Alzheimer's Disease patients often exhibit cognitive decline, with language impairment being a prominent biomarker. Spontaneous speech analysis provides a non-invasive screening approach for AD. Large language models, increasingly employed for textual feature extraction, show potential in early AD prediction. However, Automatic Speech Recognition transcription errors, stemming from language impairments in AD and Mild Cognitive Impairment patients, can lead to information loss during feature extraction. To mitigate this, we introduce the Corrected ASR Projecting, CAP model. During training, ASR-transcribed text is manually corrected one by one, and then textual features are extracted independently using BERT, Claude, GLM, and GPT-3. The CAP model is trained by aligning the ASR transcription feature space with the corrected ASR transcription feature space. Experiments on the NCMMSC 2021 dataset demonstrate that the CAP model improves classification performance for AD recognition, with the maximum accuracy improvement reaching 5.55%.

In this paper, we propose a novel transfer learning framework, named generalized subspace distribution adaptation (GSDA), to tackle the challenging cross-corpus speech emotion recognition problem. First, we learn a common low-dimensional feature subspace by utilizing a generalized subspace learning method. Second, we develop a novel distance metric to reduce the divergence between the source and target corpora, which can efficiently explore the similarity and dissimilarity information in the process of knowledge transfer. Third, to demonstrate the effectiveness of our framework, we apply GSDA to the traditional subspace learning algorithms. Finally, we conduct extensive experiments by using the low-level features and deep features on three popular emotional databases, i.e., Berlin, IEMOCAP, and CVE. The results demonstrate that the proposed framework can achieve better performance than several state-of-the-art transfer learning approaches.

Function-as-a-Service (FaaS) has become a popular programming paradigm in Serverless Computing. As the responsibility of resource provisioning shifts from users to cloud providers, the ease of use of FaaS for users may come at the expense of extra hardware costs for cloud providers. Currently, there is no report on how FaaS platforms address this challenge and the level of hardware utilization they achieve.

The number of jellyfish outbreaks is on the rise around the world, and they have been considered a serious ecological disaster. As part of the emergency response plan for jellyfish disasters, in-situ detection research that can distinguish jellyfish species and quantities is urgently required to support accurate data collection. As a typical fully supervised regression task, counting is usually regarded as requiring a large number of labeled datasets in conventional counting methods. To treat counting as a few-shot regression task that is semi-supervised, a novel adaptation strategy based on deep learning is presented in this paper. The method combines the test image with several example objects from the test image and takes advantage of the strong similarities present in the test image and the example objects contained in the image. Effective counting can be achieved without training the target object. Prediction of the density map of the test image’s objects of interest is the objective of the test. This method has been shown to be more robust than the method of detection first and counting later, and its accuracy can exceed 95%.

In practical situations, the emotional speech utterances are often collected from different devices and conditions, which will obviously affect the recognition performance. To address this issue, in this paper, a novel transfer non-negative matrix factorization (TNMF) method is presented for cross-corpus speech emotion recognition. First, the NMF algorithm is adopted to learn a latent common feature space for the source and target datasets. Then, the discrepancies between the feature distributions of different corpora are considered, and the maximum mean discrepancy (MMD) algorithm is used for the similarity measurement. Finally, the TNMF approach, which integrates the NMF and MMD algorithms, is proposed. Experiments are carried out on two popular datasets, and the results verify that the TNMF method can significantly outperform the automatic and competitive methods for cross-corpus speech emotion recognition.

Data center power is a scarce resource that often goes underutilized due to conservative planning. This is because the penalty for overloading the data center power delivery hierarchy and tripping a circuit breaker is very high, potentially causing long service outages. Recently, dynamic server power capping, which limits the amount of power consumed by a server, has been proposed and studied as a way to reduce this penalty, enabling more aggressive utilization of provisioned data center power. However, no real at-scale solution for data center-wide power monitoring and control has been presented in the literature. In this paper, we describe Dynamo -- a data center-wide power management system that monitors the entire power hierarchy and makes coordinated control decisions to safely and efficiently use provisioned data center power. Dynamo has been developed and deployed across all of Facebook's data centers for the past three years. Our key insight is that in real-world data centers, different power and performance constraints at different levels in the power hierarchy necessitate coordinated data center-wide power management. We make three main contributions. First, to understand the design space of Dynamo, we provide a characterization of power variation in data centers running a diverse set of modern workloads. This characterization uses fine-grained power samples from tens of thousands of servers and spanning a period of over six months. Second, we present the detailed design of Dynamo. Our design addresses several key issues not addressed by previous simulation-based studies. Third, the proposed techniques and design have been deployed and evaluated in large scale data centers serving billions of users. We present production results showing that Dynamo has prevented 18 potential power outages in the past 6 months due to unexpected power surges, that Dynamo enables optimizations leading to a 13% performance boost for a production Hadoop cluster and a nearly 40% performance increase for a search cluster, and that Dynamo has already enabled an 8% increase in the power capacity utilization of one of our data centers with more aggressive power subscription measures underway.

Even though a key driver for Information-Centric Networking (ICN) has been the rise in Internet video traffic, there has been surprisingly little work on analyzing the interplay between ICN and video ? which ICN caching strategies work well on video work- loads and how ICN helps improve video-centric quality of experience (QoE). In this work, we bridge this disconnect with a trace- driven study using 196M video requests from over 16M users on a country-wide topology with 80K routers. We evaluate a broad space of content replacement (e.g., LRU, LFU, FIFO) and content placement (e.g., leave a copy everywhere, probabilistic) strategies over a range of cache sizes. We highlight four key findings: (1) the best placement and re- placement strategies depend on the cache size and vary across improvement metrics; that said, LFU+probabilistic caching [37] is a close-to-optimal strategy overall; (2) video workloads show considerable caching-related benefits (e.g., -- 10% traffic reduction) only with very large cache sizes (≥ 100GB); (3) the improvement in video QoE is low (≥ 12%) if the content provider already has a substantial geographical presence; and (4) caches in the middle and the edge of the network, requests from highly populated regions and without content servers, and requests for popular content contribute most to the overall ICN-induced improvements in video QoE.

To enhance the recognition rate of speaker independent speech emotion recognition, a feature selection and feature fusion combination method based on multiple kernel learning is presented. Firstly, multiple kernel learning is used to obtain sparse feature subsets. The features selected at least n times are recombined into another subset named n-subset. The optimal n is determined by 10 cross-validation experiments. Secondly, feature fusion is made at the kernel level. Not only each kind of feature is associated with a kernel, but also the full feature set is associated with a kernel which is not considered in the previous studies. All of the kernels are added together to obtain a combination kernel. The final recognition rate for 7 kinds of emotions on Berlin Database is 83.10%, which outperforms state-of-the-art results and shows the effectiveness of our method. It is also proved that MFCCs play a crucial role in speech emotion recognition.

The widespread availability of smart mobile terminals along with the ever increasing bandwidth capabilities has promoted the popularity of mobile Internet video systems. Understanding the geographic features of mobile content consumption is of an extreme importance for the design and the performance optimization of a mobile video delivery system. This paper is a first step towards characterization of the geographic patterns of a large-scale commercial mobile video-on-demand (VoD) system, by measuring both uniformity and intensity of geographic interests on videos. In particular, we identify a geographical concentration effect of views for individual videos, which is however dependent on video popularity. We also analyze the temporal evolution trends of the geographic popularity which reveal distinct behavior of popular and non-popular videos. While the set of locations that contribute to most of the views of non-popular videos largely varies, the daily geographic popularity distribution of popular videos closely follows the distribution of global traffic and remains stable. We also examine the impact of content type and viewing sources on the geographic features of mobile videos consumption, and the correlation between content similarity and geographic locality. Finally, we provide insights into the implications of our findings.

In this paper, we examine mobile users' behavior and their corresponding video viewing patterns from logs extracted from the servers of a large scale VoD system. We focus on the analysis of the main discrepancies that might exist when users access the VoD system catalog from WiFi or 3G connections. We also study factors that might impact mobile users' interests and video popularity. The users' behavior exhibits strong daily and weekly patterns, with mobile users' interests being surprisingly spread across almost all categories and video lengths, independently of the connection type. However, by examining the activity of users individually, we observed a concentration of interests and peculiar access patterns, which allows to classify the users and thus better predict their behavior. We also find a skewed video popularity distribution and then demonstrate that the popularity of a video can be predicted using its very early popularity level. We further analyzed the sources of video viewing and found that even if search engines are the dominant sources for a majority of videos, they represent less than 10% (resp. 20%) of the sources for the highly popular videos in 3G (resp. WiFi) network. We report that both the type of connections and mobile devices in use have an impact on the viewing time and the source of viewing. Based on our findings, we provide insights and recommendations that can be used to design intelligent mobile VoD systems and help improving personalized services on these platforms.

Due to the historical and cultural reasons, English phases, especially the proper nouns and new words, frequently appear in Web pages written primarily in Asian languages such as Chinese and Korean. Although these English terms and their equivalences in the Asian languages refer to the same concept, they are erroneously treated as independent index units in traditional Information Retrieval (IR). This paper describes the degree to which the problem arises in IR and suggests a novel technique to solve it. Our method firstly extracts an English phrase from Asian language Web pages, and then unifies the extracted phrase and its equivalence(s) in the language as one index unit. Experimental results show that the high precision of our conceptual unification approach greatly improves the IR performance.