Cuffless blood pressure measurement enables unobtrusive and continuous monitoring that can be integrated with wearable devices to extend healthcare to non-hospital settings. Most of the current research has focused on the estimation of blood pressure based on pulse transit time or pulse arrival time using ECG or peripheral cardiac pulse signals as proximal time references. This study proposed the use of a phonocardiogram (PCG) and ballistocardiogram (BCG), two signals detected noninvasively, to estimate systolic blood pressure (SBP). For this, the PCG and the BCG were simultaneously measured in 21 volunteers in the rest, activity, and post-activity conditions. Different features were considered based on the relationships between these signals. The intervals between S1 and S2 of the PCG and the I, J, and K waves of the BCG were statistically analyzed. The IJ and JK slopes were also estimated as additional features to train the machine-learning algorithm. The intervals S1-J, S1-K, S1-I, J-S2, and I-S2 were negatively correlated with changes in SBP (p-val < 0.01). The features were used as explanatory variables for a regressor based on the Random Forest. It was possible to estimate the systolic blood pressure with a mean error of 3.3 mmHg with a standard deviation of ± 5 mmHg. Therefore, we foresee that this proposal has potential applications for wearable devices that use low-cost embedded systems.

Machine learning, one of the core disciplines of artificial intelligence, is an approach whose main emphasis is analytical model building. In other words, machine learning enables an automaton to make its own decisions based on a previous training process. Machine learning has revolutionized every research sector, including health care, by providing precise and accurate decisions involving minimal human interventions through pattern recognition. This is emphasized in this research, which addresses the issue of “support for diabetic neuropathy (DN) recognition.” DN is a disease that affects a large proportion of the global population. In this research, we have used gait biomarkers of subjects representing a particular sector of population located in southern Mexico to identify persons suffering from DN. To do this, we used a home-made body sensor network to capture raw data of the walking pattern of individuals with and without DN. The information was then processed using three sampling criteria and 23 assembled classifiers, in combination with a deep learning algorithm. The architecture of the best combination was chosen and reconfigured for better performance. The results revealed a highly acceptable classification with greater than 85% accuracy when using these combined approaches.

The current paper presents a structural equation model with four variables (Government, Infrastructure, Proximity to market, and supply chain Agility) affecting the Financial performance of a company. Six hypotheses or relationships among variables are proposed, supposing that Government and market Proximity are key elements to achieve a greater Agility in supply chains, considering the regional Infrastructure to determine the impact on Financial performance in manufacturing companies. The model is validated with data from a survey applied to 225 persons in 65 manufacturing companies located in Ciudad Juárez, Chihuahua, Mexico. The model is evaluated using partial least squares, and the findings indicate that there is a direct and positive effect from the Government on regional Infrastructure with a rate of 0.436. When the Government supports the availability of land, energy resources, transportation, telecommunications, mobile telephones, and other services, a positive change is achieved in the Infrastructure and supply chain Agility. Furthermore, the Government also has a direct and positive effect on the market Proximity at a rate of 0.171; consequently, the regional Infrastructure also has an effect on it. Similarly, the market Proximity directly and positively influences the supply chain Agility, as well as a company’s Financial performance at a rate of 0.506.

Parking occupancy is difficult in most modern cities because of increases in the accessibility and use of motor vehicles, and users generally take several minutes or even hours to find a place to park. In this work, we propose a smart parking prediction model in order to help users locate in advance the availability of parking near the places they plan to visit. For this it is proposed a fog computing architecture that integrates a machine learning algorithm based on AdaBoost to predict parking places hours or days in advance. Additionally, a user interface was developed, which involves the collection of user inputs through a mobile application where the user is prompted to enter the destination location and the prediction time interval. Through extensive experimentation using real-world parking flow data, our proposed algorithm demonstrated an improved level of accuracy compared with alternative prediction methods. Moreover, a simulation was conducted to evaluate the system’s latency when using cloud computing versus our hybrid approach combining both fog and cloud computing. The results showed that employing the fog module in conjunction with cloud computing significantly reduced response delay in comparison with using cloud computing alone.

Positron emission tomography (PET) imaging is widely used in nuclear medicine. However, data acquired by a PET system are generally contaminated with heavy noise, which often persists after image reconstruction. In this paper, a novel non-convex functional is introduced to suitably attenuate noise in PET images. The proposed functional contains a new regularization term defined as a convex combination of two terms: a robust function for border preserving and the L ² semi-norm. The combination coefficient depends on the gradient of the noisy image, so that it allows a selective smoothing of image regions according to their local characteristics. The proposed method has been qualitatively and quantitatively tested on both simulated and measured data, demonstrating its better performance against well-established methods for PET denoising.

Background: Efficient inventory management is critical for sustainability in supply chains. However, maintaining adequate inventory levels becomes challenging in the face of unpredictable demand patterns. Furthermore, the need to disseminate demand-related information throughout a company often relies on cloud services. However, this method sometimes encounters issues such as limited bandwidth and increased latency. Methods: To address these challenges, our study introduces a system that incorporates a machine learning algorithm to address inventory-related uncertainties arising from demand fluctuations. Our approach involves the use of an attention mechanism for accurate demand prediction. We combine it with the Newsvendor model to determine optimal inventory levels. The system is integrated with fog computing to facilitate the rapid dissemination of information throughout the company. Results: In experiments, we compare the proposed system with the conventional demand estimation approach based on historical data and observe that the proposed system consistently outperformed the conventional approach. Conclusions: This research introduces an inventory management system based on a novel deep learning architecture that integrates the attention mechanism with cloud computing to address the Newsvendor problem. Experiments demonstrate the better accuracy of this system in comparison to existing methods. More studies should be conducted to explore its applicability to other demand modeling scenarios.