IoT-Deep Learning Based Activity Recommendation System

The rising use of mobile technology and smart gadgets in the field of health has had a significant impact on the global community.Health professionals are increasingly making use of the benefits of these technologies,resulting in a major improvement in health care both in and out of clinical settings.The Internet of Things(IoT)is a new internet revolution that is a rising research area,particularly in health care.Healthcare Monitoring Systems(HMS)have progressed rapidly as the usage of Wearable Sensors(WS)and smartphones have increased.The existing framework of conventional telemedicine’s store-and-forward method has some issues,including the need for a nearby health centre with dedicated employees and medical devices to prepare patient reports.Patients’health can be continuously monitored using advanced WS that can be fitted or embedded in their bodies.This research proposes an innovative and smart HMS,which is built using recent technologies such as the IoT and Machine Learning(ML).In this study,we present an innovative and intelligent HMS based on cutting-edge technologies such as the IoT and Deep Learning(DL)+Restricted Boltzmann Machine(RBM).This DL+RBM model is clever enough to detect and process a patient’s data using a medical Decision Support System(DSS)to determine whether the patient is suffering from a major health problem and treat it accordingly.The recommended system’s behavior is increasingly investigated using a cross-validation test that determines various demographically relevant standard measures.Through a healthcare DSS,this framework is clever enough to detect and analyze a patient’s data.Experiment results further reveal that the proposed system is efficient and clever enough to deliver health care.The data reported in this study demonstrate the notion.This device is a low-cost solution for people living in distant places;anyone can use it to determine if they have a major health problem and seek treatment by contacting nearby hospitals.

Does knowledge of physical activity recommendations increase physical activity among Chinese college students？ Empirical investigations based on the transtheoretical model

Background: Based on the transtheoretical model, the current study investigated whether awareness of physical activity(PA) recommendations had an impact on the stages of PA behavior change and levels of PA among Chinese college students.Methods: In Study 1, with a cross-sectional study design, 9826 students were recruited, and their knowledge of international PA recommendations,PA stage distribution, and self-reported PA level were surveyed. Pearson's χ2 test was used to test whether those participants who were aware and not aware of PA guidelines were equally distributed across the stages of PA behavior, and independent t test was conducted to test the group difference in the actual levels of PA. In Study 2, 279 students who were not aware of the PA recommendations were randomly allocated to either an intervention group or a control group, and only those in the intervention group were presented with international PA guidelines. In both groups,students' PA stages and PA level were examined before the test and then 4 months post-test. Mc Nemar's test for correlated proportions and repeated-measures analysis of variance were conducted to examine the changes in PA stage membership and PA level after the intervention.Results: Study 1 results revealed that only 4.4% of the surveyed students had correct knowledge of PA recommendations. Those who were aware of the recommendations were in later stages of PA behavior(χ~2(4) = 167.19, p < 0.001). They were also significantly more physically active than those who were not aware of the recommendations(t(443.71) = 9.00, p < 0.001, Cohen's d = 0.53). Study 2 results demonstrated that the intervention group participants who were at the precontemplation and contemplation stages at the pre-test each progressed further in the PA stages in the post-test(χ~2(1) = 112.06, p < 0.001; χ~2(1) = 118.76, p = 0.03, respectively), although no significant change in PA level was observed(t(139) < 1, p = 0.89).Conclusion: The results showed that awareness of the PA recommendations was associated with higher stages and levels of PA behavior, and a brief educational exposure to PA recommendations led to improved stages of PA behavior but no change in the levels of PA among Chinese college students. More effective public health campaign strategies are needed to promote the dissemination of the PA recommendations and to raise the awareness of the Chinese student population.

An Alternative-Service Recommending Algorithm Based on Semantic Similarity

With the development of the Internet of Things(Io T), people's lives have become increasingly convenient. It is desirable for smart home(SH) systems to integrate and leverage the enormous information available from IoT. Information can be analyzed to learn user intentions and automatically provide the appropriate services. However, existing service recommendation models typically do not consider the services that are unavailable in a user's living environment. In order to address this problem, we propose a series of semantic models for SH devices. These semantic models can be used to infer user intentions. Based on the models, we proposed a service recommendation probability model and an alternative-service recommending algorithm. The algorithm is devoted to providing appropriate alternative services when the desired service is unavailable. The algorithm has been implemented and achieves accuracy higher than traditional Hidden Markov Model(HMM). The maximum accuracy achieved is 68.3%.

Joint model of user check-in activities for point-of-interest recommendation

With the rapid development of location-based networks, point-of-interest（POI） recommendation has become an important means to help people discover interesting and attractive locations, especially when users travel out of town. However, because users only check-in interaction is highly sparse, which creates a big challenge for POI recommendation. To tackle this challenge, we propose a joint probabilistic generative model called geographical temporal social content popularity（GTSCP） to imitate user check-in activities in a process of decision making, which effectively integrates the geographical influence, temporal effect, social correlation, content information and popularity impact factors to overcome the data sparsity, especially for out-of-town users. Our proposed the GTSCP supports two recommendation scenarios in a joint model, i.e., home-town recommendation and out-of-town recommendation. Experimental results show that GTSCP achieves significantly superior recommendation quality compared to other state-of-the-art POI recommendation techniques.