the following topics are dealt with: learning (artificial intelligence); computeraided instruction; diseases; Internet of things; educational courses; mobile computing; educational institutions; convolutional neural ...
详细信息
ISBN:
(数字)9781665422284
ISBN:
(纸本)9781665422291
the following topics are dealt with: learning (artificial intelligence); computeraided instruction; diseases; Internet of things; educational courses; mobile computing; educational institutions; convolutional neural nets; energy conservation; and medical computing.
Leveraging the labeled data from source stream to handle unlabeled data from target stream is a promising method for multi-stream classification. However, there are still two main issues, concept drifts and concept re...
详细信息
ISBN:
(纸本)9781665412667;9781665429412
Leveraging the labeled data from source stream to handle unlabeled data from target stream is a promising method for multi-stream classification. However, there are still two main issues, concept drifts and concept revolution, needed to be addressed. A couple of methods is proposed to solve them, such as adding a change detection module, modifying sliding window size and setting concept confidence. However, the majority of these approaches did not consider shared data structures among multiple data streams, which can be employed to handle these two issues. At the same time, a lot of algorithms assume that the source data stream and the target data stream are all come from the same domain. In reality, however, most data streams are from different domains with different data distributions. In this paper, therefore, we propose a novel framework Low-Rank Transfer Learning (LRTL) to address cross-domain multi-stream classification. LRTL is mainly composed of three modules, i.e., domain adaptation module, change detection module and classification module. Different from these existing multi-stream classification frameworks, we design a novel domain adaptation module, which utilizes low-rank representation and graph embedding to preserve data structures that have many benefits in dealing with concept drifts and concept revolution. Extensive experiments are carried out on the domain adaptation module and the proposed framework LRTL on multiple benchmarks, which verifies that our domain adaptation methods and frameworks can achieve the state-of-the-art results with significant improvements.
We sense a palpable lack of thoughtful consideration and innovation in the spaces we inhabit. Too often, there is an immense disconnect between the aspirations of inhabitants and the realities of these spaces (cities,...
详细信息
Presently, only a handful of research focuses on the development of interface design for e-Learning modules based on various learning styles. the current studies on this field are still limited to some usability issue...
详细信息
ISBN:
(纸本)9781728152929
Presently, only a handful of research focuses on the development of interface design for e-Learning modules based on various learning styles. the current studies on this field are still limited to some usability issues which ranging from inadequate usability of the proposed design to exclusion of important user research. Nevertheless, interface design is undoubtedly a crucial aspect influencing the success of an e-Learning system implementation. this paper outlines a user-centered study focusing on the development of an alternative interface design of e-Learning modules based on Felder-Silverman learning styles and User Centered design approach by utilizing mixed methods. the study analyzes users' learning styles, learning object preferences, interface preference, and pain points extracted from a user research which includes semi-structured interviews and certain coding techniques. the results are used as a primary guideline in order to create an alternative interface design for e-Learning modules. three out of four proposed alternative designs have better usability than the designs from the previous study based on System Usability Score measurement.
Buñuelos are a traditional food not only in Colombia but in several parts of the world. they are prepared mainly with cassava starch, cornstarch, cheese, water or milk. the purpose of this work is to determine wh...
详细信息
We consider active learning under incentive compatibility constraints. the main application of our results is to economic experiments, in which a learner seeks to infer the parameters of a subject’s preferences: for ...
详细信息
there are limitations in CMOS transistor as the technology scales down. the problem of short channel effects (SCE) has become dominant, which causes the malfunction and failure of CMOS circuits. Various devices are pr...
详细信息
ISBN:
(数字)9781665414906
ISBN:
(纸本)9781665430586
there are limitations in CMOS transistor as the technology scales down. the problem of short channel effects (SCE) has become dominant, which causes the malfunction and failure of CMOS circuits. Various devices are proposed to continue extending Moore's law and the roadmap in semiconductor industry. Memristor is a two terminal passive device, which has proven to be compatible with MOSFET microfabrication processes and also offers some distinctive features. It is a nano-dimensional device, so it saves a lot of die area and consumes less power. Similarly, FinFET structure has aided in better electrostatic control of transistor channel. the leakage current and power are reduced, thus, it shows better performance than MOS transistor. FinFET exhibits temperature effect inversion (TEI) because its I ON increases even at the superthreshold region. the integration of graphene nanoribbon (GNR) FET into IC design has shown a lot of improvements in terms of speed and power. In this work, we present the characteristics of GNRFET and design an inverter circuit using Cadence/Spectre. Following this, a three-stage ring oscillator (RO) is designed, and the results show that its center frequency is 30.2 GHz with a phase noise of -125.2dBc/Hz. In addition, it consumes 0.15 mW power, which makes it suitable for high frequency and low power applications. More so, the RO has a very good phase noise performance.
Lean Manufacturing tools were originally developed to improve manufacturing production systems and enhance productivity and quality in organizations. For this reason, they are used more frequently in manufacturing tha...
详细信息
After a brief revision of the literature, this work develops a computer-aided molecular design procedure (GCMOLD), based on the Group Contribution Equation of State, GC-EOS. the selection of solvents, for CO2 capture ...
详细信息
After a brief revision of the literature, this work develops a computer-aided molecular design procedure (GCMOLD), based on the Group Contribution Equation of State, GC-EOS. the selection of solvents, for CO2 capture in pre-combustion processes by GCMOLD, allows a systematic study of the effect of molecular functionality on solvent properties. For this problem, after the selection of a number of paraffinic and CO2-phylic groups for the synthesis of molecular structures, the GCMOLD program generates a list of solvents ranked by their solvent power. On this basis, the effect of paraffinic and polar structures on solvent power and solvent loss gives a rationale for optimum solvent selection. Finally, an innovative scheme of an absorption cycle with low energy consumption is proposed. (C) 2019 Elsevier B.V. All rights reserved.
作者:
Liu, JinyangMa, ZhiyiPeking Univ
Acad Adv Interdisciplinary Studies Beijing Peoples R China Peking Univ
Sch Elect Engn & Comp Sci Beijing Peoples R China Peking Univ
Minist Educ Key Lab High Confidence Software Technol Beijing Peoples R China
Android has been the most popular operation system in the smartphone field, and Android programming is an import branch in programming work. When dealing with programming tasks, there are many APIs that are often used...
详细信息
Android has been the most popular operation system in the smartphone field, and Android programming is an import branch in programming work. When dealing with programming tasks, there are many APIs that are often used by programmers, and it costs much time for them to choose and check the usages of APIs repeatedly. this paper raises a design of API recommendation system in android programming, which uses AST tools in Java to extract key features of codes, and uses tf-idf, LDA and API2Vec models on the data to generate recommendation results. +the experiment results- at maximum 80%+overall recall rate and nearly 50% top-10 recall rate prove the efficiency of the system.
暂无评论