Semi-automatic Model Research Articles

Residual relief modelling: digital elevation enhancement for shipwreck site characterisation

Scour processes play a critical role in the preservation status of submerged historic shipwrecks. Erosion of sediment leads to enhanced exposure of archaeological sites to physical, chemical and biological processes. Current methods for identifying erosional and depositional features at wreck sites are based primarily on visual interpretation of data, which is labour-intensive and entirely subjective. The increasing availability of high-resolution multibeam echosounder–derived digital elevation models (DEMs) of historic wreck sites allows for an entirely new level of detailed interrogation and analyses of the geomorphological features associated with these. In this study, we present a residual relief modelling method for the semi-automated extraction of such depositional and erosional features at wreck sites. Relief modelling is supplemented with a breakpoint classification approach, with final separation supported by DEM visualisation enhancement techniques. We applied the method to three World War I shipwreck sites and evaluated it against traditional manual vectorisation techniques. The results suggest that the semi-automated modelling method is robust, time-effective and capable of quantifying the products of scour processes with increased objectivity. Our method holds great potential for the objective characterisation of erosional and depositional patterns and processes at wreck sites, which have important implications for site formation studies and in situ preservation of underwater cultural heritage.

Image-based construction of building energy models using computer vision

Improving existing buildings' energy performance requires energy models that accurately represent the building. Computer vision methods, particularly image-based 3D reconstruction, can effectively support the creation of 3D building models. In this paper, we present an image-based 3D reconstruction pipeline that supports the semi-automated modeling of existing buildings. We developed two methods for the robust estimation of the building planes from a 3D point cloud that (i) independently estimate each plane and (ii) impose a perpendicularity constraint to plane estimation. We also estimate external walls' thermal transmittance values using an infrared thermography-based method, with the surface temperatures measured by a thermal camera. We validate our approach (i) by testing the pipeline's ability in constructing accurate surface models subject to different image sets with varying sizes and levels of image quality, and (ii) through a comparative analysis between the calculated energy performance metrics of a ground truth and calculated energy simulation model.

High-resolution, 3D radiative transfer modelling

Context. Interstellar dust absorbs stellar light very efficiently, thus shaping the energy output of galaxies. Studying the impact of different stellar populations on the dust heating continues to be a challenge because it requires decoupling the relative geometry of stars and dust and also involves complex processes such as scattering and non-local dust heating. Aims. We aim to constrain the relative distribution of dust and stellar populations in the spiral galaxy M 81 and create a realistic model of the radiation field that adequately describes the observations. By investigating the dust-starlight interaction on local scales, we want to quantify the contribution of young and old stellar populations to the dust heating. We aim to standardise the setup and model selection of such inverse radiative transfer simulations so these can be used for comparable modelling of other nearby galaxies. Methods. We present a semi-automated radiative transfer modelling pipeline that implements necessary steps such as the geometric model construction and the normalisation of the components through an optimisation routine. We used the Monte Carlo radiative transfer code SKIRT to calculate a self-consistent, panchromatic model of the interstellar radiation field. By looking at different stellar populations independently, we were able to quantify to what extent different stellar age populations contribute to the heating of dust. Our method takes into account the effects of non-local heating. Results. We obtained a realistic 3D radiative transfer model of the face-on galaxy M 81. We find that only 50.2% of the dust heating can be attributed to young stellar populations (≲100 Myr). We confirm that there is a tight correlation between the specific star formation rate and the heating fraction by young stellar populations, both in sky projections and in 3D, which is also found for radiative transfer models of M 31 and M 51. Conclusions. We conclude that old stellar populations can be a major contributor to the heating of dust. In M 81, old stellar populations are the dominant heating agent in the central regions, contributing to half of the absorbed radiation. Regions of higher star formation do not correspond to the highest dust temperatures. On the contrary, it is the dominant bulge which is most efficient in heating the dust. The approach we present here can immediately be applied to other galaxies. It does contain a number of caveats, which we discuss in detail.

Artificial intelligence for teleophthalmology-based diabetic retinopathy screening in a national programme: an economic analysis modelling study

Deep learning is a novel machine learning technique that has been shown to be as effective as human graders in detecting diabetic retinopathy from fundus photographs. We used a cost-minimisation analysis to evaluate the potential savings of two deep learning approaches as compared with the current human assessment: a semi-automated deep learning model as a triage filter before secondary human assessment; and a fully automated deep learning model without human assessment. In this economic analysis modelling study, using 39 006 consecutive patients with diabetes in a national diabetic retinopathy screening programme in Singapore in 2015, we used a decision tree model and TreeAge Pro to compare the actual cost of screening this cohort with human graders against the simulated cost for semi-automated and fully automated screening models. Model parameters included diabetic retinopathy prevalence rates, diabetic retinopathy screening costs under each screening model, cost of medical consultation, and diagnostic performance (ie, sensitivity and specificity). The primary outcome was total cost for each screening model. Deterministic sensitivity analyses were done to gauge the sensitivity of the results to key model assumptions. From the health system perspective, the semi-automated screening model was the least expensive of the three models, at US$62 per patient per year. The fully automated model was $66 per patient per year, and the human assessment model was $77 per patient per year. The savings to the Singapore health system associated with switching to the semi-automated model are estimated to be $489 000, which is roughly 20% of the current annual screening cost. By 2050, Singapore is projected to have 1 million people with diabetes; at this time, the estimated annual savings would be $15 million. This study provides a strong economic rationale for using deep learning systems as an assistive tool to screen for diabetic retinopathy. Ministry of Health, Singapore.

A semi-automated annotation algorithm based on weakly supervised learning for medical images

For medical image recognition, deep learning requires a massive training set, while annotation work is a tedious and time-consuming process because of the high technical threshold. Furthermore, it is difficult to guarantee annotation accuracy due to the knowledge, skills, and status of the annotator. In this research, we propose a semi-automated annotation model based on weakly supervised learning. Moreover, a target-level annotation method is proposed based on weakly supervised learning that is guided by machine learning. The machine learning method is used to screen the regions of interest (RoIs), whose semantic feature vectors are extracted by the deep learning method. Then, the machine learning method is used to cluster them, and the RoIs are finally classified and labeled by a distance comparison. Therefore, this model achieves target-level semi-automated annotation by only using image-level annotations. We applied this method to ultrasound imaging of thyroid papillary carcinoma. The experiments demonstrate the potential of this new methodology to reduce the workload for pathologists and increase the objectivity of diagnoses. We find that 89.8% of papillary thyroid carcinoma regions can be detected automatically, while 82.6% of benign and normal tissue can be excluded without the use of any additional immunohistochemical markers or human intervention.

Finding and Breaking Lie Symmetries: Implications for Structural Identifiability and Observability in Biological Modelling

A dynamic model is structurally identifiable (respectively, observable) if it is theoretically possible to infer its unknown parameters (respectively, states) by observing its output over time. The two properties, structural identifiability and observability, are completely determined by the model equations. Their analysis is of interest for modellers because it informs about the possibility of gaining insight into a model’s unmeasured variables. Here we cast the problem of analysing structural identifiability and observability as that of finding Lie symmetries. We build on previous results that showed that structural unidentifiability amounts to the existence of Lie symmetries. We consider nonlinear models described by ordinary differential equations and restrict ourselves to rational functions. We revisit a method for finding symmetries by transforming rational expressions into linear systems. We extend the method by enabling it to provide symmetry-breaking transformations, which allows for a semi-automatic model reformulation that renders a non-observable model observable. We provide a MATLAB implementation of the methodology as part of the STRIKE-GOLDD toolbox for observability and identifiability analysis. We illustrate the use of the methodology in the context of biological modelling by applying it to a set of problems taken from the literature.

A fuzzy GIS model to determine confluence morphological sensitivity to tributary inputs at the watershed scale

Confluences are key nodes of river systems that have the potential of disrupting downstream longitudinal trends in the main river through inputs of water, sediment, wood or ice delivered from tributaries. From a geomorphological perspective, confluence zones are particularly active and thus susceptible to increased flooding and bed instability, which, in turn, pose serious threats to infrastructure. However, not all confluences are active. Despite major advances in our knowledge of confluence dynamics, there has been limited progress in the development of low complexity, practical tools that use remotely sensed data to predict the spatial distribution of the main river's sensitivity to tributary inputs. We have thus developed a novel semi-automated GIS model that uses a fuzzy approach to integrate key factors (unit stream power, valley confinement and sediment connectivity potential) in order to map the distribution of the confluence morphological sensitivity (CMS) index at the watershed scale. The GIS model was tested using digital elevation models of high (LiDAR, 1 m) and coarser (10 m) resolution in the Coaticook and Gaspésie watersheds (Quebec, Canada). Results indicate that the model is useful for detecting geomorphologically active confluences and the resulting sensitivity of the main channel and thus has potential to be used in diverse river management applications (e.g., hazard reduction and freedom space mapping).

Willingness of people who are blind to accept autonomous vehicles: An empirical investigation

Attitudes of a sample of 211 UK people who are blind concerning autonomous vehicles (AVs), and the determinants of the willingness of people who are blind to travel in AVs, were examined. Participants answered an open-ended question regarding their attitudes towards level 5 AVs and the results were analysed using a semi-automated structural topic modelling procedure. (Level 5 AVs are fully autonomous anywhere, and do not require controlled areas in which to operate.) Four “topics” emerged from the exercise: (i) “hope” for future independence and freedom to travel offered by AVs to people who are blind, (ii) scepticism that AVs will ever be configured to meet the needs of people who are blind, (iii) concerns over safety, and (iv) the affordability of AVs. The four topics were employed as mediating variables in a structural equation model designed to explain the respondents’ willingness to travel in an AV. A number of covariates were presumed to influence the four mediating topics, including a participant’s desire for independence, comorbidity, locus of control, and level of generalised anxiety. Three of the mediating variables exerted significant influences on willingness to travel in an AV, i.e., hope for future independence, misgivings about safety, and affordability. Scepticism about AVs did not have a significant effect. Several implications for AV design and for the creation of public information messages promoting AVs are suggested. In particular, public information campaigns should emphasise the freedom to travel that AVs will provide for people who are blind; reassurances concerning safety; and the inevitability of AVs appearing on the roads of economically developed countries.

Staging of clear cell renal cell carcinoma using random forest and support vector machine

Kidney cancer is one of the deadliest types of cancer affecting the human body. It’s regarded as the seventh most common type of cancer affecting men and the ninth affecting women. Early diagnosis of kidney cancer can improve the survival rates for many patients. Clear cell renal cell carcinoma (ccRCC) accounts for 90% of renal cancers. Although the exact cause of the kidney cancer is still unknown, early diagnosis can help patients get the proper treatment at the proper time. In this paper, a novel semi-automated model is proposed for early detection and staging of clear cell renal cell carcinoma. The proposed model consists of three phases: segmentation, feature extraction, and classification. The first phase is image segmentation phase where images were masked to segment the kidney lobes. Then the masked images were fed into watershed algorithm to extract tumor from the kidney. The second phase is feature extraction phase where gray level co-occurrence matrix (GLCM) method was integrated with normal statistical method to extract the feature vectors from the segmented images. The last phase is the classification phase where the resulted feature vectors were introduced to random forest (RF) and support vector machine (SVM) classifiers. Experiments have been carried out to validate the effectiveness of the proposed model using TCGA-KRIC dataset which contains 228 CT scans of ccRCC patients where 150 scans were used for learning and 78 for validation. The proposed model showed an outstanding improvement of 15.12% for accuracy from the previous work.

Analyzing Security Protocol Web Implementations Based on Model Extraction With Applied PI Calculus

Analyzing security protocol web implementations is a crucial part of web security. Based on the model extraction technology, this paper first defines SubJavaScript and SubPython languages, and then establishes mapping models from SubPython and SubJavaScript to Applied PI Calculus respectively, after that, develops the semi-automatic model extraction tools SubPython2PV and SubJavaScript2PV to analyze the four widely used security protocol web implementations. The experiment shows that the four typical security protocol web implications have confidentiality, but lack of authentication.

Artificial Intelligence for Teleophthalmology-Based Diabetic Retinopathy Screening in a National Program: A Modelledn Economic Analysis Study

Background: Diabetic retinopathy (DR) screening programs worldwide are currently challenged by manpower and financial constraints. Deep learning systems (DLS) have been shown to be a clinically effective tool to detect DR, but with unknown cost implications. The purpose of this study is to conduct an economic analysis to evaluate two screening models using DLS: a semi-automated (as a “triage” filter prior to secondary human assessment) and a fully-automated (as a complete “replacement” for all human assessment) model against the current full human assessment model (a manual grading system). Methods: Using 14,880 consecutive patients with diabetes recruited from the Singapore Integrated DR Screening Program (SiDRP) between year 2014 and 2015, a decision tree model is used to compare the total costs associated with the three DR screening models in a hypothetical Singaporean diabetic cohort, over a 12-month time frame. Model parameters included DR prevalence rates, DR screening costs, cost of medical consultation; and diagnostic performance (i.e. sensitivity and specificity) of the three screening models. The outcome measure was patient-level total cost for each of the three screening models incurred within the health system. Deterministic sensitivity analyses were performed. All costs were converted to US dollars from Singaporean dollars. Findings: From the health system perspective, the semi-automated screening model is the least expensive at US$56/patient compared to the fully-automated model at US$60/patient, and the current human assessment model at US$63/patient. All three screening models yielded comparable diagnostic performances. In Singapore, the annual cost saving associated with the semi-automated model is estimated to be US$4·2 million, based on projected number of diabetic cases to approximately 600,000 patients by 2025. Interpretation: For DR screening, a semi-automated model which triages retinal photographs prior to secondary human assessment is less costly but equally effective than the current full human assessment model. This demonstrates the strong economic rationale for using DLS as an assistive tool to screen for DR. Funding: This project received funding from National Medical Research Council (NMRC) Health Service Research Grant, Ministry of Health (MOH), Singapore (National Health Innovation Center, Innovation to Develop Grant (NHIC-I2D-1409022); SingHealth Foundation Research Grant (SHF/FG648S/2015), and the Tanoto Foundation. The Singapore Diabetic Retinopathy Program (SiDRP) received funding from the MOH, Singapore (grants AIC/RPDD/SIDRP/SERI/FY2013/0018 & AIC/HPD/FY2016/0912). The Diabetes study in Nephropathy And other Microvascular complications (DYNAMO) received funding from National Medical Research Council (NMRC) Large Collaborative Grant (LCG). Declaration of Interest: Ting Daniel SW, Lim Gilbert, Lee Mong L, Hsu Wynne, and Wong Tien Y are coinventors of a patent on the deep learning system in this paper; potential conflicts of interests are managed according to institutional policies of the Singapore Health System (SingHealth) and the National University of Singapore. All other authors declare no competing interests. Ethical Approval: This study was approved by the Centralized Institutional Review Board (IRB) of SingHealth, Singapore (protocol number SHF/FG648S/2015) and conducted in accordance with the Declaration of Helsinki. Patients’ informed consent was exempted by the IRB due to the retrospective nature of study using fully anonymized retinal images.

Associations évoquées par le changement climatique chez des citoyens français et norvégiens

Communication related to climate change as well as to its consequences constitutes a major challenge; all the more so since climate is a non-observable phenomenon, in stark contrast to the weather. In this perspective, language plays a crucial role in the conceptualisation and the framing of climate change discourse.
 In this paper, French and Norwegian data stemming from representative surveys in the two countries are compared. The participants are asked to answer an open-ended question concerning their conceptions of the expression “climate change”. The French data are collected from a survey undertaken in 2016 by ELIPSS at the Sciences Po (Institut d'études politiques de Paris). The Norwegian data are generated from a survey undertaken in 2013 by the Norwegian Citizen Panel/DIGSSCORE, at the University of Bergen. The answers are first analysed through a semi-automated structural topic modeling (STM) and then assessed through an in-depth manual evaluation. Further linguistic and enunciative analyses are undertaken of a selection of the respondents’ answer provided by the surveys.
 Given the difference in the energy mix of the two countries, different associations are expected to appear from the French and the Norwegian participants. At the same time, with the common global dimension of climate change, it seems reasonable to expect some similar associations concerning the reality of the changes, the consequences and the measures of adaptation or mitigation proposed or undertaken by the two countries. These issues are discussed within the theoretical frame of enunciation, including perspectives related to concession in a polyphonic perspective and to deontic modality.

Semi-automatic segmentation from intrinsically-registered 18F-FDG\u2013PET/MRI for treatment response assessment in a breast cancer cohort: comparison to manual DCE\u2013MRI

ObjectivesTo investigate the reliability of simultaneous positron emission tomography and magnetic resonance imaging (PET/MRI)-derived biomarkers using semi-automated Gaussian mixture model (GMM) segmentation on PET images, against conventional manual tumor segmentation on dynamic contrast-enhanced (DCE) images.Materials and methodsTwenty-four breast cancer patients underwent PET/MRI (following 18F-fluorodeoxyglucose (18F-FDG) injection) at baseline and during neoadjuvant treatment, yielding 53 data sets (24 untreated, 29 treated). Two-dimensional tumor segmentation was performed manually on DCE–MRI images (manual DCE) and using GMM with corresponding PET images (GMM–PET). Tumor area and mean apparent diffusion coefficient (ADC) derived from both segmentation methods were compared, and spatial overlap between the segmentations was assessed with Dice similarity coefficient and center-of-gravity displacement.ResultsNo significant differences were observed between mean ADC and tumor area derived from manual DCE segmentation and GMM–PET. There were strong positive correlations for tumor area and ADC derived from manual DCE and GMM–PET for untreated and treated lesions. The mean Dice score for GMM–PET was 0.770 and 0.649 for untreated and treated lesions, respectively.DiscussionUsing PET/MRI, tumor area and mean ADC value estimated with a GMM–PET can replicate manual DCE tumor definition from MRI for monitoring neoadjuvant treatment response in breast cancer.

Mapping of shallow landslides with object-based image analysis from unmanned aerial vehicle data

The Black Sea Region of Turkey is one of the most landslide prone areas due to its high slope topography, heavy rainfall, and highly weathered hillslope material conditions. Preparation of landslide inventory maps is the first step in producing landslide susceptibility maps. Ground-based methods for mapping landslide occurrences are time-consuming and expensive. Additionally, landslide mapping based on satellite imageries and aerial photographs has some limitations, including climatic conditions, cost, and limited repetitive measurement capacity. Visual interpretation-based landslide mapping, which is based on satellite imageries and aerial photographs, is a time-consuming procedure that requires an experience-based expert opinion. Therefore, the data acquisition based on unmanned aerial vehicle (UAV) and landslide event inventory maps using an object-based classification approach can be superior to other methods in terms of speed and cost. In this study, we developed a semiautomatic model using object-based image analyses for rapid mapping of shallow landslides from the data obtained from UAVs after major landslide events in the Black Sea Region of Turkey. For this purpose, two test sites—Kurucasile (Bartin) and Cayeli (Rize)—were selected. Landslide mapping models were developed in the investigation sites, and the performance of the models was evaluated. The landslides' data obtained with the developed models were compared to the landslides' data produced by the experts. The comparison process revealed that landslides mapped by using UAV data have an accuracy rate higher than 86% according to the number of landslides and 83% according to the landslide area.

UFPR CampusMap: a laboratory for a Smart City developments

UFPR CampusMap: a laboratory for a Smart City developments

Glacier reconstruction of La Covacha Massif in Sierra de Gredos (central Spain) during the Last Glacial Maximum

A paleoglacier reconstruction during the Last Glacial Maximum (LGM) is presented for a high mountain area of La Covacha massif in Sierra de Gredos (Iberian Central System) in central Spain. The moraines that, according with the previous literature, had formed during the global LGM, were mapped through photo interpretation of digital aerial photographs and 3D images and detailed field surveys. The topography of the paleoglaciers was estimated using a simple steady-state model that assumed a perfectly plastic ice rheology, reconstructing the theoretical ice profiles and obtaining the ice thickness of the glaciers during the LGM. The reconstruction of the glaciers was carried out using automated and semi-automated physically-based models, obtaining more realistic results with semi-automated models. According to our study, the paleoglaciers in the study area covered an area of 34.79 km2 during the global LGM, with a maximum ice thickness of 366 meters in La Vega gorge, a total volume of 34.25 × 108 m3 and a mean paleoELA of 1932 meters. Most of the ice (∼82%) was in paleoglaciers facing north, and the rest was in paleoglaciers with other orientations. This emphasizes the importance of orientation in relation to glacier dynamics and ice accumulation. The results obtained in the calculation of paleoELAs during the global LGM in Gredos are average compared to the Iberian mountains of the Northwest where the values were much lower, and with respect to those of the Southwest, much higher. This demonstrates the importance of the exposure of Mediterranean mountains to the humidity sources coming from the NW during the global LGM, as is the case at present.

Operant Social Reward Decreases Incubation of Heroin Craving in Male and Female Rats

BackgroundWe recently reported that operant social choice–induced voluntary abstinence prevents incubation of methamphetamine craving. Here, we determined whether social choice–induced voluntary abstinence would prevent incubation of heroin craving. We also introduce a fully automatic social reward self-administration model that eliminates the intense workload and rat–human interaction of the original semiautomatic model. MethodsIn experiment 1, we trained male and female rats for social self-administration (6 days) and then for heroin self-administration (12 days). Next, we assessed relapse to heroin seeking after 1 and 15 abstinence days. Between tests, the rats underwent either forced or social choice–induced abstinence. In experiment 2, we developed a fully automatic social self-administration procedure by introducing a screen between the self-administration chamber and the social-peer chamber; the screen allows physical contact but prevents rats from crossing chambers. Next, we compared incubation of craving in rats with a history of standard (no-screen) or automatic (screen) social self-administration and social choice–induced abstinence. ResultsThe time-dependent increase in heroin seeking after cessation of drug self-administration (incubation of craving) was lower after social choice–induced abstinence than after forced abstinence. There were no differences in social self-administration, social choice–induced abstinence, and incubation of craving in rats trained in the standard semiautomatic procedure versus the novel fully automatic procedure. ConclusionsOur study demonstrates the protective effect of rewarding social interaction on heroin self-administration and incubation of heroin craving and introduces a fully automatic social self-administration and choice procedure to investigate the role of volitional social interaction in drug addiction and other psychiatric disorders.

From Point Cloud Data to Structural Analysis Through a Geometrical hBIM-Oriented Model

The assessment of the structural behavior of historic masonry structures like Gothic cathedrals is an important engineering and architectural issue, because of the economic and cultural relevance of such buildings. In this article, we present a complete numerical methodology for point clouds processing, geometrical and parametric 3D modeling, and finite element structural analysis of the spire of the Cathedral of Senlis, France. Our work highlights the particular difficulties linked with digitization and geometrical modeling of highly complex Gothic structures, as well as the need to find compromises between quality and accuracy of extracted data used for geometrical modeling and structural analysis. The methodology enables the semi-automatic transformation of a three-dimensional points cloud, surveyed through terrestrial laser scanner, into a three-dimensional geometrical historic building information modeling (hBIM)-oriented model, and its use to propose a consistent 3D finite element mesh suitable for advanced structural analysis. A full software chain is integrated in the proposed numerical process, so as to use the most important data contained in the real geometry and accurately transposed in the point clouds. After a successful data processing step with 3DReshaper software that proved to be necessary for enhancement of point clouds, a semi-automated geometrical hBIM-oriented modeling step with Rhinoceros5 software and VisualARQ plugin has allowed the construction of a hybrid model by reverse engineering from the point clouds. This 3D model, containing both geometrical and parametric data of the structure, has been exported to the Hyperworks suite for finite element structural analysis under self-weight. Our computations focused on the estimation of the structure deformation and on the distribution of compression and traction stresses in all components of the complex structure. It is found that the spire is safe. Based on reliable and properly detailed results, our study provides significant information for understanding the behavior of the structure and potential damage monitoring.

APPLICATION OF THE COMPLEX APPROACH FOR USAGE OF MUSIC COMPOSING SOFTWARE

A complex approach of using the electronic composer has been proposed. Today, the scientific community has shown great interest in the problems of studying the interrelationships of music, mathematics and psychology. Therefore, creation and giving recommendations on the practical use of musical biotechnical automated control system, which allows to compose monophonic and polyphonic sound series using a stochastic basis or a regular random signal with a uniform distribution, with an objective to further application of this sound series for musical or musicaltherapeutic effects on the object of influence — cognitive functions of the human brain (aviation dispatcher, pilot, cosmonaut, etc.), has been considered. The modernized concept of automated music synthesis is highlighted, taking into account the requirements of both the quality of composed music and a significant reduction of the composer’s routine work. Such a strategy seems to be optimal today, or at least very promising. Automated music creation is one of the most difficult tasks in both applied mathematics and the development of targeted software. Within the framework of the proposed integrated approach, an exposition of a musical piece together with a cadenza is composed by the author of a musical work manually, while its polyphonic development is carried out with the help of the music composing software. The use of random numbers or a stochastic basis in a musical composition makes it possible to get a musical signal that is original in structure but somewhat monotonous in sound. To make it more sophisticated and eliminate the triviality of the musical texture, which is a consequence of the automation of the music composition process, a digital filter based on solution of a linear differential equation in fractional derivatives (according to Caputo) is used as the activation function of the neural scheme. The result of semi-automated modeling of the system is estimated as more natural, correct and strategically perspective.

Big Data-Based Evaluation of Urban Parks: A Chinese Case Study

Urban parks play a key role in urban sustainable development. This paper proposes a method for the evaluation of public parks from the perspective of accessibility and quality. The method includes the data extraction of urban park locations and the delineation of urban built-up areas. The processing of urban park data not only involves the extraction from digital maps, but also the classification of urban parks using a semi-automated model in ArcGIS. The urban area is identified using the Point of Interest (POI) data in digital maps, taking economic and human activities into consideration. The service area and its overlapped time is included in the evaluation indicators. With a clear definition of park and urban built-up area, the evaluation result of urban parks is of great comparability. Taking China as an example, the quality of urban parks in 273 prefecture-level cities has been evaluated. The results show that the average service coverage of urban parks in Chinese cities is 64.8%, and that there are significant disparities between cities with different population sizes and locations. The results suggest the necessity to improve public parks in small-and-medium sized cities and inland areas to strengthen the coordination of urbanization and regional development.