Wyniki wyszukiwania - BazTech

1

AI, fear and employment: a nationwide study of perceived job displacement

Wysiński Przemysław

Zeszyty Naukowe. Organizacja i Zarządzanie / Politechnika Śląska

|

2025

|

z. 227

601--611

EN

Purpose: The aim of this article is to examine how the advent of artificial intelligence influences employees’ perceived risk of job displacement, with particular attention paid to age, educational level and occupational statute that mediate individuals’ fear of being replaced by AI. Design/methodology/approach: The research employs quantitative methods, specifically logistic regression analysis, using data collected from a nationwide CAWI survey conducted among Polish working-age adults (N = 816). The analysis explores the relationships between perceived fear of AI-driven job displacement and various demographic (age, education), occupational, and socioeconomic factors (savings, residence). Findings: The study finds that individuals with higher education have significantly lower levels of fear regarding AI-induced job displacement, while residents of large cities exhibit greater concern. Additionally, self-employed individuals and agricultural workers demonstrate higher anxiety about potential displacement due to AI, indicating occupational differences in perceptions. Research limitations/implications: The study is limited geographically to Poland, which may constrain the generalizability of results. Further cross-cultural research could enhance understanding. Additionally, future research might explore in-depth qualitative aspects of AI-related fears. Practical implications: Results highlight the need for targeted educational and occupational policies aimed at enhancing job security in the context of AI-driven automation. Educational institutions and employers should promote lifelong learning and upskilling, focusing particularly on groups identified as most vulnerable. Social implications: Understanding the demographic and occupational factors associated with fear of AI can help policymakers develop targeted strategies for alleviating workers' anxieties and preparing them better for technological changes. Originality/value: This study contributes to current debates on AI and labor market disruption by clearly identifying demographic, educational, occupational, and financial factors influencing individuals' perceived risk of job displacement by AI. It is valuable for scholars, policymakers, educators, and labor-market stakeholders.

2

Deeds speak louder than words – the role of ESG factors and climate literacy in shaping consumer trust in Polish banks

Iwanicz-Drozdowska Małgorzata, Kurowski Łukasz, Nowak Agnieszka

Economics and Environment

|

2025

|

No. 4

art. no. 995

EN

The growing importance of environmental, social, and governance (ESG) factors has influenced the shaping of social attitudes while also having a significant effect on the banking sector and its approach to business strategy development. The aim of this study is to assess the degree of consumer sensitivity to ESG issues within the Polish banking sector and to analyse how these attitudes shape trust in this sector. The attitudes of Polish society in this context are evaluated on the basis of 1,039 computer-assisted web interviews (CAWIs) conducted in May 2023. The data collected from the survey are then analysed via logistic regression. The findings of the study indicate that consumers are more sensitive to social factors than to environmental factors within the ESG context. However, as shown by respondents' answers, the impact of environmental issues on the overall level of trust and public perception of banking institutions should not be underestimated. The results of this study also highlight the significant role of climate literacy among respondents in shaping trust in banks whose activities negatively affect the natural environment.

PL

Rosnące znaczenie czynników środowiskowych, społecznych i ładu korporacyjnego (ESG) wpływa na kształtowanie postaw społecznych, mając jednocześnie znaczący wpływ na sektor bankowy i jego podejście do budowania strategii biznesowej. Celem niniejszego badania jest ocena wrażliwości konsumentów na kwestie ESG w polskim sektorze bankowym oraz analiza wpływu tych postaw na kształtowanie zaufania do tego sektora. Postawy społeczeństwa polskiego w tym kontekście zostały ocenione na podstawie 1 039 wywiadów CAWI, które przeprowadzono w maju 2023 roku. Dane zebrane na podstawie ankiety zostały następnie przeanalizowane za pomocą regresji logistycznej. Wyniki przeprowadzonego badania wskazują, że konsumenci są bardziej wrażliwi na czynniki społeczne niż na środowiskowe w kontekście ESG. Niemniej jednak, jak pokazały odpowiedzi respondentów, wpływ kwestii środowiskowych na ogólny poziom zaufania i postrzeganie instytucji bankowych nie może być lekceważony. Wyniki badania podkreślają również istotne znaczenie wiedzy o zmianie klimatu wśród respondentów dla utraty zaufania do banku, którego działalność szkodzi środowisku naturalnemu.

3

Intrusion detection with machine learning: a two-step federated approach.using the CIC IoT 2023 dataset

Jakotiya Komal, Shirsath Vishal, Inamdar SharanBasava

Computer Science

|

2025

|

T. 26 (2)

77--95

EN

The main objective of the planned effort is to provide analytical analyses of current intrusion detection systems grounded on ML algorithms. Furthermore, examined in this work are the useful data sets and several techniques already in use to develop an effective IDS using single, hybrid, and ensemble machine learning algorithms. The approaches in the literature have then been investi-gated under several criteria to provide a clear road and direction for the next projects that will be successful. Nowadays, companies of all kinds include an intrusion detection system (IDS), which inhibits cybercrime to protect the network, resources, and private data. Many strategies have been suggested and implemented up till now to prevent uncivil behaviour. Since machine learning (ML) approaches are successful, the proposed approach applied several ML models for the intrusion detection system. The CIC IoT 2023 Dataset is the one applied in this paper, and a two-step process for Intrusion detection was proposed. Tested with several techniques including random forest, XGBoost, logistic regression, MLP model, and RNN. Following fine-tuning, the federated learning model using neural networks had the best accuracy—99.84%.

4

Model for the prediction of performance with eco-innovation capability development criteria: a military logistic regression analysis

Bădilă Mădălina-Ioana, Bârsan Ghiță, Cioca Lucian-Ionel

Polish Journal of Management Studies

|

2024

|

Vol. 29, No. 2

87--120

EN

This research delves into a performance model particularly relevant to eco-leadership. Additionally, it examines noteworthy improvements in performance outcomes within military systems. It provides valuable insights and potential implications of significant interest to many stakeholders. By leveraging this approach, it is possible to achieve improved levels of efficiency, effectiveness, and overall performance, thereby contributing to the overarching objectives. The chosen approach includes a conceptual synthesis of systematic research on the topic of eco-leadership. The factors representative for the relationship between eco-leadership and wise military action were identified. The study results revealed a new management perspective on military technological systems by systematizing innovative green decision-making. Additionally, the study suggests recommendations for developing future ecological initiatives and interventions in the practice of military supply. Finally, the paper proposes a pragmatic model for the eco-leaders. The proposed model aims to understand all the ecological implications in military decision-making practice.

PL

Niniejsze badanie zagłębia się w model wydajności szczególnie istotny dla ekoprzewództwa. Dodatkowo analizuje znaczące poprawy wyników w systemach wojskowych. Badanie dostarcza cennych spostrzeżeń i potencjalnych implikacji ciekawych dla wielu interesariuszy. Dzięki temu podejściu można osiągnąć wyższe poziomy efektywności, skuteczności oraz poprawę ogólnych wyników, co przyczynia się do realizacji nadrzędnych celów. Przyjęte podejście obejmuje konceptualną syntezę systematycznych badań na temat ekoprzewództwa. Zidentyfikowano czynniki reprezentatywne dla związku między ekoprzewództwem a roztropnym działaniem wojskowym. Wyniki badania ujawniły nową perspektywę zarządzania wojskowymi systemami technologicznymi poprzez systematyzację innowacyjnego podejmowania zielonych decyzji. Ponadto, badanie sugeruje rekomendacje dotyczące rozwoju przyszłych inicjatyw ekologicznych oraz interwencji w praktyce wojskowego zaopatrzenia. Na koniec, artykuł proponuje pragmatyczny model dla ekoprzewódców. Proponowany model ma na celu zaprezentowanie wszystkich ekologicznych implikacji w praktyce podejmowania decyzji wojskowych.

5

Machine learning approach to predict and compare the air quality index in a confined environment

Kumar Sampath Harish, Kanish Thorapadi Chandrasekaran

Environment Protection Engineering

|

2024

|

Vol. 50, nr 4

5--27

EN

Indoor air pollution is very dangerous as people spend the majority time indoors. Cooking areas are found to be hazardous as there would be an emission of harmful pollutants. This is due to the continuous cooking process which affects people working there causing them various diseases, especially carbon monoxide poisoning. The purpose of this research is to evaluate several machine learning algorithms like support vector machine (SVM), K-nearest neighbor (KNN), logistic regression (LR), and decision tree (DT) for predicting the air quality index (AQI) of a Barbeque Nation Hotel kitchen’s confined interior environment. This investigation was done based on real-time data that was gathered by an indoor air quality monitoring system which was placed inside the kitchen for a few weeks under various cooking conditions. Results show that DT has the highest accuracy of 98.79% followed by KNN with an accuracy of 93.01%. SVM has an accuracy of 80.34%, and LR has a low accuracy of 80.20%. Therefore, DT which is a classification algorithm that comes under supervised machine learn-ing has predicted AQI accurately compared to others. Moreover, by segregating living from non-living particulate matter and nullifying them, airborne diseases like COVID-19 can be prevented in the future.

6

Predicting severe wildlife vehicle crashes (WVCs) on New Hampshire roads using a hybrid generalized additive model

Laflamme Eric M., Villamagna Amy, Kim Hyun Joong

Archives of Transport

|

2024

|

Vol. 69, iss. 1

39--57

EN

Across the United States, wildlife vehicle crashes (WVCs) are increasing and remain consistently deadly to drivers, despite a downward trend in fatal automobile accidents overall. That said, the factors related to severe WVCs are unclear. With this in mind, we pursued a statistical model to reveal factors associated with WVCs that result in severe injury or death to drivers. We hypothesize that there are statistically significant interactions and non-linear relation-ships between these factors and severity occurrence. We developed a generalized additive model (GAM) with linear terms, additive terms, and a binary response for severity. We surmise that our fitted model results will quantify the relationship between significant variables and severity occurrence, and ultimately help to develop countermeasures to mitigate serious injury. The model was fitted to WVC records occurring between 2002 and 2019 in the state of New Hampshire. Fitted linear terms revealed: 1) in inclement weather, there is about a 22% increase in the odds of severity for slick surface conditions compared to dry surface conditions; 2) for the warmer months (spring/summer), there is a 42% decrease in the odds of severity for straight roads compared to those with curvature/incline; 3) for highways, the odds of severity decreases by 48% for accidents occurring on NH’s two major intestates highways, and 4) for spring/summer (as compared to the fall/winter), there is more than a 3-fold increase in the odds of severity for two-way traffic. Fitted additive terms revealed: 1) the odds of severity increased in the early hours, between midnight and 6AM, and after 5PM; 2) speeds between 45 and 60 mph are associated with an increase in the odds of a severe accident, while both lower and higher speeds (those below 45 and above 60 mph) are associated with a decrease in the odds of a severe accident; and 3) low, mid-range, and high human population densities are associated with decreases, increases, and decreases in odds of severity, respectively. Cross validation and resulting ROC curves gave evidence that our model is well specified and an effective predictor. Results could be used to inform drivers of potentially dangerous roadways/conditions/times.

7

Simulation of delayed buses in a dumpling state and analysis of maximum waiting time using logistic regression

Tanamoto Tetsufumi, Sekiguchi Haruya, Orimo Souta, Kawakami Taisei

Transport Problems

|

2023

|

T. 18, z. 2

171--180

EN

As cities become larger and societies become more complicated, the corresponding transportation systems also become more complicated. Thus far, many important transportation models have been investigated and applied to societies. In this work, we analyze a bus transportation model that includes high randomness. By strengthening the viewpoint of the users, the bunching of buses is further explored and considered as “the dumpling bus state,” referring to cases when the next scheduled buses closely run behind a delayed bus for a while. It is described that waiting people are split into winners (people with shorter waiting times) and losers (people with longer waiting times). Waiting time is also analyzed using logistic regression to obtain the probability of people who continue to wait.

8

Application of Principle Component Analysis and logistic regression to support Six Sigma implementation in maintenance

Antosz Katarzyna, Jasiulewicz-Kaczmarek Małgorzata, Machado Jose, Relich Marcin

Eksploatacja i Niezawodność

|

2023

|

Vol. 25, no. 4

art. no. 174603

EN

Improving the efficiency of maintenance processes is one of the goals of companies. Improvement activities in this area require not only an appropriate maintenance strategy but also the use of a new approach to increase the efficiency of the process. This article focuses on using Six Sigma (SS) to improve maintenance processes. As an introduction, the generations of SS development are identified, and traditional and advanced analytical tools that can be useful in SS projects are reviewed. As part of the research, an example of the implementation of the SS project in the maintenance process using the DMAIC and selected advanced analytical methods, such as PCA and logistic regression, was presented. The PCA results showed that it was enough to have seven main components to keep about 84% of the information on variability. In developed logistic regression explained the impact of the individual factors affecting the availability of the machines. The identified factors and their interactions made it possible to define maintenance activities requiring improvements

9

Social and demographic factors in shaping the perception of work as a source of health and safety risks: a study on adult Europeans

Roszko-Wójtowicz Elżbieta, Boczkowska Katarzyna, Niziołek Konrad

Economics and Environment

|

2023

|

No. 4

1--36

EN

The aim of this article is to assess the impact of selected social and demographic factors on the perception of European adults regarding their workplace as a health and safety risk. This aligns with the sustainable development concept, which emphasizes labor rights protection and a safe working environment. Sustainable work is defined as work that doesn't compromise employees' physical or mental health over time. Utilizing data from the 2021 European Working Conditions Survey, which covered over 70,000 individuals across 36 countries and was conducted via CATI due to the pandemic, the study employs logistic regression. It analyzes three models: one encompassing all European countries, and two focusing on Eastern and Central European countries. The findings demonstrate that factors such as company size, age, occupational group, sector, employment nature, gender, service length, and education significantly influence workplace risk perception. International comparisons highlight differences in these factors across country groups, contributing to the scientific discussion in social sciences.

PL

Celem artykułu jest ocena wpływu wybranych czynników społecznych i demograficznych na postrzeganie przez dorosłych mieszkańców Europy swojej pracy jako źródła zagrożenia dla zdrowia i bezpieczeństwa. Badanie wpisuje się w koncepcję zrównoważonego rozwoju, podkreślającą ochronę praw pracowniczych i bezpieczne środowisko pracy. Zrównoważona praca definiowana jest jako taka, która nie szkodzi zdrowiu fizycznemu czy psychicznemu pracowników w dłuższym okresie. Wykorzystując dane z Europejskiego Badania Warunków Pracy z 2021 roku, obejmującego ponad 70 000 osób w 36 krajach, przeprowadzone metodą CATI z powodu pandemii, badanie zastosowało regresję logistyczną. Analizuje ono trzy modele: obejmujący wszystkie kraje europejskie oraz dwa skoncentrowane na Europie Wschodniej i Środkowej. Wyniki pokazują, że wielkość firmy, wiek, grupa zawodowa, sektor, charakter zatrudnienia, płeć, staż pracy i wykształcenie znacząco wpływają na postrzeganie ryzyka w miejscu pracy. Międzynarodowe porównania ujawniły różnice w tych czynnikach między grupami krajów, przyczyniając się do dyskusji naukowej w naukach społecznych.

10

Automated detection of cybersecurity attacks in healthcare systems with recursive feature elimination and multilayer perceptron optimization

Firat Kilincer Ilhan, Ertam Fatih, Sengur Abdulkadir, Tan Ru-San, Rajendra Acharya U.

Biocybernetics and Biomedical Engineering

|

2023

|

Vol. 43, no. 1

30--41

EN

Widespread proliferation of interconnected healthcare equipment, accompanying software, operating systems, and networks in the Internet of Medical Things (IoMT) raises the risk of security compromise as the bulk of IoMT devices are not built to withstand internet attacks. In this work, we have developed a cyber-attack and anomaly detection model based on recursive feature elimination (RFE) and multilayer perceptron (MLP). The RFE approach selected optimal features using logistic regression (LR) and extreme gradient boosting regression (XGBRegressor) kernel functions. MLP parameters were adjusted by using a hyperparameter optimization and 10-fold cross-validation approach was performed for performance evaluations. The developed model was performed on various IoMT cybersecurity datasets, and attained the best accuracy rates of 99.99%, 99.94%, 98.12%, and 96.2%, using Edith Cowan University- Internet of Health Things (ECU-IoHT), Intensive Care Unit (ICU Dataset), Telemetry data, Operating systems’ data, and Network data from the testbed IoT/IIoT network (TON-IoT), and Washington University in St. Louis enhanced healthcare monitoring system (WUSTL-EHMS) datasets, respectively. The proposed method has the ability to counter cyber attacks in healthcare applications.

11

Machine learning approach for forecasting job appeasement and employee corrosion

Swetha M. S., Mahalakshmi S., Pushpa S. K., Madihalli Amrutha T., Ananya, Bhardwaj Anand

Annals of Computer Science and Information Systems

|

2023

|

Vol. 38

85--91

EN

Employee turnover imposes costs on the organization. The quit may also cause significant and costly disruptions to the production process. The recent increase in the technological capacity to gather large magnitude of data and analyze it has changed how decision makers use them to decide on making the optimal decision. Employee attrition very similar to customer churn is an important and deciding factor affecting the revenue and success of the company. To avoid this problem, many companies now are taking guide via machine learning strategies to expect employee churn/attrition. In this paper, we are analyzing data from the past and present using different classifications like SVM, Random Forest, Decision tree, Logistic Regression, and an Ensemble model to come up with a better predictive model for the present dataset. Through this we are hoping to help the company predict employee churn and take effective measures to retain the employees and improve their economic loss due to the loss of valuable employees.

12

Enhancing naive classifier for positive unlabeled data based on logistic regression approach

Płatek Mateusz, Mielniczuk Jan

Annals of Computer Science and Information Systems

|

2023

|

Vol. 35

225--233

EN

It is argued that for analysis of Positive Unlabeled (PU) data under Selected Completely At Random (SCAR) assumption it is fruitful to view the problem as fitting of misspecified model to the data. Namely, it is shown that the results on misspecified fit imply that in the case when posterior probability of the response is modelled by logistic regression, fitting the logistic regression to the observable PU data which does not follow this model, still yields the vector of estimated parameters approximately colinear with the true vector of parameters. This observation together with choosing the intercept of the classifier based on optimisation of analogue of F1 measure yields a classifier which performs on par or better than its competitors on several real data sets considered.

13

Detecting type of hearing loss with different AI classification methods: a performance review

Kassjański Michał, Kulawiak Marcin, Przewoźny Tomasz, Tretiakow Dmitry, Kuryłowicz Jagoda, Molisz Andrzej, Koźmiński Krzysztof, Kwaśniewska Aleksandra, Mierzwińska-Dolny Paulina, Grono Miłosz

Annals of Computer Science and Information Systems

|

2023

|

Vol. 35

1017--1022

EN

Hearing is one of the most crucial senses for all humans. It allows people to hear and connect with the environment, the people they can meet and the knowledge they need to live their lives to the fullest. Hearing loss can have a detrimental impact on a person's quality of life in a variety of ways, ranging from fewer educational and job opportunities due to impaired communication to social withdrawal in severe situations. Early diagnosis and treatment can prevent most hearing loss. Pure tone audiometry, which measures air and bone conduction hearing thresholds at various frequencies, is widely used to assess hearing loss. A shortage of audiologists might delay diagnosis since they must analyze an audiogram, a graphic representation of pure tone audiometry test results, to determine hearing loss type and treatment. In the presented work, several AI-based models were used to classify audiograms into three types of hearing loss: mixed, conductive, and sensorineural. These models included Logistic Regression, Support Vector Machines, Stochastic Gradient Descent, Decision Trees, RandomForest, Feedforward Neural Network (FNN), Convolutional Neural Network (CNN), Graph Neural Network (GNN), and Recurrent Neural Network (RNN). The models were trained using 4007 audiograms classified by experienced audiologists. The RNN architecture achieved the best classification performance, with an out-of-training accuracy of 94.46%. Further research will focus on increasing the dataset and enhancing the accuracy of RNN models.

14

Measuring the effects of passengers’ socio-demographic factors on satisfaction with public bus services in a developing city: a case study in Semarang, Indonesia

Haryadi Bambang

Transport Problems

|

2022

|

T. 17, z. 2

151--160

EN

The present study aimed to assess passenger satisfaction with bus transit services based on passengers’ socio-demographic characteristics, given the service quality. An ordinal logistic regression analysis was conducted to relate passengers’ sociodemographic characteristics to their satisfaction with public bus services. The sociodemographic characteristics studied were age, gender, marital status, occupation, income, housing type, family size, and motor vehicle ownership. Data were collected by administering an onboard survey to public bus passengers. In total, 580 completed a questionnaire asking about their socio-demographic characteristics and their satisfaction with bus transit services. The study reveals that significant differences exist in the levels of passengers’ satisfaction depending on their socio-demographic characteristics. Greater satisfaction was significantly associated with being married, unemployed, and young. The delivery of public bus services needs to consider different segments of passengers.

15

Application of PCA with logistic regression in embankment drainage

Kozłowski Edward, Król Krzysztof, Rymarczyk Tomasz

Przegląd Elektrotechniczny

|

2022

|

R. 98, nr 4

127--130

EN

The article presents a method using deep-sea probes, which were used to collect measurements in electrical tomography on the leakage of flood embankments. For this purpose, the main components analysis and elasticnet in logistic regression were used. The results of research on the method of spatial analysis of object moisture are presented. Research focused on the development and comparison of algorithms and models for data analysis and reconstruction using electrical tomography. The presented algorithms were used in the process of converting the input electrical values into the conductance represented by the pixels of the output image. The article presents PCA methods in logistic regression and elastic network in logistic regression to identify leakages in shafts. Deep probes were used to collect data in electrical impedance tomography.

PL

W artykule została zaprezentowana metoda wykorzystująca sondy głębinowe, które posłużyły do zbierania pomiarów w tomografii elektrycznej na temat przesiąkania wałów przeciwpowodziowych. W tym celu została wykorzystana analiza głównych składowych oraz elasticnet w regresji logistycznej. Przedstawiono wyniki badań nad metodą przestrzennej analizy zawilgocenia obiektów. Badania koncentrowały się na opracowaniu i porównaniu algorytmów i modeli do analizy i rekonstrukcji danych z wykorzystaniem tomografii elektrycznej. Przedstawione algorytmy zostały wykorzystane w procesie konwersji wejściowych wartości elektrycznych na konduktancję reprezentowaną przez piksele obrazu wyjściowego. W artykule przedstawiono metody PCA w regresji logistycznej oraz sieci elastycznej w regresji logistycznej do identyfikacji wycieków w szybach. Do zbierania danych w tomografii impedancji elektrycznej wykorzystano sondy głębinowe.

16

Predicting the stability of open stopes using Machine Learning

Szmigiel Alicja, Apel Derek B.

Journal of Sustainable Mining

|

2022

|

Vol. 21, iss. 3

241--248

EN

The Mathews stability graph method was presented for the first time in 1980. This method was developed to assess the stability of open stopes in different underground conditions, and it has an impact on evaluating the safety of underground excavations. With the development of technology and growing experience in applying computer sciences in various research disciplines, mining engineering could significantly benefit by using Machine Learning. Applying those ML algorithms to predict the stability of open stopes in underground excavations is a new approach that could replace the original graph method and should be investigated. In this research, a Potvin database that consisted of 176 historical case studies was passed to the two most popular Machine Learning algorithms: Logistic Regression and Random Forest, to compare their predicting capabilities. The results obtained showed that those algorithms can indicate the stability of underground openings, especially Random Forest, which, in examined data, performed slightly better than Logistic Regression.

17

Revisiting strategies for fitting logistic regression for positive and unlabeled data

Wawrzeńczyk Adam, Mielniczuk Jan

International Journal of Applied Mathematics and Computer Science

|

2022

|

Vol. 32, no. 2

299--309

EN

Positive unlabeled (PU) learning is an important problem motivated by the occurrence of this type of partial observability in many applications. The present paper reconsiders recent advances in parametric modeling of PU data based on empirical likelihood maximization and argues that they can be significantly improved. The proposed approach is based on the fact that the likelihood for the logistic fit and an unknown labeling frequency can be expressed as the sum of a convex and a concave function, which is explicitly given. This allows methods such as the concave-convex procedure (CCCP) or its variant, the disciplined convex-concave procedure (DCCP), to be applied. We show by analyzing real data sets that, by using the DCCP to solve the optimization problem, we obtain significant improvements in the posterior probability and the label frequency estimation over the best available competitors.

18

Consumer Adoption of Fast-Fashion, Differences of Perceptions, and the Role of Motivations Across the Adoption Groups

Okur Nazan

Autex Research Journal

|

2022

|

Vol. 22, no. 3

365--372

EN

The purpose of this study was to determine the adoption groups of the fast-fashion consumers, evaluate the consumers’ perceptions of the fast-fashion in different groups, and model the role of “social or status image”, “uniqueness”, and “conformity” on the level of fast-fashion consumer adoption. The consumer adoption groups were determined as “innovators”, “early adopters”, “early majority”, “late majority”, and “laggards” by using a domain-specific innovativeness (DSI) scale. Consumers’ perceptions of fast-fashion were evaluated from cognitive and emotional aspects and the differences across the consumer groups were investigated by using Kruskal-–Wallis test and Mann-–Whitney U test. The roles of “social or status image”, “uniqueness”, and “conformity” on consumer groups were modeled by using ordinal logistic regression analysis. As a result of the research, consumers’ perceptions of fast-fashion were found to vary across different consumer adoption groups in terms of “being in-style products”, “expressing self-image”, “imitating the luxury fashion products”, and “frequent renewal of the collections”. Further, the findings revealed that the probabilistic relationship between different levels of consumer adoption based on innovativeness could be modeled based on the motivations of “social or status image” and “uniqueness”.

19

Different Classifier Approaches Used For Fingerprint Classification

Tiwari Meena, Mishra Ashish

Annals of Computer Science and Information Systems

|

2022

|

Vol. 33

249--253

EN

Fingerprints play an important role in public safety and criminal investigations such as: B. Legal Investigations, Law Enforcement, Cultural Access, and Social Security. It can also help to give people a comfortable and secure life. Various gender segregation strategies have been proposed. In this article, the fingerprint algorithm uses a variety of Naive Bayes classifiers, SVM, Logistics Regression and Random Forest which they use to obtain the best results of gender segregation, a new fingerprint method can be created by Naive Bayes classifier, SVM, Logistics Regression and The Random Forest used and compiled proposed from different divisions obtained the best possible division of results by Random Forest, with 98\% accuracy compared to Naive Bayes, SVM and Logistics Regression, based on Random. The forest is the most sensitive to gender segregation.

20

Machine learning prediction of future peripheral neuropathy in type 2 diabetics with percussion entropy and body mass indices

Xiao Ming-Xia, Lu Chang-Hua, Ta Na, Wei Hai-Cheng, Haryadi Bagus, Wu Hsien-Tsai

Biocybernetics and Biomedical Engineering

|

2021

|

Vol. 41, no. 3

1140--1149

EN

This study was designed to evaluate the clinical applications of body mass index (BMI) and a percussion-entropy-based index (PEINEW) for predicting the development of diabetic peripheral neuropathy (DPN) in a group of type 2 diabetes mellitus (DM) patients. The study population comprised a sample of 90 subjects with diabetics (aged 37–86 years), who went through a blood test and photoplethysmography (PPG) measurement and were then followed for 5.5 years. Conventional parameters, including the small-scale multiscale entropy index (MEISS), pulse wave velocity with electrocardiogram located (PWVmean), and PEIoriginal, were computed and compared. A logistic regression model with PEINEW and a single categorical variable (BMI) showed a graded association between the diabetics, with a high BMI (i.e., ‘‘high” category) associated with a 12.53-fold greater risk of developing DPN relative to the diabetics with a low BMI (i.e., ‘‘low” category) (p = 0.001). The odds ratio for PEINEW was 0.893. The Kaplan-Meier survival analysis showed that the diabetic patients with BMI ＞ 30 had a significantly higher cumulative incidence of PN on follow-up than those with BMI [...] 30 (log-rank test, p < 0.001). These findings suggest that BMI and PEINEW are both important risk and protective factors for new-onset DPN from diabetes mellitus and, thus, BMI and percussion entropy calculation can provide valid information that may help to identify diabetics with a high BMI and a low PEINEW as being at increased risk of future DPN.