다중혈관 관상동맥 환자에서 y-문합을 이용하여 양쪽 내흉동맥만을 사용한 우회술의 조기 성적

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Data Mining Practical Machine Learning Tools and Techniques

In recent years, deep neural networks have yielded immense success on speech recognition, computer vision and natural language processing. However, the exploration of deep neural networks on recommender systems has received relatively less scrutiny. In this work, we strive to develop techniques based on neural networks to tackle the key problem in recommendation --- collaborative filtering --- on the basis of implicit feedback. Although some recent work has employed deep learning for recommendation, they primarily used it to model auxiliary information, such as textual descriptions of items and acoustic features of musics. When it comes to model the key factor in collaborative filtering --- the interaction between user and item features, they still resorted to matrix factorization and applied an inner product on the latent features of users and items. By replacing the inner product with a neural architecture that can learn an arbitrary function from data, we present a general framework named NCF, short for Neural network-based Collaborative Filtering. NCF is generic and can express and generalize matrix factorization under its framework. To supercharge NCF modelling with non-linearities, we propose to leverage a multi-layer perceptron to learn the user-item interaction function. Extensive experiments on two real-world datasets show significant improvements of our proposed NCF framework over the state-of-the-art methods. Empirical evidence shows that using deeper layers of neural networks offers better recommendation performance.

Neural Collaborative Filtering

Learning sophisticated feature interactions behind user behaviors is critical in maximizing CTR for recommender systems. Despite great progress, existing methods seem to have a strong bias towards low- or high-order interactions, or require expertise feature engineering. In this paper, we show that it is possible to derive an end-to-end learning model that emphasizes both low- and high-order feature interactions. The proposed model, DeepFM, combines the power of factorization machines for recommendation and deep learning for feature learning in a new neural network architecture. Compared to the latest Wide & Deep model from Google, DeepFM has a shared input to its "wide" and "deep" parts, with no need of feature engineering besides raw features. Comprehensive experiments are conducted to demonstrate the effectiveness and efficiency of DeepFM over the existing models for CTR prediction, on both benchmark data and commercial data.

/pdf/deepfm-a-factorization-machine-based-neural-network-for-ctr-xde2g2fq1v.pdf

DeepFM: a factorization-machine based neural network for CTR prediction

Existing content-based music recommendation systems typically employ a \textit{two-stage} approach. They first extract traditional audio content features such as Mel-frequency cepstral coefficients and then predict user preferences. However, these traditional features, originally not created for music recommendation, cannot capture all relevant information in the audio and thus put a cap on recommendation performance. Using a novel model based on deep belief network and probabilistic graphical model, we unify the two stages into an automated process that simultaneously learns features from audio content and makes personalized recommendations. Compared with existing deep learning based models, our model outperforms them in both the warm-start and cold-start stages without relying on collaborative filtering (CF). We then present an efficient hybrid method to seamlessly integrate the automatically learnt features and CF. Our hybrid method not only significantly improves the performance of CF but also outperforms the traditional feature mbased hybrid method.

Improving Content-based and Hybrid Music Recommendation using Deep Learning

Existing music recommendation systems rely on collaborative filtering or content-based technologies to satisfy users' long-term music playing needs. Given the popularity of mobile music devices with rich sensing and wireless communication capabilities, we present in this paper a novel approach to employ contextual information collected with mobile devices for satisfying users' short-term music playing needs. We present a probabilistic model to integrate contextual information with music content analysis to offer music recommendation for daily activities, and we present a prototype implementation of the model. Finally, we present evaluation results demonstrating good accuracy and usability of the model and prototype.

Context-aware mobile music recommendation for daily activities

Transmitting large packets over wireless networks helps to reduce header overhead, but may have an adverse effect on loss rate due to corruptions in a radio link. Packet loss in lower layers, however, is typically hidden from the upper protocol layers by link or MAC layer protocols. For this reason, errors in the physical layer are observed by the application as higher variance in end-to-end delay rather than increased packet loss rate. We study the effect of packet size on loss rate and delay characteristics in a wireless real-time application. We derive an analytical model for the dependency between packet length and delay characteristics. We validate our theoretical analysis through experiments in an ad hoc network using WLAN technologies. We show that careful design of packetization schemes in the application layer may significantly improve radio link resource utilization in delay sensitive media streaming under difficult wireless network conditions.

/pdf/effect-of-packet-size-on-loss-rate-and-delay-in-wireless-2z5972pkvx.pdf

Effect of packet size on loss rate and delay in wireless links

BACKGROUND: A well-established connection exists between increased gait variability and greater fall likelihood in Parkinson's disease (PD); however, a portable, validated means of quantifying gait variability (and testing the efficacy of any intervention) remains lacking. Furthermore, although rhythmic auditory cueing continues to receive attention as a promising gait therapy for PD, its widespread delivery remains bottlenecked. The present paper describes a smartphone-based mobile application ("SmartMOVE") to address both needs. METHODS: The accuracy of smartphone-based gait analysis (utilizing the smartphone's built-in tri-axial accelerometer and gyroscope to calculate successive step times and step lengths) was validated against two heel contact-based measurement devices: heel-mounted footswitch sensors (to capture step times) and an instrumented pressure sensor mat (to capture step lengths). 12 PD patients and 12 age-matched healthy controls walked along a 26-m path during self-paced and metronome-cued conditions, with all three devices recording simultaneously. RESULTS: Four outcome measures of gait and gait variability were calculated. Mixed-factorial analysis of variance revealed several instances in which between-group differences (e.g., increased gait variability in PD patients relative to healthy controls) yielded medium-to-large effect sizes (eta-squared values), and cueing-mediated changes (e.g., decreased gait variability when PD patients walked with auditory cues) yielded small-to-medium effect sizes-while at the same time, device-related measurement error yielded small-to-negligible effect sizes. CONCLUSION: These findings highlight specific opportunities for smartphone-based gait analysis to serve as an alternative to conventional gait analysis methods (e.g., footswitch systems or sensor-embedded walkways), particularly when those methods are cost-prohibitive, cumbersome, or inconvenient. Language: en

/pdf/a-validated-smartphone-based-assessment-of-gait-and-gait-1b485gzc6m.pdf

A Validated Smartphone-Based Assessment of Gait and Gait Variability in Parkinson’s Disease

We present a prototype that automatically aligns acoustic musical signals with their corresponding textual lyrics, in a manner similar to manually-aligned karaoke. We tackle this problem using a multimodal approach, where the appropriate pairing of audio and text processing helps create a more accurate system. Our audio processing technique uses a combination of top-down and bottom-up approaches, combining the strength of low-level audio features and high-level musical knowledge to determine the hierarchical rhythm structure, singing voice and chorus sections in the musical audio. Text processing is also employed to approximate the length of the sung passages using the textual lyrics. Results show an average error of less than one bar for per-line alignment of the lyrics on a test bed of 20 songs (sampled from CD audio and carefully selected for variety). We perform holistic and per-component testing and analysis and outline steps for further development.

/pdf/lyrically-automatic-synchronization-of-acoustic-musical-4vtzavw79c.pdf

Ye Wang

Papers

Improving Content-based and Hybrid Music Recommendation using Deep Learning

Context-aware mobile music recommendation for daily activities

Effect of packet size on loss rate and delay in wireless links

A Validated Smartphone-Based Assessment of Gait and Gait Variability in Parkinson’s Disease

LyricAlly: automatic synchronization of acoustic musical signals and textual lyrics