https://reunir.unir.net/handle/123456789/14285 2026-02-16T21:35:49Z https://reunir.unir.net/handle/123456789/14305 Editor’s Note Yang, Jiachen; Song, Houbing; Khurram Khan, Muhammad With the rapid development of information and communication technologies, artificial intelligence and IoTs, more and more advanced technologies, such as machine learning, reinforcement learning, neural networks and fuzzy systems, have been introduced into industrial practices. The application of advanced technologies has greatly promoted the process of industrial revolution. However, there is big gap between controlled simulation and real evolving environment, which results in the unsatisfactory performance of the typical algorithms in practical environments. For example, in Underwater IoTs, a dynamic and uncertain marine environment can cause equipment damage, resulting in huge financial losses. Therefore, improving the robustness and adaptability of algorithms and systems, and proposing new solutions in practical applications to meet the requirements of self-developing, self-organizing, and evolving systems is essential to promote intelligent industrial applications. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2023-03-08T14:33:40Z No. of bitstreams: 1 ijimai8_1_0_0.pdf: 60247 bytes, checksum: 479d5af4a15b484b21299a0d0b09d351 (MD5); Made available in DSpace on 2023-03-08T14:33:40Z (GMT). No. of bitstreams: 1 ijimai8_1_0_0.pdf: 60247 bytes, checksum: 479d5af4a15b484b21299a0d0b09d351 (MD5) https://reunir.unir.net/handle/123456789/14304 An Efficient Probabilistic Methodology to Evaluate Web Sources as Data Source for Warehousing Sharan Sinha, Hariom; Kumar Choudhary, Saket; Kumar Solanki, Vijender Internet is the largest source of data and the requirement of data analytics have fueled the data warehouse to switch from structured conventional Data Warehouse to complex Web Data Warehouse. The dynamic and complex nature of web poses various types of complexities during synthesis of web data into a conventional warehouse. Multi-Criteria-Decision Making (MCDM) is a prominent mechanism to select the best data for storing into the data-warehouse. In this article, a method, based on the probabilistic analysis of SAW and TOPSIS methods, has been proposed to select web data sources as data sources for web data warehouse. This method deals more efficiently with the dynamic and complex nature of web. Here, the result of the selection employs the analysis of both the methods (SAW and TOPSIS) to evaluate the probability of selection of respective score (1-9) for each feature. With these probability values, the probability of selection of the next web sources has been be determined. Moreover, using the same probability values, mean score and standard deviation of the scores of respective features of selected web sources have been deduced, which are further used to fix the standard score of each feature for selection of web sources. The standard score is a parameter of the proposed Mean-Standard-Deviation (MSD) method to check the suitability of web sources individually, whereas others do the same on comparative basis. The proposed method cuts down the cost of the repetitive comparison operation, once after computation of the Standard score using Mean and Standard deviation of each individual feature. Here, the respective value of the standard score of each feature is only compared with the score of each respective feature of the next web sources, so it reduces the cost of computation and selects the web sources faster as well. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2023-03-08T14:29:34Z No. of bitstreams: 1 ijimai8_1_9_0.pdf: 1385402 bytes, checksum: e91de83950e00b8d900611eb43d65c24 (MD5); Made available in DSpace on 2023-03-08T14:29:34Z (GMT). No. of bitstreams: 1 ijimai8_1_9_0.pdf: 1385402 bytes, checksum: e91de83950e00b8d900611eb43d65c24 (MD5) https://reunir.unir.net/handle/123456789/14303 A Spatio-Temporal Attention Graph Convolutional Networks for Sea Surface Temperature Prediction Chen, Desheng; Wen, Jiabao; Lv, Caiyun Sea surface temperature (SST) is an important index to detect ocean changes, predict SST anomalies, and prevent natural disasters caused by abnormal changes, dynamic variation of which have a profound impact on the whole marine ecosystem and the dynamic changes of climate. In order to better capture the dynamic changes of ocean temperature, it’s vitally essential to predict the SST in the future. A new spatio-temporal attention graph convolutional network (STAGCN) for SST prediction was proposed in this paper which can capture spatial dependence and temporal correlation in the way of integrating gated recurrent unit (GRU) model with graph convolutional network (GCN) and introduced attention mechanism. The STAGCN model adopts the GCN model to learn the topological structure between ocean location points for extracting the spatial characteristics from the ocean position nodes network. Besides, capturing temporal correlation by learning dynamic variation of SST time series data, a GRU model is introduced into the STAGCN model to deal with the prediction problem about long time series, the input of which is the SST data with spatial characteristics. To capture the significance of SST information at different times and increase the accuracy of SST forecast, the attention mechanism was used to obtain the spatial and temporal characteristics globally. In this study, the proposed STAGCN model was trained and tested on the East China Sea. Experiments with different prediction lengths show that the model can capture the spatio-temporal correlation of regional-scale sea surface temperature series and almost uniformly outperforms other classical models under different sea areas and different prediction levels, in which the root mean square error is reduced by about 0.2 compared with the LSTM model. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2023-03-08T14:10:36Z No. of bitstreams: 1 ijimai8_1_6.pdf: 3816814 bytes, checksum: c979aaa13f7cc3fab1abd8850ed7409b (MD5); Made available in DSpace on 2023-03-08T14:10:36Z (GMT). No. of bitstreams: 1 ijimai8_1_6.pdf: 3816814 bytes, checksum: c979aaa13f7cc3fab1abd8850ed7409b (MD5) https://reunir.unir.net/handle/123456789/14295 Using the Statistical Machine Learning Models ARIMA and SARIMA to Measure the Impact of Covid-19 on Official Provincial Sales of Cigarettes in Spain Andueza, Andoni; Del Arco-Osuna, Miguel Ángel; Fornés, Bernat; González-Crespo, Rubén; Martín-Álvarez, Juan Manuel From a public health perspective, tobacco use is addictive by nature and triggers several cancers, cardiovascular and respiratory diseases, reproductive disorders, and many other adverse health effects leading to many deaths. In this context, the need to eradicate tobacco-related health problems and the increasingly complex environments of tobacco research require sophisticated analytical methods to handle large amounts of data and perform highly specialized tasks. In this study, time series models are used: autoregressive integrated moving average (ARIMA) and seasonal autoregressive integrated moving average (SARIMA) to forecast the impact of COVID-19 on sales of cigarette in Spanish provinces. To find the optimal solution, initial combinations of model parameters automatically selected the ARIMA model, followed by finding the optimized model parameters based on the best fit between the predictions and the test data. The analytical tools Autocorrelation Function (ACF), Partial Autocorrelation Function (PACF), Akaike Information Criterion (AIC), and Bayesian Information Criterion (BIC) were used to assess the reliability of the models. The evaluation metrics that are used as criteria to select the best model are: mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE), mean percentage error (MPE), mean error (ME) and mean absolute standardized error (MASE). The results show that the national average impact is slight. However, in border provinces with France or with a high influx of tourists, a strong impact of COVID-19 on tobacco sales has been observed. In addition, the least impact has been observed in border provinces with Gibraltar. Policymakers need to make the right decisions about the tobacco price differentials that are observed between neighboring European countries when there is constant and abundant cross-border human transit. To keep smoking under control, all countries must make harmonized decisions. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2023-03-07T14:25:59Z No. of bitstreams: 1 ijimai8_1_7.pdf: 3695376 bytes, checksum: ad125ea27f7e74c81ad2d02f5b972af0 (MD5); Made available in DSpace on 2023-03-07T14:25:59Z (GMT). No. of bitstreams: 1 ijimai8_1_7.pdf: 3695376 bytes, checksum: ad125ea27f7e74c81ad2d02f5b972af0 (MD5) https://reunir.unir.net/handle/123456789/14294 COVID-19 Disease Prediction Using Weighted Ensemble Transfer Learning Kumar Roy, Pradeep; Singh, Ashish Health experts use advanced technological equipment to find complex diseases and diagnose them. Medical imaging nowadays is popular for detecting abnormalities in human bodies. This research discusses using the Internet of Medical Things in the COVID-19 crisis perspective. COVID-19 disease created an unforgettable remark on human memory. It is something like never happened before, and people do not expect it in the future. Medical experts are continuously working on getting a solution for this deadly disease. This pandemic warns the healthcare system to find an alternative solution to monitor the infected person remotely. Internet of Medical Things can be helpful in a pandemic scenario. This paper suggested a ensemble transfer learning framework predict COVID-19 infection. The model used the weighted transfer learning concept and predicted the COVID- 19 infected people with an F1-score of 0.997 for the best case on the test dataset. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2023-03-07T14:15:11Z No. of bitstreams: 1 ijimai8_1_2.pdf: 3010491 bytes, checksum: 662915d100ed2fbf3de8e7dac2c15780 (MD5); Made available in DSpace on 2023-03-07T14:15:11Z (GMT). No. of bitstreams: 1 ijimai8_1_2.pdf: 3010491 bytes, checksum: 662915d100ed2fbf3de8e7dac2c15780 (MD5) https://reunir.unir.net/handle/123456789/14293 Sentiment Analysis and Classification of Hotel Opinions in Twitter With the Transformer Architecture Arroni, Sergio; Galán, Yerai; Guzmán-Guzmán, Xiomarah; Nuñez-Valdez, Edward Rolando; Gómez, Alberto Sentiment analysis is of great importance to parties who are interested is analyzing the public opinion in social networks. In recent years, deep learning, and particularly, the attention-based architecture, has taken over the field, to the point where most research in Natural Language Processing (NLP) has been shifted towards the development of bigger and bigger attention-based transformer models. However, those models are developed to be all-purpose NLP models, so for a concrete smaller problem, a reduced and specifically studied model can perform better. We propose a simpler attention-based model that makes use of the transformer architecture to predict the sentiment expressed in tweets about hotels in Las Vegas. With their relative predicted performance, we compare the similarity of our ranking to the actual ranking in TripAdvisor to those obtained by more rudimentary sentiment analysis approaches, outperforming them with a 0.64121 Spearman correlation coefficient. We also compare our performance to DistilBERT, obtaining faster and more accurate results and proving that a model designed for a particular problem can perform better than models with several millions of trainable parameters. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2023-03-07T13:58:12Z No. of bitstreams: 1 ijimai8_1_5.pdf: 1019610 bytes, checksum: 0d504615f95590cf76ca3443c1d0c2a3 (MD5); Made available in DSpace on 2023-03-07T13:58:13Z (GMT). No. of bitstreams: 1 ijimai8_1_5.pdf: 1019610 bytes, checksum: 0d504615f95590cf76ca3443c1d0c2a3 (MD5) https://reunir.unir.net/handle/123456789/14292 Blockchain Based Cloud Management Architecture for Maximum Availability Arias Maestro, Alberto; Sanjuán Martínez, Óscar; Teredesai, Ankur M.; García-Díaz, Vicente Contemporary cloud application and Edge computing orchestration systems rely on controller/worker design patterns to allocate, distribute, and manage resources. Standard solutions like Apache Mesos, Docker Swarm, and Kubernetes can span multiple zones at data centers, multiple global regions, and even consumer point of presence locations. Previous research has concluded that random network partitions cannot be avoided in these scenarios, leaving system designers to choose between consistency and availability, as defined by the CAP theorem. Controller/worker architectures guarantee configuration consistency via the employment of redundant storage systems, in most cases coordinated via consensus algorithms such as Paxos or Raft. These algorithms ensure information consistency against network failures while decreasing availability as network regions increase. Mainstream blockchain technology provides a solution to this compromise while decentralizing control via a fully distributed architecture coordinated through Byzantine-resistant consensus algorithms. This research proposes a blockchain-based decentralized architecture for cloud resource management systems. We analyze and compare the characteristics of the proposed architecture concerning the consistency, availability, and partition resistance of architectures that rely on Paxos/Raft distributed data stores. Our research demonstrates that the proposed blockchain-based decentralized architecture noticeably increases the system availability, including cases of network partitioning, without a significant impact on configuration consistency. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2023-03-07T13:45:41Z No. of bitstreams: 1 ijimai8_1_8.pdf: 913686 bytes, checksum: e9f4dff7f3c87f658ee8363bca9a7573 (MD5); Made available in DSpace on 2023-03-07T13:45:41Z (GMT). No. of bitstreams: 1 ijimai8_1_8.pdf: 913686 bytes, checksum: e9f4dff7f3c87f658ee8363bca9a7573 (MD5) https://reunir.unir.net/handle/123456789/14291 An Efficient Bet-GCN Approach for Link Prediction Saxena, Rahul; Pankaj Patil, Spandan; Kumar Verma, Atul; Jadeja, Mahipal; Vyas, Pranshu; Bhateja, Vikrant; Chun-Wei Lin, Jerry The task of determining whether or not a link will exist between two entities, given the current position of the network, is called link prediction. The study of predicting and analyzing links between entities in a network is emerging as one of the most interesting research areas to explore. In the field of social network analysis, finding mutual friends, predicting the friendship status between two network individuals in the near future, etc., contributes significantly to a better understanding of the underlying network dynamics. The concept has many applications in biological networks, such as finding possible connections (possible interactions) between genes and predicting protein-protein interactions. Apart from these, the concept has applications in many other areas of network science. Exploration based on Graph Neural Networks (GNNs) to accomplish such tasks is another focus that is attracting a lot of attention these days. These approaches leverage the strength of the structural information of the network along with the properties of the nodes to make efficient predictions and classifications. In this work, we propose a network centrality based approach combined with Graph Convolution Networks (GCNs) to predict the connections between network nodes. We propose an idea to select training nodes for the model based on high edge betweenness centrality, which improves the prediction accuracy of the model. The study was conducted using three benchmark networks: CORA, Citeseer, and PubMed. The prediction accuracies for these networks are: 95.08%, 95.07%, and 95.3%. The performance of the model is comprehensive and comparable to the other prior art methods and studies. Moreover, the performance of the model is evaluated with 90.13% for WikiCS and 87.7% for Amazon Product network to show the generalizability of the model. The paper discusses in detail the reason for the improved predictive ability of the model both theoretically and experimentally. Our results are generalizable and our model has the potential to provide good results for link prediction tasks in any domain. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2023-03-07T13:26:55Z No. of bitstreams: 1 ijimai8_1_4.pdf: 3433075 bytes, checksum: 3bb4103136d7d2931ab87df24ce17f51 (MD5); Made available in DSpace on 2023-03-07T13:26:55Z (GMT). No. of bitstreams: 1 ijimai8_1_4.pdf: 3433075 bytes, checksum: 3bb4103136d7d2931ab87df24ce17f51 (MD5) https://reunir.unir.net/handle/123456789/14290 Dataset and Baselines for IID and OOD Image Classification Considering Data Quality and Evolving Environments Zhang, Zhuo; Li, Yang; Gong, Yicheng; Yang, Yue; Ma, Shukun; Guo, Xiaolan; Ercisli, Sezai At present, artificial intelligence is in a period of rapid development, and deep learning has begun to be applied in various fields. Data, as a key part of the deep learning, its efficiency and stability, will directly affect the performance of the model, so it is valued by people. In order to make the dataset efficient, many active learning methods have been proposed, the dataset containing independent identically distribution (IID) samples is reduced with excellent performance; in order to make the dataset more stable, it should be solved that the model encounters out-of-distribution (OOD) samples to improve generalization performance. However, the current active learning method design and the method of adding OOD samples lack guidance, and people do not know what samples should be selected and which OOD samples will be added to better improve the generalization performance. In this paper, we propose a dataset containing a variety of elements called a dataset with Complete Sample Elements(CSE), the labels such as rotation angle and distance in addition to the common classification labels. These labels can help people analyze the distribution characteristics of each element of an efficient dataset, thereby inspiring new active learning methods; we also construct a corresponding OOD test set, which can not only detect the generalization performance of the model, but also helps explore metrics between OOD samples and existing dataset to guide the selected method of OOD samples, so that it can improve generalization efficiently. In this paper, we explore the distribution characteristics of efficient datasets in terms of angle element, and confirm that an efficient dataset tends to contain samples with different appearance. At the same time, experiments have proved the positive influence of the addition of OOD samples on the generalization performance of dataset. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2023-03-07T13:03:45Z No. of bitstreams: 1 ijimai8_1_1.pdf: 6576201 bytes, checksum: 4ee9b392f5fdb25f490e679ed2f10c21 (MD5); Made available in DSpace on 2023-03-07T13:03:45Z (GMT). No. of bitstreams: 1 ijimai8_1_1.pdf: 6576201 bytes, checksum: 4ee9b392f5fdb25f490e679ed2f10c21 (MD5) https://reunir.unir.net/handle/123456789/14289 Human Activity Recognition From Sensorised Patient's Data in Healthcare: A Streaming Deep Learning-Based Approach Hurtado, Sandro; García-Nieto, José; Popov, Anton; Navas-Delgado, Ismael Physical inactivity is one of the main risk factors for mortality, and its relationship with the main chronic diseases has experienced intensive medical research. A well-known method for assessing people’s activity is the use of accelerometers implanted in wearables and mobile phones. However, a series of main critical issues arise in the healthcare context related to the limited amount of available labelled data to build a classification model. Moreover, the discrimination ability of activities is often challenging to capture since the variety of movement patterns in a particular group of patients (e.g. obesity or geriatric patients) is limited over time. Consequently, the proposed work presents a novel approach for Human Activity Recognition (HAR) in healthcare to avoid this problem. This proposal is based on semi-supervised classification with Encoder-Decoder Convolutional Neural Networks (CNNs) using a combination strategy of public labelled and private unlabelled raw sensor data. In this sense, the model will be able to take advantage of the large amount of unlabelled data available by extracting relevant characteristics in these data, which will increase the knowledge in the innermost layers. Hence, the trained model can generalize well when used in real-world use cases. Additionally, real-time patient monitoring is provided by Apache Spark streaming processing with sliding windows. For testing purposes, a real-world case study is conducted with a group of overweight patients in the healthcare system of Andalusia (Spain), classifying close to 30 TBs of accelerometer sensor-based data. The proposed HAR streaming deep-learning approach properly classifies movement patterns in real-time conditions, crucial for long-term daily patient monitoring. Submitted by Susana Figueroa Navarro (susana.figueroa.n@unir.net) on 2023-03-07T12:39:36Z No. of bitstreams: 1 ijimai8_1_3.pdf: 3518563 bytes, checksum: 6573b5bd2a0673fa99edd01c4851aa6c (MD5); Made available in DSpace on 2023-03-07T12:39:36Z (GMT). No. of bitstreams: 1 ijimai8_1_3.pdf: 3518563 bytes, checksum: 6573b5bd2a0673fa99edd01c4851aa6c (MD5)