ASU Electronic Theses and Dissertations
This collection includes most of the ASU Theses and Dissertations from 2011 to present. ASU Theses and Dissertations are available in downloadable PDF format; however, a small percentage of items are under embargo. Information about the dissertations/theses includes degree information, committee members, an abstract, supporting data or media.
In addition to the electronic theses found in the ASU Digital Repository, ASU Theses and Dissertations can be found in the ASU Library Catalog.
Dissertations and Theses granted by Arizona State University are archived and made available through a joint effort of the ASU Graduate College and the ASU Libraries. For more information or questions about this collection contact or visit the Digital Repository ETD Library Guide or contact the ASU Graduate College at gradformat@asu.edu.
Filtering by
- Genre: Doctoral Dissertation
- Creators: Shen, Wei
- Creators: Berisha, Visar
The expression and perception of emotions varies across speakers and cultures, thus, determining features and classification methods that generalize well to different conditions is strongly desired. A latent topic models-based method is proposed to learn supra-segmental features from low-level acoustic descriptors. The derived features outperform state-of-the-art approaches over multiple databases. Cross-corpus studies are conducted to determine the ability of these features to generalize well across different databases. The proposed method is also applied to derive features from facial expressions; a multi-modal fusion overcomes the deficiencies of a speech only approach and further improves the recognition performance.
Besides affecting the acoustic properties of speech, emotions have a strong influence over speech articulation kinematics. A learning approach, which constrains a classifier trained over acoustic descriptors, to also model articulatory data is proposed here. This method requires articulatory information only during the training stage, thus overcoming the challenges inherent to large-scale data collection, while simultaneously exploiting the correlations between articulation kinematics and acoustic descriptors to improve the accuracy of emotion recognition systems.
Identifying context from ambient sounds in a lifelogging scenario requires feature extraction, segmentation and annotation techniques capable of efficiently handling long duration audio recordings; a complete framework for such applications is presented. The performance is evaluated on real world data and accompanied by a prototypical Android-based user interface.
The proposed methods are also assessed in terms of computation and implementation complexity. Software and field programmable gate array based implementations are considered for emotion recognition, while virtual platforms are used to model the complexities of lifelogging. The derived metrics are used to determine the feasibility of these methods for applications requiring real-time capabilities and low power consumption.
The aims of Experiment I were to (i) compare the lip reading difficulty of the AzAV sentences to that of other sentence materials, (ii) compare the speech-reading ability of CI listeners to that of normal-hearing listeners and (iii) assess the gain in speech understanding when listeners have both auditory and visual information from easy-to-lip-read and difficult-to-lip read sentences. In addition, the sentence lists were subjected to a multi-level text analysis to determine the factors that make sentences easy or difficult to speech read.
The results of Experiment I showed that (i) the AzAV sentences were relatively difficult to lip read, (ii) that CI listeners and normal-hearing listeners did not differ in lip reading ability and (iii) that sentences with low lip-reading intelligibility (10-15 % correct) provide about a 30 percentage point improvement in speech understanding when added to the acoustic stimulus, while sentences with high lip-reading intelligibility (30-60 % correct) provide about a 50 percentage point improvement in the same comparison. The multi-level text analyses showed that the familiarity of phrases in the sentences was the primary driving factor that affects the lip reading difficulty.
The aim of Experiment II was to investigate the value, when visual information is present, of bimodal hearing and bilateral cochlear implants. The results of Experiment II showed that when visual information is present, low-frequency acoustic hearing can be of value to speech understanding for patients fit with a single CI. However, when visual information was available no gain was seen from the provision of a second CI, i.e., bilateral CIs. As was the case in Experiment I, visual information provided about a 30 percentage point improvement in speech understanding.
The first part deals with modeling and identification of network dynamics. I study two types of network dynamics arising from social and gene networks. Based on the network dynamics, the proposed network identification method works like a `network RADAR', meaning that interaction strengths between agents are inferred by injecting `signal' into the network and observing the resultant reverberation. In social networks, this is accomplished by stubborn agents whose opinions do not change throughout a discussion. In gene networks, genes are suppressed to create desired perturbations. The steady-states under these perturbations are characterized. In contrast to the common assumption of full rank input, I take a laxer assumption where low-rank input is used, to better model the empirical network data. Importantly, a network is proven to be identifiable from low rank data of rank that grows proportional to the network's sparsity. The proposed method is applied to synthetic and empirical data, and is shown to offer superior performance compared to prior work. The second part is concerned with algorithms on networks. I develop three consensus-based algorithms for multi-agent optimization. The first method is a decentralized Frank-Wolfe (DeFW) algorithm. The main advantage of DeFW lies on its projection-free nature, where we can replace the costly projection step in traditional algorithms by a low-cost linear optimization step. I prove the convergence rates of DeFW for convex and non-convex problems. I also develop two consensus-based alternating optimization algorithms --- one for least square problems and one for non-convex problems. These algorithms exploit the problem structure for faster convergence and their efficacy is demonstrated by numerical simulations.
I conclude this dissertation by describing future research directions.
We first consider sensor fusion, a typical multimodal fusion problem critical to building a pervasive computing platform. A systematic fusion technique is described to support both multiple sensors and descriptors for activity recognition. Targeted to learn the optimal combination of kernels, Multiple Kernel Learning (MKL) algorithms have been successfully applied to numerous fusion problems in computer vision etc. Utilizing the MKL formulation, next we describe an auto-context algorithm for learning image context via the fusion with low-level descriptors. Furthermore, a principled fusion algorithm using deep learning to optimize kernel machines is developed. By bridging deep architectures with kernel optimization, this approach leverages the benefits of both paradigms and is applied to a wide variety of fusion problems.
In many real-world applications, the modalities exhibit highly specific data structures, such as time sequences and graphs, and consequently, special design of the learning architecture is needed. In order to improve the temporal modeling for multivariate sequences, we developed two architectures centered around attention models. A novel clinical time series analysis model is proposed for several critical problems in healthcare. Another model coupled with triplet ranking loss as metric learning framework is described to better solve speaker diarization. Compared to state-of-the-art recurrent networks, these attention-based multivariate analysis tools achieve improved performance while having a lower computational complexity. Finally, in order to perform community detection on multilayer graphs, a fusion algorithm is described to derive node embedding from word embedding techniques and also exploit the complementary relational information contained in each layer of the graph.
本研究聚焦冷链物流产业园金融服务助力冷链物流企业发展问题,主要研究内容包括:第一,基于产融结合理论,梳理冷链物流企业与产业园之间关系,从供需两侧探索冷链物流企业和产业园的金融服务的范围、类型和特点。第二,基于平台理论,构建冷链物流企业采纳产业园金融服务的研究模型,探索金融服务影响冷链物流企业的经营因素,分析冷链物流企业采纳产业园金融服务的因素和途径。第三,基于信息不对称理论,关切信息技术支持和知识分享在冷链物流企业采纳产业园提供金融服务过程中的调节作用。同时,梳理产业园提供金融服务可能面临哪些风险,制订冷链物流企业入驻园区的标准,防范风险。
本文运用实证研究方法,通过对国内18家冷链物流相关的产业园、物流园、冷链物流、商贸流通、金融等企业实地考察和专家访谈基础上,拟定问卷并对268家企业进行调查收集数据,使用结构方程模型进行假设检验。研究发现:金融服务的有形性、可靠性、移情性、经济性对冷链物流企业采纳产业园金融服务影响显著,而响应性的影响不显著。同时
信息技术支持和知识共享的调节作用不显著。最后,针对产业园吸引冷链物流企业提供金融服务、冷链物流企业采纳产业园金融服务的风险,提出防范策略措施。