A two-level stacking model for detecting abnormal users in Wechat activities

Nowadays the safety of computer networks becomes more important than other characteristics. The services which are used by a huge number of users entice hacker. Especially, online payment services are often the main target of malicious software. In the article, the computer virus SpyEye spread via Internet resources is considered. The Petri-object model of propagation process is created with the use of Petri-object simulation software written in Java. The model reproduces the events of damaging website, infecting user’s resource, sending information about vulnerabilities and sending personal data. It was suggested that users are connected when they use the same website. The investigation of the spreading time for different kinds of users’ connections topology is presented. It was considered not only well-known star and chain topologies but also their combinations and the topology with random connections. Simulation results confirm the virus spreading time dependence on user’s connections topology.

Introduction: Achievement of specified qualitative indicators in machine learning solutions depends not only on the efficiency of algorithms, but also on data properties. One of the lines for the development of classification and regression models is the specification of local properties of data. Purpose: To improve the qualitative predictors when solving classification and regression problems based on the adaptive selection of various machine learning models on separate local segments of data sample. Results: We propose a method that uses a combination of different models and machine learning algorithms on subsamples in regression and classification problems. The method is based on the calculation of qualitative predictors and the selection of the best models on the local segments of data sample. The finding of transformations of data and time series allows to create sample sets, with the data having different properties (for example, variance, sampling fraction, data range, etc.). We consider the data segmentation based on the change point detection algorithm in time series trends and on analytical information. On the example of the real dataset, we show the experimental values of the loss function for the proposed method with different classifiers on separate segments and on the whole sample. Practical relevance: The results can be used in classification and regression problems for the development of machine learning models and methods. The proposed method allows to improve classification and regression qualitative predictors by assigning models that have the best performance on separate segments.

Clustering of search results has been shown to be advantageous over the simple list presentation of search results. However, in most clustering interfaces, the clusters are not adaptive to a user’s interaction with the clustering results, and the important question “how to optimize the benefit of a clustering interface for a user” has not been well addressed in the previous work. In this paper, we study how to exploit a user’s clickthrough information to adaptively reorganize the clustering results and help a user find the relevant information more quickly. We propose four strategies for adapting clustering results based on user actions. We propose a general method to simulate different kinds of users and linearize the cluster results so that we can compute regular retrieval measures. The simulation experiments show that the adaptation strategies have different performance for different types of users; in particular, they are effective for “smart users” who can correctly recognize the best clusters, but not effective for “dummy users” who follow system’s ranking of results. We further conduct a user study on one of the four adaptive clustering strategies to see if an adaptive clustering system using such a strategy can bring users better search experience than a static clustering system. The results show that there is generally no significant difference between the two systems from a user’s perspective.

Content in collaborative systems, such as Online Social Networks, is often co-owned by multiple users with different privacy expectations, leading to possible multiuser privacy conflicts. In order to address these conflicts, we argue that users should be supported by trustworthy agents that adhere to the following criteria: (i) concealment of privacy preferences, such that only necessary information is shared with others; (ii) equity of treatment, such that different kinds of users are supported equally; (iii) collaboration of users, such that a group of users can support each other in agreement and (iv) explainability of actions, such that users know why certain information about them was shared to reach a decision.

The following paper describes the implementation of three different controllers for a wheelchair. It was built for improving people's life that could have disabilities associated with functions regarding muscle strength, power of muscle of all limbs, tone of muscle of all limbs and endurance of all muscles of the body. Using three programmed methods that allow the user to have full control over the wheelchair. By acquiring voltage signals generated in eye's movements and using Neuro-Fuzzy Networks for differentiating each one, the wheelchair is able of being controlled by eye's movements. Figuring out about different kinds of user's needs and environments, the wheelchair includes voice control in spaces where noise levels are less than 40dB. The voice commands are detected using the Speech Recognition software which is a default program installed on Microsoft Windows operative system. The eye and voice controls were designed using LabVIEW and the intelligent control toolkit (ICTL). There were developed virtual simulators on C# code that enable the patient to have a previous training for having a better wheelchair control and performance. The system was tested on a person with cerebral palsy.

The nature of explanation dialogues is examined and an expert system that provides acceptable and appropriate answers and explanations to the questions posed by different kinds of users is designed. An empirical study and analysis of natural dialogues between experts, novices and partial experts is described. From this analysis a theory of explanation dialogues (extended schema-based theory, or EST) is developed. In EST questions are interpreted by combining information from different, semantically related question types that together best capture the essence and meaning of the question. This theory is applied to the design of an architecture and computational model for interpreting questions and generating explanations. The expert system, EXPLAIN, understands the nature of the question and is able to take account of the previous dialogue. The system can tailor its responses to an individual user's characteristics, including level of expertise and depth of knowledge in the domain. >

The long-tail phenomenon tells us that there are many items in the tail. However, not all tail items are the same. Each item acquires different kinds of users. Some items are loved by the general public, while some items are consumed by eccentric fans. In this paper, we propose a novel metric, item eccentricity, to incorporate this difference between consumers of the items. Eccentric items are defined as items that are consumed by eccentric users. We used this metric to analyze two real-world datasets of music and movies and observed the characteristics of items in terms of eccentricity. The results showed that our defined eccentricity of an item does not change much over time, and classified eccentric and noneccentric items present significantly distinct characteristics. The proposed metric effectively separates the eccentric and noneccentric items mixed in the tail, which could not be done with the previous measures, which only consider the popularity of items.

Today it is not easy to imagine what would be the future of user experience (UX) design in the world of Artificial Intelligence (AI). Referring to the sector of autonomous vehicles the paper aims to explore the changes that will be brought by artificial intelligence to the innovative sector of the self-driving car. According to these transformation car interiors and passengers experiences will become very different from the actual one. The aim of the research is, starting from different kind of passengers needs (Human Centered Design approach) individuating essential factors to design autonomous cars interiors and in particular to design innovative interfaces for a better communication with the passengers and a high level of living experience for different kind of users.

Different categories of drinking houses, it is claimed, are historically related to different kinds of users and usages. Industrialism, however, entrenched the ubiquitous pub amidst the song, sin and insobriety of the poor and the new working-class urban proletariat. The public house thus became a focus of social freedoms and sexual licence, as well as a locus of more formal elements of rational recreation. Yet the public house was subject to social controls of a ferocious kind and not simply licensing constraints, and some discussion is developed in examining the class basis of recreation and leisure controls. Attention finally turns to viewing the public house as an intermediate context in a relational sense, in an historical sense and in a time sense, and one deserving further sociological attention. Historically, different types of public drinking houses have generally developed out of distinct categories of social usage. The inn developed from the coaching tradition of providing refreshment and lodgings for travellers. Such houses tended over time to foster recreation and itinerant entertainers and to be a focus of not just wealthy travellers but plyers of wares and trades-but always perhaps within the context of a dominant use by the relatively wealthy. Such drinking houses catered for catholic drinking tastes-spirits, wines and beers. The taverns were originally concerned with selling wine, the availability of wine itself being boosted by the cultivation of vines in the medieval monasteries. Such taverns, by the late eighteenth century, were virtually indistinguishable from inns and met the needs of the casual drinker, catering for a wide range of users. The alehouse was the traditional village drinking house; it had none of the accommodation or the formal entertainment patterns of the inn. It was effectively the local community drinking and meeting place and was

From the cost analysis of the data communication service, the tariff models of the service are studied. On the basis of user classification for the service, the methods of cost share to different kinds of user and the models of the cost calculation according to the number of users and the interface are presented. The charge level of this service and the models of tariff structure are proposed. The reasonable profit ratio of the service has been discussed.

This paper introduces a new web application specification based on G-DEVS MS which supplies website metric analyses to the user, i.e. an informetric characterization with a topologic visualization and also an interactive manipulation of graphs. The tool provides different indicators of consistency of the web site with regards to customizable parameters.The scope of this study aims to improve the quality and attractiveness of public (government offices) and university web portals.There are some technical constraints, i.e. the bandwidth range and DNS (Domain Name Server) definitions; which are also taken into account. This tool has been designed for different kind of users that may range from webmasters through global editing policy deciders.G-DEVS models allow us to specify, test configuration by simulation, test integration of heterogeneous components using G-DEVS/HLA interoperability and thus make the implementation easier and safer, especially when we will save time by avoiding some implementation failures.

This paper presents ASTIS, a framework for the design and generation of adaptive spatio-temporal information systems for the historical study of natural hazard risks. ASTIS is based on a modular architecture in which every module can be personalized by the designer in order to meet the needs of different kinds of users. Personalizations are performed through a model-driven approach, each module is generated from specific models, conceived by the designer. A data management module allows personalizing the content of the application via data viewpoint mechanisms. A presentation module allows designing personalized interactive visualizations. Finally, an adaptation module is in charge of performing the appropriate personalizations at runtime, in order to adapt both the content and the presentation of the information to the user characteristics.

In recent years there has been a growing need to design way-finding systems and communication more effectively, as we realize the great importance they have in everyday people’s life, becoming necessary and operative guidelines tools for improving the quality of life. Sometimes these tools are used as simple signposting or mere decorations designed to embellish a specific space, as happens in place dedicated to children. Instead they are very important and strategic instruments able to improve the liveability and usability of specific environment by different kind of users. Among these ones, the children are very particular, because they feel, think and behave in a very different way beside the adults.

With the expansion of the cloud computing usage over a wide range of areas and different kinds of users, the cloud providers are taking full advantage of all their resources as much as they can. Memory is the most expensive resource in terms of oversubscribing and this has resulted in high price to the end user. Furthermore, performing swapping in Virtual Machines (VM) is expensive, so the cloud provider usually do not offer any swapping space for its systems. As a consequence, when a VM runs out of memory, user processes are killed. This scenario in the cloud environment is especially critical, since the user loses all of his/her execution time and, by extension, the money invested in this computation. This paper addresses this critical problem by providing a kernel extension that monitors the memory requirements of a VM and prevents the out of memory state by creating swapping space dynamically. The paper describes the design and implementation of a preliminary prototype of this kernel extensions and evaluates its performance.

During the last decades a strong attention to the issues of human diversity, social inclusion and equality has developed in different fields and in the nautical one. This has allowed more and more users to approach the world of pleasure boating, including people with disability. Accordingly, several small motor boats are designed or adapted for different kinds of users. This state-of-art represents a breeding ground to employ Design for Inclusion approaches in this field. The research’s aim here described is to define DfA-based guidelines for small motor boats, in particular. To obtain this result, the study has been conducted throughout different phases. During the early stages, different case studies have been selected, filed and analysed to comprehend what their strength and lacks about accessibility and ergonomic matter are. During the last stages, starting from this critical perspective, we have drawn up design guidelines based on the principles of “DfA Italia” for small motor boats.