No abstract

In this paper, we investigate an energy cost minimization problem for a smart home in the absence of a building thermal dynamics model with the consideration of a comfortable temperature range. Due to the existence of model uncertainty, parameter uncertainty (e.g., renewable generation output, nonshiftable power demand, outdoor temperature, and electricity price) and temporally-coupled operational constraints, it is very challenging to determine the optimal energy management strategy for scheduling Heating, Ventilation, and Air Conditioning (HVAC) systems and energy storage systems in the smart home. To address the challenge, we first formulate the above problem as a Markov decision process, and then propose an energy management strategy based on Deep Deterministic Policy Gradients (DDPG). It is worth mentioning that the proposed strategy does not require the prior knowledge of uncertain parameters and building thermal dynamics model. Simulation results based on real-world traces demonstrate the effectiveness and robustness of the proposed strategy.

The rapid adoption of mobile devices has dramatically changed the access to various networking services and led to the explosion of mobile service traffic. Mobile service traffic classification has been a crucial task that attracts strong interest in mobile network management and security as well as machine learning communities for past decades. However, with more and more adoptions of encryption over mobile services, it brings a lot of challenges about mobile traffic classification. Although classical machine learning approaches can solve many issues that port and payload-based methods cannot solve, it still has some limitations, such as time-consuming, costly handcrafted features, and frequent features update. With the excellent ability of automatic feature learning, Deep Learning (DL) undoubtedly becomes a highly desirable approach for mobile services traffic classification, especially encrypted traffic. This survey paper looks at emerging research into the application of DL methods to encrypted traffic classification of mobile services and presents a general framework of DL-based mobile encrypted traffic classification. Moreover, we review most of the recent existing work according to dataset selection, model input design, and model architecture. Furthermore, we propose some noteworthy issues and challenges about DL-based mobile services traffic classification.

No abstract

China has 26 species in the tribe Arvicolini. The taxonomic status of these voles remains controversial despite much effort. Herein, we evaluate the taxonomic position of 22 species plus 2 unidentified taxa using mitochondrial DNA gene sequences (cytb + CO1). We also evaluate 18 species and 2 unidentified taxa using morphological data. Phylogenetic analyses of cytb resolve monophyly for the genera Alexandromys, Lasiopodomys, Microtus, Neodon, Proedromys, and Volemys with strong support. Stenocranius clusters with Chionomys but with very weak support. Analyses of concatenated cytb + CO1 resolve the same genera with strong support, but the topology of the tree differs from that of cytb in that Chionomys roots at the base of the tree independent of Stenocranius, which forms the sister-group of Lasiopodomys in a more terminal position. The matrilineal genealogy excludes the type species Arvicola amphibius from the rest of the Arvicolini. This species forms the sister-group of Ondatra with high support. Neodon includes N. irene, N. linzhiensis, N. fuscus, N. leucurus, N. sikimensis, Microtus clarkei, and 2 unidentified specimens. Alexandromys includes the former species Microtus oeconomus, M. kikuchii, M. limnophilus, M. fortis, and M. maximowiczii. Finally, Microtus has the subgenera Blanfordimys, Microtus, Mynomes, Pedomys, Pitymys, and Terricola, which includes the Chinese species M. agrestis, M. arvalis, and Blanfordimys juldaschi. General mixed Yule-coalescent species delimitation modeling demarcates 6 currently recognized species and 2 new species of Neodon. A principal component analysis of the morphological data among 7 matrilines shows that all variables have positive loadings of high magnitude on the 1st component. Canonical discriminant analysis for Neodon (including M. clarkei and 2 unidentified species) correctly classifies 93.0% of specimens. Overall, our analyses support the recognition of Alexandromys, Lasiopodomys, Microtus, Neodon, Proedromys, and Volemys as genera. Stenocranius includes Microtus gregalis, and the genealogical position of Stenocranius remains uncertain. The status of Arvicola requires further study. We assign M. clarkei to Neodon and describe 2 new species of Neodon.