Convolutional Neural Network Model based Students' Engagement Detection in Imbalanced DAiSEE Dataset

The COVID-19 pandemic has significantly changed learning processes. Learning, which had generally been carried out face-to-face, has now turned online. This learning strategy has both advantages and challenges. On the bright side, online learning is unbound by space and time, allowing it to take place anywhere and anytime. On the other side, it faces a common challenge in the lack of direct interaction between educators and students, making it difficult to assess students' engagement during an online learning process. Therefore, it is necessary to conduct research with the aim of automatically detecting students' engagement during online learning. The data used in this research were derived from the DAiSEE dataset (Dataset for Affective States in E-Environments), which comprises ten-second video recordings of students. This dataset classifies engagement levels into four categories: low, very low, high, and very high. However, the issue of imbalanced data found in the DAiSEE dataset has yet to be addressed in previous research. This data imbalance can cause errors in the classification model, resulting in overfitting and underfitting of the model. In this study, Convolutional Neural Network, a deep learning model, was utilized for feature extraction on the DAiSEE dataset. The OpenFace library was used to perform facial landmark detection, head pose estimation, facial expression unit recognition, and eye gaze estimation. The pre-processing stages included data selection, dimensional reduction, and normalization. The PCA and SVD techniques were used for dimensional reduction. The data were later oversampled using the SMOTE algorithm. The training and testing data were distributed at an 80:20 ratio. The results obtained from this experiment exceeded the benchmark evaluation values on the DAiSEE dataset, achieving the best accuracy of 77.97% using the SVD dimensional reduction technique. © 2023,International Journal of Advanced Computer Science and Applications. All Rights Reserved.

Introduction to the Minitrack on Smart (City) and Data Streaming Application Development: Challenges and Experiences

Building Smart (City) Applications and data streaming have been fast evolving in the last couple of years with a breadth of topics with cities on the edge of the 4th industrial revolution. With COVID-19 starting to be better addressable and people returning to big cities and downtown areas, visions for urban utopia with focus on sustainability and communities arise again. The combination of Artifical Intelligence, Internet of Things and data streaming methods open up novel research areas with large transational potential and address topics such as smart transportation and standards such as Industry 4.0. This minitrack features the concepts and ideas of Smart Applications and data streaming applications, their implementations, especially from a software engineering point of view. Submissions to this minitrack include presentations of architectures, frameworks, platforms and infrastructures as well as success stories of implementations. © 2023 IEEE Computer Society. All rights reserved.

Covid severity prediction: Who cares about the data quality?

COVID-19 is an ongoing pandemic disrupting daily life and overwhelming the healthcare infrastructure. Since the outburst of the pandemic, researchers have used various techniques to predict many aspects of the disease, including mortality rate and severity. The reproducibility of this research is challenging due to varying methodologies used to collect data, data quality, vague description of methodological approach to training prediction models, over-relying on data imputation, and over-fitting. This paper focuses on these challenges and provides a short yet comprehensive review of research on COVID mortality and severity prediction. The emphasis is on the reproducibility of the results and data quality issues. To further elaborate on the issue, we report the development of severity prediction models using two data sets. CRISP-DM is used as a methodological approach. We analyze and criticize the quality of the used data sets and how they affect the performance and limitations of the trained models. We conclude this paper with comments on data quality issues, the importance of reproducibility, and suggestions to improve reproducibility. © 2022 IEEE.

Data-informed building energy management (DiBEM) towards ultra-low energy buildings

To support building operations in reaching ultra-low energy targets, this paper proposes a data-informed building energy management (DiBEM) framework to improve energy efficiency systematically and continuously at the operation stage. Specifically, it has two key features including data-informed energy-saving potential identification and data-driven model-based energy savings evaluation. The paper demonstrates the proposed DiBEM with a detailed case study of an office and living laboratory building located in Cambridge, Massachusetts called HouseZero. It focuses on revealing the performance of the energy-efficient interventions from two-years' building performance monitoring data, as well as evaluating energy savings from the interventions based on the data-driven approach. With Year 1 as baseline, several interventions are proposed for Year 2 including improvements to controls and operation settings, encouragement of occupants' behavior for energy savings, and hardware retrofitting. These were deployed to heating/cooling, domestic hot water, lighting, plug and other loads, and photovoltaic (PV) systems. To quantify the impacts of different interventions on energy end uses, several data-driven models are developed. These models utilize linear regression, condition model, and machine learning techniques. Consequently, the heating/cooling energy consumption that was already ultra-low in Year 1 (12.8 kWh/m2) is further reduced to 9.7 kWh/m2 in Year 2, while the indoor thermal environment is well maintained. The domestic hot water energy is reduced from 2.3 kWh/m2 to 1.2 kWh/m2. The lighting energy is only increased from 0.3 kWh/m2 in pandemic operations without occupancy in Year 1 to 0.8 kWh/m2 in partial normal operations in Year 2, while the indoor illuminance level meets occupants' requirements. Combined with other relatively constant loads and the reduction of plug and other loads due to COVID building operation restrictions, the total energy use intensity is thereby reduced from 54.1 kWh/m2 to 42.8 kWh/m2, where 5.4 kWh/m2 of energy reduction for Year 2 is estimated to be contributed by the energy-efficient interventions. PV generation is 36.1 kWh/m2, with an increase of 1.4 kWh/m2 from a new inverter. In summary, this paper demonstrates the use of DiBEM through a detailed case study and long-term monitoring data as evidence to achieve ultra-low energy operations. © 2022 Elsevier B.V.

Analysis Of Village Direct Cash Assistance Policy Implementation In East Bolaang District Bolaang Mongondow Regency

Since the end of 2019, all countries have been shocked by the spread of Covid-19. Indonesia is one of the countries affected by the ongoing global disease pandemic (COVID-19). The pandemic has spread to 34 provinces. Covid-19 has had an enormous impact on the economic sector, and the government has assisted, one of which is the Village Fund Direct Cash Assistance (BLT). The Direct Cash Assistance (BLT) policy is an alternative policy dealing with the impact of the spread of Covid-19. In various media, there is a lot of news about the implementation of the BLT program, which often deviates from the applicable provisions. Therefore, analyzing the implementation of the BLT program is very important. Village Fund Direct Cash Assistance (BLTDD) is the government's response in minimizing the impact of Covid-19 on the people in the village. In the early stages of its implementation, problems were found in the form of community protests against village officials who were deemed unable to implement the Village Fund BLT policy properly. Even in some villages, it led to the destruction of the village office. On this basis, this research aims to analyze the problems that arise in implementing the Village Fund BLT policy to identify issues and challenges so that they become materials for improvement. This research was conducted with a qualitative approach. Since the end of 2019, all countries have been shocked by the spread of Covid-19. Indonesia is one of the countries affected by the ongoing global disease pandemic (COVID-19). The pandemic has spread to 34 provinces. Covid-19 has significantly impacted the economic sector, and the government has assisted, one of which is the Village Fund Direct Cash Assistance (BLT). The Direct Cash Assistance (BLT) policy is an alternative policy dealing with the impact of the spread of Covid-19. In various media, there is a lot of news about the implementation of the BLT program which often deviates from the applicable provisions. Therefore, analyzing the implementation of the BLT program is very important. Village Fund Direct Cash Assistance (BLTDD) is the government's response in minimizing the impact of Covid-19 on the people in the village. In the early stages of its implementation, problems were found in the form of community protests against village officials who were deemed unable to implement the Village Fund BLT policy properly. Even in some villages, it led to the destruction of the village office. On this basis, this research aims to analyze the problems that arise in implementing the Village Fund BLT policy to identify issues and challenges so that they become materials for improvement. This research was conducted with a qualitative approach. [ FROM AUTHOR]

Works done in the field of application of information technologies to libraries. (based on the creation of the technological model of the Azerbaijan University of Architecture and Construction Library)

One of the achievements in the field of education development in recent years is the emergence and development of digital libraries. This term began to be used in the late 80s in foreign publications in connection with the development of Project Gutenberg in 1971. This process is intensively developed and improved to this day. Depending on the level of development of the state (availability of high-speed Internet, financing of institutions, etc.), this process develops at different rates around the world and involves various public and private institutions. Digital libraries have become even more important during the COVID-19 pandemic as researchers and readers have been able to access vast amounts of resources at any time of the day during this challenging period when people have been confined to their homes. To date, the presence of an electronic library in the university has become an indicator of its respectability. There are certain criteria for university libraries, so they must cover scientific, educational and methodological literature in all taught disciplines. The main advantage of digital libraries is the confidence that they will deliver information better than it was in the past. At the same time, the creation and development of electronic libraries encounters a number of problems and difficulties. First of all, at present there is no clear understanding of what an electronic library is, what information systems should be attributed to this class, what are the requirements and evaluation criteria for them. In this article, we will analyze the emergence and development of the digital library, reveal the main obstacles to its development based on the creation of a technological model for the library of the Azerbaijan University of Architecture and Construction and the electronic library of the Mimar Sinan University of Fine Arts in Turkey [ FROM AUTHOR]

Investigating Literal and Inferential Comprehension Achievement of Grade Six Students

Literal and inferential comprehension questions characterize the types of tasks students typically complete in reading assignments in elementary schools in Indonesia. This study, a preliminary survey of more extensive research, aimed at describing Grade Six students' literal and inferential comprehension achievements. The research respondents were 198 Grade Six students from three elementary schools in Makassar, Indonesia. The research instrument used was a reading comprehension test which consisted of 35 multiple-choice questions. The data obtained were tabulated and analyzed descriptively using percentage analysis. The results of the study showed that most of the students in this study had low achievement in reading comprehension, both in literal and inferential comprehension. The research findings had an implication for the teaching and learning process of reading comprehension in Grade Six in elementary schools in Indonesia and other similar contexts. [ FROM AUTHOR]

Public Conduct In The Implementation Of The Protocol Health During The Covid-19 Pandemic In The Tolitoli Area

This research is related to public behavior in implementing health protocols during the Covid-19 pandemic in Toli-Toli Regency. Aims to find out how the public behaves in the application of health protocols. The method used is descriptive qualitative. Data collection techniques through three stages, namely, observation, then interviews, and documentation. The results of the study indicate that the knowledge aspect is well implemented from the government related to providing education or outreach directly and indirectly to the community related to the dangers of Covid-19 disease. In the Sikpa aspect, it is not in line with the knowledge aspect, where the community is largely ignorant of the application of health protocols. This attitude of indifference or disobedience greatly affects the health protocol policies that have been instructed by the government. This is in line with the last aspect, namely Action, in the previous aspect, namely the attitude that has shown a community response that is indifferent to the application of health protocols and by itself the musty actions are not carried out as expected. Based on the results of the research above, the researchers concluded that the lack of public awareness of the importance of maintaining health and avoiding the deadly disease Covid-19 in Toli-Toli Regency. Keywords. Knowledge, [ FROM AUTHOR]

The role and importance of using technology in teaching

This study aims to make an in-depth analysis of the prevalence and nature of the phenomenon of Internet use in teaching. The selected grades are grades VI to grade IX which in the literature are known as lower secondary education. The researcher has used the mixed method model, including qualitative and quantitative research strategies. The study involved n = 164 students and n = 117 teachers from eleven 9-year schools in the city of Prishtina, and n = 117 school staff. The results from the questionnaires with students that are quantitative in nature showed that the use of the Internet in schools is an integral part of the schools taken in the study. Most of the teachers stated that they had not received training to deal with the new models of application of technologies in teaching and a considerable part of them stated that they were unsure how to react in case an obstacle appeared in the non-functioning of technology during the lesson. The sample selected in the research consists of a total of 281 respondents, of which 117 were teachers and 164 students. There are a total of 117 employees and leaders of educational institutions and 164 students who will serve as samples. [ FROM AUTHOR]

The importance of interactions in supporting online study

The social distancing rules during the COVID-19 pandemic have inadvertently changed the activities of teaching and learning- with an unprecedented push to online courses. Educational institutions in developed countries have quickly adapted to the situation by developing their digital platforms to support e-learning. Whereas those in developing countries, particularly Vietnam, found it challenging to respond to the significant increase in online instruction because of lack of equipment and technology gap. This paper aims to examine a blending approach which combines visual technologies and social interactions to support fulltime remote education. Qualitative method was employed with the use of thematic analysis to examine respondents' perspectives of their daily online learning. Data was collected through semi-structured interviews of 05 lecturers and 10 undergraduate students in site construction management discipline as they are among groups experiencing seriously negative effects on quality of knowledge exchange which requires amount of time practice on-site or field-laboratory. Activity Theory was employed to guide the data analysis. Four main themes were found in related to "using interactive tools", "developing a learning support community", "defining responsibilities of educators and students" and "governing activities of educators and students" to meet learning objectives within online courses. [ FROM AUTHOR]

Impact of pixel, intensity, & temporal resolution on automatic scoring of LUS from Coronavirus disease 2019 patients

With the outbreak of the COVID-19, remote diagnosis, patient monitoring, collection, and transmission of data from electronic devices is rapidly taking share in the health sector. These devices are however limited on resources like energy, memory and processing power. Consequently, it is highly relevant to investigate minimizing the data, keeping intact the information content. The objective of this study is to thus observe the impact of pixel, intensity, & temporal resolution on automated scoring of LUS data. First, 448 videos from 20 patients were normalized to a common pixel resolution, i.e., the largest found over the dataset (841 pixels/cm2). Next, pixel and intensity resolution were further reduced by down-sampling factor of 2,3, and 4, and by quantization factor of 2,4, and 8 respectively. Furthermore, number of frames were down-sampled as a function of time by factor of 1 to 10 with step-size of 1. Resampled, quantized, and temporally reduced videos were evaluated using the DL algorithm (doi: 10.1109/TMI.2020.2994459) and frame, video, and prognostic-level results were obtained. It was found that no significant change in the prognostic results is observed when the data is reduced by 32 times to its original size and by 10 times to the original number of frames. © 2022 Acoustical Society of America.

Information Technology-based Public Service Management during covid-19 (Case Study of SIBERAS Application in Sidenreng Rappang Regency)

The problems in this study are the public service management system which is still manual, the lack of human resources, not understanding technology, inadequate infrastructure and the absence of transparency, accountability, efficiency and effectiveness and several villages that have been given the SIBERAS application (BUMDes Information System and Village Management) including Bulo Village, Aka-Akae, Carawali, Timoreng Panua etc. The presence of this system, the community can receive service management easily and quickly. The purpose of this study was to see the Effectiveness of Information Technology-Based Public Service Management (SIBERAS) during Covid-19 in Sidenreng Rappang. This research uses case study methods, literature studies or library research by taking reading sources from secondary data collected through textbooks, scientific journals, media track records. This type of research was analyzed qualitatively with an interactive model consisting of data presentation, data reduction, conclusion drawing and verification. The results of this study are that there are several village governments that do not use the SIBERAS application (BuMDes Management Information System and Village Government) for the Village Government and who use this application very effectively in managing Public Management, especially during Covid-19.

Recent Dimensionality Reduction Techniques for High-Dimensional COVID-19 Data

We are going through the last years of the COVID-19 pandemic, where almost the entire research community has focused on the challenges that constantly arise. From the computational and mathematical perspective, we have to deal with a dataset with ultra-high volume and ultra-high dimensionality in several experimental studies. An indicative example is DNA sequencing technologies, which offer a more realistic picture of human diseases at the molecular biology level. However, these technologies produce data with high complexity and ultra-high dimensionality. On the other hand, dimensionality reduction techniques are the first choice to address this complexity, revealing the hidden data structure in the original multidimensional space. Also, such techniques can improve the efficiency of machine learning tasks such as classification and clustering. Towards this direction, we study the behavior of seven well-known and cutting-edge dimensionality reduction techniques tailored for RNA-sequencing data. Along with the study of the effect of these algorithms, we propose the extension of the Random projection and Geodesic distance t-Stochastic Neighbor Embedding (RGt-SNE) algorithm, a recent t-Stochastic Neighbor Embedding (t-SNE) improvement. We suggest a new distance criterion for the kernel matrix construction. Our results show the potential of the proposed algorithm and, at the same time, highlight the complexity of the COVID-19 data, which are not separable, creating a significant challenge that the Machine Learning field will have to face. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Analysis of Data Quality and Data Privacy Factors on the Factors of Intention to Buy and Decision to Buy on e-Commerce during Pandemic COVID-19

The Covid-19 pandemic has changed the way customers shop. Previous research reports stated that during the Covid-19 pandemic there was an increase in transactions that occurred in e-Commerce and even a fairly large increase in income for the industry. On the other hand, it was found that there were often mistakes in shopping made by customers, resulting in product returns and so on. The implementation of data quality and data privacy is believed to have been carried out by e-Commerce. This study will explore how Data Quality and Data Privacy factors affect customer buying interest. This quantitative research uses the SmartPLS application to process the data and uses the SEM-PLS technique. This study used 477 e-commerce customers as respondents during the Covid-19 pandemic and from this research, interesting results were obtained for the development of e-commerce. The Complete Information factor was found to have a negative and significant influence on intention to buy, and other factors were also found that describe the behavior of customers who shop for e-commerce during the Covid-19 pandemic. © 2022 IEEE.

Analyzing The Effect of COVID-19 on Mental Health based on Bangladeshi University Students

The primary objective of this study is to determine the effect of the COVID-19 pandemic on a representative sample of Bangladeshi uni- versity students. The study conducted a cross-sectional approach including HADS (Hospital Anxiety and Depression Scale) and CAS (Coronavirus Anxiety Scale), obtaining sufficient data to evaluate the correlation between COVID- 19 Lockdown lifestyle and psychological impact on the students. The CAS (Coronavirus Anxiety Scale), Anxiety and Depression models were constructed to predict individuals' psychotic state, and an indisputable interpretation process has been consummated to assemble sufficient results. The study conducted an unequivocal evaluation to observe the crucial socio and environmental factors associated with young age, low socioeconomic position, gender, scholastic lifestyle, immobility, solitary, academic and occupational impediments. © 2022 ACM.

Data Quality Applied to Open Databases: “COVID-19 Cases” and “COVID-19 Vaccines”

To increase transparency, encourage citizen participation in decision making, and to respond efficiently, governments make a very important set of information available to their community. This information became even more relevant during COVID-19. However, if these data do not have a high level of quality, information loses reliability. An evaluation to measure data quality of two public files was conducted: “COVID-19. Cases registered in the Argentine Republic.” and “COVID-19 vaccines. Doses administered in the Argentine Republic.” using the model provided by the ISO/IEC 25012 standard and the evaluation process defined by ISO/IEC 25040. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

The Most Demanding Exercise in Different Training Tasks in Professional Female Futsal: A Mid-Season Study through Principal Component Analysis

The contextual factors related to training tasks can play an important role in how a player performs and, subsequently, in how a player trains to face a competition. To date, there has been no study that has investigated the most demanding exercise in different training tasks in female futsal. Therefore, this study aimed to determine the most demanding efforts during different training tasks in a cohort study conducted in professional biological women futsal players using principal component analysis (PCA). A total of 14 elite women futsal players (age = 24.34 ± 4.51 years;height = 1.65 ± 0.60 m;body mass = 63.20 ± 5.65 kg) participated in this study. Seventy training sessions of an elite professional women’s team were registered over five months (pre-season and in-season). Different types of exercises were grouped into six clusters: preventive exercises;analytical situations;exercises in midcourt;exercises in ¾ of the court;exercises in full court;superiorities/inferiorities. Each exercise cluster was composed of 5–7 principal components (PCs), considering from 1 to 5 main variables forming each, explaining from 65 to 75% of the physical total variance. A total of 13–19 sub-variables explained the players’ efforts in each training task group. The first PCs to explain the total variance of training load were as follows: preventive exercises (accelerations;~31%);analytical situations (impacts;~23%);exercises in midcourt (high-intensity efforts;~28%);exercises in ¾ of the court (~27%) and superiorities/inferiorities (~26%) (aerobic/anaerobic components);exercises in full court (anaerobic efforts;~24%). The PCs extracted from each exercise cluster provide evidence that may assist researchers and coaches during training load monitoring. The descriptive values of the training load support a scientific base to assist coaches in the planning of training schedules.

The Importance of Data Quality to Reinforce COVID-19 Vaccination Scheduling System: Study Case of Jakarta, Indonesia

Vaccination is one of the solutions to reduce the spread of COVID-19. Jakarta Government collaborates with the Department of Population and Civil Registration and the Provincial Health Office to build a COVID-19 vaccination scheduling system to reinforce the vaccination process in Jakarta. The development process involves 3 major stakeholders, so it requires very intense coordination and data exchange. Department of population and civil registration provides population data as vaccination targets. This data has been integrated into the system of the Jakarta Government. However, some other data, such as the location and quota of vaccination from the Provincial Health Office is collected manually using a spreadsheet. Manual exchanging data tends to cause data is often inaccurate, incomplete, inconsistent, and duplicate. This study aims to measure data quality (DQ) of the COVID-19 vaccination scheduling system in Jakarta. This study uses Total Data Quality Management (TDQM). TDQM provides a common framework to facilitate understanding in data improvisation through data quality management. Measurement and analysis of the data on database of the system using a tool, Talend. The measurement discovers that completeness (null 60.80% and blank 21.36%), validity 92.18%, accuracy 99.11%, and uniqueness 99.38%. The result shows that some data were poor quality especially due to incomplete data. © 2022 IEEE.

Using the SQuaRE series as a guarantee for GDPR compliance

In a context where the availability of information represents the opportunity for companies to gain a competitive advantage in the market through the use of sophisticated AI algorithms, data quality assumes a strategic role. With this paper we want to show that the adoption of an international quality measurement standard such as the one present in the SQuaRE series can on the one hand improve the ethical aspect of machine learning algorithms and on the other hand meet the requirements imposed by the European Community regarding the protection of personal data of citizens in Member States (GDPR). Indeed, although the attention to the protection of personal data is mainly directed towards the aspects of security and confidentiality, in a holistic view we should also evaluate the risks arising from the absence of quality in the data. In this context, we consider consistent and of reference for the international community the choice of the Italian legislator made for the Public Administrations. Since 2013 the Agency for Digital Italy (AgID) has suggested the adoption of ISO/IEC 25012 for public administrations in charge of managing databases of national interest. In the article, we propose a methodological approach that ensures the governance of data quality and some open questions regarding the homogeneity of the selected measures. © 2021 for this paper by its authors