Exploring Content Popularity in Information-Centric Networks

Information-Centric Networking(ICN), an alternative architecture to the current Internet infrastructure, focuses on the distribution and retrieval of content by employing caches in a network to reduce network traffic. The employment of caches may be accomplished using graph-based and content-based criteria such as the position of a node in a network and content popularity. The contribution of this paper lies on the characterization of content popularity for on-path in-network caching. To this end, four dynamic approaches for identifying content popularity are evaluated via simulations. Content popularity may be determined per chunk or per object, calculated by the number of requests for a content against the sum of requests or the maximum number of requests. Based on the results, chunk-based approaches provide 23% more accurate content popularity calculations than object-based approaches. In addition, approaches that are based on the comparison of a content against the maximum number of requests have been shown to be more accurate than the alternatives.

Autism Spectrum Disorder Prediction by an Explainable Deep Learning Approach

Autism Spectrum Disorder (ASD) is a developmental disorderwhose symptoms become noticeable in early years of the age though it canbe present in any age group. ASD is a mental disorder which affects the communicational, social and non-verbal behaviors. It cannot be cured completelybut can be reduced if detected early. An early diagnosis is hampered by thevariation and severity of ASD symptoms as well as having symptoms commonly seen in other mental disorders as well. Nowadays, with the emergenceof deep learning approaches in various fields, medical experts can be assistedin early diagnosis of ASD. It is very difficult for a practitioner to identifyand concentrate on the major feature’s leading to the accurate prediction ofthe ASD and this arises the need for having an automated approach. Also,presence of different symptoms of ASD traits amongst toddlers directs tothe creation of a large feature dataset. In this study, we propose a hybridapproach comprising of both, deep learning and Explainable Artificial Intelligence (XAI) to find the most contributing features for the early and preciseprediction of ASD. The proposed framework gives more accurate predictionalong with the recommendations of predicted results which will be a vital aidclinically for better and early prediction of ASD traits amongst toddlers.

Link Quality Prediction for 802.11 MANETs in Urban Microcells

In this paper we derive the optimal link quality predictor (LQPR) whose parameters are estimated from signal power and node speed samples. We propose a fast estimator for these parameters whose computational complexity is three orders lower than that of the optimal estimator with only a slight loss in accuracy thus enabling real- time execution. We show that using the most recent local mean of the signal as a predictor of future signal strength is also a very close approximation to the optimal predictor. This is the central result of this paper. It obviates the need for complex and/or computationally intensive link quality predictors for 802.11 in urban microcells and has the advantage of not requiring node speed information. The LQPRs are evaluated against the lower error bound. We show that the LQPR based on the most recent local mean of the signal predicts the packet reception probability for pedestrians in urban microcells on average with a mean absolute error of 13.47%, 16.54%, 18.21% and 19.38% for 1 s, 2 s, 3 s and 4 s into the future respectively. This LQP accuracy resembles closely the lower error bound with, for example, a difference of only 2.47% at 2 s into the future.

Functional group richness increases multifunctionality in intensively managed grasslands

Background:Agricultural yields have increased continuously over the last few decades.However,a focus solely on production can harm the environment.Diversification of agriculture has been suggested to increase production and sustainability.Biodiversity experiments showed positive effects on ecosystems and productivity.However,application of these results to intensively managed grasslands has been questioned due to differences in plant species and management regimes.Research on whether diversity can benefit multifunctionality,that is,an integrated index of multiple ecosystem functions,under intensive management,is still scarce.Methods:To address this,we manipulated plant species richness from one to six species spanning three functional groups(legumes,herbs,and grasses)in intensively managed multispecies grassland leys and examined seven ecosystem functions.Results:We found that multifunctionality increased with functional group and species richness.Legume+herb mixtures showed high multifunctionality,while grass monocultures and mixtures with high proportions of grasses had low multifunctionality.Different plant species and plant communities drove different ecosystem functions.Legumes and herbs improved productivity and water availability,while grasses enhanced invasion resistance.These results indicate that multifunctionality and individual ecosystem functions can be promoted through targeted combinations of plants with complementary ecological traits.Conclusions:Plant diversity can improve multifunctionality also under intensive management,potentially benefitting agroeconomics and sustainability.