Search results

This study explores whether a new machine learning method can more accurately predict the movement of stock prices.

This study presents a novel hybrid deep learning model, Residual-CNN-Seq2Seq (RCSNet), to predict the trend of stock price movement. RCSNet integrates the autoregressive integrated moving average (ARIMA) model, convolutional neural network (CNN) and the sequence-to-sequence (Seq2Seq) long–short-term memory (LSTM) model.

The hybrid model is able to forecast both linear and non-linear time-series component of stock dataset. CNN and Seq2Seq LSTMs can be effectively combined for dynamic modeling of short- and long-term-dependent patterns in non-linear time series forecast. Experimental results show that the proposed model outperforms baseline models on S&P 500 index stock dataset from January 2000 to August 2016.

This study develops the RCSNet hybrid model to tackle the challenge by combining both linear and non-linear models. New evidence has been obtained in predicting the movement of stock market prices.

The purpose of this study is to investigate how much visual attention is given to banner ads embedded in Web page content dependent on whether the user’s task is goal- or not goal-oriented, as well as the interplay between attention, banner location, banner click and banner recognition.

The authors used a within-subjects design where 100 participants performed two tasks – reading a news and finding where to click next – on a Web page containing three banner ads embedded into the website content. The authors gathered behavioral and eye-tracking data.

Consumers disregard banner ads when they are performing a focused task (reading news). Visual attention paid to the banners while reading – but not while free browsing – and banner location do not impact ad clicking. In addition, it is not necessary to pay full attention to a banner ad to be able to recognize it afterward.

The strategy of embedding banners in the main content of a Web page leads to higher visual attention when consumers are browsing a Web page compared to a focused task (e.g. reading). It also increases ad recognition over time compared to benchmark levels for ads placed in traditional positions.

Previous studies mainly assessed effectiveness of banners located at the top or lateral of a Web page. The authors used eye tracking as an objective measure of visual attention to banner ads embedded in Web page content and behavioral metrics to assess ad interest and measured ad recognition over time.

Investigar cuánta atención visual se presta a los banners publicitarios incrustados en el contenido de una página Web en función de si la tarea del usuario está orientada a un objetivo o no, así como la interacción entre la atención, la ubicación del banner, el clic en el banner y el reconocimiento del banner.

Se utilizó un diseño entre sujetos en el que 100 participantes realizaban dos tareas – leer una noticia y encontrar dónde hacer clic a continuación – en una página Web que contenía tres banners publicitarios incrustados en el contenido del sitio Web. Se recogieron datos conductuales y de seguimiento ocular.

Los consumidores no prestan atención a los banners publicitarios cuando están realizando una tarea concentrada (leer noticias). La atención visual prestada a los banners durante la lectura – pero no durante la navegación libre – y la ubicación de los banners no influyen en el hecho de hacer clic en los anuncios. Además, no es necesario prestar toda la atención a un banner publicitario para poder reconocerlo después.

Los estudios anteriores evaluaban principalmente la eficacia de los banners situados en la parte superior o lateral de una página Web. Nosotros utilizamos el seguimiento ocular como medida objetiva de la atención visual a los banners incrustados en el contenido de la página Web y métricas de comportamiento para evaluar el interés por el anuncio, y medimos el reconocimiento del anuncio a lo largo del tiempo.

La estrategia de incrustar banners en el contenido principal de una página Web aumenta la atención visual de los consumidores cuando navegan por una página Web en comparación con una tarea específica (por ejemplo, leer). También aumenta el reconocimiento del anuncio a lo largo del tiempo en comparación con los niveles de referencia de los anuncios colocados en posiciones tradicionales.

研究用户对嵌入在网页内容中的横幅广告的视觉注意程度, 取决于用户的任务是否以目标为导向, 以及注意、横幅位置、横幅点击和横幅识别之间的相互作用。

我们采用了主体内设计, 100名参与者在一个含有三个嵌入网站内容的横幅广告的网页上执行两项任务–阅读新闻和寻找下一步的点击位置。我们收集了行为和眼球追踪数据。

消费者在执行重点任务（阅读新闻）时忽略了横幅广告。阅读时对横幅广告的视觉关注–而不是自由浏览时–以及横幅广告的位置并不影响广告点击。此外, 不一定要完全注意横幅广告才能在事后认出它。

以前的研究主要评估位于网页顶部或侧面的横幅广告的效果。我们用眼动仪作为对嵌入网页内容的横幅广告的视觉注意力的客观测量, 用行为指标来评估广告的兴趣, 并测量了广告在一段时间内的识别度。

在网页的主要内容中嵌入横幅广告的策略导致消费者在浏览网页时, 与重点任务（如阅读）相比, 视觉注意力更高。与放置在传统位置的广告的基准水平相比, 它也会随着时间的推移增加广告识别度。

As the tourism industry becomes more vital for the success of many economies around the world, the importance of technology in tourism grows daily. Alongside increasing tourism importance and popularity, the amount of significant data grows, too. On daily basis, millions of people write their opinions, suggestions and views about accommodation, services, and much more on various websites. Well-processed and filtered data can provide a lot of useful information that can be used for making tourists' experiences much better and help us decide when selecting a hotel or a restaurant. Thus, the purpose of this study is to explore machine and deep learning models for predicting sentiment and rating from tourist reviews.

This paper used machine learning models such as Naïve Bayes, support vector machines (SVM), convolutional neural network (CNN), long short-term memory (LSTM) and bidirectional long short-term memory (BiLSTM) for extracting sentiment and ratings from tourist reviews. These models were trained to classify reviews into positive, negative, or neutral sentiment, and into one to five grades or stars. Data used for training the models were gathered from TripAdvisor, the world's largest travel platform. The models based on multinomial Naïve Bayes (MNB) and SVM were trained using the term frequency-inverse document frequency (TF-IDF) for word representations while deep learning models were trained using global vectors (GloVe) for word representation. The results from testing these models are presented, compared and discussed.

The performance of machine and learning models achieved high accuracy in predicting positive, negative, or neutral sentiments and ratings from tourist reviews. The optimal model architecture for both classification tasks was a deep learning model based on BiLSTM. The study’s results confirmed that deep learning models are more efficient and accurate than machine learning algorithms.

The proposed models allow for forecasting the number of tourist arrivals and expenditure, gaining insights into the tourists' profiles, improving overall customer experience, and upgrading marketing strategies. Different service sectors can use the implemented models to get insights into customer satisfaction with the products and services as well as to predict the opinions given a particular context.

This study developed and compared different machine learning models for classifying customer reviews as positive, negative, or neutral, as well as predicting ratings with one to five stars based on a TripAdvisor hotel reviews dataset that contains 20,491 unique hotel reviews.

Solar power forecasting will have a significant impact on the future of large-scale renewable energy plants. Predicting photovoltaic power generation depends heavily on climate conditions, which fluctuate over time. In this research, we propose a hybrid model that combines machine-learning methods with Theta statistical method for more accurate prediction of future solar power generation from renewable energy plants. The machine learning models include long short-term memory (LSTM), gate recurrent unit (GRU), AutoEncoder LSTM (Auto-LSTM) and a newly proposed Auto-GRU. To enhance the accuracy of the proposed Machine learning and Statistical Hybrid Model (MLSHM), we employ two diversity techniques, i.e. structural diversity and data diversity. To combine the prediction of the ensemble members in the proposed MLSHM, we exploit four combining methods: simple averaging approach, weighted averaging using linear approach and using non-linear approach, and combination through variance using inverse approach. The proposed MLSHM scheme was validated on two real-time series datasets, that sre Shagaya in Kuwait and Cocoa in the USA. The experiments show that the proposed MLSHM, using all the combination methods, achieved higher accuracy compared to the prediction of the traditional individual models. Results demonstrate that a hybrid model combining machine-learning methods with statistical method outperformed a hybrid model that only combines machine-learning models without statistical method.

Efficient traffic incident management is needed to alleviate the negative impact of traffic incidents. Accurate and reliable estimation of traffic incident duration is of great importance for traffic incident management. Previous studies have proposed models for traffic incident duration prediction; however, most of these studies focus on the total duration and could not update prediction results in real-time. From a traveler’s perspective, the relevant factor is the residual duration of the impact of the traffic incident. Besides, few (if any) studies have used dynamic traffic flow parameters in the prediction models. This paper aims to propose a framework to fill these gaps.

This paper proposes a framework based on the multi-layer perception (MLP) and long short-term memory (LSTM) model. The proposed methodology integrates traffic incident-related factors and real-time traffic flow parameters to predict the residual traffic incident duration. To validate the effectiveness of the framework, traffic incident data and traffic flow data from Shanghai Zhonghuan Expressway are used for modeling training and testing.

Results show that the model with 30-min time window and taking both traffic volume and speed as inputs performed best. The area under the curve values exceed 0.85 and the prediction accuracies exceed 0.75. These indicators demonstrated that the model is appropriate for this study context. The model provides new insights into traffic incident duration prediction.

The incident samples applied by this study might not be enough and the variables are not abundant. The number of injuries and casualties, more detailed description of the incident location and other variables are expected to be used to characterize the traffic incident comprehensively. The framework needs to be further validated through a sufficiently large number of variables and locations.

The framework can help reduce the impacts of incidents on the safety of efficiency of road traffic once implemented in intelligent transport system and traffic management systems in future practical applications.

This study uses two artificial neural network methods, MLP and LSTM, to establish a framework aiming at providing accurate and time-efficient information on traffic incident duration in the future for transportation operators and travelers. This study will contribute to the deployment of emergency management and urban traffic navigation planning.

This paper aims to develop predictive methods, based on recurrent neural networks, useful to support facility managers in building maintenance tasks, by collecting information coming from a computerized maintenance management system (CMMS).

This study applies data-driven and text-mining approaches to a CMMS data set comprising more than 14,500 end-users’ requests for corrective maintenance actions, collected over 14 months. Unidirectional long short-term memory (LSTM) and bidirectional LSTM (Bi-LSTM) recurrent neural networks are trained to predict the priority of each maintenance request and the related technical staff assignment. The data set is also used to depict an overview of corrective maintenance needs and related performances and to verify the most relevant elements in the building and how the current facility management (FM) relates to the requests.

The study shows that LSTM and Bi-LSTM recurrent neural networks can properly recognize the words contained in the requests, thus correctly and automatically assigning the priority and predicting the technical staff to assign for each end-user’s maintenance request. The obtained global accuracy is very high, reaching 93.3% for priority identification and 96.7% for technical staff assignment. Results also show the main critical building elements for maintenance requests and the related intervention timings.

This work shows that LSTM and Bi-LSTM recurrent neural networks can automate the assignment process of end-users’ maintenance requests if trained with historical CMMS data. Results are promising; however, the trained LSTM and Bi-LSTM RNN can be applied only to different hospitals adopting similar categorization.

The data-driven and text-mining approaches can be integrated into the CMMS to support corrective maintenance management by facilities management contractors, i.e. to properly and timely identify the actions to be carried out and the technical staff to assign.

The improvement of the maintenance of the health-care system is a key component of improving health service delivery. This work shows how to reduce health-care service interruptions due to maintenance needs through machine learning methods.

This study develops original methods and tools easily integrable into IT workflow systems (i.e. CMMS) in the FM field.

This paper presents the Edge Load Management and Optimization through Pseudoflow Prediction (ELMOPP) algorithm, which aims to solve problems detailed in previous algorithms; through machine learning with nested long short-term memory (NLSTM) modules and graph theory, the algorithm attempts to predict the near future using past data and traffic patterns to inform its real-time decisions and better mitigate traffic by predicting future traffic flow based on past flow and using those predictions to both maximize present traffic flow and decrease future traffic congestion.

ELMOPP was tested against the ITLC and OAF traffic management algorithms using a simulation modeled after the one presented in the ITLC paper, a single-intersection simulation.

The collected data supports the conclusion that ELMOPP statistically significantly outperforms both algorithms in throughput rate, a measure of how many vehicles are able to exit inroads every second.

Furthermore, while ITLC and OAF require the use of GPS transponders and GPS, speed sensors and radio, respectively, ELMOPP only uses traffic light camera footage, something that is almost always readily available in contrast to GPS and speed sensors.

Previous dynamic prediction models rarely handle multi-period data with different intervals, and the large-scale patient hospital records are not effectively used to improve the prediction performance. This paper aims to focus on the prediction of cardiovascular disease using the improved long short-term memory (LSTM) model.

A new model based on the traditional LSTM was proposed to predict cardiovascular disease. The irregular time interval is smoothed to obtain the time parameter vector, and it is used as the input of the forgetting gate of LSTM to overcome the prediction obstacle caused by the irregular time interval.

The experimental results show that the dynamic prediction model proposed in this paper obtained a significant better classification performance compared with the traditional LSTM model.

In this paper, the authors improved the LSTM by smoothing the irregular time between different medical stages of the patient to obtain the temporal feature vector.

The recent innovations of Industry 4.0 have made it possible to easily collect data related to a production environment. In this context, information about industrial equipment – gathered by proper sensors – can be profitably used for supporting predictive maintenance (PdM) through the application of data-driven analytics based on artificial intelligence (AI) techniques. Although deep learning (DL) approaches have proven to be a quite effective solutions to the problem, one of the open research challenges remains – the design of PdM methods that are computationally efficient, and most importantly, applicable in real-world internet of things (IoT) scenarios, where they are required to be executable directly on the limited devices’ hardware.

In this paper, the authors propose a DL approach for PdM task, which is based on a particular and very efficient architecture. The major novelty behind the proposed framework is to leverage a multi-head attention (MHA) mechanism to obtain both high results in terms of remaining useful life (RUL) estimation and low memory model storage requirements, providing the basis for a possible implementation directly on the equipment hardware.

The achieved experimental results on the NASA dataset show how the authors’ approach outperforms in terms of effectiveness and efficiency the majority of the most diffused state-of-the-art techniques.

A comparison of the spatial and temporal complexity with a typical long-short term memory (LSTM) model and the state-of-the-art approaches was also done on the NASA dataset. Despite the authors’ approach achieving similar effectiveness results with respect to other approaches, it has a significantly smaller number of parameters, a smaller storage volume and lower training time.

The proposed approach aims to find a compromise between effectiveness and efficiency, which is crucial in the industrial domain in which it is important to maximize the link between performance attained and resources allocated. The overall accuracy performances are also on par with the finest methods described in the literature.

The proposed approach allows satisfying the requirements of modern embedded AI applications (reliability, low power consumption, etc.), finding a compromise between efficiency and effectiveness.

The prediction of stock market (SM) indices is a fascinating task. An in-depth analysis in this field can provide valuable information to investors, traders and policy makers in attractive SMs. This article aims to apply a correlation feature selection model to identify important technical indicators (TIs), which are combined with multiple deep learning (DL) algorithms for forecasting SM indices.

The methodology involves using a correlation feature selection model to select the most relevant features. These features are then used to predict the fluctuations of six markets using various DL algorithms, and the results are compared with predictions made using all features by using a range of performance measures.

The experimental results show that the combination of TIs selected through correlation and Artificial Neural Network (ANN) provides good results in the MADEX market. The combination of selected indicators and Convolutional Neural Network (CNN) in the NASDAQ 100 market outperforms all other combinations of variables and models. In other markets, the combination of all variables with ANN provides the best results.

This article makes several significant contributions, including the use of a correlation feature selection model to select pertinent variables, comparison between multiple DL algorithms (ANN, CNN and Long-Short-Term Memory (LSTM)), combining selected variables with algorithms to improve predictions, evaluation of the suggested model on six datasets (MASI, MADEX, FTSE 100, SP500, NASDAQ 100 and EGX 30) and application of various performance measures (Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error(RMSE), Mean Squared Logarithmic Error (MSLE) and Root Mean Squared Logarithmic Error (RMSLE)).