Post quantum blockchain architecture for internet of things over NTRU lattice

The Internet of Things (IoT) and blockchain, the hottest frontier technologies in recent years, are expected to lead the next technological revolution. Blockchain promises to solve the current challenges encountered by the IoT. However, most of the proposed blockchain-based IoT architectures, which are based on discrete logarithm or large integer factorization problems, are susceptible to quantum attacks. Several quantum-resistant blockchain schemes have recently been proposed. However, the efficiency of their construction or the equipment required is not satisfactory. In this paper, to construct a more efficient postquantum blockchain infrastructure, we propose blockchain architecture for the IoT over the NTRU lattice and provide a cryptographic security proof of the scheme. Attributed to the more efficient underlying lattice structure, our scheme has excellent performance when compared to the existing quantum-resistant blockchain scheme, and we reduce the transaction size from hundreds of megabytes to several kilobytes. To further improve the blockchain's performance, we present the general framework of segregated witnesses and aggregate signatures over the NTRU lattice. Our scheme promises a blockchain solution for resource-constrained environments.

Innovative online learning strategies for the successful construction of student self-awareness during the COVID-19 pandemic: Merging TAM with TPB

The ongoing Corona Virus Disease 2019 (COVID-19) pandemic presents several challenges to the education system including technical, cognitive, managerial, and behavioral ones. As a result of these pressures, education systems are undergoing dramatic changes. The persistent state of the pandemic leading to anincrease in connectivity between teachers and students' devices, and the growth of online learning, is changing how students learn and the risks they have to manage themselves. The education sector typically employs some technical models to assess students' attitudes. Moreover, there is an ongoing intention to use online learning. In addition to technological factors, psychological factors were incorporated into the assessment. And intentions and attitudes are from a cognitive standpoint. Based on empirical research on online learning conducted among university students under epidemic normalization, the main goal of this paper is to examine the relationship between self-awareness and the willingness to use it continuously. During COVID-19 pandemic, the research framework created for this study was tested on 429 college students. The integrated Technology Acceptance Model (TAM) and Theory of Planned Behavior (TPB) model's hypotheses were empirically examined. It was found that self-awareness and the intention to use online learning during the epidemic are consistently related. Self-awareness profoundly and significantly impacts the decision to continue using online learning. The study's findings can gauge participants' intent to continue. This study's result can help assess the intention to continue to use online learning during COVID-19.This can help provide more valid assessment results beneficial for the management of online learning.

Modified Transformer architecture to Explain Black box models in Narrative form

The current XAI techniques present explanations mainly as visuals and structured data. However, these explanations are difficult to be interpreted by a non-expert user. Here, the use of Natural Language Generation (NLG) based techniques can help to represent explanations in human-understandable format. The paper addresses the issue of automatic generation of narratives using a modified transformer approach. Further, due to unavailability of a relevant annotated dataset for development and testing, we also propose a verbalization template approach to generate the same. The input of the transformer is linearized to convert the data-to-text task into text-to-text task. The proposed work is evaluated on a verbalized explained PIMA Indians diabetes dataset and exhibits significant improvement as compared to existing baselines for both, manual and automatic evaluation. Also, the narratives provide better comprehensibility to be trusted by human evaluators than the non-NLG counterparts. Lastly, an ablation study is performed in order to understand the contribution of each component.

NIR Spectroscopy Oranges Origin Identification Framework Based on Machine Learning

Research on the identification model of orange origin based on machine learning in Near infrared (NIR) spectroscopy. According to the characteristics of NIR spectral data, a complete general framework for origin identification is proposed. It includes steps such as data preprocessing, feature selection, model building and cross validation. Compare multiple preprocessing algorithms and multiple machine learning algorithms under the framework. Based on NIR spectroscopy to identify the origin of orange, a good identification result was obtained. Improve the accuracy of orange origin identification and obtained the best origin identification accuracy of 92.8%.

Research on Personalized Recommendation Methods for Online Video Learning Resources

It is not easy to find learning materials of interest quickly in the vast amount of online learning materials. The purpose of this study is to find students’ interests according to their learning behaviors in the network and to recommend related video learning materials. For the students who do not leave an evaluation record in the learning platform, the association rule algorithm in data mining is used to find out the videos that students are interested in and recommend them. For the students who have evaluation records in the platform, we use the collaborative filtering algorithm based on items in machine learning, and use the Pearson correlation coefficient method to find highly similar video materials, and then recommend the learning materials they are interested in. The two methods are used in different situations, and all students in the learning platform can get recommendation. Through the application, our methods can reduce the data search time, improve the stickiness of the platform, solve the problem of information overload, and meet the personalized needs of the learners.