Purpose - Brand reputation (BR) is one of the most important factors that affect the consumer-brand relationship and give businesses a competitive advantage. Businesses with a strong BR can increase their market share...
详细信息
Purpose - Brand reputation (BR) is one of the most important factors that affect the consumer-brand relationship and give businesses a competitive advantage. Businesses with a strong BR can increase their market shares and product market prices, in addition to gaining a competitive advantage. In order for businesses to have these advantages, they need to know and analyze their consumers. This study aimed to develop an alternative analysis method by using classification algorithms and regression analysis to measure and evaluate the effect of consumers' BR perceptions on their willingness to pay premium prices (WPP). Design/methodology/approach - The research data were collected from 483 participants by the online survey method due to the COVID-19 pandemic. The data were first analyzed with regression analysis, and the effect of BR on WPP was found to be significant. Then, using artificial intelligence (AI) methods that were not used in previous studies, consumers' perceptions of BR and WPP were clustered and classified. Findings - The results revealed the highest and lowest customer groups with BR and WPP and empirically demonstrated that highly accurate practical classification models can be applied to determine strategies in line with these findings. Originality/value - The model proposed in this study offers an integrated approach by using AI and regression analysis together and tries to fill the gap in the literature in this field. Therefore, the novelty of this study is to quantitatively reveal and evaluate the relationship between BR and WPP by using AI classification algorithms and regression analysis together.
Curcumae Longae Rhizoma (CLRh), Curcumae Radix (CRa), and Curcumae Rhizoma (CRh), derived from the different medicinal parts of the Curcuma species, are blood-activating analgesics commonly used for promoting blood ci...
详细信息
Curcumae Longae Rhizoma (CLRh), Curcumae Radix (CRa), and Curcumae Rhizoma (CRh), derived from the different medicinal parts of the Curcuma species, are blood-activating analgesics commonly used for promoting blood circulation and relieving pain. Due to their certain similarities in chemical composition and pharmacological effects, these three herbs exhibit a high risk associated with mixing and indiscriminate use. The diverse methods used for distinguishing the medicinal origins are complex, time-consuming, and limited to intraspecific differentiation, which are not suitable for rapid and systematic identification. We developed a rapid analysis method for identification of affinis and different medicinal materials using attenuated total reflection-Fourier-transform infrared spectroscopy (ATR-FTIR) combined with machine learning algorithms. The original spectroscopic data were pretreated using derivatives, standard normal variate (SNV), multiplicative scatter correction (MSC), and smoothing (S) methods. Among them, 1D + MSC + 13S emerged as the best pretreatment method. Then, t-distributed stochastic neighbor embedding (t-SNE) was applied to visualize the results, and seven kinds of classification models were constructed. The results showed that support vector machine (SVM) modeling was superior to other models and the accuracy of validation and prediction was preferable, with a modeling time of 127.76 s. The established method could be employed to rapidly and effectively distinguish the different origins and parts of Curcuma species and thus provides a technique for rapid quality evaluation of affinis species.
The purpose of our study was to evaluate the accuracy with which classification algorithms could distinguish among standing postures based on center-of-pressure (CoP) trajectories. We performed a secondary analysis of...
详细信息
The purpose of our study was to evaluate the accuracy with which classification algorithms could distinguish among standing postures based on center-of-pressure (CoP) trajectories. We performed a secondary analysis of published data from three studies: Study A) assessment of balance control on firm or foam surfaces with eyes-open or closed, Study B) quantification of postural sway in forward-backward and side-to-side directions during four standing-balance tasks that differed in difficulty, and Study C) an evaluation of the impact of two modes of transcutaneous electrical nerve stimulation on balance control in older adults. Three classification algorithms (decision tree, random forest, and k-nearest neighbor) were used to classify standing postures based on the extracted features from CoP trajectories in both the time and time-frequency domains. Such classifications enable the identification of differences and similarities in control strategy. Our results, especially those involving time-frequency features, demonstrated that distinct CoP trajectories could be identified from the extracted features in all conditions and postures in each study. Although the overall classification accuracy was similar using time-frequency features (similar to 86%) for the three studies, there were substantial differences in accuracy across conditions and postures in Studies A and B but not in Study C. Nonetheless, the models were far superior to the published results with conventional metrics in distinguishing between the conditions and postures. Moreover, a Shapley Additive exPlanation analysis was able to identify the most important features that contributed to the classification performance of the models.
ObjectivesTo perform a systematic review and meta-analysis to evaluate the effectiveness of machine learning (ML) algorithms in the diagnosis of vestibular *** to the absence of defined biomarkers for diagnosing vesti...
详细信息
ObjectivesTo perform a systematic review and meta-analysis to evaluate the effectiveness of machine learning (ML) algorithms in the diagnosis of vestibular *** to the absence of defined biomarkers for diagnosing vestibular migraine (VM), it is valuable to determine which clinical, physical, and exploratory information is most crucial to diagnosing this disease. The use of artificial intelligence tools could streamline this *** systematic review followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines and searched for records from PubMed, Scopus, and Web of Science. Observational (case-control and cohort) studies were included to assess the ability of artificial intelligence (AI) to distinguish VM from other vestibular disorders. Risk of bias and applicability concerns were assessed using the Quality Assessment of Diagnostic Accuracy Studies-AI *** total of 14 articles were included in the systematic review, and 10 were eligible for meta-analysis. The main inputs included for the ML algorithms were anamnesis (medical history), physical examination, results from audiological and vestibular tests, and imaging. The global sensitivity was 0.85 (95% confidence interval [CI] 0.73-0.92, I2 = 96%), while the global specificity was 0.89 (95% CI 0.84-0.93, I2 = 95%). The pooled diagnostic odds ratio was 48.15 (95% CI 17.64-131.43, I2 = 97%). Using the bivariate model, the area under the curve and for the summary receiver operating characteristic curve, using the 10 available studies, was 0.94 (95% CI 0.86-0.96).ConclusionMachine learning algorithms could be used as effective tools for the diagnosis process in VM. The use of models trained with three to four inputs yield the highest accuracy, compared to other strategies. However, the design and validation of these studies could be improved to ensure the reproducibility and generalizability of results.
Anomaly detection systems can identify unknown attacks, butless precise and frequently raise false alarms. This research looks at machine learning methods to develop intrusion detection systems that may be applied to ...
详细信息
ISBN:
(数字)9798331521691
ISBN:
(纸本)9798331521707
Anomaly detection systems can identify unknown attacks, butless precise and frequently raise false alarms. This research looks at machine learning methods to develop intrusion detection systems that may be applied to current computer networks. First, a three-step optimization method is shown to improve the quality of the detection: 1) using improved data to rebalance the dataset, 2) training various models and 3) combining the output of the top models. The models used in this approach are trained on known attacks, and hence anomaly detection is not possible. We examined the sensitivity, accuracy, false positive rate, ROC curve, and other general classification algorithms of several binary classifiers, including Naive Bayes, Linear SVM, Random Forest, and XGBoost, to address current problems. Our findings suggested that some improvements could be made to current models. In order to defend against future attacks,we plan to utilize the Artificial Neural Network (ANN) approach, a deep learning technique, for detecting attacks and retaining them in long-term memory.
This paper presents an image data classification algorithm based on deep learning. By integrating a Convolutional Block Attention Module (CBAM) into the ResNet-50 backbone, we form an enhanced attention residual modul...
详细信息
ISBN:
(数字)9798331533694
ISBN:
(纸本)9798331533700
This paper presents an image data classification algorithm based on deep learning. By integrating a Convolutional Block Attention Module (CBAM) into the ResNet-50 backbone, we form an enhanced attention residual module and validate it on the CUB-200-2011 dataset. Transfer learning is employed using ImageNet pre-trained weights, with images uniformly resized and randomly cropped to ensure consistent input. Training utilizes a stochastic gradient descent (SGD) optimizer, combined with a cosine annealing strategy for dynamic learning rate adjustment, and incorporates data augmentation techniques such as random flipping and color jitter to improve model generalization. The findings from the experiments show that the model markedly improves the effectiveness of classification. It accurately locates key areas in complex backgrounds and effectively captures local detailed features, thereby improving the learning of important features and reducing background noise interference. Ablation studies show that introducing the attention mechanism significantly boosts model accuracy, while combining channel grouping attention further enhances semantic feature learning. These findings highlight the proposed method's superiority in finegrained image classification tasks.
Heart complication is one of the most dangerous diseases that take many victims all around the world. This paper presented heart disease prediction based on machine learning algorithms. In this method, hyper-parameter...
详细信息
Linear and nonlinear methods of pattern classification which have been found useful in laboratory investigations of various recognition tasks are reviewed. The discussion includes correlation methods, maximum likeliho...
详细信息
Linear and nonlinear methods of pattern classification which have been found useful in laboratory investigations of various recognition tasks are reviewed. The discussion includes correlation methods, maximum likelihood formulations with independence or normality assumptions, the minimax Anderson-Bahadur formula, trainable systems, discriminant analysis, optimal quadratic boundaries, tree and chain expansions of binary probability density functions, and sequential decision schemes. The area of applicability, basic assumptions, manner of derivation, and relative computational complexity of each algorithm are described. Each method is illustrated by means of the same two-class two-dimensional numerical example. The "training set" in this example comprises four samples from either class; the "test set" is the set of all points in the normal distributions characterized by the sample means and sample covariance matrices of the training set. Procedural difficulties stemming from an insufficient number of samples, various violations of the underlying statistical models, linear nonseparability, noninvertible covariance matrices, multimodal distributions, and other experimental facts of life are touched on.
This paper describes the design and development of a classification algorithms Framework (CAF) using the JetBrains MPS domain-specific languages (DSLs) development environment. It is increasingly recognized that the s...
详细信息
This paper describes the design and development of a classification algorithms Framework (CAF) using the JetBrains MPS domain-specific languages (DSLs) development environment. It is increasingly recognized that the systems of the future will contain some form of adaptivity therefore making them intelligent systems as opposed to the static systems of the past. These intelligent systems can be extremely complex and difficult to maintain. Descriptions at higher-level of abstraction (system-level) have long been identified by industry and academia to reduce complexity. This research presents a Framework of classification algorithms at system-level that enables quick experimentation with several different algorithms from Naive Bayes to Logistic Regression. It has been developed as a tool to address the requirements of British Telecom's (BT's) data-science team. The tool has been presented at BT and JetBrains MPS and feedback has been collected and evaluated. Beyond the reduction in complexity through the system-level description, the most prominent advantage of this research is its potential applicability to many application contexts. It has been designed to be applicable for intelligent applications in several domains from business analytics, eLearning to eHealth, etc. Its wide applicability will contribute to enabling the larger vision of Artificial Intelligence (AI) adoption in context.
The identification and localization of structural damage plays an important role in the health monitoring of civil structures. However, when the number of potentially damaged structures is high it can be difficult to ...
详细信息
The identification and localization of structural damage plays an important role in the health monitoring of civil structures. However, when the number of potentially damaged structures is high it can be difficult to distinguish which ones have actually suffered damage and where further investigations need to be directed. It can be therefore useful to have procedures and algorithms that allow indicating automatically, as a preliminary step of deeper investigations, the possible occurrence of damage and its approximate position. In this context, the paper explores the variations of the natural frequencies for plane and 3D framed structures due to localized damage within macro-regions into which the structure can be divided. Based on numerically generated data, it is shown how the position of the damage within different macro-regions produces different and recognizable scenarios with respect to the variations of the natural frequencies. This allows to make use of classic data classification procedures, through which it is possible to automatically obtain indications on the macro-region of the structure subject to damage, thus limiting the extent of the investigations to be carried out on site.
暂无评论