Remote monitoring of a fall condition or activities and daily life (ADL) of elderly patients has become one of the essential purposes for modern telemedicine. Internet of Things (IoT) and artificial intelligence (AI) techniques, including machine and deep learning models, have been recently applied in the medical field to automate the diagnosis procedures of abnormal and diseased cases. They also have many other applications, including the real-time identification of fall accidents in elderly patients. The goal of this article is to review recent research whose focus is to develop AI algorithms and methods of fall detection systems (FDS) in the IoT environment. In addition, the usability of different sensor types, such as gyroscopes and accelerometers in smartwatches, is described and discussed with the current limitations and challenges for realizing successful FDSs. The availability problem of public fall datasets for evaluating the proposed detection algorithms are also addressed in this study. Finally, this article is concluded by proposing advanced techniques such as lightweight deep models as one of the solutions and prospects of futuristic smart IoT-enabled systems for accurate fall detection in the elderly.

No abstract

The bio-cell cycle is controlled by a complex biochemical network of signaling pathways. Modeling such challenging networks accurately is imperative for the understanding of their detailed dynamical behavior. In this paper, we construct, analyze, and verify a hybrid Petri net (HPN) model of a complex biochemical network that captures the role of an important protein (namely p53) in deciding the fate of the cell. We model the behavior of the cell nucleus and cytoplasm as two stochastic and continuous Petri nets, respectively, combined together into a single HPN. We use simulative model checking to verify three different properties that capture the dynamical behavior of p53 protein with respect to the intensity of the ionizing radiation (IR) to which the cell is exposed. For each IR dose, 1000 simulation runs are carried out to verify each property. Our verification results showed that the fluctuations in p53, which relies on IR intensity, are compatible with the findings of the preceding simulation studies that have previously examined the role of p53 in cell fate decision.

This paper describes a strategy for verifying data-hazard correctness of out-of-order processors that implement register-renaming. We define a set of predicates to characterize register-renaming techniques and provide a set of model-checking obligations that are sufficient to guarantee that a register-renaming technique satisfies data-hazard correctness. We demonstrate how two register renaming techniques (retirement-register-file and dual-RAT) instantiate our predicates, and present model checking results for the Dual-RAT technique, which is based on the Intel Pentium R 4 processor.