{"title":"ChatGPT vs human expertise in the context of IT recruitment","authors":"Tomasz Szandała","doi":"10.1016/j.eswa.2024.125868","DOIUrl":"10.1016/j.eswa.2024.125868","url":null,"abstract":"<div><div>This study aims to address the gap in understanding the extent to which AI can replace human technical interviewers in the recruitment process. It investigates the potential of a Large Language Models, specifically ChatGPT, Google Gemini and Mistral, in assessing candidates’ competencies in Information Technology (IT) compared to evaluations made by human experts. The experiment involved three experienced DevOps specialists who assessed the written responses of 21 candidates to ten industry-relevant questions; each limited to 500 characters. The evaluation was conducted using a simple yet effective −2 to 2 scale, with −2 indicating a negative assessment for incorrect answers, 0 for ambiguous or incomplete answers, and 2 for excellent responses. The same set of responses was then evaluated by LLMs, adhering to the identical criteria and scale. This comparative analysis aims to determine the reliability and accuracy of AI in replicating expert human judgement in IT recruitment. The study’s findings, backed by the Fleiss kappa test, show that human reviewers are not perfectly aligned in their judgement. On the other hand, the AI tool also lacks consistency, as the consequent repetition of the same review request may result in a different decision. The results are anticipated to contribute to the ongoing discourse on AI-assisted decision-making and its practical applications in human resource management and recruitment.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"264 ","pages":"Article 125868"},"PeriodicalIF":7.5,"publicationDate":"2024-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142756747","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yumin Ma , Luyao Li , Jiaxuan Shi , Juan Liu , Fei Qiao , Junkai Wang
{"title":"A new data-driven production scheduling method based on digital twin for smart shop floors","authors":"Yumin Ma , Luyao Li , Jiaxuan Shi , Juan Liu , Fei Qiao , Junkai Wang","doi":"10.1016/j.eswa.2024.125869","DOIUrl":"10.1016/j.eswa.2024.125869","url":null,"abstract":"<div><div>As a mainstream means for solving smart shop floor production scheduling problems, the data-driven scheduling method has gained considerable attention in recent years. However, extant studies have primarily utilized physical shop floor data with limited quantity and quality to train scheduling models, which suffer from the drawbacks of long training time and poor scheduling performance. Therefore, this study proposes a new data-driven scheduling method based on digital twin for smart shop floors, which utilizes the data from physical shop floor and digital shop floor constructed by digital twin to train scheduling models. Specifically, in this method, a model-level data fusion mechanism is designed to achieve the fusion and complementary advantages of these two types of data, thus providing sufficient and high-quality data support for high-precision model training. Additionally, a multi-layer feedforward neural network with a generative adversarial network-based sample expansion mechanism is further integrated to efficiently generate scheduling decisions. Experiments in a semiconductor production shop floor are conducted to confirm the effectiveness of the proposed method.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"264 ","pages":"Article 125869"},"PeriodicalIF":7.5,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142745826","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A new hybrid swarm intelligence-based maximum power point tracking technique for solar photovoltaic systems under varying irradiations","authors":"Vijay Laxmi Mishra, Yogesh Kumar Chauhan, Kripa Shankar Verma","doi":"10.1016/j.eswa.2024.125786","DOIUrl":"10.1016/j.eswa.2024.125786","url":null,"abstract":"<div><div>Partial shading condition (PSC) adversely affects the maximum power production from the solar array. To overcome this issue, this study has proposed a new hybrid swarm intelligence-based maximum power point tracking (MPPT) algorithm namely marine predator algorithm-particle swarm optimization (MPA-PSO). The novel MPA-PSO is implemented on a recently proposed 4 × 4 permutation combination-based solar topology (PCR). The proposed MPA-PSO improves the efficacy of MPA by updating the velocity in three successive steps; low-velocity phase (v = 0.1), unit velocity phase (v = 1), and high-velocity phase (v ≧10) respectively. Later the global searching and local searching ability is confirmed by PSO. Thus, the novel proposed MPA-PSO improves the optimization efficiency of MPA and updates the position of the PSO algorithm with the MPA algorithm leading to an effective handling of exploration and exploitation phases. The novel MPA-PSO overcomes the challenges of long convergence time by decreasing the swarm size. Further, the challenges like capture of global power in the local peaks and slow change of shading patterns are overcome by the novel hybrid MPA-PSO. The performance of the proposed MPA-PSO is compared with MPA, PSO, and influential flower pollination algorithm (IFPA) under various realistic shading patterns. The specific improvements of the novel MPA-PSO include the reduction in convergence time by 9.08 % to 15.16 % and an increment in average power by 67.29 W against MPA, PSO, and IFPA respectively. Thus, the novel hybrid MPA-PSO discloses greater flexibility and versatility over other considered algorithms in this study.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"264 ","pages":"Article 125786"},"PeriodicalIF":7.5,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142745824","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"An enhanced interval-valued PM2.5 concentration forecasting model with attention-based feature extraction and self-adaptive combination technology","authors":"Jiaming Zhu , Peng Zheng , Lili Niu , Huayou Chen , Peng Wu","doi":"10.1016/j.eswa.2024.125867","DOIUrl":"10.1016/j.eswa.2024.125867","url":null,"abstract":"<div><div>Accurate predictions of air quality enable governments and relevant authorities to take promptly measures for protecting public health. With the increasing time-varying nature of air pollutants, predicting daily average concentrations alone is no longer sufficient for environmental management and risk warning. Hence, this paper proposes a multi-resolution interval-valued PM<sub>2.5</sub> concentration combination prediction model, which based on interval decomposition and attention mechanism reconstruction. Firstly, the interval-valued time series (ITS) was decomposed and adaptively reconstructed using the binary empirical mode decomposition (BEMD) algorithm and attention-based reconstruction. Subsequently, multi-resolution linear projection layers were applied to extract temporal features from the time series. Finally, a hybrid prediction module was implemented that combines CNN and LSTM to predict each subsequence and integrate them to derive the final interval prediction values for PM2.5. In the proposed framework, the reconstruction technique effectively resolved the issue of inconsistent numbers of different feature decomposition subsequences, while the linear projection layer fully captured the multi-resolution characteristics of the time series. Empirical studies conducted in three districts of Beijing showed that, compared to state-of-the-art baseline models, the framework reduced the average values of five interval evaluation metrics by 11.2%, 17.4%, 11.7%, 10.5%, and 14.8%, respectively. This interval-valued prediction framework can effectively assist urban air quality management and warning.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"264 ","pages":"Article 125867"},"PeriodicalIF":7.5,"publicationDate":"2024-11-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142745664","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"LLMOverTab: Tabular data augmentation with language model-driven oversampling","authors":"Tokimasa Isomura , Ryotaro Shimizu , Goto Masayuki","doi":"10.1016/j.eswa.2024.125852","DOIUrl":"10.1016/j.eswa.2024.125852","url":null,"abstract":"<div><div>In recent years, Large Language Model (LLM) have seen significant advancements, attracting attention for their applications in various fields. These models have shown promising results in handling tabular data, especially in cases with limited datasets, by leveraging pre-trained knowledge. However, their effectiveness in addressing imbalanced data in tabular formats is less explored. To bridge this gap, our study introduces LLMOverTab, a novel approach using LLMs for oversampling in imbalanced tabular data. We conducted comprehensive experiments on diverse tabular datasets to assess the effectiveness of LLMOverTab, demonstrating its potential in improving the handling of imbalanced data. The study also explores application of LLMOverTab in zero-shot and few-shot learning contexts, providing insights into its adaptability. Additionally, we analyze the oversampled data, offering reflections on the quality of generated samples. Our research not only showcases the utility of LLMOverTab in managing imbalanced tabular data, but also opens new avenues for the application of language models in various tasks of tabular data. This study adds to the increasing interest in applying LLMs to various task domains. It provides new perspectives for the innovative use of LLMs in structured tabular data fields, highlighting their potential in a range of applications.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"264 ","pages":"Article 125852"},"PeriodicalIF":7.5,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142745727","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Gradient-based differential neural network to time-varying constrained quadratic programming","authors":"Bolin Liao , Yang Zeng , Tinglei Wang , Zhan Li","doi":"10.1016/j.eswa.2024.125893","DOIUrl":"10.1016/j.eswa.2024.125893","url":null,"abstract":"<div><div>This paper introduces a novel approach to solving time-varying quadratic programming (TVQP) problems with time-dependent constraints, using gradient-based differential neural networks (GDNN). We establish the theoretical framework for both conventional gradient neural networks (CGNN) and GDNN models, highlighting their effectiveness in addressing dynamic optimization challenges. Comparative theoretical analyses show that the proposed GDNN model achieves higher accuracy than the CGNN model, significantly reducing solution errors with exponential convergence. Moreover, the use of a sign-bi-power activation function (SBPAF) ensures reasonable convergence times for the GDNN model. Our approach is validated through simulations of TVQP problems under specific constraints. The results demonstrate that while both models are capable of solving these problems, the GDNN model outperforms the CGNN model in minimizing optimization errors (residual errors), especially when varying the scaling factor <span><math><mi>γ</mi></math></span>, the GDNN model also shows superior performance and more efficient convergence.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"264 ","pages":"Article 125893"},"PeriodicalIF":7.5,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142745735","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Language of actions: A generative model for activity recognition and next move prediction from motion sensors","authors":"Hasan Oğul","doi":"10.1016/j.eswa.2024.125947","DOIUrl":"10.1016/j.eswa.2024.125947","url":null,"abstract":"<div><div>Increasing use of motion sensors in wearable and mobile devices has fuelled the development of new computational models to detect and monitor the context of the people via streaming data from those devices. A particular task is the recognition of current activity from motion signals acquired from miniature inertial sensors, such as accelerometers, embedded in wearable devices. The problem is formally defined as classification of a single-source triaxial motion signal into one of pre-defined categories of human activities. In this study, we propose a data processing framework based on a generative action model, which is inspired by language models in text processing, to understand actions and explain resulting activity. We show that the model can be used for several tasks such as activity recognition from a completed action or next move prediction in an incomplete action with known activity. The framework was tested on three different benchmark datasets, where the signals were collected from accelerometers worn in chest or wrist and labelled according to different activities relevant to position of the sensor placed. The model achieved 97.7% accuracy for recognizing hand activities using wrist-worn sensors, and 97.8–99% accuracy for recognizing whole-body activities using chest-worn sensors. The experimental results indicate the proposed model can provide an easily interpretable means of activity recognition and outperform many of the existing solutions in terms of classification accuracy. Furthermore, the model provides a strong baseline for next move prediction in an action, which may find applications in robotic simulations, human–computer interaction and synthetic data generation.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"264 ","pages":"Article 125947"},"PeriodicalIF":7.5,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142745663","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Random image masking and in-batch feature mixing for self-supervised learning","authors":"Guiyu Li, Jun Yin","doi":"10.1016/j.eswa.2024.125898","DOIUrl":"10.1016/j.eswa.2024.125898","url":null,"abstract":"<div><div>Contrastive learning has already had a significant impact in the field of self-supervised learning. The contrast of positive and negative samples is critical for contrastive learning. Recently, a revolutionary breakthrough has revealed that it is possible to learn meaningful representations without the need of negative samples. Nevertheless, using two randomly augmented views of the same instance as positive samples inevitably leads to its limitations. The design of positive samples becomes critically important and often necessitates domain-specific expertise. These methods invariably emphasize maximizing the similarity between two views, with a focus on global information invariance: different views of the same image yield approximately similar representations after encoding. Hence, we propose a novel methodology aimed at generating more intricate positive instances at both the image and feature level, termed random image masking and in-batch feature mixing. The former introduces local information loss through random masking of images, compelling the model to learn generalizable representations that focus on local information. The latter generates virtual positive samples by mixing samples within the batch in feature space, breaking free from the limitations of traditional data augmentation. We validate the superiority of our proposed method through experiments on several public datasets, the proposed method significantly enhances the self-supervised learning performance for downstream tasks, particularly in classification and object detection tasks.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"264 ","pages":"Article 125898"},"PeriodicalIF":7.5,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142756832","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Josyl Mariela Rocamora Reyes , Ivan Wang-Hei Ho , Man-Wai Mak
{"title":"Wi-Fi CSI fingerprinting-based indoor positioning using deep learning and vector embedding for temporal stability","authors":"Josyl Mariela Rocamora Reyes , Ivan Wang-Hei Ho , Man-Wai Mak","doi":"10.1016/j.eswa.2024.125802","DOIUrl":"10.1016/j.eswa.2024.125802","url":null,"abstract":"<div><div>Fingerprinting systems based on channel state information (CSI) often rely on updated databases to achieve indoor positioning with high accuracy and resolution of centimeter-level. However, regularly maintaining a large fingerprint database is labor-intensive and computationally expensive. In this paper, we explore the use of deep learning for recognizing long-term temporal CSI data, wherein the site survey was completed weeks before the online testing phase. Compared to other positioning algorithms such as time-reversal resonating strength (TRRS), support vector machines (SVM), and Gaussian classifiers, our deep neural network (DNN) model shows a performance improvement of up to 10% for multi-position classification with centimeter-level resolution. We also exploit vector embeddings, such as i-vectors and d-vectors, which are traditionally employed in speech processing. With d-vectors as the compact representation of CSI, storage and processing requirements can be reduced without affecting performance, facilitating deployments on resource-constrained devices in IoT networks. By injecting i-vectors into a hidden layer, the DNN model originally for multi-position localization can be transformed to location-specific DNN to detect whether the device is static or has moved, resulting in a performance boost from 75.47% to 80.62%. This model adaptation requires a smaller number of recently collected fingerprints as opposed to a full database.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"264 ","pages":"Article 125802"},"PeriodicalIF":7.5,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142745731","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yun Lin , Zhenghai Guo , Qingbin Meng , Chong Li , Tianxing Ma
{"title":"Prediction of peak strength under triaxial compression for sandstone based on ABC-SVM algorithm","authors":"Yun Lin , Zhenghai Guo , Qingbin Meng , Chong Li , Tianxing Ma","doi":"10.1016/j.eswa.2024.125923","DOIUrl":"10.1016/j.eswa.2024.125923","url":null,"abstract":"<div><div>The peak strength is a significant parameter in rock engineering, the traditional empirical strength criteria for rocks show good agreement with test results under specific conditions. However, it is not completely accurate for a wide range of loading stress domains and uncorrelated rock types. In this research, porosity, uniaxial compressive strength (UCS) and confining pressure are selected as input variables, and the artificial bee colony (ABC) algorithm is used to optimize the support vector machine (SVM) model. Finally, we validate and comparatively analyze the applicability of the models based on the testing set and the comprehensive evaluation indexes (namely correlation coefficient (R<sup>2</sup>), root mean square error (RMSE) and mean absolute percentage error (MAPE)). Meanwhile, the cosine amplitude method is applied to analyze the correlation between the peak strength and the input variables. The results indicate that both SVM model and ABC-SVM model are suitable for the prediction of peak strength under triaxial compression. Additionally, the ABC-SVM model obviously has better prediction performance by comparison.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"264 ","pages":"Article 125923"},"PeriodicalIF":7.5,"publicationDate":"2024-11-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142746195","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}