Search

Objective The purpose of this study was to develop a natural language processing (NLP) pipeline to identify incidental thyroid nodules (ITNs) meeting criteria for sonographic follow-up and to assess both adherence rates to white paper recommendations and downstream outcomes related to these incidental findings. Methods 21583 non-contrast chest CT reports from 2017 and 2018 were retrospectively evaluated to identify reports which included either an explicit recommendation for thyroid ultrasound, a description of a nodule ≥ 1.5 cm, or description of a nodule with suspicious features. Reports from 2018 were used to train an NLP algorithm called fastText for automated identification of such reports. Algorithm performance was then evaluated on the 2017 reports. Next, any patient from 2017 with a report meeting criteria for ultrasound follow-up was further evaluated with manual chart review to determine follow-up adherence rates and nodule-related outcomes. Results NLP identified reports with ITNs meeting criteria for sonographic follow-up with an accuracy of 96.5% (95% CI 96.2-96.7) and sensitivity of 92.1% (95% CI 89.8-94.3). In 10006 chest CTs from 2017, ITN follow-up ultrasound was indicated according to white paper criteria in 81 patients (0.8%), explicitly recommended in 46.9% (38/81) of patients, and obtained in less than half of patients in which it was appropriately recommended (17/35, 48.6%). Discussion NLP accurately identified chest CT reports meeting criteria for ITN ultrasound follow-up. Radiologist adherence to white paper guidelines and subsequent referrer adherence to radiologist recommendations showed room for improvement.

Clear legal content of white papers provides certainty, stability and trust in the relations between all the participants in initial coins offering (ICO) procedures and contributes to the successfu...

In this paper, the implementation of artificial neural networks (multilayer perceptron [MLP] and radial base functions [RBF]) and the upgraded Markov chain model have been studied and performed to identify the human behavior patterns during rock, paper, and scissors game. The main motivation of this research is the design and construction of an intelligent robot with the ability to defeat a human opponent. MATLAB software has been used to implement intelligent algorithms. After implementing the algorithms, their effectiveness in detecting human behavior pattern has been investigated. To ensure the ideal performance of the implemented model, each player played with the desired algorithms in three different stages. The results showed that the percentage of winning computer with MLP and RBF neural networks and upgraded Markov model, on average in men and women is 59%, 76.66%, and 75%, respectively. Obtained results clearly indicate a very good performance of the RBF neural network and the upgraded Markov model in the mental modeling of the human opponent in the game of rock, paper, and scissors. In the end, the designed game has been employed in both hardware and software which include the Zana intelligent robot and a digital version with a graphical user interface design on the stand. To the best knowledge of the authors, the precision of novel presented method for determining human behavior patterns was the highest precision among all of the previous studies.

In this paper, we present a system for automatic evaluation of the quality of a question paper. Question paper plays a major role in educational assessment. The quality of a question paper is crucial to fulfilling the purpose of the assessment. In many education sectors, question papers are prepared manually. A prior analysis of a question paper might help in finding the errors in the question paper, and better achieving the goals of the assessment. In this experiment, we focus on higher education in the technical domain. First, we conducted a student survey to identify the key factors that affect the quality of a question paper. The top factors we identified are question relevance, question difficulty, and time requirement. We explored the strategies to handle these factors and implemented them. We employ various concepts and techniques for the implementation. The system finally assigns a numerical quality score against these factors. The system is evaluated using a set of question papers collected from various sources. The experimental results show that the proposed system is quite promising.

Paper-based microfluidic devices are popular for their ability to automate multistep assays for chemical or biological sensing at a low cost, but the design of paper microfluidic networks has largely relied on experimental trial and error. A few mathematical models of flow through paper microfluidic devices have been developed and have succeeded in explaining experimental flow behavior. However, the reverse engineering problem of designing complex paper networks guided by appropriate mathematical models is largely unsolved. In this article, we demonstrate that a two-dimensional paper network (2DPN) designed to sequentially deliver three fluids to a test zone on the device can be computationally designed and experimentally implemented without experimental trial and error. This was accomplished by three new developments in modeling flow through paper networks: (i) coupling of the Richards equation of flow through porous media to the species transport equation, (ii) modeling flow through assemblies of multiple paper materials (test membrane and wicking pad), and (iii) incorporating limited-volume fluid sources. We demonstrate the application of this model in the optimal design of a paper-based signal-enhanced immunoassay for a malaria protein, PfHRP2. This work lays the foundation for the development of a computational design toolbox to aid in the design of paper microfluidic networks. ©

Introduction: Water is essential for normal functioning of the human body. Total fluid intake assessment using fluid record method is considered to be a burden for respondents, and the development of technology is expected to contribute favourably to this issue. My Fluid Diary is a smartphone-based application developed by the researcher as a fluid intake recording tool. This study aimed to evaluate the acceptance of manual, paper-based fluid intake recording compared to using My Fluid Diary as a trial among Indonesian vocational female students. Methods: A qualitative study was conducted to explore students’ acceptance of fluid intake recording using the smartphone-based application. An exploratory case study approach involving 38 female students as key informants was used via focus group discussion and in-depth interview as a method of triangulation. Results: Based on the data, female adolescents admitted that the application was more acceptable for fluid intake than recording manually using a book, in consideration of three aspects - the benefits, the easiness, and the application display or features. Based on its benefits, My Fluid Diary was mentioned as easy to learn and use. However, in order to improve the application, there is still a need for research development. Conclusion: My Fluid Diary was an application with respectable acceptance for fluid record compared to the manual, paper-based method among female adolescents.

PurposeSynergy indicators and social network analysis (SNA), as practical tools, provide the possibility of explaining the pattern of scientific collaboration and visualization of network relations. Recognition of scientific capacities is the basis of synergy. The present study aims to measure and discover the synergistic networks of COVID-19’s top papers at the level of co-authorship, countries, journals, bibliographic couples and titles.Design/methodology/approachThe synergy indicator, co-authorship co-citation network analysis methods were applied. The research population comprises COVID-19’s top papers indexed in Essential Science Indicator and Web of Science Core Collection 2020 and 2021. Excel 2016, UCINET 6.528.0.0 2017, NetDraw, Ravar Matrix, VOSviewer version 1.6.14 and Python 3.9.5 were applied to analyze the data and visualize the networks.FindingsThe findings indicate that considering the three possible possibilities for authors, countries and journals, more redundancy and information are created and potential for further cooperation is observed. The synergy of scientific collaboration has revealed that “Wang, Y,” “USA” and “Science of the Total Environment” have the most effective capabilities and results. “Guan (2020b)” and “Zhou (2020)” are bibliographic couplings that have received the most citations. The keywords “CORONAVIRUS DISEASE 2019 (COVID-19)” were the most frequent in article titles.Originality/valueIn a circumstance that the world is suffering from a COVID-19 pandemic and all scientists are conducting various researches to discover vaccines, medicines and new treatment methods, scientometric studies, and analysis of social networks of COVID-19 publications to be able to specify the synergy rate and the scientific collaboration networks, are not only innovative and original but also of great importance and priority; SNA tools along with the synergy indicator is capable of visualizing the complicated and multifaceted pattern of scientific collaboration in COVID-19. As a result, analyses can help identify existing capacities and define a new space for using COVID-19 researchers’ capabilities.

Headline generation is a challenging subtask of abstractive text summarization, which its output should be a summary, shorter than one sentence. It would be precious to develop a dataset for the evaluation of abstractive summarization methods on this task in the Persian language. There are several datasets for headline generation in Persian, most of which are not large enough to be used by more sophisticated methods of text summarization, such as deep learning models. Moreover, all of these datasets are focused on daily news and there is no dataset for summarizing scientific Persian papers. In this article, we present “ElmNet,” a headline generation dataset of about 400,000 abstract/headline pairs of scientific papers, gathered from six major publishers for scientific articles in Persian. We, moreover, evaluate the performance of the most important deep learning-based headline generation methods, on the proposed dataset. The results prove the comparability of the performance of the state-of-the-art methods on this task, to their results on the existing English datasets.

This study aimed to evaluate the effect of nanocellulose addition on the physical–mechanical properties of the paper produced from different fiber blends, besides comparing two nanocellulose addition methods. Three different fibers were used for fiber blending (eucalyptus, sisal, and pine). Handsheets were formed based on the mixing of all possible combinations at a 45/55 ratio in 2% consistency and 60 g/m2. Handsheet reinforcements were performed by two methods: The mixture method (MT) was a mixture of nanocellulose along with pulp during paper formation in 3, 5, and 10% addition; the coating method (CT) was the superficial coating of dry formed papers in 10% addition. Nanocellulose was produced by mechanical microfibrillation of sisal pulp. Handsheets were evaluated by physical and strength properties. Nanocellulose addition increased thickness, volume, grammage, apparent density, opacity, roughness, tensile strength, tensile index, stretch, bursting index, tear index, and fold endurance by 8.7, 8.8, 10.4, 2.1, 4.1, 23.2, 45.7, 31.8, 20.1, 14.2, 21.1, and 271.6% but reduced bulk, brightness, and air permeance by 1.9, 3.4, and 71.7%, respectively. The reinforcement methods presented distinct results. In physical properties, an increasing tendency toward nanocellulose (MT) increase was observed in thickness, grammage, and apparent density despite the decreasing trend in air permeance. No tendency was observed in other physical properties. In general, CT presented higher values of thickness, grammage, bulk, and brightness but lower values of apparent density and opacity, compared to MT. The mixture method showed an increasing tendency in strength properties with the increase of nanocellulose content. CT obtained fewer strength properties compared to MT.

Comparative studies on paper and pencil– and computer-based tests principally focus on statistical analysis of students’ performances. In educational assessment, comparing students’ performance (in terms of right or wrong results) does not imply a comparison of problem-solving processes followed by students. In this paper, we present a theoretical tool for task analysis that allows us to highlight how students’ problem-solving processes could change in switching from paper to computer format and how these changes could be affected by the use of one environment rather than another. In particular, the aim of our study lies in identifying a set of indexes to highlight possible consequences that specific changes in task formulation have, in terms of task comparability. Therefore, we propose an example of the use of the tool for comparing paper-based and computer-based tasks.

General diagnosis of poultry viruses primarily relies on detection of viruses in samples, but many farms are located in remote areas requiring logistic transportation. Filter paper cards are a usef...

Internet of Things (IoT) has drawn important attention in recent years since it has made revolutionary changes in human life. The IoT enables the exchange of information or data in a wide variety of applications such as smart buildings, smart health, smart transport, and so on. As billions of connected things communicate with each other and can interchange sensitive information that may be revealed. Hence, strengthening IoT’s security and preserving users’ privacy is a crucial challenge. The aim of this paper is to provide a comprehensive study of the IoT security. Several IoT security attacks are examined and a taxonomy of the security requirements based on the attacks purposes is proposed. Furthermore, recent security solutions are described and classified based on their application area. Ultimately, open research directions and security challenges are discussed.

Due to the growth of e-commerce, most of the banking transactions are made on the online platform and all these transactions are made on the websites provided by the merchant or the payable apps and because of this the vulnerability of attacks has increased and there are also chances of using fraudulent websites and apps by the attackers though there are many high-security algorithms are been used for safeguarding against vulnerabilities. The way of judging the relation of trust on the online platform has become a major issue, so a proper trust model also needs to be maintained. In this paper, we reviewed various security algorithms which involve cryptographic algorithms, machine learning, anonymization, and masking techniques, blockchain, distributed networks, and many more to provide integrity, privacy, reliability, authentication, security, and risk-less e-commerce platform.

The accuracy of a predictive system is critical for predictive maintenance and to support the right decisions at the right times. Statistical models, such as ARIMA and SARIMA, are unable to describe the stochastic nature of the data. Neural networks, such as long short-term memory (LSTM) and the gated recurrent unit (GRU), are good predictors for univariate and multivariate data. The present paper describes a case study where the performances of long short-term memory and gated recurrent units are compared, based on different hyperparameters. In general, gated recurrent units exhibit better performance, based on a case study on pulp paper presses. The final result demonstrates that, to maximize the equipment availability, gated recurrent units, as demonstrated in the paper, are the best options.

Cyber Forensics is termed as scientific methods or applications in association with the judiciary or court of laws. The aim behind these methods is to unveil the digital evidence to be utilized in court for solving crime cases. This sort of technology wasn’t practiced before therefore most criminals tend to urge away with their criminal acts without valid proof to incriminate or prosecute them. During that time the oaths, confessions, testimonies from witnesses were the sole determining factors of evidence Crimes committed within electronic or digital domains, particularly within cyberspace, have become common. Criminals are using technology to commit their offenses and make new challenges for law enforcement agents, attorneys, judges, military, and security professionals. Digital forensics has become a vital instrument in identifying and solving computer-based and computerassisted crime. This paper provides a quick introduction to cyber forensics. During this paper we present a typical model for both Incident Response and Computer Forensics processes which mixes their advantages in an exceedingly flexible way: It allows for a management oriented approach in digital investigations while retaining the chance of a rigorous forensics investigation. Keywords: cyber forensics, digital forensic science, computer forensics, evidence, judicial system.

Text summarization is one problem in natural language processing that generates a brief version of the original document. This research took attention for some researchers in this last decade and growing fast, including Indonesia language. This paper aims to recap summarization text research especially in Indonesia language. As usual, this paper discusses two summarization approaches, extractive and abstractive. In fact, the number of research of extractive is more than abstractive. This paper investigates some methods such as Statistical Based Approach, Graph Based Approach, Machine Learning Approach, Fuzzy Logic Approach, Algebraic Approach, and Hybrid Approach. This paper shows some methods details and summarize the results. Keywords— Text summarization, extractive summary, abstractive summary, natural language processing

Many Indonesian spelling errors occur in research papers published to the public, closely related to academics in all institutions such as research institutions, government, schools, and universities. The spelling errors usually writing punctuation, writing letters, writing words, writing words originating from foreign or regional languages (uptake words), using affixed words, and writing ineffective sentences. The mistakes made by the academics then become a cycle in the academic environment. They usually provide guidance for writing an undergraduate thesis, thesis, dissertations to students, or the other forms of documents and scientific papers. Therefore, the research proposed the application to facilitate all authors of scientific papers in producing quality scientific works based on the General Guidelines for Indonesian Spelling published by the Agency for Development and Language Development. The application is named KEBI 1.0 Checker (Indonesian Spelling Error 1.0 Checker), a web-based application with a built-in algorithm to detect and correct Indonesian Spelling in scientific papers. The experiment result shows that the application has given the best accuracy performance to correct the non-standard words, and typographical errors reached 100% and 55,52%, respectively. The application also has been detected 209 meaningless words. The application processing time is relatively low, the average time needed to correct non-standard words is 0.016 seconds, and typo words are 14.58 seconds. KEBI 1.0 Checker is helpful for the end-user in academics but needs to improve the vocabulary of the large corpus in various fields of science for correcting typo words.

The NIST selection process for standardizing Post-Quantum Cryptography Mechanisms is currently running. Many papers already studied their theoretical security, but the resistance in deployed device has not been much investigated so far. In particular, fault attack is a serious threat for algorithms implemented in embedded devices. One particularly powerful technique is to use safe-error attacks. Such attacks exploit the fact that a specific fault may or may not lead to a faulty output depending on a secret value. In this paper, we investigate the resistance of various Post-Quantum candidates algorithms against such attacks.