This study presents a comprehensive analysis of methods, techniques, and technologies employed in facial emotion recognition in human-robot interaction (HRI). A total of 124 articles were reviewed, selected based on s...
详细信息
ISBN:
(数字)9798331521950
ISBN:
(纸本)9798331521967
This study presents a comprehensive analysis of methods, techniques, and technologies employed in facial emotion recognition in human-robot interaction (HRI). A total of 124 articles were reviewed, selected based on specific criteria, resulting in 80 relevant studies for analysis. Techniques such as CNNs, Transfer Learning, and ViT stand out for their effectiveness, while approaches like HOG and LBP remain relevant in lowcost scenarios. Widely used datasets, such as FER-2013 and CK+, demonstrate robustness, and hardware solutions range from highperformance setups to accessible options like Google Colab. The study concludes by highlighting the importance of multimodal techniques and the potential of approaches such as ViT and MTL, proposing strategies to overcome variability challenges and adapt to real classroom conditions.
The approaches that currently constitute the state-of-the-art for the task of regression on continuous data streams usually involve ensembles, regression trees, and regression rules. They have been found to work very ...
The approaches that currently constitute the state-of-the-art for the task of regression on continuous data streams usually involve ensembles, regression trees, and regression rules. They have been found to work very well for certain situations but generally consume computational resources to a prohibitive extent. In this paper, we propose a new method based on an ensemble of linear regressions for the regression task adapted to handle continuous data streams. The technique has been named Adaptive Linear Regression (ALR). The algorithm combines strategies that contribute to high prediction accuracy using (i) distinct sliding window sizes for training each ensemble element, and (ii) a dynamic regressor selection method for final ensemble voting. After an extensive experimental study, ALR was found to exhibit high predictive performance and outperform state-of-the-art ensemble regressors on data streams for real and synthetic datasets. Moreover, it exhibits low processing time in its parallel version and is faster than ARF-Reg in its serial version. The paper also presents an analysis of how the choice of sliding window size for training favors accuracy.
In an era of information overload, manually annotating the vast and growing corpus of documents and scholarly papers is increasingly impractical. Automated keyphrase extraction addresses this challenge by identifying ...
详细信息
ISBN:
(数字)9798350362480
ISBN:
(纸本)9798350362497
In an era of information overload, manually annotating the vast and growing corpus of documents and scholarly papers is increasingly impractical. Automated keyphrase extraction addresses this challenge by identifying representative terms within texts. However, most existing methods focus on short documents (up to 512 tokens), leaving a gap in processing long-context documents. In this paper, we introduce LongKey, a novel framework for extracting keyphrases from lengthy documents, which uses an encoder-based language model to capture extended text intricacies. LongKey uses a max-pooling embedder to enhance keyphrase candidate representation. Validated on the comprehensive LDKP datasets and six diverse, unseen datasets, LongKey consistently outperforms existing unsupervised and language model-based keyphrase extraction methods. Our findings demonstrate LongKey’s versatility and superior performance, marking an advancement in keyphrase extraction for varied text lengths and domains.
Social media has been a data source for various applications, given its characteristic of working as a social sensor. Many applications in several areas, such as brand reputation and online opinion monitoring, use thi...
Social media has been a data source for various applications, given its characteristic of working as a social sensor. Many applications in several areas, such as brand reputation and online opinion monitoring, use this valuable resource to understand the users of services and products. This paper describes an application in the soccer domain, considering data collected from a social media textual data stream. The goal is to detect possible sentiment drifts related to actual events in a soccer match. This task is challenging as we resort to short texts made available during a short time (match length). We evaluated four drift detectors using four metrics: false alarms, delay (considering the number of posts), delay, and missing drifts. Our results show that ADWIN had a stable performance in sentiment drift detection compared to other methods in timely detecting the flagged drifts, raising a small number of false alarms. Given the drifts detected, we used Incremental Word-Vectors to monitor words of interest and check their relatedness to actual events in the match. We empirically assert that the closest words trace back to the sentiment drift generator events.
Peaks in time series represent significant events in the measurements of a phenomenon over time, such as a sudden increase in the sales of an item on a specific day of the week. Predicting peaks in advance can support...
详细信息
ISBN:
(数字)9798350359312
ISBN:
(纸本)9798350359329
Peaks in time series represent significant events in the measurements of a phenomenon over time, such as a sudden increase in the sales of an item on a specific day of the week. Predicting peaks in advance can support decision-making in various domains. For example, predicting demand for healthcare services helps adjust nurses’ work schedules in a hospital. This paper proposes a time series mining task named peak prediction, from which most applications that manage resources based on expected demand can benefit. We investigate various approaches, such as conventional machine learning and deep learning methods, to build global and individual models for peak prediction in time series. We evaluate these approaches in a load demand problem on smart meter energy consumption. In this task, a model predicts the customer’s maximum daily energy consumption in the following days (7 days ahead) and identifies which day it will occur. Accurate peak demand predictions for the consumers in a region help utility companies make informed decisions regarding capacity planning, load balancing, and integrating renewable energy sources. Since we are interested in two target variables simultaneously (i.e., peak magnitude and peak position), we evaluated whether multi-target approaches improve single-target models’ performance by correlating both targets in the learning process. Our experimental evaluation considers a dataset comprising three years of daily energy consumption from 1,757 customers. The results show the potential of individual machine learning models induced by simple algorithms such as Linear Regression and XGBoost and multi-target methods’ lack of contribution (or even negative impact) for the performance.
Process Mining (PM) is a research discipline that helps organizations track and optimize processes to support their business. Further, it focuses on providing process analysis techniques and tools, and several of its ...
Process Mining (PM) is a research discipline that helps organizations track and optimize processes to support their business. Further, it focuses on providing process analysis techniques and tools, and several of its applications have been described in the literature. The start point for PM is using event logs generated by information systems to analyze processes. These event logs need to be extracted from databases and prepared for use because the quality of the event logs used as input is critical to the success of any PM effort. In this article, we present a systematic mapping review to provide the reader with highlights of the state-of-the-art techniques for event log preparation. Based on the retrieved studies, we identified six main categories of log preparation techniques: extraction, cleaning, repair, non-adequate granularity, quality evaluation, and privacy. The results are explored quantitatively and qualitatively. All results are made available through spreadsheets and charts. We believe this paper is a starting point for researchers to identify the studies that would help them prepare event logs for PM.
Fuels are crucial for any country's development and economy, impacting various sectors such as transportation, industry, and electricity generation. Accurate prediction of monthly fuel demand can improve supply ch...
详细信息
ISBN:
(数字)9798350374889
ISBN:
(纸本)9798350374896
Fuels are crucial for any country's development and economy, impacting various sectors such as transportation, industry, and electricity generation. Accurate prediction of monthly fuel demand can improve supply chain management, strategic decision-making, and financial planning for businesses while helping governments develop decarbonization policies and estimate pollutant emissions. This paper explores machine learning models to forecast fossil fuels and biofuel demand 12 months ahead, using univariate time series data representing the historical sales of 27 Brazilian states, one of the world's leading producers and consumers of fuels. We evaluate different time series feature sets, machine learning regression models, and prediction strategies to address the complexity of fuel sales influenced by factors such as economic conditions and geopolitical events. Our comprehensive evaluation aims to determine an effective setting for predictive models in the fuel domain. Our results show that popular feature extractors for time series, such as Catch22 and TsFresh, cannot improve the original data representation for most forecasting models. Although focused on Brazil, our findings apply to other countries, since the trained models do not rely on external variables, such as micro and macroeconomic indicators.
In recent decades, there has been a significant increase in the presence of robots in the daily operations of industries. Automated Guided Vehicles (AGVs) used in industrial environments are gaining prominence due to ...
详细信息
ISBN:
(数字)9798331521554
ISBN:
(纸本)9798331521561
In recent decades, there has been a significant increase in the presence of robots in the daily operations of industries. Automated Guided Vehicles (AGVs) used in industrial environments are gaining prominence due to their numerous applications, ranging from logistic tasks such as material transport to more complex process tasks like replacing conveyor belts in production lines. For a mobile robot to operate in these environments, it must possess skills to perform its functions and ensure safety. In this regard, simulating a computational model of a real autonomous system can contribute to developing new operational strategies. The objective of this work is to explore the use of a Digital Twin for an Automated Guided Vehicle (AGV), aiming to design and validate navigation and obstacle avoidance algorithms, with the intent to optimize the operation of these devices in industrial environments. In the current study, the AGV G3R1000 was used, which was modeled in detail in FUSION 360 software, along with a production line from the AGVS company in Brazil. As validation, the digital robot was used to design the navigation software using the PID control system and obstacle avoidance using Fuzzy control. The algorithm developed in the digital robot was applied to the real robot, and a performance comparison was made. In conclusion, it is possible to use the simulated robot to design algorithms for the real robot, saving resources such as time and equipment.
Dynamic classifier selection (DCS) regards well-known machine learning techniques in the batch setting that leverage ensemble performance. Most of the methods use similarity-based methods as a proxy, culminating in hi...
Dynamic classifier selection (DCS) regards well-known machine learning techniques in the batch setting that leverage ensemble performance. Most of the methods use similarity-based methods as a proxy, culminating in high computation costs and becoming unfeasible in many streaming scenarios. In this paper, we propose a DCS method able to cope with the high-speed streaming setting, which is based on the performance of base learners in the most recent instances. The impact of our method is evaluated with different ensembles for data streams. We also propose modifications to an Online Boosting method, which has its performance improved with DCS. Our method increases the accuracy and kappa statistic of state-of-the-art ensembles with low overhead of time processing and memory.
In this paper we investigate the suitability of different types of Dynamic Classifier Selection approaches for the task of multimodal music mood classification. The dynamic selection methods evaluated were: KNORA-UNIO...
In this paper we investigate the suitability of different types of Dynamic Classifier Selection approaches for the task of multimodal music mood classification. The dynamic selection methods evaluated were: KNORA-UNION, KNORAELIMINATE, Dynamic Ensemble Selection Performance, Overall Local Accuracy, Local Class Accuracy, Multiple Classifier Behaviour, A Priori and A Posteriori. The experiments were performed using the Brazilian Music Mood Database, which is a multimodal database, containing the audio signal itself, beyond their visual representation (i.e. spectrogram) and the lyrics. The obtained results have shown that the use of dynamic classifier selection methods can improve the classification results for the task at hand.
暂无评论