Search

This study analyzed the current status, hotspots, and emerging trends of global research on cognitive frailty, in order to provide new research ideas for researchers. Articles and reviews related to cognitive frailty, published from 2013 to 2021, were retrieved from the Web of Science Core Collection (WoSCC) database on 26 November 2021. CiteSpace 5.8.R3 was employed for data analyses. A total of 2077 publications were included. There has been a rapid growth of publications on cognitive frailty research since 2016. The United States, Italy, England, and Australia have been the leading research centers of cognitive frailty; however, China has also recently focused on this topic. The National Center for Geriatrics and Gerontology, and Shimada H. were found to be the most prolific institution and author, respectively. Co-citation analysis identified 16 clusters, of which the largest was cognitive frailty. The keywords which occurred most frequently were “older adult”, followed by “cognitive impairment”, “frailty”, “risk”, “dementia”, “prevalence”, “mortality”, “health”, and “Alzheimer’s disease”. Burst keyword detection revealed a rising interest in cognitive frailty models. By analyzing these publications from recent years, this study provides a comprehensive analysis of cognitive frailty research.

Accurate and up-to-date biodiversity forecasts enable robust planning for environmental management and conservation of landscapes under a wide range of uses. Future predictions of the species composition of ecological communities complement more frequently reported species richness estimates to better characterize the different dimensions of biodiversity. The models that make community composition forecasts are calibrated with data on species' geographic patterns for the present, which may not be good proxies for future patterns. The future establishment of novel communities represents data on species interactions unaccounted for by these models. However, detecting them in a systematic way presents challenges due to the lack of monitoring data for landscapes with high environmental turnover, where such communities are likely to establish. Here, we propose lightweight monitoring over both ecological and anthropogenic disturbance gradients using passive sensors (i.e., those that operate continuously without much human input) to detect novel communities with the aim of updating models that make community composition forecasts. Monitoring over these two gradients should maximize detection of novel communities and improve understanding of relationships between community composition and environmental change. Further, barriers regarding cost and effort are reduced by using relatively few sensors requiring minimal upkeep. Ongoing updates to community composition forecasts based on novel community data and better understanding of the associated uncertainty should improve future decision-making for both resource management and conservation efforts.

Motivation Flow cytometry (FCM) and transcription profiling are the two widely used assays in translational immunology research. However, there is no data integration pipeline for analyzing these two types of assays together with experiment variables for biomarker inference. Current FCM data analysis mainly relies on subjective manual gating analysis, which is difficult to be directly integrated with other automated computational methods. Existing deconvolutional analysis of bulk transcriptomics relies on predefined marker genes in the transcriptomics data, which are unavailable for novel cell types and does not utilize the FCM data that provide canonical phenotypic definitions of the cell types. Results We developed a novel analytics pipeline—FastMix—for computational immunology, which integrates flow cytometry, bulk transcriptomics and clinical covariates for identifying cell type-specific gene expression signatures and biomarker genes. FastMix addresses the ‘large p, small n’ problem in the gene expression and flow cytometry integration analysis via a linear mixed effects model (LMER) for both cross-sectional and longitudinal studies. Its novel moment-based estimator not only reduces bias in parameter estimation but also is more efficient than iterative optimization. The FastMix pipeline also includes a cutting-edge flow cytometry data analysis method—DAFi—for identifying cell populations of interest and their characteristics. Simulation studies showed that FastMix produced smaller type I/II errors than competing methods. Validation using real data of two vaccine studies showed that FastMix identified a consistent set of signature genes as in independent single-cell RNA-seq analysis, producing additional interesting findings. Availability and implementation Source code of FastMix is publicly available at https://github.com/terrysun0302/FastMix. Supplementary information Supplementary data are available at Bioinformatics online.

Using a deconvolution algorithm, it is shown that resonant inelastic X-ray scattering (RIXS) spectra can be reliably estimated from measurements of photoelectrons created through absorption of RIXS photons in a chosen material. The method works on previously reported data with ∼0.5 eV resolution, and simulations show its potential for accurately estimating spectral features with hundreds of meV or smaller width., Resonant inelastic X-ray scattering (RIXS) has become an important scientific tool. Nonetheless, conventional high-resolution (few hundred meV or less) RIXS measurements, especially in the soft X-ray range, require low-throughput grating spectrometers, which limits measurement accuracy. Here, the performance of a different method for measuring RIXS, i.e. photoelectron spectrometry for analysis of X-rays (PAX), is computationally investigated. This method transforms the X-ray measurement problem of RIXS to an electron measurement problem, enabling use of high-throughput, compact electron spectrometers. X-rays to be measured are incident on a converter material and the energy distribution of the resultant photoelectrons, the PAX spectrum, is measured with an electron spectrometer. A deconvolution algorithm for analysis of such PAX data is proposed. It is shown that the deconvolution algorithm works well on data recorded with ∼0.5 eV resolution. Additional simulations show the potential of PAX for estimation of RIXS features with smaller widths. For simulations using the 3d levels of Ag as a converter material, and with 105 simulated detected electrons, it is estimated that features with a few hundred meV width can be accurately estimated in a model RIXS spectrum. For simulations using a sharp Fermi edge to encode RIXS spectra, it is estimated that one can accurately distinguish 100 meV FWHM peaks separated by 45 meV with 105 simulated detected electrons that were photoemitted from within 0.4 eV of the Fermi level.

Background Computationally derived (“synthetic”) data can enable the creation and analysis of clinical, laboratory, and diagnostic data as if they were the original electronic health record data. Synthetic data can support data sharing to answer critical research questions to address the COVID-19 pandemic. Objective We aim to compare the results from analyses of synthetic data to those from original data and assess the strengths and limitations of leveraging computationally derived data for research purposes. Methods We used the National COVID Cohort Collaborative’s instance of MDClone, a big data platform with data-synthesizing capabilities (MDClone Ltd). We downloaded electronic health record data from 34 National COVID Cohort Collaborative institutional partners and tested three use cases, including (1) exploring the distributions of key features of the COVID-19–positive cohort; (2) training and testing predictive models for assessing the risk of admission among these patients; and (3) determining geospatial and temporal COVID-19–related measures and outcomes, and constructing their epidemic curves. We compared the results from synthetic data to those from original data using traditional statistics, machine learning approaches, and temporal and spatial representations of the data. Results For each use case, the results of the synthetic data analyses successfully mimicked those of the original data such that the distributions of the data were similar and the predictive models demonstrated comparable performance. Although the synthetic and original data yielded overall nearly the same results, there were exceptions that included an odds ratio on either side of the null in multivariable analyses (0.97 vs 1.01) and differences in the magnitude of epidemic curves constructed for zip codes with low population counts. Conclusions This paper presents the results of each use case and outlines key considerations for the use of synthetic data, examining their role in collaborative research for faster insights.

Background Smartphone location data can be used for observational health studies (to determine participant exposure or behavior) or to deliver a location-based health intervention. However, missing location data are more common when using smartphones compared to when using research-grade location trackers. Missing location data can affect study validity and intervention safety. Objective The objective of this study was to investigate the distribution of missing location data and its predictors to inform design, analysis, and interpretation of future smartphone (observational and interventional) studies. Methods We analyzed hourly smartphone location data collected from 9665 research participants on 488,400 participant days in a national smartphone study investigating the association between weather conditions and chronic pain in the United Kingdom. We used a generalized mixed-effects linear model with logistic regression to identify whether a successfully recorded geolocation was associated with the time of day, participants’ time in study, operating system, time since previous survey completion, participant age, sex, and weather sensitivity. Results For most participants, the app collected a median of 2 out of a maximum of 24 locations (1760/9665, 18.2% of participants), no location data (1664/9665, 17.2%), or complete location data (1575/9665, 16.3%). The median locations per day differed by the operating system: participants with an Android phone most often had complete data (a median of 24/24 locations) whereas iPhone users most often had a median of 2 out of 24 locations. The odds of a successfully recorded location for Android phones were 22.91 times higher than those for iPhones (95% CI 19.53-26.87). The odds of a successfully recorded location were lower during weekends (odds ratio [OR] 0.94, 95% CI 0.94-0.95) and nights (OR 0.37, 95% CI 0.37-0.38), if time in study was longer (OR 0.99 per additional day in study, 95% CI 0.99-1.00), and if a participant had not used the app recently (OR 0.96 per additional day since last survey entry, 95% CI 0.96-0.96). Participant age and sex did not predict missing location data. Conclusions The predictors of missing location data reported in our study could inform app settings and user instructions for future smartphone (observational and interventional) studies. These predictors have implications for analysis methods to deal with missing location data, such as imputation of missing values or case-only analysis. Health studies using smartphones for data collection should assess context-specific consequences of high missing data, especially among iPhone users, during the night and for disengaged participants.

Background Patients’ access to and use of electronic medical records (EMRs) places greater information in their hands, which helps them better comanage their health, leading to better clinical outcomes. Despite numerous benefits that promote health and well-being, patients’ acceptance and use of EMRs remains low. We study the impact of predictors that affect the use of EMR by patients to understand better the underlying causal factors for the lower use of EMR. Objective This study aims to examine the critical system (eg, performance expectancy and effort expectancy) and patient characteristics (eg, health condition, issue involvement, preventive health behaviors, and caregiving status) that influence the extent of patients’ EMR use. Methods We used secondary data collected by Health Information National Trends Survey 5 cycle 3 and performed survey data analysis using structural equation modeling technique to test our hypotheses. Structural equation modeling is a technique commonly used to measure and analyze the relationships of observed and latent variables. We also addressed common method bias to understand if there was any systematic effect on the observed correlation between the measures for the predictor and predicted variables. Results The statistically significant drivers of the extent of EMR use were performance expectancy (β=.253; P Conclusions The study found that health characteristics, such as chronic conditions and patient disposition (eg, preventive health behavior and issue involvement), directly affect the extent of EMR use. The study also revealed that issue involvement mediates the impact of preventive health behaviors and the presence of chronic conditions on the extent of patients’ EMR use.

BackgroundAn electronic personal health record (ePHR), also known as a personal health record (PHR), has been broadly defined as an electronic application through which individuals can access, manage, and share their health information in a secure and confidential environment. Although ePHRs can benefit individuals as well as caregivers and health care providers, the use of ePHRs among individuals continues to remain low.ObjectiveThe current study aims to examine the relationship between human-technology interaction factors and ePHR use among adults and then to compare the different effects of human-technology interaction factors on ePHR use between younger adults (18-54 years old) and older adults (55 years of age and over).MethodsWe analyzed data from the Health Information National Trends Survey (HINTS 5 cycle 3) collected from US adults aged 18 years old and over in 2019. Descriptive analysis was conducted for all variables and each item of ePHR use. Bivariate tests (Pearson correlation coefficient for categorical variable and F test for continuous variables) were conducted over 2 age groups. Finally, after adjustments were made for sociodemographics and health care resources, a weighted multiple linear regression was conducted to examine the relationship between human-technology interaction factors and ePHR use.ResultsThe final sample size of 1363 (average age 51.19) was divided into 2 age groups: 18 to 54 years old and 55 years old and older. The average level of ePHR use was low (mean 2.76, range 0-8). There was no significant difference in average ePHR use between the 2 age groups. Including clinical notes was positively related to ePHR use in both groups: 18 to 54 years old (β=.28, P=.005), 55 years old and older (β=.15, P=.006). Although accessing ePHRs using a smartphone app was only associated with ePHR use among younger adults (β=.29; PConclusionsThis study found that including clinical notes was positively related to ePHR use in both age groups, which suggested that including clinical notes as a part of ePHRs might improve the effective use of ePHRs among patients. Moreover, accessing ePHRs using a smartphone app was associated with higher ePHR use among younger adults while ease of understanding health information in ePHRs was linked to higher ePHR use among older adults. The design of ePHRs should provide the option of being accessible through mobile devices to promote greater ePHR use among young people. For older adults, providers could add additional notes to explain the health information recorded in the ePHRs.

Background For several major chronic diseases including asthma, chronic obstructive pulmonary disease, chronic kidney disease, and diabetes, a state-of-the-art method to avert poor outcomes is to use predictive models to identify future high-cost patients for preemptive care management interventions. Frequently, an American patient obtains care from multiple health care systems, each managed by a distinct institution. As the patient’s medical data are spread across these health care systems, none has complete medical data for the patient. The task of building models to predict an individual patient’s cost is currently thought to be impractical with incomplete data, which limits the use of care management to improve outcomes. Recently, we developed a constraint-based method to identify patients who are apt to obtain care mostly within a given health care system. Our method was shown to work well for the cohort of all adult patients at the University of Washington Medicine for a 6-month follow-up period. It is unknown how well our method works for patients with various chronic diseases and over follow-up periods of different lengths, and subsequently, whether it is reasonable to perform this predictive modeling task on the subset of patients pinpointed by our method. Objective To understand our method’s potential to enable this predictive modeling task on incomplete medical data, this study assesses our method’s performance at the University of Washington Medicine on 5 subgroups of adult patients with major chronic diseases and over follow-up periods of 2 different lengths. Methods We used University of Washington Medicine data for all adult patients who obtained care at the University of Washington Medicine in 2018 and PreManage data containing usage information from all hospitals in Washington state in 2019. We evaluated our method’s performance over the follow-up periods of 6 months and 12 months on 5 patient subgroups separately—asthma, chronic kidney disease, type 1 diabetes, type 2 diabetes, and chronic obstructive pulmonary disease. Results Our method identified 21.81% (3194/14,644) of University of Washington Medicine adult patients with asthma. Around 66.75% (797/1194) and 67.13% (1997/2975) of their emergency department visits and inpatient stays took place within the University of Washington Medicine system in the subsequent 6 months and in the subsequent 12 months, respectively, approximately double the corresponding percentage for all University of Washington Medicine adult patients with asthma. The performance for adult patients with chronic kidney disease, adult patients with chronic obstructive pulmonary disease, adult patients with type 1 diabetes, and adult patients with type 2 diabetes was reasonably similar to that for adult patients with asthma. Conclusions For each of the 5 chronic diseases most relevant to care management, our method can pinpoint a reasonably large subset of patients who are apt to obtain care mostly within the University of Washington Medicine system. This opens the door to building models to predict an individual patient’s cost on incomplete data, which was formerly deemed impractical. International Registered Report Identifier (IRRID) RR2-10.2196/13783

Global cities play a significant role in world economy as they serve as key hubs of economic activity and trade. These cities are centers of innovation, finance, culture, and commerce, attracting businesses and entrepreneurs from all over the world. They are characterized by their openness, diversity, and their ability to attract and retain talent. This paper includes a bibliometric analysis of the structure of global cities through examining the literature on global cities, including the document type, country/territory distribution, institution distribution, geographical distribution of authors, specially most active authors and their interests or research areas, relationships between principal authors and more relevant journals, and the research hot spots. The input data consists of journal articles archived by the Web of Science from 1991 to 2023, and the analysis is performed using SciMAT and VOS Viewer. The result of this paper would provide valuable insights into the state of research on this topic, including who is conducting research, where it is being conducted, what types of publications are being produced, and which themes are having the most impact on the field. Such an analysis would be useful for researchers, policymakers, and other stakeholders interested in understanding the role of global cities in the world economy. Refereed/Peer-reviewed

My technical report focuses on the design and implementation of a virtual platform to test the NGS Shipboard. During my internship, I was part of the navigation team with a primary focus on enhancing the navigation and combat systems of naval gunfire ships. Our primary goal was to establish an effective platform for testing the navigation and combat capabilities of various naval ships. Our team successfully designed and developed a virtual shipboard model that recorded data from different ships. Its application extended to our project, where we utilized virtual reality to model and test ship designs. The Navy's decision to adopt virtual reality in ship design stemmed from the potential timesaving benefits it offered and the emerging advancements in virtual reality and how it is evolving. My STS research paper analyzes how businesses can enhance their understanding of how to create effective customer interactions that fulfill customer needs and expectations by examining the impact of technology and emerging trends. The widespread adoption of digital technologies has revolutionized customer-business interactions, leading to a shift in dynamics. Online experiences prioritize personalization, convenience, and speed and customer behavior and expectations are influenced by various factors, including cultural norms, social contexts, and individual preferences. This STS research paper highlights the rise of online shopping, saving customers time and making it easier to purchase products online over in-person interactions. The synthetic connection between the technical report and the STS research paper is the emergence of virtual reality. Augmented reality is a form of virtual reality, and it is used widely in e-commerce sales and enhances shopping experiences by providing interactive experiences. With online shopping becoming a more sociotechnical phenomena, and the navy utilizing virtual reality to provide interactive experiences to test ships, we can analyze the advancements in technology and how technology is saving us time.

With the development of big data concept and technology, big data has an important impact on human development. This paper studies the relationship between the consumption pattern and mental health of enterprise employees under the normalization of epidemic prevention and control. Starting from the consumption structure and behavior of enterprise employees, it defines the meaning of enterprise employees’ consumption and the connotation of enterprise employees’ health psychology and analyzes the relationship between consumption behavior and consumption psychology and the elements of enterprise employees’ health psychology. Based on the change of employees’ income structure and consumption patterns, this paper speculates the relationship between employees’ consumption patterns and mental health, analyzes the correlation between employees’ consumption patterns and mental health through a questionnaire survey, and calculates the Correlation Clustering statistical results. It plays an important role in building a good enterprise staff consumption culture under the normalization of epidemic prevention and control and effectively realizes the significance of purifying the social consumption environment.

Thermo-mechanical Pulping (TMP) is one of the most energy-intensive industries where most of the electrical energy is consumed in the refining process. This paper proposes the energy-saving refining optimization strategy by integrating the machine learning algorithm and heuristic optimization method. First, refining specific energy consumption (RSEC) and pulp quality identification models are developed using Artificial Neural Networks. In the second step, the developed identification models are incorporated with the Genetic algorithm to minimize the total refining specific energy consumption while maintaining the same pulp quality. Simulation results prove that a deep multilayer perceptron neural network is a powerful tool for creating refining energy and quality identification models with the model correlation coefficients of 0.97, 0.94, 0.92, and 0.67 for the first-stage RSEC, second-stage RSEC, final pulp fiber length, and freeness prediction, respectively. Findings confirm that the average total RSEC reduction of 14 % is achievable by utilizing the proposed optimization method.

With the economic development, smart communities have been widely studied and applied. However, the system in this field is not perfect, and there are still a series of problems, such as high construction cost, low level of intelligence, mutual independence of different systems, difficulty in unified management, and so on. To solve the above problems, this paper proposes the smart community big data dynamic analysis model based on logistic regression model. First, this paper constructs the big data research architecture of smart community based on IOT technology, including IAAs, DAAS, PAAS, and SaaS layers and the virtual service layer of resource scheduling of spatiotemporal information cloud platform optimized by spatiotemporal law. And the IoT platform is designed to collect data to lay the foundation for research. Second, this paper is oriented to the big data application requirements with distribution and mobility as the main technical characteristics. Based on the distributed data flow, this paper designs mining operator to provide technical support for the data mining algorithm; at the same time, this paper constructs a high-dimensional random matrix model for measuring big data and then deduces its abnormal data detection theory and method to detect high-dimensional abnormal data. Finally, this paper uses logistic regression model to predict the development trend of smart community and provide guarantee for smart community service. The simulation results show the efficiency and accuracy of prediction can be improved based on logistic regression model. Furthermore, it effectively avoid repeated construction and waste of resources in the community and form a new community management model based on intelligent and information-based social management and service.

This paper constructs a platform framework for extensive data analysis of college students’ psychological quality with the help of the thinking mode of big data and related technologies and proposes the construction principles, data sources, data processing methods, data platform construction, and platform application of big data analysis platform for college students’ psychological quality assessment. This paper combines the application methods of big data technology, collects the management data related to the psychological quality assessment of college students, saves them into the system database with certain storage logic, and realizes the function of psychological quality assessment through the design of selected psychological quality assessment data, data management and data resource management and other parts based on the data results of extensive data analysis. This study provides some insights into the psychological quality assessment of college students. The strength of association between the variables of psychological quality assessment of college students changes over time, but the overall psychological structure is more stable. This stable psychological structure characteristic is conducive to constructing the policy of constant psychological education in large universities.

As a class of randomized learner model, stochastic configuration networks (SCNs) have been successfully applied in a few data analytics tasks. Given the industrial big data modeling tasks, however, the original SCNs potentially lead to excessive training time. To this end, this paper extends SCNs to a hybrid parallel version, termed HPSCNs. In the hybrid parallel learning algorithm, two SCNs are synchronously constructed. The difference between the two of them is that one employs a point-incremental algorithm, and another one adopts a block-incremental algorithm. Moreover, a data parallel method is established based on a dynamic block strategy to accelerate the establishment of candidate node pool for each SCN. Additionally, this paper proposes an adaptive hyperparameter adjustment method, which allows the hyperparameters in the supervisory mechanism to be automatically adjusted along with the learning process. Comparative experiments are first conducted through four large-scale benchmark datasets, followed by the fully discussion on the algorithm parameters. Finally, a practical industrial application case is made, where a grinding particle size soft sensor is developed based on HPSCN, showing the effectiveness of the proposed algorithm.

Evaluating air transport service quality is fundamen-tal to ensure acceptable quality standards for users and improve the services offered to passengers and tourists. In the transportation literature there is a wide range of studies about the evaluation of public transport service quality based on passengers’ perceptions; however, more recently, the evaluation of air transport service quality is becoming a relevant issue. Evaluating service quality in air transport sector represents a more stimulating chal-lenge, given the complexity of air transport system in re-gards to the other systems; in fact, air transport service is characterised by a great variety of service aspects relat-ing to services offered by the airlines and provided by the companies managing airports. The complexity of such a service requires a deep investigation on the methods adopted for collecting and analysing the data regarding passengers’ perceptions. We propose this paper just for treating these interesting aspects and to provide an ex-haustive literature review of the studies analysing ser-vice quality from the passengers’ point of view, where the opinions of the passengers are collected by the Customer Satisfaction Surveys (CSS). We decided to select papers published within the last decade (2010–2020) in journals indexed in important databases such as Scopus and WoS.

As an educational concept based on learning output, OBE (Outcome-Based Education) is student-centered and emphasizes students’ personal progress and learning achievement. Based on BD (big data) analysis, this paper proposes a new talent training mode for the electronic information science and technology specialty. This model employs BD analysis technology to examine the correlation index between social demand and talent cultivation, based on the employment situation of students in the country in previous years. The teaching reform was carried out under the OBE concept, and a new training scheme was formed. Training objectives, graduation requirements, curriculum system, and continuous improvement mechanism were all determined. This paper proposes an algorithm for determining the degree of similarity between the knowledge required by the organization and the knowledge held by its employees. The person with the highest similarity is identified as the training candidate by the algorithm, and the training candidate is then trained according to the knowledge that the organization requires. Talent training in the field of electronic information science and technology has yielded positive results.

It is generally understood that administrative data at the level of the individual, family and wider population is fundamental to delivering client centred services which aim to support families and respond to, and reduce child abuse. They are valuable to policy makers and practitioners and play an important role in research. The focus of this paper is the potential use of administrative data from statutory family support and child protection and welfare services in Ireland for policy, practice and research. In the context of an evolving legislative and policy framework in Ireland, we provide an overview of the statutory family support and child protection services provided by Tusla Child and Family Agency. We suggest that this context provides an exceptional opportunity for developing administrative data sets in child protection and welfare and in family support. The benefits and challenges of developing administrative data sets are discussed. The paper concludes with recommendation for developing and linking administrative data sets to better understand and respond to the needs of children and families presenting to the services

Introduction: In today's rapid development of science and technology, digital network data mining technology is developing as fast as the expansion of the frontiers of science and technology allows, with a very broad application level, covering most of the civilized environment. However, there is still much to explore in the application of sports training. Objective: Analyze the feasibility of data mining based on the digital network of sports training, maximizing athletes’ training. Methods: This paper uses the experimental analysis of human FFT, combined with BP artificial intelligence network and deep data mining technology, to design a new sports training environment. The controlled test of this model was designed to compare advanced athletic training modalities with traditional modalities, comparing the athletes’ explosive power, endurance, and fitness. Results: After 30 days of physical training, the athletic strength of athletes with advanced fitness increased by 15.33%, endurance increased by 15.85%, and fitness increased by 14.23%. Conclusion: The algorithm designed in this paper positively impacts maximizing athletes’ training. It may have a favorable impact on training outcomes, as well as increase the athlete's interest in the sport. Level of evidence II; Therapeutic studies - investigating treatment outcomes.

Information and Communication Technologies, to a long extent, have a major influence on our social life, economy as well as on worldwide security. Holistically, computer networks embrace the Information Technology. Although the world is never free from people having malicious intents i.e. cyber criminals, network intruders etc. To counter this, Intrusion Detection System (IDS) plays a very significant role in identifying the network intrusions by performing various data analysis tasks. In order to develop robust IDS with accuracy in intrusion detection, various papers have been published over the years using different classification techniques of Data Mining (DM) and Machine Learning (ML) based hybrid approach. The present paper is an in-depth analysis of two focal aspects of Network Intrusion Detection System that includes various pre-processing methods in the form of dimensionality reduction and an assortment of classification techniques. This paper also includes comparative algorithmic analysis of DM and ML techniques, which applied to design an intelligent IDS. An experiment al comparative analysis has been carried out in support the verdicts of this work using ‘Python’ language on ‘kddcup99’ dataset as benchmark . Experimental analysis had been done in which we had found more impact on dimensionality reduction and MLP performed well in the true classification to establish secure network. The motive behind this effort is to detect different kinds of malware as early as possible with accuracy, to provide enhanced observant among various existing techniques that may help the fascinated researchers for future potential works.

Purpose The prediction of by-product gas is an important guarantee for the full utilization of resources. The purpose of this research is to predict gas consumption to provide a basis for gas dispatch and reduce the production cost of enterprises. Design/methodology/approach In this paper, a new method using the ensemble empirical mode decomposition (EEMD) and the back propagation neural network is proposed. Unfortunately, this method does not achieve the ideal prediction. Further, using the advantages of long short-term memory (LSTM) neural network for long-term dependence, a prediction method based on EEMD and LSTM is proposed. In this model, the gas consumption series is decomposed into several intrinsic mode functions and a residual term (r(t)) by EEMD. Second, each component is predicted by LSTM. The predicted values of all components are added together to get the final prediction result. Findings The results show that the root mean square error is reduced to 0.35%, the average absolute error is reduced to 1.852 and the R-squared is reached to 0.963. Originality/value A new gas consumption prediction method is proposed in this paper. The production data collected in the actual production process is non-linear, unstable and contains a lot of noise. But the EEMD method has the unique superiority in the analysis data aspect and may solve these questions well. The prediction of gas consumption is the result of long-term training and needs a lot of prior knowledge. Relying on LSTM can solve the problem of long-term dependence.

Handling missing values and large-dimensional features are crucial requirements for data-driven fault diagnosis systems. However, most intelligent data-driven diagnostic systems are not able to handle missing data. The presence of high-dimensional feature sets can also further complicate the process of fault diagnosis. This paper aims to devise a missing data imputation unit along with a dimensionality reduction unit in the pre-processing module of the diagnostic system. This paper proposes a novel pooling strategy for missing data imputation (PSMI). This strategy can simplify complex patterns of missingness and incrementally update the pool. The pre-processing module receives incomplete observations, PSMI estimates missing values, and, then, the dimensionality reduction unit transforms completed observations onto a lower-dimensional feature space. These transformed observations are then fed as inputs to the fault classification module for decision making and diagnosis. This diagnostic scheme makes use of various state-of-the-art missing data imputation, dimensionality reduction and classification algorithms. This enables a comprehensive comparison and allows to find the best techniques for the sake of diagnosing faults in the Tennessee Eastman process. The obtained results show the effectiveness of the proposed pooling strategy and indicate that principal component analysis imputation and heteroscedastic discriminant analysis approaches outperform other imputation and dimensionality reduction techniques in this diagnostic application.

Big data analytics involve systematic approach to find hidden patterns to help the organization grow from large volume and variety of data. In recent years big data analytics is widely used in the agricultural domain to improve yield. Viticulture (the cultivation of grapes) is one of the most lucrative farming in India. It is a subdivision of horticulture and is the study of wine growing. The demand for Indian Wine is increasing at about 27% each year since the 21st century and thus more and more ways are being developed to improve the quality and quantity of the wine products. In this paper, we focus on a specific agricultural practice as viticulture. Weather forecasting and disease detection are the two main research areas in precision viticulture. Leaf disease detection as a part of plant pathology is the key research area in this paper. It can be applied on vineyards of India where farmers are bereft of the latest technologies. Proposed system architecture comprises four modules: Data collection, data preprocessing, classification and visualization. Database module involve grape leaf dataset, consists of healthy images combined with disease leaves such as Black measles, Black rot, and Leaf blight. Models have been implemented on Apache Hadoop using map reduce programming framework. It apply feature extraction to extract various features of the live images and classification algorithm with reduced computational complexity. Gray Level Co-occurrence Matrix (GLCM) followed by K-Nearest Neighborhood (KNN) algorithm. System also recommends the necessary steps and remedies that the viticulturists can take to assure that the grapes can be salvaged at the right time and in the right manner based on classification results. Overall system will help Indian viticulturists to improve the harvesting process. Accuracy of the model is 72% and it can be increased as a future work by including deep learning with time series grape leaf images.

The massive number of sensors deployed in the Internet of Things (IoT) produce gigantic amounts of data for facilitating a wide range of applications. Deep Learning (DL) would undoubtedly play a role in generating valuable inferences from this massive volume of data and hence will assist in creating smarter IoT. In this regard, exploring the potential of DL for IoT data analytics becomes highly crucial. This paper begins with a concise discussion on the Deep Neural Network (DNN) and its different architectures. The potential benefits that DL will bring to the IoT are also discussed. Then, a detailed review of DL-driven IoT use-cases is presented. Moreover, this paper formulates a DL-based model for Human Activity Recognition (HAR). It carries out a performance comparison of the proposed model with other machine learning techniques to delineate the superiority of the DL model over other techniques. Apart from enlightening the potential of DL in IoT applications, this paper will serve as an impetus to encourage advanced research in the realm of DL-driven IoT applications.

Data quality has become an area of increasing concern in marketing research. Methods of collecting data, types of data analyzed, and data analytics techniques have changed substantially in recent years. It is important, therefore, to examine the current state of marketing research, and particularly self-administered questionnaires. This paper provides researchers important advice and rules of thumb for crafting high quality research in light of the contemporary changes occuring in modern marketing data collection practices. This is accomplished by a proposed six-step research design process that ensures data quality, and ultimately research integrity, are established and maintained throughout the research process—from the earliest conceptualization and design phases, through data collection, and ultimately the reporting of results. This paper provides a framework, which if followed, will result in reduced headaches for researchers and more robust results for decision makers.

В статье рассматривается потенциал динамического подхода анализа данных в изучении поведения пользователей в социальных сетях. В настоящее время в социальных сетях появляется информация, которая позволяет дифференцировать группы пользователей по их активности в рамках технических возможностей той или иной социальной сети. Представлено описание, дан краткий анализ информационного поля в региональных сообществах Томской области, сформирована кластеризация постов - три сферы жизнедеятельности общества: социальная, экономическая и политическая. Методология: применен динамический подход к анализу данных социальных сетей; осуществлен анализ поведения пользователей, структуры узлов и связей социальных сетей, который позволяет выявить скорость роста или уменьшения размера сети, перераспределение связей между группами. После получения списка информативных и уникальных постов произведен семантический анализ текстов с помощью инструмента для текстовой аналитики PolyAnalyst. Результаты: простроены семантические связи между словами и представлены в виде графов. Выделены два «центра», связывающих все наиболее часто встречающие слова - Томск и Томская область. С помощью инструмента для текстовой аналитики PolyAnalyst выделены популярные персоны и организации. «Позитивный контент» зафиксирован в освещении программы «Безопасные и качественные дороги» в регионе в социальной сети для формирования положительного медиаобраза власти в области. Социально активные пользователи привлекают внимание к социальной тематике. Так, среди наиболее популярных постов наибольшее число посвящено социальной сфере, далее следуют политическая и экономическая. Вместе с тем социальные сети являются также и доступным в настоящее время инструментом манипуляции общественным мнением. The paper considers the potential of a dynamic data analysis approach in studying user behavior in social networks. Currently, information appears on social networks that allows differentiating user groups by their activity within the technical capabilities of a particular social network. The paper introduces the description, a brief analysis of the information field in the regional communities of the Tomsk region; the clustering of posts into three spheres of the life of society: social, economic and political, is formed. Methodology. A dynamic approach was used to analyze social media data. The analysis of user behavior, the structure of nodes and connections of social networks is carried out, which makes it possible to identify the rate of growth or decrease in the size of the network, the redistribution of connections between groups. After receiving a list of informative and unique posts, a semantic analysis of the texts was performed using the PolyAnalyst text analytics tool. Results. The semantic connections between words were built and presented in the form of graphs. Two «centers» are highlighted that connect all the most frequently encountered words - Tomsk and Tomsk Oblast. Popular people and organizations are highlighted using the PolyAnalyst text analytics tool. The greatest positive content was recorded in the coverage of the Safe and High-Quality Roads program in the region in the social network to form a positive media image of the authorities in the region. Socially active users draw attention to social topics. So, among the most popular posts, the largest number is devoted to the social sphere, followed by the political and economic. At the same time, social networks are also a currently available tool for manipulating public opinion.

Introduction: The emergence of the concepts like Big Data, Data Science, Machine Learning (ML), and the Internet of Things (IoT) in recent years has added the potential of research in today's world. The continuous use of IoT devices, sensors, etc. that collect data continuously is putting tremendous pressure on the existing IoT network. Materials and Methods: This resource-constrained IoT environment is flooded with data acquired from millions of IoT nodes deployed at the device level. The limited resources of the IoT Network have driven the researchers towards data Management. This paper focuses on data classification at the device level, edge/fog level, and cloud level using machine learning techniques. Results: The data coming from different devices is vast and is of variety. Therefore, it becomes essential to choose the right approach for classification and analysis. This will help in optimizing the data at the device, edge/fog level for better performance of the network in the future. Conclusion: This paper presents data classification, machine learning approaches, and a proposed mathematical model for the IoT environment.

The rapid development of Internet technology has promoted the vigorous development of the multimedia. As one of the most classic instruments, the violin has been fully developed in its creation, education, and performance. In the face of more and more violin performances, the effective organization and retrieval of these musical works is an urgent problem to be solved, while it is common to classify and organize music based on the emotional properties of the performance. Deep learning is a model based on feature hierarchy and unsupervised feature learning, which has strong learning ability and adaptability. Based on the recurrent neural network (RNN) method, long short-term memory (LSTM) is one of the classic models of deep learning that can effectively learn the characteristics of time series data and achieve effective predictions. Therefore, based on the classical Hevner emotion classification model, this paper proposes an emotion recognition method for dynamic violin performances based on LSTM, which selects acoustic features and classifies the audio acoustic signals contained in the violin performances. In order to verify the effectiveness of this method, this paper carries out data labeled, feature selection, and model test on the actual violin music data by turn. The results show that the proposed method can greatly reduce the training time and improve the prediction accuracy, which reached 83%, higher than the existing methods. Meanwhile, the accuracy and iteration times of violin playing music of different emotional categories are also counted. Moreover, the method is robust to the genre, timbre, and noise changes, and the emotion recognition effect is superior.

With the continuous rise of my country’s international status, the cultivation of students’ cross-cultural thinking ability has become an important goal of college English teaching. Since the twentieth century, theories about critical thinking ability have been abundant, and how to improve students’ critical thinking ability is also a hotspot of reform. In foreign countries, there are rich teaching models, but in China, it is still a major problem to be solved to cultivate students’ speculative ability through specific teaching methods. How teachers’ classroom teaching is related to the cultivation of speculative ability. In addition to having direct application significance for teachers to realize the cultivation of speculative ability in routine teaching, the research on these issues is conducive to opening the “black box” of classroom instruction. The most crucial tasks in teaching speculative reading and cross-cultural education in today’s college English curriculum are the only means of enhancing students’ critical thinking and cross-cultural communication skills. This paper analyses, researches, and applies the diagnostic evaluation model using data gathered during system usage. In order to enhance the diagnostic evaluation function of the college English diagnostic practice system and the associated test paper generation algorithm, the author then designs and implements two test recommendation algorithms in accordance with the diagnostic evaluation model.

In this paper, a CNN model for color element data analysis of the urban spatial environment is constructed through an in-depth study of color element data analysis. This paper investigates a high-order structure formed by a few nodes; it proposes a motif-based graph autoencoder MODEL, combining redefined first- and second-order similarities and perfectly integrating motif structure and autoencoder. The algorithm first proposes an efficient graph transformation method to add the influence of central nodes. It then offers a primary awareness mechanism to aggregate the information of noncentral neighbors. Cen GCN_D and Cen GCN_E outperform the latest algorithms in node classification, link prediction, node clustering, and network visualization. As the number of network layers increases, the advantages of these two variants become progressively more prominent. This paper uses a support vector machine to implement classification validation based on CNN. The experimental results show that when 450 images are randomly selected as training data, the classification accuracy obtained by using the features of different CNN output layers is distributed between 91.4% and 95.2%. When the training set of the experiment reaches more than 300, the accuracy can exceed 90%, and the experimental results corresponding to different training sets a more stable trend. Finally, the trained classifier model is obtained in this thesis, which achieves the purpose of fast classification prediction based on CNN for color element data analysis of urban spatial environments.

With the rapid development of computer science, there are more and more kinds of discrete dynamic systems. Computer integrated system CIMS, network communication database administrator system, and human behavior analysis system are all discrete dynamic systems. At present, many researchers have studied by adding human behavior data to discrete dynamic systems. This paper aims to study the behavior data of English learners by using the discrete dynamic modeling technology of complex systems and the discrete dynamic system modeling method of Petri nets. By adding the behavior data of learners to the discrete dynamic system of fuzzy Petri nets, the system is diagnosed and optimized. The experimental results show that the complex discrete dynamic system in this paper has achieved good experimental results according to the performance indicators selected in theory. Based on the combination of the above technologies and systems, the fuzzy Petri net discrete dynamic system studied in this paper improves the processing speed of English learners' behavior data.

The development of light detection and ranging (lidar) technology began in the 1960s, following the invention of the laser, which represents the central component of this system, integrating laser scanning with an inertial measurement unit (IMU) and Global Positioning System (GPS). Lidar technology is spreading to many different areas of application, from those in autonomous vehicles for road detection and object recognition, to those in the maritime sector, including object detection for autonomous navigation, monitoring ocean ecosystems, mapping coastal areas, and other diverse applications. This paper presents lidar system technology and reviews its application in the modern road transportation and maritime sector. Some of the better-known lidar systems for practical applications, on which current commercial models are based, are presented, and their advantages and disadvantages are described and analyzed. Moreover, current challenges and future trends of application are discussed. This paper also provides a systematic review of recent scientific research on the application of lidar system technology and the corresponding computational algorithms for data analysis, mainly focusing on deep learning algorithms, in the modern road transportation and maritime sector, based on an extensive analysis of the available scientific literature.

In today's world, women's safety is a significant and crucial problem. Even in these modern times, where technology has improved considerably, women's safety remains a worry. Incidences of rape, stalking, taunting, sexual assault, molestation, harassment, domestic abuse and other forms of violence are progressing daily. Many rules and regulations have been enacted to prevent these heinous acts. Despite this, the rate of crime is rapidly increasing. The Government has developed a number of devices and applications; however they do not make use of advanced technologies like Machine Learning, Data Science etc. The paper highlights various research papers in the context of women safety, women awareness and machine learning process. Machine learning has the power to predict and analyze the data in an effective and efficient way. As the quality of data plays a vital role during the analysis, so data preparation is a crucial step of machine learning process because the raw data may be noisy, incomplete or inconsistent. The collected data from women respondents is prepared and pre-processed to transform the raw data into a structured and understandable format. Lastly, the data is analyzed using principal component analysis, KMO and Bartlett's Test to predict the important and correlated parameters that influence the women safety.

The motivations behind the technical report and the science, technology, and society (STS) research paper in this portfolio stem from a desire to bring greater awareness to and reduce the stigma surrounding mental illnesses. The technical report, “Evaluating Administered Differences of Brief Jail Mental Health Screener and Impacts of Diagnoses & Treatment of Linked Inmates with Severe Mental Illness” analyzes the way in which individuals with severe mental illness are identified for treatment once booked into jail and trends between diagnosis and treatment received. This was accomplished by looking into inmates’ responses to the Brief Jail Mental Health Screener (BJMHS) at Albemarle County Regional Jail (ACRJ), as well as diagnosis and treatment data from Region Ten Community Services (R10) which provides mental health, developmental disorder, and substance use services. While the technical report analyzes the infrastructure for addressing the needs of individuals once they have been arrested, the STS paper provides a heavier focus into the interactions of these individuals with first responders at the time of a mental health emergency call. The STS paper, “Investigating the Potential Role of Telehealth Technology in Police Response to Mental Health Emergencies”, aims to identify key requirements for implementing telehealth technology into existing criminal justice systems. Additionally, the paper specifically addresses the question of feasibility for implementing the technology in Charlottesville and similar cities. The two papers together provide a comprehensive look at the intersection of the criminal justice system and mental health, as well as offer tools in order to support future decision making in this area. The capstone team who completed the work recorded in the technical paper utilized data and statistical analysis methods using computing software to draw conclusions, such as the underrepresentation of Black males in the population of people who screen in to receive mental health treatment at ACRJ. This research was the continuation of over a decade-long partnership between the University of Virginia Systems Engineering department and agencies including, ACRJ, Central Virginia Regional Jail (CVRJ), R10, and OAR (Office of Aid and Restoration). Findings were presented in detailed figures and statistics and further analysis on the administration of the screener and use of R10 services was conducted. The STS research paper applies methods from the actor-network theory to answer the research questions. Identifying requirements for telehealth technology involved visually mapping key actors in the network on the technological, human, organizational, and macro scales. Analyzing feasibility of the technology in Charlottesville was accomplished by interviewing an expert actor in the local criminal justice system, Tom von Hemert, the Crisis Intervention Team (CIT) Coordinator for the Thomas Jefferson Area. The actor-network theory framework provided a strong outline for analyzing the addition of a new actor due to its attention to the ever-changing nature of complex systems.

My technical project titled "Analysis of Supreme Court Justice's Voting Behavior: Correlation One's Data Science 4 All/Empowerment Project" and my STS research paper titled "Analysis of Amazon's Rekognition Software using the Actor-Network Theory" share the theme of the lack of diversity in data science and artificial intelligence. Correlation One's Data Science 4 All/Empowerment program (DS4A), the program through which I did my technical project, was created to address the lack of data science professionals from under-represented communities. Meanwhile, Amazon's Rekognition software was criticized for its inability to identify women and people with dark skin. Both papers critique the industry and its lack of diversity by showing the negative effects of the issue and how some companies are making initiatives to address it. Members of the DS4A program engaged in a 13-week training course in which we learned industry-level data science techniques and skills. We also received mentorship from data science professionals and discussed ways in which to tackle the field's lack of diversity. Through the program, I created an insightful interactive dashboard that analyzes Supreme Court Justice's Voting Behavior. We did so by acquiring a federal data set with information about the Supreme court and its justices from its creation in 1789 to 2019. We cleaned and analyzed the data set using the techniques we learned from the program lecturers and presented our insights on a publicly accessible interactive dashboard. We found that contrary to survey data, the justices tend to vote with the majority, and they typically reverse the discussion of the lower courts. Additionally, in the STS Research Project, I analyzed Amazon's Rekognition Software and deemed it unethical after evaluating the software through the Actor-Network-Theory. It was revealed that while the facial recognition software was made to be used by a wide audience, it was not able to accurately identify women and people with darker skin tones. The rogue actors in this network were the non-diverse data set, which led to a software trained to be most accurate for white men only, and the non-diverse team of software developers who, as network builders, were not able to advocate for the underrepresented users that will interact with their products, they excluded a section of their customer base. By working on both projects, I identified the effect of the lack of diversity and the steps that were taken to address the issue. At Amazon, the lack of diversity contributed to the failure of the software and they were unable to serve a portion of their customer base. For the latter, Correlation One created the DS4A program to address situations in which professionals were not diverse enough to advocate for minority communities. These projects prompted me to reflect on how companies choose to respond to issues in tech and how that affects the companies' image and customer base, as well as the industry itself. Without Correlation One's program, I would not have known that there are people consistently advocating for inclusion and creating a tangible program to address it, and without Amazon's software, I would not be aware of how pioneers in the industry fail to recognize and address pressing issues. As a professional in the field, I hope that I will be able to advocate for all actors in society and ensure that the products I create and innovate will serve as many people as possible with no group being excluded.

ChatGPT, a conversational AI interface that utilizes natural language processing and machine learning algorithms, is taking the world by storm and is the buzzword across many sectors today. Given the likely impact of this model on data science, through this perspective article, we seek to provide an overview of the potential opportunities and challenges associated with using ChatGPT in data science, provide readers with a snapshot of its advantages, and stimulate interest in its use for data science projects. The paper discusses how ChatGPT can assist data scientists in automating various aspects of their workflow, including data cleaning and preprocessing, model training, and result interpretation. It also highlights how ChatGPT has the potential to provide new insights and improve decision-making processes by analyzing unstructured data. We then examine the advantages of ChatGPT’s architecture, including its ability to be fine-tuned for a wide range of language-related tasks and generate synthetic data. Limitations and issues are also addressed, particularly around concerns about bias and plagiarism when using ChatGPT. Overall, the paper concludes that the benefits outweigh the costs and ChatGPT has the potential to greatly enhance the productivity and accuracy of data science workflows and is likely to become an increasingly important tool for intelligence augmentation in the field of data science. ChatGPT can assist with a wide range of natural language processing tasks in data science, including language translation, sentiment analysis, and text classification. However, while ChatGPT can save time and resources compared to training a model from scratch, and can be fine-tuned for specific use cases, it may not perform well on certain tasks if it has not been specifically trained for them. Additionally, the output of ChatGPT may be difficult to interpret, which could pose challenges for decision-making in data science applications.

This paper adopts the method of psychological data analysis to conduct in-depth research and analysis on the correlation between teachers’ classroom teaching behaviors and students’ knowledge acceptance. Firstly, this paper proposes a health factor prediction model, which is specifically divided into clustering and then classification model and a clustering and classification synthesis model. The classroom learning process is coded, sampled, and quantified to obtain data on students’ learning behaviors, and a visualization system based on classroom students’ learning behaviors is designed and developed to record and analyze students’ behaviors in the classroom learning process and grasp students’ classroom learning. These two models use algorithms to fine-grained divide the dataset from the perspective of subject users and mental health factors, respectively, and then use decision tree algorithms to classify and predict the mental health factor information by the subject user base information. Second, based on the collected datasets, we designed comparison experiments to validate the clustering-then-classification model and the integrated clustering-classification model and selected the optimal model for comparison. Teachers should increase effective praise and encouragement behaviors; teachers should increase meaningful teacher-student interaction behaviors; teachers should be proficient in teaching media technology to reduce unnecessary time wastage. Strategies to enhance teachers’ TPACK include enriching teachers’ knowledge base of CK, TK, and PK; developing teachers’ integration thinking; and enriching teachers’ types of activities for integrating technology.

Despite the prevalence of transient-searching facilities operating across most wavelengths, the ultraviolet (UV) transient sky remains to be systematically studied. We have recently initiated the Transient Ultraviolet Objects (TUVO) project, with which we search for serendipitous UV transients in data from currently available UV instruments, with a focus on the UV/Optical (UVOT) telescope aboard the Neil Gehrels Swift Observatory (an overview of the TUVO project is described in a companion paper). Here we describe TUVOpipe, the pipeline we constructed in order to find such transients in the UVOT data, using difference image analysis. The pipeline is run daily on all new public UVOT data (which are available 6-8 hours after the observations are performed), so we discover transients in near real-time. This allows for follow-up observations to be performed. From October 1, 2020, to the time of submission, we have processed 75,183 individual UVOT images and we currently detect an average rate of ~100 transient candidates per day. Of these daily candidates, on average ~30 are real transients, separated by human vetting from the remaining `bogus' transients which were not discarded automatically within the pipeline. Most of the real transients we detect are known variable stars, though we also detect many known active galactic nuclei and accreting white dwarfs. TUVOpipe can additionally run in archival mode, whereby all archival UVOT data of a given field is scoured for `historical' transients; in this mode we also mostly find variable stars. However, some of the transients we find (in particular in the real-time mode) represent previously unreported new transients, or undiscovered outbursts of known transients, predominantly outbursts from cataclysmic variables. In this paper we describe the operation of (both modes of) TUVOpipe and some of the initial results we have so far obtained., Comment: 31 pages, 39 figures. Accepted for publication in Astronomy & Astrophysics (date of acceptance: 09/02/2022)

Novel data science approaches are needed to confront large-scale infectious disease epidemics such as COVID-19, human immunodeficiency viruses, African swine flu and Ebola. Human beings are now equipped with richer data and more advanced data analytics methodologies, many of which have become available only in the last decade. The theme issue Data Science Approaches to Infectious Diseases Surveillance reports the latest interdisciplinary research on developing novel data science methodologies to capitalize on the rich ‘big data’ of human behaviours to confront infectious diseases, with a particular focus on combating the ongoing COVID-19 pandemic. Compared to conventional public health research, articles in this issue present innovative data science approaches that were not possible without the growing human behaviour data and the recent advances in information and communications technology. This issue has 12 research papers and one review paper from a strong lineup of contributors from multiple disciplines, including data science, computer science, computational social sciences, applied maths, statistics, physics and public health. This introductory article provides a brief overview of the issue and discusses the future of this emerging field. This article is part of the theme issue ‘Data science approaches to infectious disease surveillance’.

Due to massive expansion of trading businesses, especially e-commerces, it is necessary for companies to compete for their status among customers. As most of the customers value customer experience and claim that customer experience is the most important parameter when it comes to their decision making, in this work we focus on exploring those claims using “Black Friday” dataset. The aim of this study is to perform customer segmentation and suggest a strategy based on customers’ analysis and division, and to propose an optimal model for predicting customers’ behavior. Data mining and machine learning techniques were used to perform analysis, clustering, and model building. At first, data cleaning and preprocessing was done, followed by an extensive analysis of data. Then, K-means clustering algorithm was used to perform segmentation. Finally, three different models were built with a goal of predicting customers’ purchase behavior (in this case purchase value). After comparing the results of the models, it was concluded that Random Forest Regressor performed the best. In this paper we discuss results that we got, compare them to the previous studies and draw conclusions that might be useful for marketers and decision makers, as they can be the base for their new strategies. Potential improvements and upgrades were suggested at the end of this paper.

Smart products, Social Media and innovative market research lead to an abundance of customer data, yet due to their heterogeneous sources and structures, they are scattered throughout the company. Joining these different types of data can lead to a large gain in customer insights that would not have been possible by analyzing the data individually. It is a necessary step for the transition of the current mostly hypothesis-based product design process towards a data-driven one and enables accelerated product development with truly innovative products tailored to the customer. This paper explains the holistic approach to identifying customer needs and requirements: the digital shadow of the customer. It is a concept transferred from the Internet of Production and its digital shadows of products and processes. The paper first gives an overview of customer data that form the customer data lake and reviews current data analysis methods using an explorative literature review. We then explain the concepts of the digital shadow and data lake, their main principles and benefits of using digital shadows for product development.

This paper analyzes weather data recorded by typical oceanographic buoys using data analytics and regression techniques. Time series data over a period of more than four decades (1976 – 2020) are reviewed and profiled. A set of key variables including seasonality, wind speed, wind direction, wave period, wave direction, etc., are screened from the buoy measurements to build a predictive model based on multiple linear regression for significant wave height prediction. A sensitivity analysis is then conducted for the available weather window corresponding to specified threshold operational limits of the significant wave height. Key insights are presented along with suggestions for future work to assist marine operators in planning and derisking offshore operations. Utilizing the algorithms and workflows presented in this paper, a user can increase confidence in weather window prediction, and develop safer, efficient offshore operation plans.

In image classification with Deep Convolutional Neural Networks (DCNNs), the number of parameters in pointwise convolutions rapidly grows due to the multiplication of the number of filters by the number of input channels that come from the previous layer. Existing studies demonstrated that a subnetwork can replace pointwise convolutional layers with significantly fewer parameters and fewer floating-point computations, while maintaining the learning capacity. In this paper, we propose an improved scheme for reducing the complexity of pointwise convolutions in DCNNs for image classification based on interleaved grouped filters without divisibility constraints. The proposed scheme utilizes grouped pointwise convolutions, in which each group processes a fraction of the input channels. It requires a number of channels per group as a hyperparameter Ch. The subnetwork of the proposed scheme contains two consecutive convolutional layers K and L, connected by an interleaving layer in the middle, and summed at the end. The number of groups of filters and filters per group for layers K and L is determined by exact divisions of the original number of input channels and filters by Ch. If the divisions were not exact, the original layer could not be substituted. In this paper, we refine the previous algorithm so that input channels are replicated and groups can have different numbers of filters to cope with non exact divisibility situations. Thus, the proposed scheme further reduces the number of floating-point computations (11%) and trainable parameters (10%) achieved by the previous method. We tested our optimization on an EfficientNet-B0 as a baseline architecture and made classification tests on the CIFAR-10, Colorectal Cancer Histology, and Malaria datasets. For each dataset, our optimization achieves a saving of 76%, 89%, and 91% of the number of trainable parameters of EfficientNet-B0, while keeping its test classification accuracy.

Forest fire is one of the serious threats to the population and infrastructure of Irkutsk Oblast because its territory is heavily forested. This paper discusses the main stages of solving the problem of forecasting the risk of forest fires via a case-based approach, including data preprocessing, formation of a case model, and creation of a prototype of a case-based expert system. The main contributions of the paper are the following: a case model that provides a compact representation of information about weather conditions, vegetation type, and infrastructure of the region in relation to the possible risk of a wildfire; a case-base containing information about wildfires in Irkutsk Oblast for the period from 2017 to 2020; and a methodology for creating prototypes of case bases providing the transformation of decision tables of a special type. The approbation of the approach was carried out for separate forest districts, namely Bodaibinsk and Kazachinsk-Lena. The accuracy score was used for the evaluation of the results of forecasting the risk of wildfires. The average score value reached 0.51. The evaluation results revealed that application of the case-based approach can be considered as the initial stage for deeper investigations with the use of different methods (data mining, neural networks) for more accurate forecasting.

The papers in this special section focus on innovative data analysis methods for biomedicine. Biomedical engineers as well as bioinformaticians have been working on data structures and methods to manage huge quantities of data that can be stored and efficiently accessed in both local data storage and cloud data structures. Recent activities and experiences reported in the literature reflect the new developments on how to access, process, and transform data into solutions for clinicians and patients. This special issue has been designed during the COVID-19 pandemic, at the end of 2019, with a focus to present some of the best papers at ACM-BCB 2019 (Buffalo, NY).

The connection with customers is a key task of companies, which can be achieved through diverse communication channels, among which one profitable way includes interactive websites. This paper first presents a synthetic review of previous studies on the topic of websites’ interactivity. So far, we observe interactivity through individual models of interactivity. In this paper, four modelling variables are used, which make this paper more complex in the understanding of interactivity. Further, a new research development is exposed, with emphasis on experiment structuring, modelling variables configuration, results achievement, and data analysis and interpretation. It has been ascertained that the model based on four variables creates a broader research framework, enabling an effective analysis of their overall correlations, as well of correlations between each of its components. The applicative part of the research was unrolled with effective participation of a group of 350 students, who were homogeneous in their profiles and activities. Based on the results of an initial test, 240 students were selected and participated in the main test, who all had a particular interest in searching for a job, practice, or training course on the Internet. The research reveals a higher positive impact of interactive websites vs. non-interactive websites, and compares computer use to mobile devices. It also reveals how user perception and behaviour can be positively impacted by making website searches easier, and allowing users to comment on advertisements, share the content on social media, use e-mail marketing, etc.

Research-based on user behavior analysis for authentication is the motivation for this research. We move ahead using a behavioral approach to identify malicious users and legitimate users. In this paper, we have explained how we have applied big data analytics to application-layer logs and predicted malicious users by employing a Machine Learning algorithm based on certain metrics explained later in the paper. Machine Learning would present a list of IP addresses or user identification tokens (UIT),deduced from live data which would be performing a malicious activity or are suspected of malicious activity based on their browsing behavior. We have created an e-commerce web application and induced vulnerabilities intentionally for this purpose. We have hosted our setup on LAMP [1] stack based on AWS cloud [2] . This method has a huge potential as any organization can imply this to monitor probable attackers thus narrowing down on their efforts to safeguard their infrastructure. The idea is based on the fact that the browsing pattern, as well as the access pattern of a genuine user,varies widely with that of a hacker. These patterns would be used to sort out the incoming traffic from and list out IP addresses and UIT that are the most probable cases of hack attempts.

Despite great efforts to increase energetic retrofitting rates in the residential building stock, greenhouse gas emissions are still too high to counteract climate change. One barrier is that policy measures are mostly national and do not address local differences. Even though there is plenty of research on instruments to overcome general barriers of energetic retrofitting, literature does not consider differences in local peculiarities. Thus, this paper aims to provide guidance for policy-makers by deriving evidence from over 19 million Energy Performance Certificates and socio-economic data from England, Scotland, and Wales. We find that building archetypes with their respective energetic retrofitting needs differ locally and that socio-economic factors show a strong correlation to the buildings’ energy efficiency, with the correlation varying depending on different degrees of this condition. For example, factors associated to employment mainly affect buildings with lower energy efficiency whereas the impact on more efficient buildings is limited. The findings of this paper allow for tailoring local policy instruments to fit the local peculiarities. We obtain a list of the most important socio-economic factors influencing the regional energy efficiency. Further, for two exemplary factors, we illustrate how local policy instruments should consider local retrofitting needs and socio-economic factors.

Using recent advances in data analytics techniques and tools, this paper proposes a novel data-centric paradigm for riser fatigue analysis in which practitioners can efficiently make use of large hindcast and measured metocean datasets directly in the design process. In the conventional fatigue design method for offshore risers systems, in order to reduce the computational cost practitioners tend to condense large hindcast metocean datasets into small wave datasets, so-called wave scatter diagrams, to represent the long-term variation in significant wave height, Hs, and peak period, Tp, at a site of interest. These methods tend to predict rather conservative riser loading conditions and hence fatigue lives due to the information lost in the condensing method, which can limit the application of steel catenary and lazy wave risers (SCRs and SLWRs) with larger diameters (outside diameter, OD > 18") whose design is governed by fatigue. This paper proposes enhanced frameworks for more accurate prediction of the fatigue life of SCRs and SLWRs located in swell dominant regions by enabling the direct use of large measured and hindcast metocean datasets in the fatigue design process of risers. Firstly, we introduce a novel detailed framework that uses an “ANN-based technique” with a “representative (P50) year” concept to enable large metocean datasets to be directly used for accurate estimation of riser fatigue life that is suitable for detailed design stages. Secondly, we propose an alternative innovative framework based on the use of Monte Carlo methods for more efficient long-term fatigue assessment of risers. Finally, we demonstrate the usefulness of the proposed frameworks by calculating the riser fatigue lives and comparing them against those obtained via conventional wave-condensing strategies. For the case studied here, the results show that using the proposed framework can significantly increase the estimated riser fatigue life over the values estimated using conventional wave condensing methods.