Multi-microphone speech enhancement methods typically require a reference position with respect to which the target signal is estimated. Often, this reference position is arbitrarily chosen as one of the reference microphones. However, it has been shown that the choice of the reference microphone can have a significant impact on the final noise reduction performance. In this paper, we therefore theoretically analyze the impact of selecting a reference on the noise reduction performance with near-end noise being taken into account. Following the generalized eigenvalue decomposition (GEVD) based optimal variable span filtering framework, we find that for any linear beamformer, the output signal-to-noise ratio (SNR) taking both the near-end and far-end noise into account is reference dependent. Only when the near-end noise is neglected, the output SNR of rank-1 beamformers does not depend on the reference position. However, in general for rank-r beamformers with r>1 (e.g., the multichannel Wiener filter) the performance does depend on the reference position. Based on these, we propose an optimal algorithm for microphone reference selection that maximizes the output SNR. In addition, we propose a lower-complexity algorithm that is still optimal for rank-1 beamformers, but sub-optimal for the general rank-r beamformers. Experiments using a simulated microphone array validate the effectiveness of both proposed methods and show that in terms of quality, several dB can be gained by selecting the proper reference microphone.

With tremendous amount of recommendation algorithms proposed every year, one critical issue has attracted a considerable amount of attention: there are no effective benchmarks for evaluation, which leads to two major concerns, i.e., unreproducible evaluation and unfair comparison. This paper aims to conduct rigorous (i.e., reproducible and fair) evaluation for implicit-feedback based top-N recommendation algorithms. We first systematically review 85 recommendation papers published at eight top-tier conferences (e.g., RecSys, SIGIR) to summarize important evaluation factors, e.g., data splitting and parameter tuning strategies, etc. Through a holistic empirical study, the impacts of different factors on recommendation performance are then analyzed in-depth. Following that, we create benchmarks with standardized procedures and provide the performance of seven well-tuned state-of-the-arts across six metrics on six widely-used datasets as a reference for later study. Additionally, we release a user-friendly Python toolkit, which differs from existing ones in addressing the broad scope of rigorous evaluation for recommendation. Overall, our work sheds light on the issues in recommendation evaluation and lays the foundation for further investigation. Our code and datasets are available at GitHub (https://github.com/AmazingDD/daisyRec).

Hypericin is a naturally occurring compound synthesized by certain species of the genus Hypericum, with various pharmacological effects. It is used as a natural photosensitizing agent with great potential in photodynamic therapy. This review discusses the latest results about the biosynthetic pathways and chemical synthetic routes to obtain hypericin. Although many analysis methods can be used for the determination of hypericin purity, HPLC has become the method of choice due to its fast and sensitive analyses. The extraction and purification of hypericin are also described. Hypericin can be used as a photosensitizer due to a large and active π-electron conjugated system in its structure. Medical applications of hypericin are not easy due to several unsolved practical problems, which include hypericin phototoxicity, poor solubility in water, and extreme sensitivity to light, heat, and pH.

Laccase is a versatile multicopper oxidase that holds great promise for many biotechnological applications. For such applications, it is essential to explore good biocatalytic systems for high activity and recyclability. The feasibility of membrane enclosed enzymatic catalysis (MEEC) for enzyme recycling with laccase was evaluated. The dialysis membrane enclosed laccase catalysis (DMELC) was tested for the conversion of the non-phenolic model substrate 2,2′-Azino-bis(3-ethylbenzthiazoline-6-sulfonate) (ABTS). Trametes versicolor laccase was found to be completely retained by the dialysis membrane during the process. The ABTS total conversion after DMELC reached the same values as the batch reaction of the enzyme in solution. The efficiency of DMELC conversion of ABTS under different process conditions including shaking speed, temperature, ABTS concentration and pH was investigated. The repetitive dialysis minimally affected the activity and the protein content of the enclosed laccase. DMELC retained 70.3 ± 0.8% of its initial conversion after 5 cycles. The usefulness of MEEC extends to other enzymes with the benefit of superior activity of an enzyme in solution and the recyclability which is normally only obtained with immobilized enzymes.[Figure not available: see fulltext.]

Hypericin is considered to be the most biologically active substance in the crude extract of Hypericum perforatum L. (also known as St. John's wort) and has a wide range of pharmacological effects. In this study, a high resolution high performance liquid chromatography method for determining hypericin was established by comparing different chromatographic conditions. Xylanase-assisted extraction and microwave-assisted extraction can improve the extraction yield of hypericin significantly. And the coupling strategy between two methods resulted in a significant difference on the extraction yield. Microwave-assisted extraction after xylanase-assisted extraction was found to be the most efficient strategy for extracting hypericin. The yield was 0.319 ± 0.006 mg g ⁻¹ , which was a 209.7% increase over unassisted extraction. The combination of enzyme assisted extraction followed by microwave assisted extraction can be more commonly applied to improve extraction efficiency of bioactive compounds from plants.

We report the use of commercial laundry powder as a biocatalyst for a range of lipase-catalysed reactions including (trans)esterification, ester hydrolysis and chemoenzymatic epoxidation reactions. The enzymatic laundry powder exhibited excellent stability and recyclability, making it a readily available and cheap biocatalyst for chemical transformations.

Representation learning (RL) has recently proven to be effective in capturing local item relationships by modeling item co-occurrence in individual user's interaction record. However, the value of RL for recommendation has not reached the full potential due to two major drawbacks: 1) recommendation is modeled as a rating prediction problem but should essentially be a personalized ranking one; 2) multi-level organizations of items are neglected for fine-grained item relationships. We design a unified Bayesian framework MRLR to learn user and item embeddings from a multi-level item organization, thus benefiting from RL as well as achieving the goal of personalized ranking. Extensive validation on real-world datasets shows that MRLR consistently outperforms state-of-the-art algorithms.

Feature hierarchy (FH) has proven to be effective to improve recommendation accuracy. Prior work mainly focuses on the influence of vertically affiliated features (i.e. child-parent) on user-item interactions. The relationships of horizontally organized features (i.e. siblings and cousins) in the hierarchy, however, has only been little investigated. We show in real-world datasets that feature relationships in horizontal dimension can help explain and further model user-item interactions. To fully exploit FH, we propose a unified recommendation framework that seamlessly incorporates both vertical and horizontal dimensions for effective recommendation. Our model further considers two types of semanti-cally rich feature relationships in horizontal dimension, i.e. complementary and alternative relationships. Extensive validation on four real-world datasets demonstrates the superiority of our approach against the state of the art. An additional benefit of our model is to provide better interpretations of the generated recommendations.

Although demonstrated to be efficient and scalable to large-scale data sets, clustering-based recommender systems suffer from relatively low accuracy and coverage. To address these issues, we develop a multiview clustering method through which users are iteratively clustered from the views of both rating patterns and social trust relationships. To accommodate users who appear in two different clusters simultaneously, we employ a support vector regression model to determine a prediction for a given item, based on user-, item-and prediction-related features. To accommodate (cold) users who cannot be clustered due to insufficient data, we propose a probabilistic method to derive a prediction from the views of both ratings and trust relationships. Experimental results on three real-world data sets demonstrate that our approach can effectively improve both the accuracy and coverage of recommendations as well as in the cold start situation, moving clustering-based recommender systems closer towards practical use.

Collaborative filtering suffers from the problems of data spar-sity and cold start, which dramatically degrade recommendation performance. To help resolve these issues, we propose TntstSVD, a trust-based matrix factorization technique. By analyzing the social trust data from four real-world data sets, we conclude that not only the explicit but also the implicit influence of both ratings and trust should be taken into consideration in a recommendation model. Hence, we build on top of a state-of-the-art recommendation algorithm SVD++ which inherently involves the explicit and implicit influence of rated items, by further incorporating both the explicit and implicit influence of trusted users on the prediction of items for an active user. To our knowledge, the work reported is the first to extend SVD++ with social trust information. Experimental results on the four data sets demonstrate that our approach TrustSVD achieves better accuracy than other ten counterparts, and can better handle the concerned issues.

The large array of recommendation algorithms proposed over the years brings a challenge in reproducing and comparing their performance. This paper introduces an open-source Java library that implements a suite of state-of-the-art algorithms as well as a series of evaluation metrics. We empirically find that LibRec performs faster than other such libraries, while achieving competitive evaluative performance.

Trust has been extensively studied and its effectiveness demonstrated in recommender systems. Due to the lack of explicit trust information in most systems, many trust metric approaches have been proposed to infer implicit trust from user ratings. However, previous works have not compared these different approaches, and oftentimes focus only on the performance of predictive item ratings. In this paper, we first analyse five kinds of trust metrics in light of the properties of trust. We conduct an empirical study to explore the ability of trust metrics to distinguish explicit trust from implicit trust and to generate accurate predictions. Experimental results on two real-world data sets show that existing trust metrics cannot provide satisfying performance, and indicate that future metrics should be designed more carefully.

Trust is one source of information that has been widely adopted to personalize online services for users, such as in product recommendations. However, trust information is usually very sparse or unavailable for most online systems. To narrow this gap, we propose a principled approach that predicts implicit trust from users' interactions, by extending a well-known trust antecedents framework. Specifically, we consider both local and global trustworthiness of target users, and form a personalized trust metric by further taking into account the active user's propensity to trust. Experimental results on two real-world datasets show that our approach works better than contemporary counterparts in terms of trust ranking performance when direct user interactions are limited.

User ratings are the essence of recommender systems in e-commerce. Lack of motivation to provide ratings and eligibility to rate generally only after purchase restrain the effectiveness of such systems and contribute to the well-known data sparsity and cold start problems. This article proposes a new information source for recommender systems, called prior ratings. Prior ratings are based on users' experiences of virtual products in a mediated environment, and they can be submitted prior to purchase. A conceptual model of prior ratings is proposed, integrating the environmental factor presence whose effects on product evaluation have not been studied previously. A user study conducted in website and virtual store modalities demonstrates the validity of the conceptual model, in that users are more willing and confident to provide prior ratings in virtual environments. A method is proposed to show how to leverage prior ratings in collaborative filtering. Experimental results indicate the effectiveness of prior ratings in improving predictive performance.