their surroundings gained historic and cultural significance. This significance is oftentimes acknowledged and numerous roads and road infrastructure objects with their surrounding environment are listed and protected. Notwithstanding this, it is necessary to note that the ways in which roads, their surrounding environment, and adjacent objects can manifest heritage values, can be complex, and are not
This paper analyzes the new method to create a safe living environment for a city. CPTED (Crime P... more This paper analyzes the new method to create a safe living environment for a city. CPTED (Crime Prevention Through Environmental Design) is an innovative interdisciplinary method for crime prevention in living environment implemented using environmental design and urban planning tools. This paper aims to investigate the possibilities of application of CPTEDstrategies in Lithuanian residential areas, and to identify elements of urban environment that affect crime. Calculation of crime risk and CPTED audit for determination of urban design was applied for the research of residential areas in Kaunas City, Lithuania. During the research unique database was created. For the identifications of relations and causations between crimes, id est. thefts from motor vehicles, robbery, intentional damage of property,and urban environmental factors correlation and linear regression analysis were applied. The results demonstrate that post-Soviet residential areas and the parking areas within them w...