Predictive Models for Energy-Efficient Clouds: An Analysis on Real-Life and Synthetic Data

Underwater Wireless Sensor Networks (UWSNs) are subjected to a multitude of real-life challenges. Maintaining adequate power consumption is one of the critical ones, for obvious reasons. This includes proper energy consumption due to nodes close to and far from the sink node (gateway), which affect the overall energy efficiency of the system. These wireless sensors gather and route the data to the onshore base station through the gateway at the sea surface. However, finding an optimum and efficient path from the source node to the gateway is a challenging task. The common reasons for the loss of energy in existing routing protocols for underwater are (1) a node shut down due to battery drainage, (2) packet loss or packet collision which causes re-transmission and hence affects the performance of the system, and (3) inappropriate selection of sensor node for forwarding data. To address these issues, an energy efficient packet forwarding scheme using fuzzy logic is proposed in this work. The proposed protocol uses three metrics: number of hops to reach the gateway node, number of neighbors (in the transmission range of a node) and the distance (or its equivalent received signal strength indicator, RSSI) in a 3D UWSN architecture. In addition, the performance of the system is also tested with adaptive and non-adaptive transmission ranges and scalable number of nodes to see the impact on energy consumption and number of hops. Simulation results show that the proposed protocol performs better than other existing techniques or in terms of parameters used in this scheme.

Download Full-text

Decision Support Tool for Offshore Wind Farm Vessel Routing under Uncertainty

Energies ◽

10.3390/en11092190 ◽

2018 ◽

Vol 11 (9) ◽

pp. 2190 ◽

Cited By ~ 3

Author(s):

Rafael Dawid ◽

David McMillan ◽

Matthew Revie

Keyword(s):

Wind Farm ◽

Real Life ◽

Synthetic Data ◽

Optimal Solution ◽

Decision Support Tool ◽

Offshore Wind ◽

Offshore Wind Farm ◽

Support Tool ◽

Trade Offs ◽

The Impact

This paper for the first time captures the impact of uncertain maintenance action times on vessel routing for realistic offshore wind farm problems. A novel methodology is presented to incorporate uncertainties, e.g., on the expected maintenance duration, into the decision-making process. Users specify the extent to which these unknown elements impact the suggested vessel routing strategy. If uncertainties are present, the tool outputs multiple vessel routing policies with varying likelihoods of success. To demonstrate the tool’s capabilities, two case studies were presented. Firstly, simulations based on synthetic data illustrate that in a scenario with uncertainties, the cost-optimal solution is not necessarily the best choice for operators. Including uncertainties when calculating the vessel routing policy led to a 14% increase in the number of wind turbines maintained at the end of the day. Secondly, the tool was applied to a real-life scenario based on an offshore wind farm in collaboration with a United Kingdom (UK) operator. The results showed that the assignment of vessels to turbines generated by the tool matched the policy chosen by wind farm operators. By producing a range of policies for consideration, this tool provided operators with a structured and transparent method to assess trade-offs and justify decisions.

Download Full-text

The Use of Synthetic Data to Facilitate Eye Segmentation Using Deeplabv3+

Annals of Emerging Technologies in Computing ◽

10.33166/aetic.2021.03.001 ◽

2021 ◽

Vol 5 (3) ◽

pp. 1-10

Author(s):

Melih Öz ◽

Taner Danışman ◽

Melih Günay ◽

Esra Zekiye Şanal ◽

Özgür Duman ◽

...

Keyword(s):

Neural Networks ◽

Deep Neural Networks ◽

Data Augmentation ◽

Real Life ◽

Synthetic Data ◽

Limited Data ◽

Test Set ◽

Human Eye ◽

Context Data ◽

Head Positions

The human eye contains valuable information about an individual’s identity and health. Therefore, segmenting the eye into distinct regions is an essential step towards gathering this useful information precisely. The main challenges in segmenting the human eye include low light conditions, reflections on the eye, variations in the eyelid, and head positions that make an eye image hard to segment. For this reason, there is a need for deep neural networks, which are preferred due to their success in segmentation problems. However, deep neural networks need a large amount of manually annotated data to be trained. Manual annotation is a labor-intensive task, and to tackle this problem, we used data augmentation methods to improve synthetic data. In this paper, we detail the exploration of the scenario, which, with limited data, whether performance can be enhanced using similar context data with image augmentation methods. Our training and test set consists of 3D synthetic eye images generated from the UnityEyes application and manually annotated real-life eye images, respectively. We examined the effect of using synthetic eye images with the Deeplabv3+ network in different conditions using image augmentation methods on the synthetic data. According to our experiments, the network trained with processed synthetic images beside real-life images produced better mIoU results than the network, which only trained with real-life images in the Base dataset. We also observed mIoU increase in the test set we created from MICHE II competition images.

Download Full-text

Prediction Under Uncertainty: Dissociating Sensory from Cognitive Expectations in Highly Uncertain Musical Contexts

10.1101/2021.08.18.456640 ◽

2021 ◽

Author(s):

Iris Mencke ◽

David Ricardo Quiroga-Martinez ◽

Diana Omigie ◽

Franz Schwarzacher ◽

Niels T Haumann ◽

...

Keyword(s):

Predictive Models ◽

Musical Training ◽

Real Life ◽

Behavioral Experiment ◽

Music Listening ◽

Tonal Music ◽

And Behavior ◽

Predictive Processes ◽

Musical Context ◽

High Uncertainty

Predictive models in the brain rely on the continuous extraction of regularities from the environment. These models are thought to be updated by novel information, as reflected in prediction error responses such as the mismatch negativity (MMN). However, although in real life individuals often face situations in which uncertainty prevails, it remains unclear whether and how predictive models emerge in high-uncertainty contexts. Recent research suggests that uncertainty affects the magnitude of MMN responses in the context of music listening. However, musical predictions are typically studied with MMN stimulation paradigms based on Western tonal music, which are characterized by relatively high predictability. Hence, we developed an MMN paradigm to investigate how the high uncertainty of atonal music modulates predictive processes as indexed by the MMN and behavior. Using MEG in a group of 20 subjects without musical training, we demonstrate that the magnetic MMN in response to pitch, intensity, timbre, and location deviants is evoked in both tonal and atonal melodies, with no significant differences between conditions. In contrast, in a separate behavioral experiment involving 39 non-musicians, participants detected pitch deviants more accurately and rated confidence higher in the tonal than in the atonal musical context. These results indicate that contextual tonal uncertainty modulates processing stages in which conscious awareness is involved, although deviants robustly elicit low-level pre-attentive responses such as the MMN. The achievement of robust MMN responses, despite high tonal uncertainty, is relevant for future studies comparing groups of listeners' MMN responses to increasingly ecological music stimuli.

Download Full-text

Energy Efficient Sensor Node Deployment Scheme for Two Stage Routing Protocol of Wireless Sensor Networks assisted IoT

ECTI Transactions on Electrical Engineering, Electronics, and Communications ◽

10.37936/ecti-eec.2020182.240541 ◽

2020 ◽

Vol 18 (2) ◽

pp. 158-169

Author(s):

Anshu Kumar Dwivedi ◽

Awadhesh Kumar Sharma ◽

Pawan Singh Mehra

Keyword(s):

Wireless Sensor Networks ◽

Sensor Networks ◽

Routing Protocol ◽

Energy Efficient ◽

Sensor Node ◽

Golden Ratio ◽

Real Life ◽

Wireless Sensor ◽

Two Stage ◽

Node Deployment

Now a day wireless sensor networks (WSNs) is an essential unit of the internet of things (IoT). IoT theater a vital role in real-time applications which is more useful in real life. Due to its small price and potential use, WSNs have shown importance in different applications over the past year. Health concerns, environmental observation, human protection, military operations, surveillance systems, etc. WSNs have a small device called a sensor node (SN) that has a limited battery. IoT based WSNs consume more energy in sensor node communication. Therefore a Novel energy-efficient sensor node deployment scheme for two-stage routing protocol (EE- DSTRP) has been proposed to reduce the energy consumption of sensor nodes and extend the lifetime of the network. Sensor node deployment is a novel approach based on the golden ratio. All traditional protocols divide network zones for communication. No existing protocols tell about the sensor node deployment ratio in each zone. The deployment method is an important factor in reducing the energy usage of a network. To validate its efficiency, in this article, simulation results prove that the proposed IoT based EE-DSTRP protocol is superior to other existing protocols.

Download Full-text

ECOLOGICAL EFFICIENCY AND PROFITABILITY OF THE PROJECT OF THE POULTRY FARM ILLUMINATION ON THE PLATFORM OF HOLLOW MIRRORED TUBULAR LIGHT GUIDES

VESTNIK OF ASTRAKHAN STATE TECHNICAL UNIVERSITY ◽

10.24143/1812-9498-2017-1-37-44 ◽

2017 ◽

pp. 37-44 ◽

Cited By ~ 1

Author(s):

Brakale Gennaro ◽

Svetlana Aleksandrovna Biryukova ◽

Julia Olegovna Klimantova ◽

Sergey Jurevich Pleshkov

Keyword(s):

Energy Efficient ◽

Real Life ◽

Poultry Meat ◽

Poultry Farm ◽

Ecological Efficiency ◽

Efficient Technology ◽

Cattle Breeding ◽

The Russian Federation ◽

Energy Efficient Technology ◽

Light Guides

The article deals with the project of lighting the hull of a poultry farm (Belokamenniy village, Asbest town, the Sverdlovsk Region), which is organizationally a part of the poultry farm "Sverdlovskaya". The peculiarity of the project is that a real-life version of lighting is proposed to be replaced with an energy-efficient, eco-friendly project that allows not only to cover the initial costs, but also systematically support a higher production of valuable food products, such as eggs, poultry meat. The work presents the calculation of the illumination of the room, performed with the help of an exclusive computer program developed by the engineers of the Italian company "Solarspot International S.R.L.". Recommendations are given to increase the production of poultry and eggs through the use of innovative energy-efficient technology for the transportation of natural light for producers. The profitability of this technology is proved when applied in the cattle-breeding complex of the Russian Federation in terms of different value of the national currency.

Download Full-text

T1D Hypoglycemia Prediction Algorithms: A Systematic Review (Preprint)

10.2196/preprints.34699 ◽

2021 ◽

Author(s):

Stella Tsichlaki ◽

Lefteris Koumakis ◽

Manolis Tsiknakis

Keyword(s):

Type 1 Diabetes ◽

Blood Glucose ◽

Digital Libraries ◽

Predictive Models ◽

Real Life ◽

Blood Glucose Monitoring ◽

Detection Techniques ◽

Glucose Levels ◽

Wide Range

BACKGROUND Diabetes is a chronic condition that necessitates regular monitoring and self-management of the patient's blood glucose levels. People with type 1 diabetes (T1D) can live a productive life if they receive proper diabetes care. Nonetheless, a loose glycemic control might increase the risk of developing hypoglycemia. This incident can occur due to a variety of causes, such as taking additional doses of insulin, skipping meals, or over-exercising. Mainly, the symptoms of hypoglycemia range from mild dysphoria to more severe conditions, if not detected in a timely manner. OBJECTIVE In this review, we report on innovative detection techniques and tactics for identifying and preventing hypoglycemic episodes, focusing on type 1 diabetes. METHODS A systematic literature search following the PRISMA guidelines was performed focusing on the “PUBMED”, “Google Scholar”, “IEEE Xplore” and “ACM” digital libraries to find articles about technologies related to hypoglycemia detection in type 1 diabetes patients. RESULTS The presented approaches have been utilized or devised to enhance blood glucose monitoring and boost its efficacy to forecast future glucose levels, which could aid the prediction of future episodes of hypoglycemia. We detected nineteen predictive models for hypoglycemia, specifically on type 1 diabetes, utilizing a wide range of algorithmic methodologies, spanning from statistics (10%) to machine learning (52%) and deep learning (38%). The algorithms employed most are the kalman filtering and classification models (SVM, KNN, random forests). The performance of the predictive models was found overall to be satisfactory, reaching accuracies between 70% and 99% which proves that such technologies are capable to facilitate the prediction of T1D hypoglycemia. CONCLUSIONS It is evident that CGM can improve the glucose control in diabetes but predictive models for hypo- and hyper- glycemia using only mainstream noninvasive sensors such as wristbands and smartwatches are foreseen to be the next step for mHealth in T1D. Prospective studies are required to demonstrate the value of such models in real-life mHealth interventions.

Download Full-text

Improving the Design of Energy-Efficient Building Retrofitting

Advances in Civil and Industrial Engineering - Design Solutions for nZEB Retrofit Buildings ◽

10.4018/978-1-5225-4105-9.ch007 ◽

2018 ◽

pp. 165-185

Author(s):

Mari Aino Hukkalainen ◽

Krzysztof Klobut ◽

Tarja Mäkeläinen ◽

Vanda Dimitriou ◽

Dariusz Leszczyński

Keyword(s):

Decision Making ◽

Energy Efficient ◽

Real Life ◽

Multiple Criteria Decision Making ◽

Energy System ◽

Energy Performance ◽

User Preference ◽

Trade Offs ◽

Practical Guidelines ◽

Energy Simulations

Practical guidelines are presented for improved process for design and retrofitting of energy-efficient buildings, with an aim to integrate buildings better with the neighbourhood energy system, among others through energy matching. The chapter describes the role of energy simulations in an integrated building retrofitting process and how to select technologies for the retrofitting toward nearly zero energy building level. Feasibility of performing a holistic analysis of retrofitting options can be increased through the integration of BIM, well populated, and linked databases and a multi-criteria decision-making approach. Multiple-criteria decision-making methods aid taking into account a number of building energy performance and user-preference-related criteria and the trade-offs between the different criteria for each retrofitting option. The real-life viewpoints and benefits of utilising the developed methods and processes are discussed, especially from the Eastern European view.

Download Full-text