Lightweight LSTM-Based Adaptive CQI Feedback Scheme for IoT Devices.

As the number of Internet of things (IoT) devices increases exponentially, scheduling and managing the radio resources for IoT devices has become more important. To efficiently allocate radio resources, the base station (BS) needs the channel state information (CSI) of devices every time. Hence, each device needs to periodically (or aperiodically) report its channel quality indicator (CQI) to the BS. The BS determines the modulation and coding scheme (MCS) based on the CQI reported by the IoT device. However, the more a device reports its CQI, the more the feedback overhead increases. In this paper, we propose a long short-term memory (LSTM)-based CQI feedback scheme, where the IoT device aperiodically reports its CQI relying on an LSTM-based channel prediction. Additionally, because the memory capacity of IoT devices is generally small, the complexity of the machine learning model must be reduced. Hence, we propose a lightweight LSTM model to reduce the complexity. The simulation results show that the proposed lightweight LSTM-based CSI scheme dramatically reduces the feedback overhead compared with that of the existing periodic feedback scheme. Moreover, the proposed lightweight LSTM model significantly reduces the complexity without sacrificing performance.

Efficacies of Cognitive Interventions in the Elderly with Subjective Cognitive Decline: A Prospective, Three-Arm, Controlled Trial.

BACKGROUND AND PURPOSE: A cognitive intervention (CI) is thought to improve cognition and delay cognitive decline via neuronal plasticity and cognitive resilience. Subjective cognitive decline (SCD) might be the first symptomatic stage of Alzheimer's disease, but few studies have examined the beneficial effect of CIs in SCD. We aimed to determine the efficacy of a 12-week, small-group-based, multidomain CI in elderly patients with SCD. METHODS: Participants diagnosed with SCD (aged 55-75 years) were consecutively allocated to three groups: group 1, which received group-based CI implementation with lifestyle modifications; group 2, which received home-based lifestyle modifications without CI; and group 3, in which no action was taken. The primary outcome variables were the scores on computerized tests of the Cambridge Neuropsychological Test Automated Battery (CANTAB). The secondary outcomes included scores on tests evaluating general cognition, memory, visuospatial, and executive functions, as well as scores for the quality of life (QoL), anxiety, depression, and degree of subjective complaints. Changes in scores during the study period were compared between groups. RESULTS: The study was completed by 56 SCD participants. The baseline characteristics did not differ among the groups. The primary outcomes (CANTAB scores) did not differ among the groups. However, the outcomes for phonemic word fluency, verbal memory, QoL, and mood were better for group 1 than for the other two groups. Improvements in verbal memory function and executive function were related to the baseline cognitive scores and group differences. CONCLUSIONS: CI in SCD seems to be partially beneficial for executive function, memory, QoL, and mood, suggesting that CI is a useful nonpharmacological treatment option in this population.