Working in collaborative environments is an essential skill for computing professionals. In our program, students have significant team experience from previous classes;almost all of our classes in Cal Poly's Comp...
详细信息
In this work, we propose a novel ensemble neural network design that is capable of classifying the emotional context of short sentences. Our model consists of three distinct branches, each of which is composed of a co...
详细信息
Ferrite is used in inductive power transfer (IPT) pads to improve magnetic coupling and reduce magnetic field leakage, but it is brittle and costly. A potential alternative to ferrites in IPT pads is soft-magnetic com...
详细信息
ISBN:
(数字)9781665484459
ISBN:
(纸本)9781665484466
Ferrite is used in inductive power transfer (IPT) pads to improve magnetic coupling and reduce magnetic field leakage, but it is brittle and costly. A potential alternative to ferrites in IPT pads is soft-magnetic composites (SMCs). SMCs have lower relative magnetic permeability, but can be lower cost with better mechanical properties that enable longer IPT system lifetimes. This paper uses an optimisation approach to design Double-D (DD) pads which incorporate both ferrite and SMC, for the primary side of an EV charger IPT system. In this paper, the optimisation process converges on results that concentrate ferrite in the central, high-field regions of the DD pad as ferrite significantly shapes magnetic field distribution. The optimisation process places SMCs in the outer regions of the pad to shield the leakage magnetic field. A selected Ferrite-SMC Double-D (FSDD) design showed only 3% drop in coupling, despite extensive reductions in leakage and ferrite volume. This performance was verified by transferring 1kVA uncompensated apparent power to a FFDD secondary at 93% efficiency.
With the rise of web-based social networking, a great many short texts/micro-messages are exchanged daily. Although short texts/micro-messages are a powerful and efficient way to communicate among individuals, their a...
详细信息
To process data more efficiently, big data frameworks provide data abstractions to developers. However, due to the abstraction, there may be many challenges for developers to understand and debug the data processing c...
详细信息
Automatic Speech Recognition (ASR) systems can be trained to achieve remarkable performance given large amounts of manually transcribed speech, but large labeled data sets can be difficult or expensive to acquire for ...
详细信息
To process data more efficiently, big data frameworks provide data abstractions to developers. However, due to the abstraction, there may be many challenges for developers to understand and debug the data processing c...
详细信息
ISBN:
(纸本)9781665429757
To process data more efficiently, big data frameworks provide data abstractions to developers. However, due to the abstraction, there may be many challenges for developers to understand and debug the data processing code. To uncover the challenges in using big data frameworks, we first conduct an empirical study on 1,000 Apache Spark-related questions on Stack Overflow. We find that most of the challenges are related to data transformation and API usage. To solve these challenges, we design an approach, which assists developers with understanding and debugging data processing in Spark. Our approach leverages statistical sampling to minimize performance overhead, and provides intermediate information and hint messages for each data processing step of a chained method pipeline. The preliminary evaluation of our approach shows that it has low performance overhead and we receive good feedback from developers.
The collaborative approach which are born OER (Open Educational Resource) is the joint search for pedagogical and technological challenges to achieve improved quality reconstruction. It is necessary to demonstrate def...
详细信息
Climate is rapidly changing around the world. Over time, there have been significant changes in the weather. Rainfall is now erratic due to climate change. The frequency of extreme weather events like droughts and flo...
详细信息
Climate is rapidly changing around the world. Over time, there have been significant changes in the weather. Rainfall is now erratic due to climate change. The frequency of extreme weather events like droughts and floods has increased due to climate change, necessitating the need for more precise and timely rainfall forecasts. For strategic reasons including agriculture, water resource management, and architectural design, rain forecasting is crucial. The naturally occurring non-stationary component in the rainfall time series impairs model performance for practical hydrologists and drought risk assessors. We present a rain predicting model based on machine learning to address the forecasting issue. In our work, we predict the possibility of rain the next day on the basis of last 10 years' data. The variables that were calculated during the experiments were humidity, pressure, evaporation, sunshine, rainfall, and so on. Random Forest gave the 90% accuracy with 0.904 Area under Curve, highest out of all the algorithms. The model's performance will significantly aid in the rain forecast.
暂无评论