Google Cloud Research Articles

Evaluation of WebRTC in the Cloud for Surgical Simulations: A case study on Virtual Rotator Cuff Arthroscopic Skill Trainer (ViRCAST).

Web Real-Time Communication (WebRTC) is an open-source technology which enables remote peer-to-peer video and audio connection. It has quickly become the new standard for real-time communications over the web and is commonly used as a video conferencing platform. In this study, we present a different application domain which may greatly benefit from WebRTC technology, that is virtual reality (VR) based surgical simulations. Virtual Rotator Cuff Arthroscopic Skill Trainer (ViRCAST) is our testing platform that we completed preliminary feasibility studies for WebRTC. Since the elasticity of cloud computing provides the ability to meet possible future hardware/software requirements and demand growth, ViRCAST is deployed in a cloud environment. Additionally, in order to have plausible simulations and interactions, any VR-based surgery simulator must have haptic feedback. Therefore, we implemented an interface to WebRTC for integrating haptic devices. We tested ViRCAST on Google cloud through haptic-integrated WebRTC at various client configurations. Our experiments showed that WebRTC with cloud and haptic integrations is a feasible solution for VR-based surgery simulators. From our experiments, the WebRTC integrated simulation produced an average frame rate of 33 fps, and the hardware integration produced an average lag of 0.7 milliseconds in real-time.

AI-powered Digital Transformation: Tools, Benefits and Challenges for Marketers – Case Study of LPP

The article aims to show the role (benefits and challenges) of AI-powered digital marketing tools for marketers in the age of digital transformation. The considerations were related to the Polish market and a case study of LPP, a Polish clothing retailer. The starting point for this study was the analysis of the literature on the concept of artificial intelligence (AI) with reference to digital marketing. In the next steps, the results of the research on the Polish market conducted by the Digital Poland Foundation and presented in the report entitled “State of Polish AI 2021” were reviewed, and an application case study of the largest Polish clothing company – LPP – was conducted. The study is of an introductory and exploratory nature. It recognises the significant role of AI in digital transformation in the context of digital marketing in the Polish market. The implementation of solutions based on artificial intelligence algorithms, such as the Google Cloud, analytical platform and data repository, e-commerce infrastructure, chatbot, Genesys PureCloud, Google Dialogflow and the AI-based function in the PSIwms Warehouse Management System in LPP's distribution centre significantly improves the efficiency of online order processing without compromising the quality of products and order fulfilment time. By applying a case study analysis, the importance of AI-based tools in the digital transformation process, including digital marketing, in the Polish market was demonstrated. Marketers, including CMOs, were shown the benefits of applying AI-related technological solutions in the field of e-commerce optimisation and customer service.

Following the Digital Thread – A Cloud-Based Observation

In this research article, the buzzwords of digital thread, digital twin, and Industry 4.0 are examined by means of a systematic literature review. The key concepts shaping these paradigms are investigated to achieve an overview of existing solutions. First, the body of the literature is explored to provide general observations on similarities and differences between the concepts. Subsequently, an overview of key technologies is provided that are necessary to achieve the vision of the digital thread. Based on the identified technologies, state-of-the-art solutions relating to digital thread are discussed. Finally, this research work presents a high-level architecture for realizing the digital thread based on the conducted technology analysis. The architecture is also dedicated to providing a cloud-based observation combining business solutions (e.g., SAP products) and cloud platforms (e.g., Google Cloud). To conclude the research carried out here, an outlook is given on possible future developments based on the work accomplished.

On the Integration of Google Cloud and SAP HANA for Adaptive Supply Chain in Retailing

The retailing industry witnessed a significant shift in the past years, which introduced significant modifications in the standard procedures and regular practices of supply chains (SC). These necessary modifications and worldwide distress caused major disruptions and instabilities in SC. Organizations started developing digital-transformation strategies, which include the integration and analysis of external data sources to detect disruptions in SC to retain a competitive advantage in the market. Developing such strategies requires exploring current technologies and investigating the use of cloud capabilities for adaptive supply chain management (A-SCM). The lack of flexibility in strategic and operative supply chain practices causes a significant loss of optimization potential. Therefore, in this study, we investigate data sources and solution techniques that might be beneficial to developing A-SCM practices. Based on the conducted literature analysis and cloud technologies, we present a hybrid architecture for A-SCM, integrating Google Cloud technologies, SAP HANA, simulation, and optimization components.

Method of identifying urban heat islands by remote sensing based on big data

In recent decades, the speed of construction, expansion, and development of smart cities by humans has been increasing faster, thanks to new technologies. However, alongside the fantastic development of new technologies also comes negative impacts such as climate change. One of the characteristics of climate change is the changing thermal comfort of humans living in the city. Heat stress is a feature of the urban heat island phenomenon. Congestion of airflows within the urban area causes localized hot areas, causing a temperature difference of 2-3 degrees between the areas inside the city and the suburbs. This study presents a method for determining surface temperature and the location of heat islands based on Google's cloud computing platform. The platform uses a combination of satellite imagery, Earth observation data, and machine learning algorithms to allow users to identify and measure changes in land use, ecosystems, and climate patterns at a global scale. Google Earth Engine enables researchers and organizations to process enormous amounts of data with short turnaround times. The method described in the article allows the analysis and retrieval of data in the large dataset of the Landsat 8 satellite. By determining the location of heat islands, the government, policymakers, and planners can develop plans to cope with the urban heat island phenomenon and improve the quality of life for residents.

SAGE: Steering the Adversarial Generation of Examples With Accelerations

To generate image adversarial examples, state-of-the-art black-box attacks usually require thousands of queries. However, massive queries will introduce additional costs and exposure risks in the real world. Towards improving the attack efficiency, we carefully design an acceleration framework SAGE for existing black-box methods, which is composed of sLocator (initial point optimization) and sRudder (search process optimization). The core idea of SAGE in terms of 1) saliency map can guide the perturbations towards the most adversarial direction and 2) exploiting bounding box (bbox) to capture those salient pixels in the black-box attack. Meanwhile, we provide a series of observations and experiments that demonstrate bbox holds model invariance and process invariance. We extensively evaluate SAGE on four state-of-the-art black-box attacks involving three popular datasets (MNIST, CIFAR10, and ImageNet). The results show that SAGE could present fundamental improvements even against robust models that use adversarial training. Specifically, SAGE could reduce >20% of queries and improve the success rate of attacks to 95%~100%. Compared with the other acceleration framework, SAGE fulfills the more significant effect in a flexible, stable, and low-overhead manner. Moreover, our practical evaluation (Google Cloud Vision API) shows SAGE can be applied to real-world scenarios.

A MODEL OF USING INFORMATION AND DIGITAL TECHNOLOGIES TO EVALUATE THE EFFECTIVENESS OF PEDAGOGICAL RESEARCH

The paper clarifies the definitions of "information and digital technologies", "effectiveness of pedagogical research", and "evaluation of the effectiveness of pedagogical research using information and digital technologies". A model of using information and digital technologies to evaluate the effectiveness of pedagogical research has been developed, which contains four blocks: purpose, content, organizational and activity, and evaluation and result. The selected components are characterized. In particular, the purpose of the model is to develop the content and technologies for using information and digital technologies to evaluate the effectiveness of pedagogical research; the purpose group, and regulatory documents on which the developed model is based. The following digital tools and platforms are highlighted in the content block: scientometric databases, electronic scientific and educational libraries, altmetric tools, etc. In the organizational and activity block, the following topics are proposed as possible topics for seminars/webinars: evaluating the effectiveness of pedagogical research using statistical modules of scientific digital libraries, Google cloud services, international and domestic scientometric databases, scientific social networks, altmetric and bibliometric systems, and creating an e-portfolio. The evaluation and result block considers project-competition, scientific-publication, scientometric, altmetric, expert and representative scientific criteria and indicators for evaluating the effectiveness of pedagogical research of scholars, research and teaching staff, research institutions, and HEIs. The weight of each criterion can be adjusted by introducing coefficients of significance. The result of the developed model is the improvement of the competence of researchers and academic staff using information and digital technologies to evaluate the effectiveness of pedagogical research.

Achieving Decentralized and Dynamic SSO-Identity Access Management System for Multi-Application Outsourced in Cloud

Existing single sign-on (SSO) access control systems typically rely on the traditional protocols requiring additional authentication mechanism and/or identity providers. As the growing demand in outsourcing system resources such as data and applications to the cloud platform, implementing traditional SSO models to support efficient and fine-grained access control for multi-user and multi-application environment is not practical. In this paper, we propose a blockchain-based identification and access management (IAM) scheme called D <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> -IAM to provide strong security measures for controlling SSO access to resources in the cloud. At a core of D <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> -IAM, all access control processes are done by the smart contracts and blockchain where the access transactions are well retained for the accountability. In our system, the SSO authentication is based on highest authentication level and hashed-based token that significantly reduces the communication overhead for multi-system authentication. For the authorization system, D <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> -IAM enables fine-grained access through the access policy modeled in document database written and enforced to each customer. Finally, we conducted the experiments on Google cloud to show that our D <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> -IAM system is efficient for the implementation. The performance test showed that our proposed system is approximately 4 times efficient than the average processing time of three existing works.

The Economic Impact of Cloud Technologies on the Industry 4.0 Development

This article explores the profound economic impact of cloud technologies on Industry 4.0, focusing on how these technologies are revolutionizing the industrial sector. It delves into the transformation of IT investments from capital expenditure (CAPEX) to operational expenditure (OPEX) due to cloud computing. This shift is making advanced digital technologies more accessible and affordable, particularly for small and medium-sized enterprises (SMEs). By reducing the need for significant upfront investments and providing scalable, pay-as-you-go solutions, cloud computing significantly enhances the return on investment (ROI) for Industry 4.0 initiatives. A comparative analysis of major cloud service providers—Amazon Web Services (AWS), Google Cloud Platform (GCP), and Microsoft Azure—reveals the diverse range of services and economic benefits they offer for Industry 4.0 applications. AWS leads with comprehensive IoT and machine learning services, GCP excels in data analytics and AI capabilities, and Microsoft Azure provides robust enterprise integrations and hybrid cloud solutions. The article also addresses critical challenges such as security, compliance, and the risks associated with cloud provider lock-in. It offers strategic insights into cost management practices that can maximize the economic benefits of cloud adoption, such as leveraging multi-cloud strategies and utilizing auto-scaling and reserved instances. Furthermore, the article includes case studies from leading industrial companies like Siemens, General Electric, BMW, and ABB. These examples illustrate how cloud-based Industry 4.0 solutions enhance operational efficiency, reduce costs, and drive innovation. For instance, Siemens leverages AWS for scalable IoT solutions, GE utilizes Azure for data-driven industrial insights, and BMW employs GCP for advanced data analytics to improve manufacturing processes. In conclusion, cloud technologies are essential enablers of Industry 4.0, offering significant economic advantages and fostering innovation and efficiency. By overcoming historical barriers to entry, especially for SMEs, and providing flexible, scalable solutions, cloud computing is transforming the industrial landscape, driving growth, and facilitating the widespread adoption of advanced manufacturing technologies.

Accelerating Minimap2 for Accurate Long Read Alignment on GPUs.

Long read sequencing technology is becoming increasingly popular for Precision Medicine applications like Whole Genome Sequencing (WGS) and microbial abundance estimation. Minimap2 is the state-of-the-art aligner and mapper used by the leading long read sequencing technologies, today. However, Minimap2 on CPUs is very slow for long noisy reads. ~60-70% of the run-time on a CPU comes from the highly sequential chaining step in Minimap2. On the other hand, most Point-of-Care computational workflows in long read sequencing use Graphics Processing Units (GPUs). We present minimap2-accelerated (mm2-ax), a heterogeneous design for sequence mapping and alignment where minimap2's compute intensive chaining step is sped up on the GPU and demonstrate its time and cost benefits. We extract better intra-read parallelism from chaining without losing mapping accuracy by forward transforming Minimap2's chaining algorithm. Moreover, we better utilize the high memory available on modern cloud instances apart from better workload balancing, data locality and minimal branch divergence on the GPU. We show mm2-ax on an NVIDIA A100 GPU improves the chaining step with 5.41 - 2.57X speedup and 4.07 - 1.93X speedup : costup over the fastest version of Minimap2, mm2-fast, benchmarked on a Google Cloud Platform instance of 30 SIMD cores.

A dataset of water transparency of Sanya River based on Sentinel-2 data during 2019–2021

As one of the most important water quality parameters on the radar screen of environmental protection sectors, water transparency reveals the turbidity degree of water and plays an important role in the primary productivity of water body and water ecosystem. As an independent island water system, Hainan Province has abundant surface inland water resources and plentiful river runoff. However, due to the influence of dry and wet monsoons and topography, the aquatic systems are characterized by uneven spatial and temporal distribution, and there are few studies on the water quality of inland water bodies on Hainan Island. In this study, we took Sanya River in Sanya, Hainan Province as the study area, and used the QAAv6-based semi-analytic model to retrieve the water transparency of Sanya River in time series from 2019 to 2021 based on the GEE cloud computing platform and the massive Sentinel-2 surface reflectance data stored in Google Cloud. With regard to the extraction of dynamic water area from Sanya River, we adopted the algorithm combining the normalized water body index NDWI with OTUS automatic threshold segmentation to extract the small river water. The data are stored in GeoTiff raster format, and the pixel transparency value and coordinate information are stored at the same time for easy reading and analysis by relevant GIS software. The inversion of long time series transparency based on the GEE cloud database is highly efficient. The dataset can serve as valuable scientific evidence for the water quality monitoring, water pollution control, and aquatic ecological protection of Sanya River.

Exploring the Key Design Attributes of Cafés from User-Generated Contents - A Case Study of Two Cafés of Unique Interior Designs in Yeonnam-dong, Seoul -

In the last couple of decades, the use of social media has consistently increased. Different social media platforms allow users to interact and create diverse types of content, making them able to share their opinions. With brands getting involved in these platforms, it is important to know how their image is portrayed by their customers on social media. This includes the café industry. The purpose of our study is twofold. One is to understand which design attributes make a café appealing to social media users, and another is to examine whether the Google Cloud Vision API is able to differentiate the key design attributes using user-generated content, which are Instagram posts in this research. In order to achieve these aims, we conducted a comparative case study using two cafés of unique interior designs located in Yeonnam-dong in Seoul, South Korea. Specifically, Greem Cafe and Perception Coffee were used. Using these cases as hashtags, we scraped the posts using a Python web scraper and screened out the posts irrelevant to the cafés. After, we ran them through the Google Cloud Vision API to obtain the labels and screened out the labels irrelevant to the interior designs, such as people and amenities. Finally, we were able to categorize the label to different design attributes and compare and contrast the labels from two cafés. The main differences shown in the results from the labels are that Greem Café had Color and Cartoon attribute labels like “Black-and-White” and “Drawing” that clearly represent the cartoonish interior design style. On the other hand, Perception Coffee’s most frequent label, “Wood” along with other labels like “Aeolian Landform” identify their wooden ceiling design. With these results, it is shown that the Google Cloud Vision API is able to distinguish the main design elements from both cafés. This research utilizes a new tool that can be useful for future researchers and designers that deal with big data, also this research brings insight for designers at the time of creating new places by analyzing data made by consumers and promotes the usage of social media data as a tool for design thinking.

Implementasi Sistem Otomasi Order Mentoring Pada Marketplace Mentoring Platform Nusademy

The COVID-19 pandemic has caused the acceleration of digitalization to occur throughout the world in various aspects of life, one of which is in the world of education. The openness of access to learning resources has not been the right solution for humans to learn independently. There are details in the learning process that require the guidance of a teacher called a mentor. In line with this, PT Nusademy Solusi Indonesia (Nusademy) built a marketplace mentoring platform that allows learning to take place in a network between users and mentors. Nusademy provides an opportunity for users to able to choose learning topics and mentors according to their needs. In it, there are steps for mentoring orders, which are currently still being processed manually by the admin every time there is a transaction. So, we need a system that can bridge users with mentors to share benefits without having to depend on admin availability. Python is a programming language that has characteristics suitable for autonomous system development and integration with third-party services. This study aims to create, implement, and test an automated order mentoring system on the Nusademy Web Application which is integrated with the Xendit payment application, the Google Calendar scheduling application, and the Google Hangouts video-conferencing application. The automation system provides automatic services in billing, checking payment status, communication processes between users and admins, communication processes between admins and mentors, creating virtual mentoring rooms, and notification of mentoring agenda reminders. The system is launched on a cloud computing-based server which can enable automatic capacity scaling based on user requests using Google Cloud Run. Testing of the order mentoring automation system is carried out by considering aspects of system capability, system reliability, level of effectiveness, user experience, and business analysis.

Cloud-native distributed genomic pileup operations.

Pileup analysis is a building block of many bioinformatics pipelines, including variant calling and genotyping. This step tends to become a bottleneck of the entire assay since the straightforward pileup implementations involve processing of all base calls from all alignments sequentially. On the other hand, a distributed version of the algorithm faces the intrinsic challenge of splitting reads-oriented file formats into self-contained partitions to avoid costly data exchange between computational nodes. Here, we present a scalable, distributed, and efficient implementation of a pileup algorithm that is suitable for deploying in cloud computing environments. In particular, we implemented: (i) our custom data-partitioning algorithm optimized to work with the alignment reads, (ii) a novel and unique approach to process alignment events from sequencing reads using the MD tags, (iii) the source code micro-optimizations for recurrent operations, and (iv) a modular structure of the algorithm. We have proven that our novel approach consistently and significantly outperforms other state-of-the-art distributed tools in terms of execution time (up to 6.5x faster) and memory usage (up to 2x less), resulting in a substantial cloud cost reduction. SeQuiLa is a cloud-native solution that can be easily deployed using any managed Kubernetes and Hadoop services available in public clouds, like Microsoft Azure Cloud, Google Cloud Platform or Amazon Web Services. Together with the already implemented distributed range joins and coverage calculations, our package provides end-users with an unified SQL interface for convenient analyzing of population-scale genomic data in an interactive way. https://biodatageeks.github.io/sequila/. Supplementary data are available at Bioinformatics online.

WITHDRAWN: Optimal Scheduling Method of Information System Operation and Maintenance Resources Based On Data Perception in Cloud Computing

Through a network, cloud computing provides users with access to computer resources including software and hardware as a service which requires effective scheduling strategies to handle these resources due to the size and dynamic resource provisioning of current data centres. The difficulty in the current scheduling ways to optimise cost and execution time has led us to propose our optimization strategy based scheduling as a solution. This research proposes novel technique in information system based optimal scheduling and resource maintenance for data perception in cloud computing to improve scheduling and resource maintenance of cloud network for operation in information system through meta-heuristic glowwormkernel particle swarm optimization (MGKPSO) and Bayesian network based multi-cloud Software defined networks (SDN). The different cloud service providers selected for this experiment are: LocalStack, Google Cloud, and Amazon Web Services (AWS). The experimental analysis reveals that the proposed technique attained Quality of Service (QoS) of 73%, Throughput of 95%, latency of 67%, data transmission of 81%, Packet delivery ratio (PDR) of 93%.

A PEER-TO-PEER AIR QUALITY MONITORING SYSTEM USING IOT SENSORS AND CLOUD PLATFORMS

This paper presents the design and implementation of an air quality monitoring system that combines Internet of Things (IoT) sensors, cloud computing platforms, and peer-to-peer (P2P) networking. The system uses IoT sensors to collect real-time air quality data from multiple geographic areas. This data is sent to cloud platforms, including AWS IoT Core, for processing and storage. A P2P network of servers, with each server responsible for a specific area, enables distributed access to the air quality data. The system also incorporates machine learning models deployed on the Google Cloud Platform to provide air quality predictions. The proposed architecture for wide-area air quality monitoring is feasible and scalable based on experimental results.

SciSpot: Scientific Computing On Temporally Constrained Cloud Preemptible VMs

Scientific computing applications are being increasingly deployed on cloud computing platforms. Transient servers such as EC2 spot instances and Google Preemptible VMs, can be used to lower the costs of running applications on the cloud by up to <inline-formula><tex-math notation="LaTeX">$10\times$</tex-math></inline-formula> . However, the frequent preemptions and resource heterogeneity of these transient servers introduces many challenges in their effective and efficient use. In this paper, we develop techniques for modeling and mitigating preemptions of transient servers, and present SciSpot, a software framework that enables low-cost scientific computing on the cloud. SciSpot deploys applications on Google Cloud Preemptible Virtual Machines that exhibit temporally constrained preemptions: VMs are always preempted in a 24 hour interval. Our empirical analysis shows that the preemption rate is generally bathtub shaped, which raises multiple fundamental challenges in performance modeling and policy design. We develop a new reliability model for temporally constrained preemptions, and use statistical mechanics to show why the bathtub shape is generally exhibited. SciSpot’s design is guided by our observation that many emerging scientific computing applications that integrate machine learning with simulations, can be deployed as “bags” of jobs, which represent multiple instantiations of the same computation with different physical model parameters. For a bag of jobs, SciSpot finds the optimal transient server on-the-fly, by taking into account the price, performance, and preemption rates of different servers. SciSpot reduces costs by <inline-formula><tex-math notation="LaTeX">$5\times$</tex-math></inline-formula> compared to conventional cloud deployments, and reduces makespans by up to <inline-formula><tex-math notation="LaTeX">$10\times$</tex-math></inline-formula> compared to conventional high performance computing clusters.

Toward deceiving the intrusion attacks in containerized cloud environment using virtual private cloud‐based moving target defense

SummaryThe container‐based cloud has its distinct security challenges. In this article, moving target defense (MTD) is used to increase the cost and effort of the attacker to exploit resources and follow an attack path to compromise the critical resources in a container‐based cloud. The existing MTD mechanisms for cloud have not focused on intruder prevention inside containerized environment. The proposed solution is one of its kind that utilizes resource movement inside and across the virtual private network in the cloud to deceive intruders. The framework continuously changes the target/container to increase confusion about the routing path, so attackers cannot follow the simple attack path. This obscure cloud architecture increases the delay in attack and gives system/network administrators significant time to use Intrusion Detection mechanisms for countering the attack. The proposed scheme is implemented on the Google Cloud Platform (GCP) by using an extensive network of nodes hosting the stateful pods that are created and destroyed periodically. The experimental analysis confirmed that the proposed scheme substantially increased the attack path length and added obscurity at a low computation cost. However, as per experiments, implementing the proposed scheme in GCP slightly increases the dollar cost.

Design of Mobile 3D Augmented Reality on Marker Visual Inspection Mask

Augmented reality is a ground-breaking technology that allows users to communicate with an enticing real-world experience to receive messages or knowledge. Today, mask inspection is essential to relay information to society through an augmented reality where extensive information about masks is required and identifying them is challenging. Furthermore, with augmented reality, society may have access to the fascinating way of getting information on the masks, assisting in spreading knowledge, particularly during this pandemic. The augmented reality on a visual inspection mask (ARVIM) was created utilizing 3D images on an Android smartphone platform. The models were created using Blender Animation and Unity 3D software. Vuforia Engine and Android Studio applications were used to build a personalized mobile Augmented Reality application. Google Cloud was used to store data that are accessible to users. ARVIM has facilitated teaching and interaction with 3D AR effects enjoyable for users. The analysis results on the use of ARVIM revealed that ARVIM obtained a high easiness rating of 80%. While 83% of respondents say ARVIM can help distinguish between different types of masks, 88% of respondents agreed that ARVIM's design is acceptable and approachable. This initiative enhances society's education in interactive and mixed-reality innovation settings through a long-distance and innovative teaching method that gives a comprehensive Google Platform experience.

Correlating fluency theory-based visual aesthetic liking of landscape with landscape types and features

ABSTRACT People inherently assess landscapes by creating spontaneous aesthetic liking judgments based on the surrounding stimuli. To understand these judgements objectively, use may be made of the fluency theory of aesthetic pleasure (the psychological processes through which people experience beauty). This study aims to predict people’s visual aesthetic preferences based on fluency theory and to correlate these preferences with landscape types and features. An ordinary least squares (OLS) regression model was developed to predict visual aesthetic liking, using image statistics as explanatory variables. We determined types of landscape using Landscape Character Assessment (LCA) and applied viewshed analyses distinguishing between near, medium, and far zones. We identified landscape features by content analysis making use of machine learning-based image recognition supplied by Google Cloud Vision API. The results show that vegetation and geological forms were the most significant features for people’s visual aesthetic liking, followed by waterscapes and built structures/human settlements. The viewshed analyses indicated that ‘medium-altitude, low-gradient artificial areas’ were visible in photographs with high aesthetic visual liking in all zones (i.e., at all distances). When the photographs showing this type of landscape are examined, the artificial areas in the photographs turn out to consist mostly of historical buildings or remains. This finding suggests that historical sites are not just important for their cultural value, but for their visual aesthetic value as well.