Flight-schedule using Dijkstra's algorithm with comparison of routes findings

<span>The Dijkstra algorithm, also termed the shortest-route algorithm, is a model that is categorized within the search algorithms. Its purpose is to discover the shortest-route, from the beginning node (origin node) to any node on the tracks, and is applied to both directional and undirected graphs. However, all edges must have non-negative values. The problem of organizing inter-city flights is one of the most important challenges facing airplanes and how to transport passengers and commercial goods between large cities in less time and at a lower cost. In this paper, the authors implement the Dijkstra algorithm to solve this complex problem and also to update it to see the shortest-route from the origin node (city) to the destination node (other cities) in less time and cost for flights using simulation environment. Such as, when graph nodes describe cities and edge route costs represent driving distances between cities that are linked with the direct road. The experimental results show the ability of the simulation to locate the most cost-effective route in the shortest possible time (seconds), as the test achieved 95% to find the suitable route for flights in the shortest possible time and whatever the number of cities on the tracks application.</span>

Evaluation of Diagnostic Performance of Machine Learning Algorithms to Classify the Fetal Heart Rate Baseline from Cardiotocograph

Cardiotocography (CTG) is the widely used cost-effective, non-invasive technique to monitor the fetal heart and mother’s uterine contraction pressure to assess the wellbeing of the fetus. The most important parameters of fetal heart is the baseline upon which the other parameters viz. acceleration, deceleration and variability depend. Accurate classification of the baseline into either normal, bradycardia or tachycardia is thus important to assess the fetal-health. Since visual estimation has its limitations, the authors use various Machine Learning Algorithms to classify the baseline. 110 CTG traces from CTU-UHB dataset, were divided into three subsets using stratified sampling to ensure that the sample is the accurate depiction of the population. The results were analyzed using various statistical methods and compared with the visual estimation by three obstetricians. FURIA provided greatest accuracy of 98.11%. From the analysis of Bland-Altman Plot FURIA was also found to have best agreement with physicians’ estimation.

Machine Learning and Soil Humidity Sensing: Signal Strength Approach

The Internet-of-Things vision of ubiquitous and pervasive computing gives rise to future smart irrigation systems comprising the physical and digital worlds. A smart irrigation ecosystem combined with Machine Learning can provide solutions that successfully solve the soil humidity sensing task in order to ensure optimal water usage. Existing solutions are based on data received from the power hungry/expensive sensors that are transmitting the sensed data over the wireless channel. Over time, the systems become difficult to maintain, especially in remote areas due to the battery replacement issues with a large number of devices. Therefore, a novel solution must provide an alternative, cost- and energy-effective device that has unique advantage over the existing solutions. This work explores the concept of a novel, low-power, LoRa-based, cost-effective system that achieves humidity sensing using Deep Learning techniques that can be employed to sense soil humidity with high accuracy simply by measuring the signal strength of the given underground beacon device.

Micropower system optimization for the telecommunication towers based on various renewable energy sources

This study investigates the technical and cost-effective performance of options renewable energy sources to develop a green off-grid telecommunication tower to replace diesel generators in Malaysia. For this purpose, the solar, wind, pico-hydro energy, along with diesel generators, were examined to compare. In addition, the modeling of hybrid powering systems was conducted using hybrid optimization model for energy (HOMER) simulation based on techno-economic analysis to determine the optimal economically feasible system. The optimization findings showed that the hybrid high-efficiency fixed photovoltaic (PV) system with battery followed by 2 kW pico-hydropower and battery are the optimal configurations for powering off-grid telecommunication towers in Malaysia with the lowest net present cost (NPC) and cost of energy (COE). These costs of NPC and COE are more down than diesel generator costs with battery by 17.45%, 16.45%, 15.9%, and 15.5%, respectively. Furthermore, the economic evaluation of the high-efficiency solar fixed PV panels system annual cash flow compared to the diesel generator with the battery system indicated a ten-year payback period.

Modulating the production of xylanase by Bacillus pumilus BS131 through optimization using waste fiber sludge

In recent days, cheapest alternative carbon source for fermentation purpose is desirable to minimize production cost. Xylanases have become attractive enzymes as their potential in bio-bleaching of pulp and paper industry. The objective of the present study was to identify the potential ability on the xylanase production by locally isolated Bacillus pumilus BS131 by using waste fiber sludge and wheat bran media under submerged fermentation. Culture growth conditions were optimized to obtain significant amount of xylanase. Maximum xylanase production was recorded after 72 hours of incubation at 30 °C and 7 pH with 4.0% substrate concentration. In the nutshell, the production of xylanase using inexpensive waste fiber sludge and wheat-bran as an alternative in place of expensive xylan substrate was more cost effective and environment friendly.

A Unified FPGA Virtualization Framework for General-Purpose Deep Neural Networks in the Cloud

INFerence-as-a-Service (INFaaS) has become a primary workload in the cloud. However, existing FPGA-based Deep Neural Network (DNN) accelerators are mainly optimized for the fastest speed of a single task, while the multi-tenancy of INFaaS has not been explored yet. As the demand for INFaaS keeps growing, simply increasing the number of FPGA-based DNN accelerators is not cost-effective, while merely sharing these single-task optimized DNN accelerators in a time-division multiplexing way could lead to poor isolation and high-performance loss for INFaaS. On the other hand, current cloud-based DNN accelerators have excessive compilation overhead, especially when scaling out to multi-FPGA systems for multi-tenant sharing, leading to unacceptable compilation costs for both offline deployment and online reconfiguration. Therefore, it is far from providing efficient and flexible FPGA virtualization for public and private cloud scenarios. Aiming to solve these problems, we propose a unified virtualization framework for general-purpose deep neural networks in the cloud, enabling multi-tenant sharing for both the Convolution Neural Network (CNN), and the Recurrent Neural Network (RNN) accelerators on a single FPGA. The isolation is enabled by introducing a two-level instruction dispatch module and a multi-core based hardware resources pool. Such designs provide isolated and runtime-programmable hardware resources, which further leads to performance isolation for multi-tenant sharing. On the other hand, to overcome the heavy re-compilation overheads, a tiling-based instruction frame package design and a two-stage static-dynamic compilation, are proposed. Only the lightweight runtime information is re-compiled with ∼1 ms overhead, thus guaranteeing the private cloud’s performance. Finally, the extensive experimental results show that the proposed virtualized solutions achieve up to 3.12× and 6.18× higher throughput in the private cloud compared with the static CNN and RNN baseline designs, respectively.