Search

Abstract Background Traditionally, existing studies assessing the health associations of accelerometer-measured movement behaviors have been performed with few averaged values, mainly representing the duration of physical activities and sedentary behaviors. Such averaged values cannot naturally capture the complex interplay between the duration, timing, and patterns of accumulation of movement behaviors, that altogether may be codependently related to health outcomes in adults. In this study, we introduce a novel approach to visually represent recorded movement behaviors as images using original accelerometer outputs. Subsequently, we utilize these images for cluster analysis employing deep convolutional autoencoders. Methods Our method involves converting minute-by-minute accelerometer outputs (activity counts) into a 2D image format, capturing the entire spectrum of movement behaviors performed by each participant. By utilizing convolutional autoencoders, we enable the learning of these image-based representations. Subsequently, we apply the K-means algorithm to cluster these learned representations. We used data from 1812 adult (20–65 years) participants in the National Health and Nutrition Examination Survey (NHANES, 2003–2006 cycles) study who worn a hip-worn accelerometer for 7 seven consecutive days and provided valid accelerometer data. Results Deep convolutional autoencoders were able to learn the image representation, encompassing the entire spectrum of movement behaviors. The images were encoded into 32 latent variables, and cluster analysis based on these learned representations for the movement behavior images resulted in the identification of four distinct movement behavior profiles characterized by varying levels, timing, and patterns of accumulation of movement behaviors. After adjusting for potential covariates, the movement behavior profile characterized as “Early-morning movers” and the profile characterized as “Highest activity” both had lower levels of insulin (P

Understanding the impact of Climate Variability (CV) on crop yield is crucial for developing sustainable agriculture practices, especially in regions vulnerable to climate change. This study aims to identify the causes of the observed decline in potato yield in Northern Finland by analyzing Remote Sensing data and statistical analysis on climatic variables from 2001 to 2020. First, the exception years with critical production (2004, 2006, 2008, 2012, 2015) were selected based on the anomaly in the annual potato yield. Then a variety of extreme indices based on precipitation and Land Surface Temperature occurrence and intensity during the growing season were calculated to find how much impact they have on potato yield. Principal Component Analysis was used to select the most significant ones among the extreme indices. Finally, through a multiple regression analysis, we found that extreme precipitation events and cumulative temperature explain around 48 % potato yield variations in which extreme precipitation (with 38 %) had much more impact than cumulative temperature (with 10 %). We concluded that one degree increase in cumulative temperature increases potato yield by 19.64 kg/ha and in contrast, heavy precipitation plays a negative role, i.e., one day increase in extreme precipitation events, decreases potato yield by 2085 kg/ha.

With increased digitalization and e-government services, Artificial Intelligence (AI) gained momentum. This paper focuses on AI-governance in Child Social Care field, exploring how aspects of individual, family/community factors are embedded in organizational level, especially when dealing with children resilience and wellbeing. A three-level based review has been conducted. In the first part we explored the interlink between individual factors associated to either resilience or wellbeing are connected to community and governance level where a new conceptual model is provided. In the second phase, we conducted an in-depth systematic literature review using PRISMA review protocol where new categorizations of identified literature with respect to individual, family and community levels in child social care field were suggested, while in the third phase, a review of relevant AI-initiatives in Europe and USA was performed. Finally, a comprehensive discussion of the literature review outcomes was carried out and a new updated conceptual model was provided.

Over the past few years, the number and volume of data sources in healthcare databases has grown exponentially. Analyzing these voluminous medical data is both opportunity and challenge for knowledge discovery in health informatics. In the last decade, social network analysis techniques and community detection algorithms are being used more and more in scientific fields, including healthcare and medicine. While community detection algorithms have been widely used for social network analysis, a comprehensive review of its applications for healthcare in a way to benefit both health practitioners and the health informatics community is still overwhelmingly missing. This paper contributes to fill in this gap and provide a comprehensive and up-to-date literature research. Especially, categorizations of existing community detection algorithms are presented and discussed. Moreover, most applications of social network analysis and community detection algorithms in healthcare are reviewed and categorized. Finally, publicly available healthcare datasets, key challenges, and knowledge gaps in the field are studied and reviewed.

Abstract Food recommendation systems have been increasingly developed in online food services to make recommendations to users according to their previous diets. Although unhealthy diets may cause challenging diseases such as diabetes, cancer, and premature heart diseases, most of the developed food recommendation systems neglect considering health factors in their recommendation process. This emphasizes the importance of the reliability of the recommendation from the health content perspective. This paper proposes a new food recommendation system based on health-aware reliability measurement. In particular, we develop a time-aware community detection approach that groups users into disjoint sets and utilizes the identified communities as the nearest neighbors set in rating prediction. Then, a novel reliability measurement is introduced by considering both the health and accuracy criteria of predictions to evaluate the reliability of predicted ratings. Also, the unreliable predictions are recalculated by removing ineffective users from the nearest neighbors set. Finally, the recalculated predictions are utilized to generate a list of foods as recommendations. Different experiments on a crawled dataset demonstrate that the proposed method enhances the performance around 7.63%, 6.97%, 7.37%, 15.09%, and 16.17% based on precision, recall, F1, normalized discounted cumulative gain (NDCG), and health metrics, respectively, compared to the second-best model.

Abstract This paper investigates car parking users’ behaviors from social media perspective using social network based analysis of online communities revealed by mining the associated hashtags in Twitter. We propose a new interpretable community detection approach for mapping user’s car parking behavior by combining Clique, K-core and Girvan–Newman community detection algorithms together with a content-based analysis that exploits polarity, relative frequency and dominant topics. Twitter API was used to collect relevant data by tracking popular car-parking hashtags. A social network graph is constructed using a similarity-based analysis. Finally, interpretable communities are inferred by monitoring the outcomes of clique, K-core and Girvan–Newman community detection algorithms. This interpretability is linked to the aggregation of keywords, hashtags and/or location attributes of the tweet messages as well as a visualization module that enables interaction with users. In parallel, a global trend analysis investigates parking types and Twitter influence with respect to both sentiment polarity and dominant trends (extracted using KeyBERT based approach) is performed. The implementation of this social media analytics has uncovered several aspects associated to car-parking behaviors. A comparison with some state-of-the-art community detection methods has also been carried out and revealed some similarities with our developed approach.

Food recommender-systems are considered an effective tool to help users adjust their eating habits and achieve a healthier diet. This paper aims to develop a new hybrid food recommender-system to overcome the shortcomings of previous systems, such as ignoring food ingredients, time factor, cold start users, cold start food items and community aspects. The proposed method involves two phases: food content-based recommendation and user-based recommendation. Graph clustering is used in the first phase, and a deep-learning based approach is used in the second phase to cluster both users and food items. Besides a holistic-like approach is employed to account for time and user-community related issues in a way that improves the quality of the recommendation provided to the user. We compared our model with a set of state-of-the-art recommender-systems using five distinct performance metrics: Precision, Recall, F1, AUC and NDCG. Experiments using dataset extracted from “Allrecipes.com” demonstrated that the developed food recommender-system performed best.

Abstract Without deploying face anti‐spoofing countermeasures, face recognition systems can be spoofed by presenting a printed photo, a video, or a silicon mask of a genuine user. Thus, face presentation attack detection (PAD) plays a vital role in providing secure facial access to digital devices. Most existing video‐based PAD countermeasures lack the ability to cope with long‐range temporal variations in videos. Moreover, the key‐frame sampling prior to the feature extraction step has not been widely studied in the face anti‐spoofing domain. To mitigate these issues, this paper provides a data sampling approach by proposing a video processing scheme that models the long‐range temporal variations based on Gaussian weighting function (GWF). Specifically, the proposed scheme encodes the consecutive t frames of video sequences into a single RGB image based on a Gaussian‐weighted summation of the t frames. Using simply the data sampling scheme alone, it is demonstrated here that state‐of‐the‐art performance can be achieved without any bells and whistles in both intra‐database and inter‐database testing scenarios for the three public benchmark datasets; namely, replay‐Attack, MSU‐MFSD, and CASIA‐FASD. In particular, the proposed scheme provides a much lower error (from 15.2% to 7.6% on CASIA‐FASD and 5.9% to 4.9% on replay‐attack) compared to baselines in cross‐database scenarios.

In food diet communication domain, images convey important information to capture users' attention beyond the traditional ingredient content, making it crucial to influence user-decision about the relevancy of a given diet. By using a deep learning-based image clustering method, this paper proposes an Explainable Food Recommendation system that uses the visual content of food to justify their recommendations. n the recommendation system. Especially, a new similarity score based on a tendency measure that quantifies the extent to which user community prefers a given food category is introduced and incorporated in the recommendation. Finally, a rule-based explainability is introduced to enhance transparency and interpretability of the recommendation outcome. Our experiments on a crawled dataset showed that the proposed method enhances recommendation quality in terms of precision, recall, F1, and Normalized Discounted Cumulative Gain (NDCG) by 7.35%, 6.70%, 7.32% and 14.38%, respectively, when compared to other existing methodologies for food recommendation. Besides ablation study is performed to demonstrate the technical soundness of the various components of our recommendation system.

Several Artificial Intelligence-based models have been developed for cancer prediction. In spite of the promise of artificial intelligence, there are very few models which bridge the gap between traditional human-centered prediction and the potential future of machine-centered cancer prediction. In this study, an efficient and effective model is developed for gene selection and cancer prediction. Moreover, this study proposes an artificial intelligence decision system to provide physicians with a simple and human-interpretable set of rules for cancer prediction. In contrast to previous deep learning-based cancer prediction models, which are difficult to explain to physicians due to their black-box nature, the proposed prediction model is based on a transparent and explainable decision forest model. The performance of the developed approach is compared to three state-of-the-art cancer prediction including TAGA, HPSO and LL. The reported results on five cancer datasets indicate that the developed model can improve the accuracy of cancer prediction and reduce the execution time.

Abstract Positioning and location estimation of targets either for mobile or stationary nodes is very important, especially after the astonishing developments of the wired and/or wireless communications, as well as the popularity of handheld devices. To assist in accessing services or managing resources, numerous users, application developers, and service providers require accurate position information. Owing to the boom of multisensory systems, wireless technology, and autonomous systems, many positioning systems have been proposed. These positioning systems differ based on the adopted technology, type of sensory information, communication protocol, algorithm, and accuracy level. These different approaches impose a non-negligible amount of uncertainty and challenges; in such case, fuzzy-logic-based localization systems offer an attractive and feasible approach to overcome some of the reported challenges and handle uncertainties, depending on its proven mathematical framework for handling vagueness and uncertainty. Intuitively, fuzzy sets and fuzzy inference systems are initially intended to incorporate granularity and flexibility of human knowledge, which characterize complex system behaviors without explicitly requiring precise mathematical models or when a complete and exhaustive list of comprehending factors are ill known. This study demonstrates the benefits of fuzzy sets, fuzzy logic, and fuzzy inference systems in wireless positioning problems. Notably, as a way to benefit both the academic community and practitioners of system positioning, we review and investigate various fuzzy-related techniques and methodologies. To the best of our knowledge, this is the first comprehensive review that focuses solely on fuzzy-based positioning systems.

Several Artificial Intelligence-based models have been developed for COVID-19 disease diagnosis. In spite of the promise of artificial intelligence, there are very few models which bridge the gap between traditional human-centered diagnosis and the potential future of machine-centered disease diagnosis. Under the concept of human-computer interaction design, this study proposes a new explainable artificial intelligence method that exploits graph analysis for feature visualization and optimization for the purpose of COVID-19 diagnosis from blood test samples. In this developed model, an explainable decision forest classifier is employed to COVID-19 classification based on routinely available patient blood test data. The approach enables the clinician to use the decision tree and feature visualization to guide the explainability and interpretability of the prediction model. By utilizing this novel feature selection phase, the proposed diagnosis model will not only improve diagnosis accuracy but decrease the execution time as well.

The research focus in remote sensing scene image classification has been recently shifting towards deep learning (DL) techniques. However, even the state-of-the-art deep-learning-based models have shown limited performance due to the inter-class similarity and the intra-class diversity among scene categories. To alleviate this issue, we propose to explore the spatial dependencies between different image regions and introduce patch-based discriminative learning (PBDL) for remote sensing scene classification. In particular, the proposed method employs multi-level feature learning based on small, medium, and large neighborhood regions to enhance the discriminative power of image representation. To achieve this, image patches are selected through a fixed-size sliding window, and sampling redundancy, a novel concept, is developed to minimize the occurrence of redundant features while sustaining the relevant features for the model. Apart from multi-level learning, we explicitly impose image pyramids to magnify the visual information of the scene images and optimize their positions and scale parameters locally. Motivated by this, a local descriptor is exploited to extract multi-level and multi-scale features that we represent in terms of a codeword histogram by performing k-means clustering. Finally, a simple fusion strategy is proposed to balance the contribution of individual features where the fused features are incorporated into a bidirectional long short-term memory (BiLSTM) network. Experimental results on the NWPU-RESISC45, AID, UC-Merced, and WHU-RS datasets demonstrate that the proposed approach yields significantly higher classification performance in comparison with existing state-of-the-art deep-learning-based methods.

Medical image captioning is a very challenging task that has been rarely addressed in the literature on natural image captioning. Some existing image captioning techniques exploit objects present in the image next to the visual features while generating descriptions. However, this is not possible for medical image captioning when one requires following clinician-like explanations in image content descriptions. Inspired by the preceding, this paper proposes using medical concepts associated with images, in accordance with their visual features, to generate new captions. Our end-to-end trainable network is composed of a semantic feature encoder based on a multi-label classifier to identify medical concepts related to images, a visual feature encoder, and an LSTM model for text generation. Beam search is employed to ensure the best selection of the next word for a given sequence of words based on the merged features of the medical image. We evaluated our proposal on the ImageCLEF medical captioning dataset, and the results demonstrate the effectiveness and efficiency of the developed approach.

In the drastic period of climate change the con- tinuous data monitoring of snow characteristic is required.The immensely impact of snow on hydro production, water resource management and its inhabitants, drive to the need for the importance of snow information such as its extent, dynamics and water it holds at global and local scale. At present, there are various approaches such as traditional ground-based approach, optical satellite imaging and the radio, which are available for snow monitoring at global scale. However, the use of these approaches incurs from large labor and high monitoring cost. Since, the advance in sensor technologies and Internet of Things (Iot), provides an appealing possibility to develop a framework for monitoring snow parameters at enormously low cost. In this study. we implemented two machine learning classifiers model based on the input acquired from the low-cost wearable sensor platform. The results of Random forest classifier showed the accuracy of 88.8%, indicate a promising alternative in snow depth measurements with in-situ validation, when data or wireless sensor network are not available or affordable.

This paper suggests a novel sentence-to-sentence similarity measure. The proposal makes use of both word embedding and named-entity based semantic similarity. This is motivated by the increasing short text phrases that contain named-entity tags and the importance to detect various levels of hidden semantic similarity even in case of high noise ratio. The proposal is evaluated using a set of publicly available datasets as well as an in-house built dataset, while comparison with some state of art algorithms is performed.

Vegetation height plays a crucial role in various ecological and environmental applications, such as biodiversity assessment and monitoring, landscape characterization, conser- vation planning and disaster management. Its estimation is traditionally based on in situ measurements or airborne Light Detection and Ranging sensors. However, such methods are often proven insufficient in covering large area landscapes due to high demands in cost, labor and time. Since, the emergence of wearable technology, ubiquitous sensors and Internet of Things offers an appealing framework for monitoring environmental parameters at extremely low cost, which, in turn, contributes to the development of affordable real-time vegetation monitoring system. This is especially relevant to rural environments and underdeveloped countries. We proposed a methodology for data acquisition from a ubiquitous sensor wearable platform and developed a machine-learning model to learn vegetation height on the basis attribute associated with pressure sensor. The proposed methods are proven particularly effective in a region where the land has forestry structure. The results of linear regression model (r2 = 0.81 and RSME = 16.73 cm) and multi-regression model (r2= 0.83 and RSME = 15.73 cm), indicate a promising alternative in vegetation height estimation when in situ or Light Detection and Ranging data or wireless sensor network are not available or affordable, thus facilitating and reducing the cost of ecological monitoring and environmental sustainability planning tasks.

This paper examines the development of an auto- matic summarizer for storytelling. The approach makes use of semantic role labelling and co-referencing in natural language processing. The developed approach has been tested and eval- uated using BBC news summary dataset and Grimm Hansel Gretel novel dataset where a comparison with a state of art TextRank summarizer has been carried out. The results demonstrate the feasibility of the proposal and pave the way for new enhancement of the model to take into account additional constraints that can be imposed on the summarizer