https://doi.org/10.5220/0013441300003928

Airbnb, a prominent online marketplace, facilitates short-and long-term rentals by connecting customers with property owners offering entire apartments or private rooms.Accurate price prediction is crucial for both the platform and rental property owners.Previous studies have primarily focused on statistical methods and pre-processing techniques, with limited exploration of the impact of location attributes.This paper aims to enhance price prediction models for Airbnb listings by incorporating location data.Utilizing data from InsideAirbnb for Istanbul, we implemented various data pre-processing techniques and enriched the dataset with location-specific information.Our findings show that incorporating these location-based features significantly improved model performance, increasing the adjusted R 2 metric by 22.5% and reducing Mean Absolute Error (MAE) by %10.This enhancement was achieved by using location-related index values and public transportation data provided by the Istanbul Metropolitan Municipality.These advancements can help property owners optimize rental prices and assist urban planners in making informed decisions about city infrastructure development.

The traditional method to authenticate users on mobile devices or applications requires usernames and passwords. This approach authenticates the user only at the entry point of an application without providing continuous authentication during the whole session. This paper explores the use of behavioral biometrics, which involves tracking the unique movements of a user while interacting with a device, for continuous authentication on a mobile banking application. As a methodology, we use binary classification and explore the performance of deep learning algorithms. A dataset is collected from 45 participants using a mobile banking application in Turkey. We train four different types of deep architectures, including Multilayer Perceptron (MLP), LSTM, bi-directional LSTM, and convolutional LSTM. The dataset includes data from both touch screens and motion sensors. The results of the experiments reveal that MLP and the convolutional-LSTM algorithms achieve the best performance on raw data from both motion sensors and touch screens. Accuracy rates are over 99.85%, and FAR, FRR, and EER are below 0.5%.

In this paper, we use Hand Movement Orientation and Grasp (HMOG) sensor data to authenticate smart phone users. The way a user holds, grasps a mobile phone or touches to it are all key factors for authentication. At the moment of a user makes an event on his/her smart phone, three sensors automatically collect data about magnitude, angular speed and acceleration. Moreover, touching and holding events also produce data about pressure and coordinates. In this paper, we build four types of machine learning algorithms (decision forest, boosted decision tree, support vector machine, logistic regression) to predict user authentication. The data used in this experiment (HMOG) are collected from 100 students. We compare the results of the algorithms and for our scenario, we show that decision forest algorithm with normalized data gives best results.

The emission of CO2 due to ICT (Information and Communication Technologies) is found as equivalent to aviation sector. Although the energy consumption in ICT is due both to hardware and software. In recent decade, the energy efficiency studies focus on the hardware part, especially with the development of cloud computing. Indeed, it is the software application that is responsible for executing tasks, that indirectly affects the hardware energy consumption. This work focus on software energy consumption. We introduce a methodology which evaluates and improves the software greenability by considering its energy consumption, performance and readability. Contrary to existing methodologies, we associate the effect of several components (CPU, memory, disk and network) when estimating software energy consumption instead of considering only the CPU as it is the case in literature. Moreover, the proposed framework can dynamically examine source code to integrate some measurement functionality. A Tool to Estimate Energy Consumption (TEEC) is implemented and its applicability is demonstrated on the case of cloud-based business application provisioning software, called MADONA. MADONA allows dynamically generating service-oriented business applications by automatically composing business services and automatically deploying the generated applications on cloud environment.

In this paper, we consider a spectrum trading network. The primary service providers (PSPs), which are the long term owners of chunks of frequency spectrum, lease portions of their licensed frequency bands to secondary users for short term basis. The PSPs have also their own regular customers who expect to receive a minimum amount of bandwidth and a minimum level of quality of service. The existence of various network elements that want to maximize its own profits makes the problem very complex, with usually conflicting objective functions. The proposed framework in this paper aims at investigating the impact of power emission of secondary users to the pricing process. We have used a model based on game theory for PSPs' pricing problem to provide with a well defined equilibrium. The spectrum demand of secondary users is modeled using the multi-nomial logit (MNL) which is a kind of discrete choice model. We have used the MNL model to estimate the probability that a secondary user chooses a particular PSP as the seller. The application of the framework is shown on a simple demonstrative example. The results show that the proposed framework allows PSPs to make additional profit while preserving the social welfare of the network.

The underutilization of spectrum coupled with developments in network technologies has prompted a number of proposals for managing spectrum. Dynamic spectrum access radio technology, which is based on cognitive radio technology, promises to increase spectrum sharing and thus overcome the lack of available spectrum for new communication services. In this paper, the pricing and the transmission power control processes are investigated in a cognitive radio network. The considered network consists of multiple primary service providers which have some unutilized bandwidth; and multiple secondary users that require spectrum bands. In this multiple-seller and multiple-buyer environment, the proposed framework aims at determining the optimum price values for unit spectrum bands that maximizes PSPs profits while protecting the social welfare of their network. Furthermore, the framework considers the power control, especially the effect of transmission power on the profit of PSPs. Modeling the competitive relationships among network elements as games ensures analyzing all elements' behaviors and actions in a formalized way. The existence of various network elements that want to maximize its own profits makes the problem very complex, with usually conflicting objective functions. We have used a model based on game theory for PSPs' pricing problem to provide with a well defined equilibrium. The simulation results show that the proposed framework allow PSPs to make up to 45%-86% of additional profit while preserving the social welfare of the network.

The traditional static spectrum access approach, which assigns a fixed portion of the spectrum to a specific license holder for exclusive use, is unable to manage the spectrum efficiently any longer. In an effort to improve the efficiency of its usage, alternative spectrum allocation scenarios are being proposed. One of these technologies is the Dynamic Spectrum Access which enables wireless users to share a wide range of available spectrum in an opportunistic manner. In this paper, we study an architecture for a competitive spectrum exchange marketplace, a theoretic base, and the empirical work for spectrum price formation. The competitive spectrum exchange marketplace architecture considers short term sub-lease of unutilized spectrum bands to different service providers. Our proposed pricing model applies game theory as its mathematical base. The Nash equilibrium point tells the spectrum holders the ideal price values where profit is maximized at the highest level of customer satisfaction. Our empirical results prove that the service providers' demand depends on the price and QoS of that band as well as the price and QoS offering of its competitors.

In the last decades, the development of the mobile telecommunication industry has triggered the increase of demand for wireless spectrum. Dynamic spectrum management (DSM) concept has been emerged with the development of cognitive radio technologies just to enable efficient utilization of the scarce spectrum. However, DSM will provide significant economic and social benefits only if it becomes widely utilized. For this to occur, the next generation wireless market itself must evolve. This paper analyzes a novel brokering architecture for next generation cognitive radio-based communication platform. We develop a simple competitive economic model among the players of our proposed architecture.

The approach presented in this paper aims at establishing a bandwidth allocation scheme for use in Geostationary Earth Orbit (GEO) satellite networks. As various multimedia applications necessitate large amounts of capacity, an efficient bandwidth management algorithm comes into prominence in order to provide high quality of service (QoS) to users. The first stage of the algorithm involves determining the portion of bandwidth that should be offered to a Satellite Gateway (SG), while the second stage consists of sharing this allocated bandwidth among different traffic flow types. At this point, the strategic pricing concept which means building a balance between the customer's desires and the network operator's profits emerges. The proposed approach has the objective to solve simultaneously these two consecutive allocation problems and moreover to propose their pricing scheme. Analytical and simulation results demonstrate the effectiveness of the suggested approach in terms of efficient bandwidth usage.

Pricing the future services in next generation mobile networks will play a key role from the operator point of view to achieve the maximum revenue and utilization rate. Moreover, pricing these services is a very important issue to users since the acceptance of the services is directly related to the quality of service (QoS) offered to their subscribers. Network operators who provide different wireless services face two major challenges: (1) social welfare maximization; and (2) price determination. In this article, we focus on proposing a simple and robust charging approach for wireless applications. We aim to publish a unit price for each wireless product class taking into account the issues of social welfare maximization and price determination. When compared with the flat-rate model, where the fee is fixed and does not vary with the actual usage of the bandwidth, the suggested solution is able to provide a better quality of service to the users as well as greater revenue to the network operator.