Pedometer-free Geomagnetic Fingerprinting with Casual Walking Speed

The geomagnetic field has been wildly advocated as an effective signal for fingerprint-based indoor localization due to its omnipresence and local distinctive features. Prior survey-based approaches to collect magnetic fingerprints often required surveyors to walk at constant speeds or rely on a meticulously calibrated pedometer (step counter) or manual training. This is inconvenient, error-prone, and not highly deployable in practice. To overcome that, we propose Maficon, a novel and efficient pedometer-free approach for geo ma gnetic fi ngerprint database con struction. In Maficon, a surveyor simply walks at casual (arbitrary) speed along the survey path to collect geomagnetic signals. By correlating the features of geomagnetic signals and accelerometer readings (user motions), Maficon adopts a self-learning approach and formulates a quadratic programming to accurately estimate the walking speed in each signal segment and label these segments with their physical locations. To the best of our knowledge, Maficon is the first piece of work on pedometer-free magnetic fingerprinting with casual walking speed. Extensive experiments show that Maficon significantly reduces walking speed estimation error (by more than 20%) and hence fingerprint error (by 35% in general) as compared with traditional and state-of-the-art schemes.

Cervical Cytology–Histology Correlation Based on the American Society of Cytopathology Guideline (2017) at the Russian National Medical Research Center for Obstetrics, Gynecology, and Perinatology

Recent evidence suggests that a cytology–histology correlation (CHC) with discrepancy detection can both evaluate errors and improve the sensitivity and specificity of the cytologic method. We aimed to analyze the errors in cytologic–histologic discrepancies according to the CHC protocol guideline of the American Society of Cytopathology (2017). This retrospective study included 273 patients seen at the National Medical Research Center of Obstetrics, Gynecology and Perinatology (Moscow, Russia) between January 2019 and September 2021. The patients’ mean age was 34 ± 8.1 years. The cytology–histology agreement was noted in 158 cases (57.9%). Major discrepancies were found in 21 cases (7.6%), while minor discrepancies were noted in 93 cases (34.1%). The reason for 13 (4.8%) discrepancies was a colposcopy sampling error and, in 46 (16.8%) cases, the reason was a Papanicolaou (PAP) test sampling error. The discrepancy between primary and reviewed cytology was due interpretive errors in 13 (4.8%) cases and screening errors in 42 (15.4%) cases. We demonstrated that the ASC guidelines facilitate cervical CHC. A uniform application of these guidelines would standardize cervical CHCs internationally, provide a scope for the inter-laboratory comparison of data, and enhance self-learning and peer learning.

A Computer Vision Sensor for AI Accelerated Detection and Tracking of Occluded Objects

A prominent problem in computer vision is occlusion, which occurs when an object’s key features temporarily disappear behind another crossing body, causing the computer to struggle with image detection. While the human brain is capable of compensating for the invisible parts of the blocked object, computers lack such scene interpretation skills. Cloud computing using convolutional neural networks is typically the method of choice for handling such a scenario. However, for mobile applications where energy consumption and computational costs are critical, cloud computing should be minimized. In this regard, we propose a computer vision sensor capable of efficiently detecting and tracking covered objects without heavy reliance on occlusion handling software. Our edge-computing sensor accomplishes this task by self-learning the object prior to the moment of occlusion and uses this information to “reconstruct” the blocked invisible features. Furthermore, the sensor is capable of tracking a moving object by predicting the path it will most likely take while travelling out of sight behind an obstructing body. Finally, sensor operation is demonstrated by exposing the device to various simulated occlusion events. Keywords: Computer vision, occlusion handling, edge computing, object tracking, dye sensitized solar cell. Corresponding author Email: [email protected]

Addressing big data variety using an automated approach for data characterization

The creation of new knowledge from manipulating and analysing existing knowledge is one of the primary objectives of any cognitive system. Most of the effort on Big Data research has been focussed upon Volume and Velocity, while Variety, “the ugly duckling” of Big Data, is often neglected and difficult to solve. A principal challenge with Variety is being able to understand and comprehend the data. This paper proposes and evaluates an automated approach for metadata identification and enrichment in describing Big Data. The paper focuses on the use of self-learning systems that will enable automatic compliance of data against regulatory requirements along with the capability of generating valuable and readily usable metadata towards data classification. Two experiments towards data confidentiality and data identification were conducted in evaluating the feasibility of the approach. The focus of the experiments was to confirm that repetitive manual tasks can be automated, thus reducing the focus of a Data Scientist on data identification and thereby providing more focus towards the extraction and analysis of the data itself. The origin of the datasets used were Private/Business and Public/Governmental and exhibited diverse characteristics in relation to the number of files and size of the files. The experimental work confirmed that: (a) the use of algorithmic techniques attributed to the substantial decrease in false positives regarding the identification of confidential information; (b) evidence that the use of a fraction of a data set along with statistical analysis and supervised learning is sufficient in identifying the structure of information within it. With this approach, the issues of understanding the nature of data can be mitigated, enabling a greater focus on meaningful interpretation of the heterogeneous data.

Neuroevolutionary reinforcing learning of neural networks

The article presents the results of combining 4 different types of neural network learning: evolutionary, reinforcing, deep and extrapolating. The last two are used as the primary method for reducing the dimension of the input signal of the system and simplifying the process of its training in terms of computational complexity.In the presented work, the neural network structure of the control device of the modeled system is formed in the course of the evolutionary process, taking into account the currently known structural and developmental features of self-learning systems that take place in living nature. This method of constructing it makes it possible to bypass the specific limitations of models created on the basis of recombination of already known topologies of neural networks.

The Student Experiences of Teaching and Learning in Transnational Higher Education: A Phenomenographic Study from a British-Qatari Partnership

Transnational higher education (TNHE) of UK universities has been noticeably expanding during the last two decades in the Arab Gulf region, but few studies investigated qualitatively the different ways in which students in that region experience both teaching and learning. The aim of this study is to understand the ways that students conceptualise their learning and educational experiences at a British TNHE in Qatar. Employing a phenomenographic approach, we interviewed forty students in a TNHE UK programme within a Qatari higher education institution (HEI). The outcomes of our interviews generated three hierarchically related categories as follows: developing academic skills, acquiring self-learning skills, and acquiring employability skills. Our findings also suggest themes of interdependence in learning and transferability of skills developed by students. This study offers HEIs a better understanding and insight into the design of TNHE programmes that would respond to the students’ learning experiences and educational development.

Blended Learning: Past and Present with Special Reference to COVID-19 Pandemic

The Clayton Christensen academy describes blended learning as a structured educational program in which a student learns at least in part into internet-based content delivery and training with some characteristic of academic supervision from home. This process involved time, place, pattern, and careful monitoring facilities. It also encouraged the learners to feel more optimistic regarding their studies. The fundamental concept of driving blended learning is that it encourages a combination of self-learning and collective communication-oriented practices. However, during COVID-19 besides virtual and non-formal institutions, the formal educational institutes also moved to blended learning. As this was a new practice for the formal instructors and learners, therefore, this study was carried out for discovering the concept of blended learning with special reference to COVID-19 pandemic and for this reason three sub purposes were; shed light on the concept of blended learning; to describe terminologies used for blended learning in the past and present with special reference to COVID-19 pandemic and to discover blended learning strategies in the past and presnt with special reference to COVID-19. This study chartered a qualitative method with succeeding in the analysis of documents related to blended learning and how this strategy was used during COVID -19 for engaging the formal instructors with their students. The Study followed the five years documents available online since 2011-20. But some documents from 2021 were also viewed for methodology.The researchers’ inquiry into 10 years of data was for the purpose to discover the past strategies of blended learning in comparison to the strategies used during COVID-19. Data were analyzed through emerging themes from the documents. Therefore, the main themes aided to interpret the results. The results exposed dissimilar terms for blended learning such as F2F, hybrid, and the online teaching-learning process.The strategies used during COVID-19 were more advanced as compared to the past years. Traditional methods of blended learning included online sessions and face-to-face classes. Microsoft, Webinar, TREAD, zoom, and Google Classroom, and other applications have been commonly used throughout the COVID-19 affected countries. The formal institutions for the teaching-learning process to carry out in COVID-19 period frequently practiced some new strategies.