A Computational Intelligence Approach to Predict Energy Demand Using Random Forest in a Cloudera Cluster

Society’s energy consumption has shot up in recent years, making the prediction of its demand a current challenge to ensure an efficient and responsible use. Artificial intelligence techniques have proven to be potential tools in handling tedious tasks and making sense of large-scale data to make better business decisions in different areas of knowledge. In this article, the use of random forests algorithms in a Big Data environment is proposed for household energy demand forecasting. The predictions are based on the use of information from different sources, confirming a fundamental role of socioeconomic data in consumer’s behaviours. On the other hand, the use of Big Data architectures is proposed to perform horizontal and vertical scaling of the solution to be used in real environments. Finally, a tool for high-resolution predictions with great efficiency is introduced, which enables energy management in a very accurate way.

Can we scale up a comprehensive school-based eye health programme in Zambia?

Background Globally, 19 million children have preventable vision impairment simply because refractive and eye health services are inaccessible to most of them. In Zambia, 50,000 school children need spectacle provision. The School-based Eye Health Programme (SEHP) has been identified worldwide as a proven strategy to address childhood blindness. Given the great benefits of it, the Zambian government intends to scale up the programme. This scalability assessment aims to identify and evaluate the essential components of an effective SEHP, determine roles, assess existing capacities within user organisations, identify environmental facilitating and inhibiting factors, and estimate the minimum resources necessary for the scaling up and their proposed scale-up strategies. Methods Five elements (innovation, user organisation, resource team, environment, and strategies for horizontal and vertical scaling-up) were assessed guided by the ExpandNet-WHO Nine Steps for Developing a Scaling-Up Strategy. Literature reviews and stakeholders' interviews were conducted to collect data for this assessment. Subsequently, twenty questions in the Worksheets for Developing a Scaling-up Strategy were used to systematically reporting the assessment outcome. Results Additional components of SEHP incorporated in Zambia's model enhanced the innovation's credibility and relevance. The resource team was relatively competent in the pilot, and the same team will be employed during the scaling-up. Political instability, the lack of supply chain, and unstable financial supports were identified as inhibiting factors. The objectives of SEHP were aligned with the National Eye Health Strategic Plan 2017–2021 that support the institutionalisation of the SEHP into the existing School Health and Nutrition Programme. For the pace of expansion, replicating SEHP to another district rather than a province will be more realistic. Conclusion Scaling up a comprehensive SEHP in Zambia is feasible, provided if sufficient funding is available. Additionally, the pace must be adapted to the local context to ensure that every component within the SEHP is intact.

Prediction of the vertical scaling of soil organic carbon in temperate forest soils using percolation theory

Forest soil stores a large portion of soil organic carbon (SOC), making it one of the essential components of global carbon cycling. There is apparent spatial variability of SOC in forest soils, but the mechanism that regulates the vertical pattern of SOC is still not clear. Understanding the vertical distribution as well as the transport process of SOC can be of importance in developing comprehensive SOC models in forest soils, as well as in better estimating terrestrial carbon cycling. We propose a theoretical scaling derived from percolation theory to predict the vertical scaling of SOC with soil depth in temperate forest soils, with the hypothesis that the content of SOC along soil profile is limited by the transport of solute. The powers of the vertical scaling of 5 published datasets across different regions of the world are −0.920, −1.097, −1.196, −1.062, and −1.038, comparing with the theoretical value of −1.149. Field data from Changbai Mountain region, Jilin, China, with spatial variation of SOC correlating strongly to temperature, precipitation, and sampling slope is constrained well by theoretical boundaries predicted from percolation theory, indicating that the vertical transport so as the content of SOC along soil profile is limited by solute transport, which can be described by percolation theory in both small and large scales. Prediction of SOC content in Changbai Mountain region based on an estimated SOC content at 0.15 m from available data demonstrates a good agreement with field observation, suggesting the potential of collaborating the presented model with other surface soil models to predict SOC storage and carbon cycling in temperate forest soils.

Can we scale up a comprehensive school-based eye health programme in Zambia?

Background Globally, 19 million children have preventable vision impairment simply because refractive and eye health services are inaccessible to most of them. In Zambia, 50,000 school children need spectacle provision. The School-based Eye Health Programme (SEHP) has been identified worldwide as a proven strategy to address childhood blindness. Given the great benefits of it, the Zambian government intends to scale up the programme. This scalability assessment aims to identify and evaluate the essential components of an effective SEHP, determine roles, assess existing capacities within user organisations, identify environmental facilitating and inhibiting factors, and estimate the minimum resources necessary for the scaling up and their proposed scale-up strategies. Methods Five elements (innovation, user organisation, resource team, environment, and strategies for horizontal and vertical scaling-up) were assessed guided by the ExpandNet-WHO Nine Steps for Developing a Scaling-Up Strategy. Literature reviews and stakeholders' interviews were conducted to collect data for this assessment. Subsequently, twenty questions in the Worksheets for Developing a Scaling-up Strategy were used to systematically reporting the assessment outcome. Results Additional components of SEHP incorporated in Zambia's model enhanced the innovation's credibility and relevance. The resource team was relatively competent in the pilot, and the same team will be employed during the scaling-up. Political instability, the lack of supply chain, and unstable financial supports were identified as inhibiting factors. The objectives of SEHP were aligned with the National Eye Health Strategic Plan 2017–2021 that support the institutionalisation of the SEHP into the existing School Health and Nutrition Programme. For the pace of expansion, replicating SEHP to another district rather than a province will be more realistic. Conclusion Scaling up a comprehensive SEHP in Zambia is feasible, provided if sufficient funding is available. Additionally, the pace must be adapted to the local context to ensure that every component within the SEHP is intact.

Graph-directed random fractal interpolation function

"Barnsley introduced in [1] the notion of fractal interpolation function (FIF). He said that a fractal function is a (FIF) if it possess some interpolation properties. It has the advantage that it can be also combined with the classical methods or real data interpolation. Hutchinson and Ruschendorf [7] gave the stochastic version of fractal interpolation function. In order to obtain fractal interpolation functions with more exibility, Wang and Yu [9] used instead of a constant scaling parameter a variable vertical scaling factor. Also the notion of fractal interpolation can be generalized to the graph-directed case introduced by Deniz and  Ozdemir in [5]. In this paper we study the case of a stochastic fractal interpolation function with graph-directed fractal function."

Analysis and architecture design of scalable fractional motion estimation for H.264 encoding

FractionalMotion Estimation (FME) is an important part of the H.264/AVC video encoding standard. FME can significantly increase the compression ratio achievable by video encoders while improving video quality. However, it is computationally expensive and can consist of over 45% of the total motion estimation runtime. To maximize the performance and hardware utilization of FME implementations on Field-Programmable Gate Arrays (FGPAs), one needs to effectively exploit the inherent parallelism in an algorithm. In the work we explore two approaches to FME algorithm parallelization in order to effectively increase the processing power of the computing hardware. The first method is referred to as vertical scaling and the second horizontal scaling. In total, we implemented six scaled FME designs on a Xilinx Virtex-5 FPGA. We found that our best scaled FME design exhibited a speedup of 8x over the horizontally scaled designs. Additionally, we conclude that scaling vertically within 4x4 pixel sub-block is more efficient than scaling horizontally across several sub-blocks. As a result we were able to achieve higher video resolutions at lower resource costs. In particular, it is shown that the best vertically scaled design can achieve 30 fps of QSXGA (2560x2048) video using 4 reference frames with only 25.5L LUTS and 28.7K registers.

Analysis and architecture design of scalable fractional motion estimation for H.264 encoding

FractionalMotion Estimation (FME) is an important part of the H.264/AVC video encoding standard. FME can significantly increase the compression ratio achievable by video encoders while improving video quality. However, it is computationally expensive and can consist of over 45% of the total motion estimation runtime. To maximize the performance and hardware utilization of FME implementations on Field-Programmable Gate Arrays (FGPAs), one needs to effectively exploit the inherent parallelism in an algorithm. In the work we explore two approaches to FME algorithm parallelization in order to effectively increase the processing power of the computing hardware. The first method is referred to as vertical scaling and the second horizontal scaling. In total, we implemented six scaled FME designs on a Xilinx Virtex-5 FPGA. We found that our best scaled FME design exhibited a speedup of 8x over the horizontally scaled designs. Additionally, we conclude that scaling vertically within 4x4 pixel sub-block is more efficient than scaling horizontally across several sub-blocks. As a result we were able to achieve higher video resolutions at lower resource costs. In particular, it is shown that the best vertically scaled design can achieve 30 fps of QSXGA (2560x2048) video using 4 reference frames with only 25.5L LUTS and 28.7K registers.