Hasil untuk "Cybernetics"

Pablo Guillén, Enrique Frias-Martinez

Alzheimer’s disease (AD) is a neurodegenerative disorder characterized by memory loss. While applying Machine Learning (ML) demands a certain level of expertise, which is often a barrier for healthcare professionals, automated machine learning (AutoML) significantly lowers this barrier. This study analyzes an AutoML tool (PyCaret) for AD classification and prediction. Two experiments were designed to evaluate its diagnostic and prognostic capabilities with AD, Mild cognitive impairment (MCI), and Normal Controls (NC). SHapley Additive exPlanations (SHAP) was used to explain the ML models. For diagnosis, it had an accuracy of 98.6% for NC vs AD, 91.3%, for NC vs MCI, 92.5% for MCI vs AD, and 89.5% for the multiclass NC vs MCI vs AD. Regarding the prognosis capabilities, prediction of future cognitive states four years after their initial visit produced an accuracy of 92.8% for NC vs AD, 82.7% for NC vs MCI, 90.2% for MCI vs AD, and 81.4% for NC vs MCI vs AD. These results are in range and, in some cases, improve the state of the art even when compared to deep learning solutions. They confirm the potential of AutoML tools to automate ML algorithm selection and tuning for a specific medical application.

G.I. Greisukh, I.A. Levin, O.A. Zakharov

Using the example of the development of two simple dual-band monofocal IR objectives, approaches to the layout and design of their optical schemes are demonstrated, depending on whether compensation for the effects of temperature changes on the optical characteristics of these lenses is required or not. It is shown that in the case when thermal compensation is not required, superior optical characteristics can be achieved in a simple triplet, in which the flat surface of the frontal fractional lens carries a diffractive microstructure. In the case of passive athermalization, the optical scheme of the objective becomes more complicated and consists of refractive two-line power and correction components, in the latter of which the flat surface of one of the lenses carries a diffractive microstructure. Due to highly efficient diffractive microstructures, the longitudinal chromaticism of both objectives is reduced almost to the diffraction limit and, in combination with a low level of residual monochromatic aberrations at high light intensity, the maximum resolution is provided for uncooled microbolometers used as matrix receivers.

Timur Mamedov, Denis Kuplyakov, Anton Konushin

The idea of the person re-identification (Re-ID) task is to find the person depicted in the query image among other images obtained from different cameras. Algorithms solving this task have important practical applications, such as illegal action prevention and searching for missing persons through a smart city’s video surveillance. In most of the papers devoted to the problem under consideration, the authors propose complex algorithms to achieve a better quality of person Re-ID. Some of these methods cannot be used in practice due to technical limitations. In this paper, we propose several approaches that can be used in almost all popular modern re-identification algorithms to improve the quality of the problem being solved and do not practically increase the computational complexity of algorithms. In real-world data, bad images can be fed into the input of the Re-ID algorithm; therefore, the new Filter Module is proposed in this paper, designed to pre-filter input data before feeding the data to the main re-identification algorithm. The Filter Module improves the quality of the baseline by <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>2.6</mn><mo>%</mo></mrow></semantics></math></inline-formula> according to the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>R</mi><mi>a</mi><mi>n</mi><msub><mi>k</mi><mn>1</mn></msub></mrow></semantics></math></inline-formula> metric and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>3.4</mn><mo>%</mo></mrow></semantics></math></inline-formula> according to the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>m</mi><mi>A</mi><mi>P</mi></mrow></semantics></math></inline-formula> metric on the Market-1501 dataset. Furthermore, in this paper, a fully automated data collection strategy from surveillance cameras for self-supervised pre-training is proposed in order to increase the generality of neural networks on real-world data. The use of self-supervised pre-training on the data collected using the proposed strategy improves the quality of cross-domain upper-body Re-ID on the DukeMTMC-reID dataset by <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1.0</mn><mo>%</mo></mrow></semantics></math></inline-formula> according to the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>R</mi><mi>a</mi><mi>n</mi><msub><mi>k</mi><mn>1</mn></msub></mrow></semantics></math></inline-formula> and <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>m</mi><mi>A</mi><mi>P</mi></mrow></semantics></math></inline-formula> metrics.

Esmat Momeni

Purpose: Identifying, accessing, and evaluating course content, along with the skills of extracting, reasoning, and inferring, lead to the organization and presentation of materials in teaching. The purpose of the current research is to enhance the educational content of Bruner's curriculum by incorporating information literacy skills and critical thinking. Method: The current research is fundamental in terms of its purpose and has conducted using with the comparative qualitative content analysis method, with a directional approach. Research data has been collected in six stages through the study of library documents. The validity of the current research is based on content and reliability, utilizing library texts and documents. The reliability is ensured through a detailed description of steps and information analysis, as well as the principle of verifiability by maintaining documents related to different stages of the research. Finally, the principle of accuracy is intended to convey the research results accurately and in detail. Findings: The research findings indicated that the ability to identify information needs and analyze effectively empowers learners to respond to both typical and atypical questions within the content. The skill of obtaining the required information and the ability to infer encourage learners to engage critically with the content, prompting them to problematize and build upon previous concepts at the start of the lesson. The ability to critique and evaluate information sources, along with inferential reasoning skills, can transform content from simple to complex by presenting new concepts in a prominent and specific manner. The skill of optimal utilization of information sources and the ability of inductive reasoning are essential for learners to comprehend concepts by identifying similarities and differences, promoting practical guessing based on the content. The skill of complying with legal and ethical principles in information use, along with the skill of evaluation, fosters awareness in learners and lays the foundation for active participation, teamwork, self-direction, and independence. Conclusion: Learners in the process draw based on the fourteen cases of the educational from of curriculum, integrating the skills of information literacy and thinking. This integration helps them thinking, establish connections relationships information the information in their leading leads enhanced greater understanding, learning, learning the assimilation of new achieving content concepts. new. It is suggested to enhance the educational content of Bruner's curriculum by incorporating critical thinking skills and information literacy.

Szymon Muszynski, Zbigniew Tarapata

This paper describes methods and techniques of measuring similarity of musical pieces. This topic is crucial in plagiarism control and arrangement evaluation as these processes depend in particular on a previous experience and subjective aesthetical feelings of a researcher. Although there are some common frameworks for comparing musical pieces (i.e., some characteristics of compared pieces and details to consider), having a set of comprehensive metrics would allow to make such comparisons more unbiased. We show that such a comparison can be made using a network representation of a track. Tracks are compared using a structural and quantitative similarity between matrices corresponding to these musical pieces. In this article, we describe network representations of music. We introduce a set of specific methods of calculating this similarity and study their characteristics. We also evaluate them on the set of test pieces and provide results. We show that this method can be especially used for detecting instances of plagiarism between pieces and evaluating similarity of created arrangements, thus measuring their “innovativeness”.

M.G. Tokmachev

The paper proposes an algorithm for processing a photo of a granule in order to determine its volume. Factors that influence the result of automatic data processing in the optical micrometry method are investigated. It is shown that by estimating the outline of an ellipse-shaped granule, the algorithm determines its volume with a relative error of 0.4 %, which corresponds to an error in determining the granule diameter of 1 pixel.

Daniela D'Auria, Vincenzo Moscato, Marco Postiglione et al.

The ever-increasing availability of Electronic Health Records (EHRs) is the key enabling factor of precision medicine, which aims to provide therapies and diagnoses based not only on medical literature, but also on clinical experience and individual information of patients (e.g. genomics, lifestyle, health history). The unstructured nature of EHRs has posed several challenges on their effective analysis, and heterogeneous graphs are the most suitable solution to handle the heterogeneity of information contained in EHRs. However, while EHRs are an extremely valuable data source, information from current medical literature has yet to be considered in clinical decision support systems. In this work, we build an heterogeneous graph from Italian EHRs provided by the Hospital of Naples Federico II, and we define a methodological workflow allowing us to predict the presence of a link between patients and diagnosed diseases. We empirically demonstrate that linking concepts to biomedical ontologies (e.g. UMLS, DBpedia) — which allow us to extract entities and relationships from medical literature — is significantly beneficial to our link-prediction workflow in terms of Area Under the ROC curve (AUC) and Mean Reciprocal Rank (MRR).

Dan Liu, Xiaoming Liu, Zhuo Chen et al.

Remotely controlled soft continuum robots with active steering capability have broad prospects in medical applications. However, conventional continuum robots have the miniaturization challenge. This paper presents a microscale soft continuum microrobot with steering and locomotion capabilities based on magnetic field actuation. The magnetically driven soft continuum microrobot is made of NdFeB particles and polydimethylsiloxane (PDMS), and it can be as small as 200 μm in diameter. Moreover, a hydrogel layer is covered on the surface of the microrobot, which not only overcomes the adhesion force between the microobjects and the soft tip but also reduces the friction between the microrobot and substrate. The performance test indicates the soft continuum microrobot featured excellent control and steering capabilities. The experimental results demonstrate that the soft continuum microrobot can travel through the microfluidic channel by its own vibration and flexibly steer in a bifurcation environment. Moreover, the micromanipulation of microbeads in the microfluidic channels proves that the proposed microscale soft continuum microrobot has a great potential for intravascular manipulation.

Shweta Chauhan, Philemon Daniel, Shefali Saxena et al.

Learning machine translation by using only monolingual data sets is a complex task as there are many possible ways to connect or associate target sentences with source sentences. The monolingual word embeddings are linearly mapped on a common shared space through robust learning or adversarial training in an unsupervised way, but these learning techniques have fundamental limitations in translating sentences. In this paper, a simple yet effective method has been proposed for fully unsupervised machine translation that is based on cross-lingual sense to word embedding instead of cross-lingual word embedding and language model. We have utilized word sense disambiguation to incorporate the source language context in order to select the sense of a word more appropriately. A language model for considering target language context in lexical choices and denoising autoencoder for language insertion, deletion, and reordering are integrated. The proposed approach eliminates the problem of noisy target language context due to erroneous word translations. This work takes into account the challenge of homonyms and polysemous words in the case of morphologically rich languages. The experiments performed on English-Hindi and Hindi-English using different evaluation metrics show an improvement of +3 points in BLEU and METEOR-Hindi over the baseline system.

Dr. Saeid Safdari (Iran)

SUBJECT AND OBJECTIVES: The pervasive phenomenon of the Islamic uprising has taken the West by surprise, and for this reason, with the available tools, it analyzed it to discover the strengths and weaknesses of the problem, and to be able to face such an analysis; but on the other hand, the religion of Islam is a religion of development and  it calls for all kinds of knowledge and asks the Muslim ummah to improve the elements of power in  their soul and try to be the best ummah and to be the pioneer of the people of the world.METHOD AND FINDING: The religion of Islam in the West and the interaction way Western societies and governments and their interaction with Muslim minorities in those countries is a topic that has been the focus of analysts and culturologists for nearly two decades in scientific, academic, and media circles in Europe and the United States. Meanwhile, it seems that different attitudes and schools of thought towards Islam and Muslims living in Europe and America are far from the objective and practical situation of social movements of minorities and Islamic currents in these areas, in other words, due to the existence of different views and approaches on how to interact with these religious minorities, Islamic currents in the West find themselves in deep identity straits.CONCLUSION: The present study sought to explain the concept of Islamophobia and Islamism in the West, which was used to explain this meaning and concept.

Hirotoshi Hishida, Riku Kasahara, Keiko Hishida et al.

It is widely known that music affects physical and mental condition, and attempts to prescribe music instead of medicine are being made in various places. However, there are large individual differences in effects of music. Authors consider that general prescription method has not been established yet. In the present study, a music therapy experiment was conducted at an actual concert held in public. It was a piano recital commemorating the 250th anniversary of Beethoven's birth, and all the pieces played were Beethoven's. Twenty-eight subjects was women and men, aged 19 to 68. They were classified into four groups according to whether they liked classical music and whether they knew the pieces to be performed. Their blood pressure, pulse wave, cardiac orientation, hand sweat, salivary amylase, and muscle hardness were measured. Results suggested that Beethoven's piano pieces generally provide a relaxing effect on the listeners. In this paper, the experimental results are discussed, which is mainly on the pulse wave measurement conducted on four subjects, on the blood pressure, and on the directivity of the mind conducted on all subjects. Furthermore, it turned out that the method needed to be improved when experiments were conducted at an actual concert.

article editorial

.

Muhammad Uzar Ali, Bhupesh Kumar Mishra, Dhavalkumar Thakker et al.

A key aspect of the development of Smart Cities involves the efficient and effective management of resources to improve liveability. Achieving this requires large volumes of sensors strategically deployed across urban areas. In many cases, however, it is not feasible to install devices in remote and inaccessible areas, resulting in incomplete data coverage. In such situations, citizens can often play a crucial role in filling this data collection gap. A popular complimentary science to traditional sensor-based data collection is to design Citizen Science (CS) activities in collaboration with citizens and local communities. Such activities are also designed with a feedback loop where the Citizens benefit from their participation by gaining a greater sense of awareness of their local issues while also influencing how the activities can align best with their local contexts. The participation and engagement of citizens are vital and yet often a real challenge in ensuring the long-term continuity of CS projects. In this paper, we explore engagement factors, factors that help keeping engagement high, in technology-centric CS projects where technology is a key enabler to support CS activities. We outline a literature review of exploring and understanding various motivational and engagement factors that influence the participation of citizens in technology-driven CS activities. Based on this literature, we present a mobile-based flood monitoring citizen science application aimed at supporting data collection activities in a real-world CS project as part of an EU project. We discuss the results of a user evaluation of this app, and finally discuss our findings within the context of citizens’ engagement.

G. Allaire, Frédéric de Gournay, F. Jouve et al.

Vasily Vartanyan, Daria Shteinbrekher

There are a large number of modern approaches to the development and implementation of organizational knowledge management systems, methodologies and models of knowledge management. Each of them has its own peculiarities, advantages, and disadvantages, aimed at supporting the knowledge saving process. At the same time, the question of the knowledge system effectiveness remains unclear, what complicates the decision-making process. The article analyzes modern approaches to assessing the effectiveness of the knowledge management system and the feasibility of its implementation in the project environment. The approaches analyzed, such as Kaplan-Norton's Balanced Scorecard (Kaplan-Norton), Non-material Asset Monitor (K.Sweeb), Skandia Navigator (Edvinsson), etc., can be used as macro indicators to determine the benefits of Knowledge Management System, but these indicators cannot reflect actual benefits gained solely by this system in relation to business processes and organizational project objectives. Thus, the actual scientific task is not only to develop a specific method of quantifying the benefits that the Knowledge Management System provides, but also to create indicators for project implementation evaluation through Knowledge Management System efficiency. The paper objective is to develop a comprehensive method for evaluation of the effectiveness of the Knowledge Management System, taking into account the specifics of project management. The proposed model is a multi-stage process, which allows increasing the reliability of the final decisions on knowledge management in the project and evaluating the profitability of the system. In addition, the model allows reducing the cost of the project, by simulating the influence of the system elements on project parameters. The proposed model is aimed at optimization (the choice of the best algorithm from several), identification (the definition of a system with the most relevant qualifications to the real object in the given conditions) or decision-making on Knowledge Management System in a project environment.  Further research will be aimed at the development of automated tools for implementing the model, which will optimize the use of the model in project-oriented organizations.

Nataliia Bilan

In the article the current state of foreign linguistic preparation of future power-engineering specialists in technical institutions of higher education is investigated and analysed. On the basis of the theoretical review of scientific and pedagogical literature it is presented the positions of researchers and the personal treatment of the designated process are offered. Foreign linguistic preparation is an inseparable component of purposeful process of vocational training of undergraduates of power specialties which is directed to the achievement of the educational, developing, educator, world outlook, professional purpose, and is characterized by acquisition of foreign-language and background knowledge, accompanies formation of practical abilities and skills, foreign-language competence and professional and personal qualities of future power engineering specialists. On the basis of experimental work results, it is defined and proved forms of the organization and implementation of foreign-language training of undergraduates in technical institutions of higher education which provide attending of the combined classes in the scientific discipline «Business English», language courses, membership in scientific circles, participation in student’s conferences, creative competitions, passing of educational practices and internship abroad. Taking into account such criteria as the organization of educational process, material and technical resources, educational and methodical providing, the contingent of students, the international activity, - the condition of foreign-language training of undergraduates of power specialties in technical institutions of the higher education is estimated by a five-point system. It is determined that foreign-language training of future power engineers is based on competent, personally focused, active, problematical and differentiated approaches realization of which is provided by the harmonious use of communicative, situational and group methods of training with innovative pedagogical technologies. On the basis of observation and poll the positive attitude and the considerable interest of undergraduates of power specialties in a learning of foreign languages and also difficulty which arise in the course of foreign-language preparation is revealed and proved ways of their overcoming. Behind the results of an empirical research, levels of formation of foreign-language competence of future power engineers are determined and their ranging behind receptive and productive types of colloquial activity is carried out. On the example of the theme «Official Journey to Germany», it is proved possibilities of complex development and improvement of skills of audition, reading, oral and written language of student’s power engineering specialists. The reasons of mediocre level of competence in foreign languages by future power engineers are defined and the elimination of which will allow to avoid shortcomings of the organization and fulfilment of foreign language training of future power-engineers in the higher education establishments.

Zongzhao Zhou, Y. Ong, P. Nair et al.

Yuanguo Zhu

Shervan Fekri-Ershad, Farshad Tajeripour

Visual quality inspection systems play an important role in many industrial applications. In this respect, surface defect detection is one of the problems that have received much attention by image processing scientists. Until now, different methods have been proposed based on texture analysis. An operation that provides discriminate features for texture analysis is local binary patterns (LBP). LBP was first introduced for gray-level images that makes it useless for colorful samples. Sensitivity to noise is another limitation of LBP. In this article, a new noise-resistant and multi-resolution version of LBP is used that extracts color and texture features jointly. Then, a robust algorithm is proposed for detecting abnormalities in surfaces. It includes two steps. First, new version of LBP is applied on full defect-less surface images, and the basic feature vector is calculated. Then, by image windowing and computing the non-similarity amount between windows and basic vector, a threshold is computed. In test phase, defect parts are detected on test samples using the tuned threshold. High detection rate, low computational complexity, low noise sensitivity, and rotation invariant are some advantages of our proposed approach.

Hermann Schmidt, German ’proto-cybernetics