Search results

Cracks are prevalent signs of pavement distress found on highways globally. The use of artificial intelligence (AI) and deep learning (DL) for crack detection is increasingly considered as an optimal solution. Consequently, this paper introduces a novel, fully connected, optimised convolutional neural network (CNN) model using feature selection algorithms for the purpose of detecting cracks in highway pavements.

To enhance the accuracy of the CNN model for crack detection, the authors employed a fully connected deep learning layers CNN model along with several optimisation techniques. Specifically, three optimisation algorithms, namely adaptive moment estimation (ADAM), stochastic gradient descent with momentum (SGDM), and RMSProp, were utilised to fine-tune the CNN model and enhance its overall performance. Subsequently, the authors implemented eight feature selection algorithms to further improve the accuracy of the optimised CNN model. These feature selection techniques were thoughtfully selected and systematically applied to identify the most relevant features contributing to crack detection in the given dataset. Finally, the authors subjected the proposed model to testing against seven pre-trained models.

The study's results show that the accuracy of the three optimisers (ADAM, SGDM, and RMSProp) with the five deep learning layers model is 97.4%, 98.2%, and 96.09%, respectively. Following this, eight feature selection algorithms were applied to the five deep learning layers to enhance accuracy, with particle swarm optimisation (PSO) achieving the highest F-score at 98.72. The model was then compared with other pre-trained models and exhibited the highest performance.

With an achieved precision of 98.19% and F-score of 98.72% using PSO, the developed model is highly accurate and effective in detecting and evaluating the condition of cracks in pavements. As a result, the model has the potential to significantly reduce the effort required for crack detection and evaluation.

The proposed method for enhancing CNN model accuracy in crack detection stands out for its unique combination of optimisation algorithms (ADAM, SGDM, and RMSProp) with systematic application of multiple feature selection techniques to identify relevant crack detection features and comparing results with existing pre-trained models.

Artificial intelligence (AI) agents have been increasingly applied in the tourism and hospitality industry. However, AI service failure is inevitable. Thus, AI service recovery merits empirical investigation. This study aims to explore how AI empathic accuracy affects customers’ satisfaction in the context of AI service recovery.

A moderated mediation model was presented to describe the effect of empathic accuracy on customer satisfaction via four scenario-based experiments.

The results reveal the positive impact of AI empathic accuracy on customer satisfaction and the mediating effects of perceived agency and perceived experience. Moreover, anthropomorphism moderates the empathic accuracy effect.

This paper expanded AI service studies by exploring the significance of empathic accuracy in customer recovery satisfaction. The results provide a novel theoretical viewpoint on retaining customers following AI service failure.

人工智能（AI）设备已越来越多地应用于旅游业和酒店业。然而, AI服务失败是不可避免的。因此, AI服务补救值得进一步实证研究。本研究探讨了AI共情准确性如何影响顾客对AI服务补救的满意度。

通过四个基于场景的实验, 提出了一个有调节的中介模型来描述共情准确性对顾客满意度的影响。

结果揭示了AI共情准确性对顾客满意度有积极影响, 感知能动性和感知感受性具有中介效应。此外, 拟人化调节了共情准确性的效应。

本文通过探讨共情准确性在顾客服务补救满意度中的作用, 拓展了AI服务研究。研究结果为AI服务失败后如何留住顾客提供了新的理论视角。

Las agentes de inteligencia artificial (IA) se aplican cada vez más en el sector del turismo y la hostelería. Sin embargo, los fallos de los servicios de IA son inevitables. Por lo tanto, la recuperación de servicios de IA merece una investigación empírica. Esta investigación explora cómo la precisión empática de la IA afecta a la satisfacción de los clientes con la recuperación del servicio de IA.

Se presentó un modelo de mediación moderado para describir el efecto de la precisión empática en la satisfacción del cliente mediante cuatro experimentos basados en escenarios.

Los resultados revelan el impacto positivo de la precisión empática de la IA en la satisfacción del cliente y los efectos mediadores de la agencia percibida y la experiencia percibida. Además, el antropomorfismo modera el efecto de la precisión empática.

Este artículo amplía los estudios sobre los servicios de IA al investigar el papel de la precisión empática en la satisfacción del cliente. Los resultados aportan un punto de vista teórico novedoso sobre la retención de clientes tras el fallo de un servicio de IA.

In construction projects, engineering variations are very common and create breeding grounds for opportunistic claims. This study investigates the complementary effect between an inspection mechanism and a reputation system in deterring opportunistic claims, considering an employer with limited inspection accuracy and a contractor, which can be either reputation-concerned or opportunistic.

This paper applies a signaling game to investigate the complementary effect between the employer's inspection and a reputation system in deterring the contractor's possible opportunistic claim, considering the information-flow influence of claiming prices.

This study finds that in the exogenous-inspection-accuracy case, the employer does not always inspect the claim. A more stringent reputation system complements a less accurate inspection only when the inspection cost is lower than a threshold, but may decline the employer's surplus or social welfare. In the optimal-inspection-accuracy case, the employer always inspects the claim. However, only a sufficiently stringent reputation system can guarantee the effectiveness of an optimal inspection in curbing opportunistic claims. A more stringent reputation system has a value-stepping effect on the employer's surplus but may unexpectedly impair social welfare, whereas a higher inspection cost efficiency always reduces social welfare.

This article contributes to the project management literature by combing the signaling game theory with the reputation theory and thus embeds the problem of inspection mechanism design into a broader socio-economic framework.

Depression is a mental health problem characterized by a persistent sense of sadness and loss of interest. EEG signals are regarded as the most appropriate instruments for diagnosing depression because they reflect the operating status of the human brain. The purpose of this study is the early detection of depression among people using EEG signals.

(i) Artifacts are removed by filtering and linear and non-linear features are extracted; (ii) feature scaling is done using a standard scalar while principal component analysis (PCA) is used for feature reduction; (iii) the linear, non-linear and combination of both (only for those whose accuracy is highest) are taken for further analysis where some ML and DL classifiers are applied for the classification of depression; and (iv) in this study, total 15 distinct ML and DL methods, including KNN, SVM, bagging SVM, RF, GB, Extreme Gradient Boosting, MNB, Adaboost, Bagging RF, BootAgg, Gaussian NB, RNN, 1DCNN, RBFNN and LSTM, that have been effectively utilized as classifiers to handle a variety of real-world issues.

1. Among all, alpha, alpha asymmetry, gamma and gamma asymmetry give the best results in linear features, while RWE, DFA, CD and AE give the best results in non-linear feature. 2. In the linear features, gamma and alpha asymmetry have given 99.98% accuracy for Bagging RF, while gamma asymmetry has given 99.98% accuracy for BootAgg. 3. For non-linear features, it has been shown 99.84% of accuracy for RWE and DFA in RF, 99.97% accuracy for DFA in XGBoost and 99.94% accuracy for RWE in BootAgg. 4. By using DL, in linear features, gamma asymmetry has given more than 96% accuracy in RNN and 91% accuracy in LSTM and for non-linear features, 89% accuracy has been achieved for CD and AE in LSTM. 5. By combining linear and non-linear features, the highest accuracy was achieved in Bagging RF (98.50%) gamma asymmetry + RWE. In DL, Alpha + RWE, Gamma asymmetry + CD and gamma asymmetry + RWE have achieved 98% accuracy in LSTM.

A novel dataset was collected from the Central Institute of Psychiatry (CIP), Ranchi which was recorded using a 128-channels whereas major previous studies used fewer channels; the details of the study participants are summarized and a model is developed for statistical analysis using N-way ANOVA; artifacts are removed by high and low pass filtering of epoch data followed by re-referencing and independent component analysis for noise removal; linear features, namely, band power and interhemispheric asymmetry and non-linear features, namely, relative wavelet energy, wavelet entropy, Approximate entropy, sample entropy, detrended fluctuation analysis and correlation dimension are extracted; this model utilizes Epoch (213,072) for 5 s EEG data, which allows the model to train for longer, thereby increasing the efficiency of classifiers. Features scaling is done using a standard scalar rather than normalization because it helps increase the accuracy of the models (especially for deep learning algorithms) while PCA is used for feature reduction; the linear, non-linear and combination of both features are taken for extensive analysis in conjunction with ML and DL classifiers for the classification of depression. The combination of linear and non-linear features (only for those whose accuracy is highest) is used for the best detection results.

Improving the diversity of recommendation information has become one of the latest research hotspots to solve information cocoons. Aiming to achieve both high accuracy and diversity of recommender system, a hybrid method has been proposed in this paper. This study aims to discuss the aforementioned method.

This paper integrates latent Dirichlet allocation (LDA) model and locality-sensitive hashing (LSH) algorithm to design topic recommendation system. To measure the effectiveness of the method, this paper builds three-level categories of journal paper abstracts on the Web of Science platform as experimental data.

(1) The results illustrate that the diversity of recommended items has been significantly enhanced by leveraging hashing function to overcome information cocoons. (2) Integrating topic model and hashing algorithm, the diversity of recommender systems could be achieved without losing the accuracy of recommender systems in a certain degree of refined topic levels.

The hybrid recommendation algorithm developed in this paper can overcome the dilemma of high accuracy and low diversity. The method could ameliorate the recommendation in business and service industries to address the problems of information overload and information cocoons.

Assessing front end engineering design (FEED) accuracy is significant for project owners because it can support informed decision-making, including confidence in cost and schedule predictions. A framework to measure FEED accuracy does not exist in the literature or in practice, not does systematic data directly linking FEED accuracy to project performance. This paper aims to focus first on gauging and quantifying FEED accuracy, and second on measuring its impact on project performance in terms of cost change, schedule change, change performance, financial performance and customer satisfaction.

A novel measurement scheme was developed for FEED accuracy as a comprehensive assessment of factors related to the project leadership and execution teams, management processes and resources; to assess the environment surrounding FEED. The development of this framework built on a literature review and focus groups, and used the research charrettes methodology, guided by a research team of 20 industry professionals and input from 48 practitioners representing 31 organizations. Data were collected from 33 large industrial projects representing over $8.8 billion of installed cost, allowing for a statistical analysis of the framework's impact on performance.

This paper describes: (1) twenty-seven critical FEED accuracy factors; (2) an objective and scalable method to measure FEED accuracy; and (3) data showing that projects with high FEED accuracy outperformed projects with low FEED accuracy by 20 percent in terms of cost growth in relation to their approved budgets.

FEED accuracy is defined as the degree of confidence in the measured level of maturity of the FEED deliverables to serve as a basis of decision at the end of detailed scope, prior to detailed design. Assessing FEED accuracy is significant for project owners because it can support informed decision-making, including confidence in cost and schedule predictions.

FEED accuracy has not been assessed before, and it turned out to have considerable project performance implications. The new framework presented in this paper is the first of its kind, it has been tested rigorously, and it contributes to both the literature body of knowledge as well as to practice. As one industry leader recently stated, “it not only helped to assess the quality and adequacy of the technical documentation required, but also provided an opportunity to check the organization's readiness before making a capital investment decision.”

This study aims to examine the effects of product market competition (PMC) on analysts’ earnings forecast attributes, particularly forecast accuracy and dispersion. The authors also investigate whether investor protection moderates the relationship between PMC and forecast attributes.

The sample covers 49,578 firm-year observations from 38 countries. This study uses an ordinary least squares regression, a Heckman two-stage regression and an instrumental two-stage least squares regression.

This study finds that PMC is associated with higher forecast accuracy and lower dispersion. The results also show that investor protection enhances the effect of PMC on forecast accuracy and dispersion. These findings imply that countries with strong investor protection have a better information environment, as exhibited by the stronger relationship between PMC and analysts’ forecast properties.

The findings highlight the importance of strong governance mechanisms in both the country and industry environments. Policymakers, including government agencies and financial regulators, can leverage these insights to formulate regulations that promote competition, ensure investor protection and facilitate informed investment decisions.

This study advances our understanding of how PMC affects analysts’ earnings forecast attributes. In addition, it pioneers evidence of the moderating role of investor protection in the relationship between PMC and forecast attributes.

To improve the speed and accuracy of turbine blade film cooling design process, the most advanced deep learning models were introduced into this study to investigate the most suitable define for prediction work. This paper aims to create a generative surrogate model that can be applied on multi-objective optimization problems.

The latest backbone in the field of computer vision (Swin-Transformer, 2021) was introduced and improved as the surrogate function for prediction of the multi-physics field distribution (film cooling effectiveness, pressure, density and velocity). The basic samples were generated by Latin hypercube sampling method and the numerical method adopt for the calculation was validated experimentally at first. The training and testing samples were calculated at experimental conditions. At last, the surrogate model predicted results were verified by experiment in a linear cascade.

The results indicated that comparing with the Multi-Scale Pix2Pix Model, the Swin-Transformer U-Net model presented higher accuracy and computing speed on the prediction of contour results. The computation time for each step of the Swin-Transformer U-Net model is one-third of the original model, especially in the case of multi-physics field prediction. The correlation index reached more than 99.2% and the first-order error was lower than 0.3% for multi-physics field. The predictions of the data-driven surrogate model are consistent with the predictions of the computational fluid dynamics results, and both are very close to the experimental results. The application of the Swin-Transformer model on enlarging the different structure samples will reduce the cost of numerical calculations as well as experiments.

The number of U-Net layers and sample scales has a proper relationship according to equation (8). Too many layers of U-Net will lead to unnecessary nonlinear variation, whereas too few layers will lead to insufficient feature extraction. In the case of Swin-Transformer U-Net model, incorrect number of U-Net layer will reduce the prediction accuracy. The multi-scale Pix2Pix model owns higher accuracy in predicting a single physical field, but the calculation speed is too slow. The Swin-Transformer model is fast in prediction and training (nearly three times faster than multi Pix2Pix model), but the predicted contours have more noise. The neural network predicted results and numerical calculations are consistent with the experimental distribution.

This paper creates a generative surrogate model that can be applied on multi-objective optimization problems. The generative adversarial networks using new backbone is chosen to adjust the output from single contour to multi-physics fields, which will generate more results simultaneously than traditional surrogate models and reduce the time-cost. And it is more applicable to multi-objective spatial optimization algorithms. The Swin-Transformer surrogate model is three times faster to computation speed than the Multi Pix2Pix model. In the prediction results of multi-physics fields, the prediction results of the Swin-Transformer model are more accurate.

In typical model-based calibration, linearization errors are derived inevitably, and non-negligible negative impact will be induced on the identification results if the rotational kinematic errors are not small enough or the lengths of links are too long, which is common in the industrial cases. Thus, an accurate two-step kinematic calibration method minimizing the linearization errors is presented for a six-DoF serial robot to improve the calibration accuracy.

The negative impact of linearization on identification accuracy is minimized by removing the responsible linearized kinematic errors from the complete kinematic error model. Accordingly, the identification results of the dimension-reduced new model are accurate but not complete, so the complete kinematic error model, which achieves high identification accuracy of the rest of the error parameters, is combined with this new model to create a two-step calibration procedure capable of highly accurate identification of all the kinematic errors.

The proportions of linearization errors in measured pose errors are quantified and found to be non-negligible with the increase of rotational kinematic errors. Thus, negative impacts of linearization errors are analyzed quantitatively in different cases, providing the basis for allowed kinematic errors in the new model. Much more accurate results were obtained by using the new two-step calibration method, according to a comparison with the typical methods.

This new method achieves high accuracy with no compromise on completeness, is easy to operate and is consistent with the typical method because the second step with the new model is conveniently combined without changing the sensors or measurement instrument setup.

The aim of this study is to investigate subject independent emotion recognition capabilities of EEG and peripheral physiological signals namely: electroocoulogram (EOG), electromyography (EMG), electrodermal activity (EDA), temperature, plethysmograph and respiration. The experiments are conducted on both modalities independently and in combination. This study arranges the physiological signals in order based on the prediction accuracy obtained on test data using time and frequency domain features.

DEAP dataset is used in this experiment. Time and frequency domain features of EEG and physiological signals are extracted, followed by correlation-based feature selection. Classifiers namely – Naïve Bayes, logistic regression, linear discriminant analysis, quadratic discriminant analysis, logit boost and stacking are trained on the selected features. Based on the performance of the classifiers on the test set, the best modality for each dimension of emotion is identified.

 The experimental results with EEG as one modality and all physiological signals as another modality indicate that EEG signals are better at arousal prediction compared to physiological signals by 7.18%, while physiological signals are better at valence prediction compared to EEG signals by 3.51%. The valence prediction accuracy of EOG is superior to zygomaticus electromyography (zEMG) and EDA by 1.75% at the cost of higher number of electrodes. This paper concludes that valence can be measured from the eyes (EOG) while arousal can be measured from the changes in blood volume (plethysmograph). The sorted order of physiological signals based on arousal prediction accuracy is plethysmograph, EOG (hEOG + vEOG), vEOG, hEOG, zEMG, tEMG, temperature, EMG (tEMG + zEMG), respiration, EDA, while based on valence prediction accuracy the sorted order is EOG (hEOG + vEOG), EDA, zEMG, hEOG, respiration, tEMG, vEOG, EMG (tEMG + zEMG), temperature and plethysmograph.

Many of the emotion recognition studies in literature are subject dependent and the limited subject independent emotion recognition studies in the literature report an average of leave one subject out (LOSO) validation result as accuracy. The work reported in this paper sets the baseline for subject independent emotion recognition using DEAP dataset by clearly specifying the subjects used in training and test set. In addition, this work specifies the cut-off score used to classify the scale as low or high in arousal and valence dimensions. Generally, statistical features are used for emotion recognition using physiological signals as a modality, whereas in this work, time and frequency domain features of physiological signals and EEG are used. This paper concludes that valence can be identified from EOG while arousal can be predicted from plethysmograph.