User authentication on mobile devices with dynamical selection of biometric techniques for optimal performance

Author(s):  
Xiaobu Yuan ◽  
Md. Saifur Rahim
Author(s):  
Weixiang Xu ◽  
Xiangyu He ◽  
Tianli Zhao ◽  
Qinghao Hu ◽  
Peisong Wang ◽  
...  

Large neural networks are difficult to deploy on mobile devices because of intensive computation and storage. To alleviate it, we study ternarization, a balance between efficiency and accuracy that quantizes both weights and activations into ternary values. In previous ternarized neural networks, a hard threshold Δ is introduced to determine quantization intervals. Although the selection of Δ greatly affects the training results, previous works estimate Δ via an approximation or treat it as a hyper-parameter, which is suboptimal. In this paper, we present the Soft Threshold Ternary Networks (STTN), which enables the model to automatically determine quantization intervals instead of depending on a hard threshold. Concretely, we replace the original ternary kernel with the addition of two binary kernels at training time, where ternary values are determined by the combination of two corresponding binary values. At inference time, we add up the two binary kernels to obtain a single ternary kernel. Our method dramatically outperforms current state-of-the-arts, lowering the performance gap between full-precision networks and extreme low bit networks. Experiments on ImageNet with AlexNet (Top-1 55.6%), ResNet-18 (Top-1 66.2%) achieves new state-of-the-art.


2020 ◽  
Vol 17 (3) ◽  
pp. 67-78
Author(s):  
O. V. Manzhula

The article considers the issues of using new information and communication technologies (ICTs) when conducting the Russian Census related to the introduction of mobile devices and the Internet, which provide new opportunities for improving the quality and timeliness of the collecting and primary processing of statistical information about the population.In 2010, the Russian Census was conducted in the Russian Federation, which had many differences from previous censuses. All the technological stages of Russian Census – 2010 were automated starting from the development of machine-readable forms of census questionnaires and up to the preparation of publications of its outcomes.In the course of the trial population census held in 2018, ROSSTAT first combined the use of the Internet and mobile devices for collecting the information about the population. So, from October 1 to October 10, 2018 an online census was conducted for the whole country. Then, from October 11 to October 14, 2018 the information collected during the online census was processed, from October 15 to October 31, 2018, a survey was conducted by census takers in the regions of the trial population census – 2018 with the use of tablets and machine-readable documents. However, as the experience of the trial population census – 2018 demonstrated, one method of collecting information about the population cannot be equally efficient in all regions of Russia, due to the different attitude of the population to the methods of collecting information, as well as the conditions for the availability of information and communication technologies (ICTs) to the population in each region.The experience gained indicates the need for each region to choose the method of collecting and primary processing of statistical information about the population for each region based on a combination of Internet, mobile and traditional technologies that is adaptive to the regional conditions of the population census (remoteness and inaccessibility of some regions, the unreadiness of individual segments of the population to use modern ICTs for collecting information, Internet accessibility in various regions, different attitude of the population to census methods). The solution of this problem is an important condition for increasing the coverage of the population, the accuracy and reliability of the results and reducing the cost of conducting a census in each subject of Russia.The use of new information and communication technologies related to introduction of mobile devices and the Internet opens up new opportunities for improving the quality and timeliness of the collection and primary processing of statistical information about the population. However, with the development of census technologies, the number of alternative options for organizing it is growing. All this makes it necessary to justify the selection of a rational method of collecting and primary processing of statistical information about the population based on the regional characteristics of the development and accessibility of ICT, the consent of the population to interact with public authorities through the Public Services Portal, availability of ICTs in households. The validity of this choice is associated with the use of methods and decision-making models that are adequate to the peculiarities of the task.Purpose. Development of models for the selection of the rational method of collecting and primary processing of information of the Russian Census for each region of Russia using mobile devices and Internet technologies that correspond to the existing technological environment and the specificities of organizing Russian Census processes.Materials and methods. In the process of performing the preset tasks, methods of system and statistical analysis, expert assessment and systems, the fuzzy-set theory and cluster analysis were used. Calculations were carried out using MS Excel application software packages and IBM SPSS STATISTICS statistical software package.Results. The scientific article describes the developed expert system and models for substantiating a rational method of collecting and processing primary information in each Russian region based on their clustering according to the features characterizing the level of ICT development and their accessibility to the population in each region, the population's consent to cooperate with governmental authorities through the Public Services Portal, accessibility of ICT use in households and identifying the compliance of possibilities provided by alternative methods of collecting and processing the information on the population to the characteristics of readiness of the population, census personnel and territorial state statistics agency for conducting a census using modern ICTs and the limitations on the cost of conducting Russian Census in each region.Conclusion. The paper discusses the methodology that allows for the implementation of basic concept of the Russian Census, which is to ensure maximum coverage of the population while making informed management decisions on the choice of methods for collecting and primary processing of Russian Census information in each region of Russia, taking into account regional characteristics of the development and accessibility of ICTs, the consent of the population to interaction with public authorities through the Public Services Portal, access to ICTs in households.


2017 ◽  
Vol 90 (8-9) ◽  
pp. 1179-1190 ◽  
Author(s):  
Wenting Li ◽  
Yaosheng Shen ◽  
Ping Wang

Information ◽  
2020 ◽  
Vol 11 (4) ◽  
pp. 220 ◽  
Author(s):  
Witold Chmielarz

The main objective of this article was to identify the conditions for the use of smartphones and mobile applications in Poland in the second half of 2018. The scope of the present analysis was limited to a selected sample of more than 470 respondents, and it examined the group of the most active users of smartphones and mobile applications. The author adopted the CAWI (computer associated web interview) method, which was previously verified by a randomly selected pilot sample, in his study. The obtained results were compared with the findings of other studies. They indicated that users of smartphones and mobile applications in Poland do not differ in their assessments from users in Europe and around the world. In this context, the key implication for researchers is the identified level of development of the use of smartphones and mobile applications in Poland at the end of 2018. The main limitation of the research was the selection of the research sample, which consisted only of members of the academic community. The scope of this article aimed to fill a gap in terms of the quantitative and qualitative methods that are applied to examine the use of mobile devices and mobile software. At the same time, this study creates the foundations for further research on intercultural differences. It is important to note that the present research sample needs to be extended beyond the academic community for the research results to be fully generalized.


2020 ◽  
Vol 170 ◽  
pp. 107118 ◽  
Author(s):  
Chen Wang ◽  
Yan Wang ◽  
Yingying Chen ◽  
Hongbo Liu ◽  
Jian Liu

Sign in / Sign up

Export Citation Format

Share Document