The use of data-derived label hierarchies in multi-label classification

Instead of traditional (multi-class) learning approaches that assume label independency, multi-label learning approaches must deal with the existing label dependencies and relations. Many approaches try to model these dependencies in the process of learning and integrate them in the final predictive model, without making a clear difference between the learning process and the process of modeling the label dependencies. Also, the label relations incorporated in the learned model are not directly visible and can not be (re)used in conjunction with other learning approaches. In this paper, we investigate the use of label hierarchies in multi-label classification, constructed in a data-driven manner. We first consider flat label sets and construct label hierarchies from the label sets that appear in the annotations of the training data by using a hierarchical clustering approach. The obtained hierarchies are then used in conjunction with hierarchical multi-label classification (HMC) approaches (two local model approaches for HMC, based on SVMs and PCTs, and two global model approaches, based on PCTs for HMC and ensembles thereof). The experimental results reveal that the use of the data-derived label hierarchy can significantly improve the performance of single predictive models in multi-label classification as compared to the use of a flat label set, while this is not preserved for the ensemble models.     

SN-38 loading capacity of hydrophobic polymer blend nanoparticles: formulation,optimization and efficacy evaluation

One of the most important problems in nanoencapsulation of extremely hydrophobic drugs is poor drug loading due to rapid drug crystallization outside the polymer core. The effort to use nanoprecipitation, as a simple one-step procedure with good reproducibility and FDA approved polymers like Poly(lactic-co-glycolic acid) (PLGA) and Polycaprolactone (PCL), will only potentiate this issue. Considering that drug loading is one of the key defining characteristics, in this study we attempted to examine whether the nanoparticle (NP) core composed of two hydrophobic polymers will provide increased drug loading for 7-Ethyl-10-hydroxy-camptothecin (SN-38), relative to NPs prepared using individual polymers. D-optimal design was applied to optimize PLGA/PCL ratio in the polymer blend and the mode of addition of the amphiphilic copolymer Lutrol^®F127 in order to maximize SN-38 loading and obtain NPs with acceptable size for passive tumor targeting. Drug/polymer and polymer/polymer interaction analysis pointed to high degree of compatibility and miscibility among both hydrophobic polymers, providing core configuration with higher drug loading capacity. Toxicity studies outlined the biocompatibility of the blank NPs. Increased in vitro efficacy of drug-loaded NPs compared to the free drug was confirmed by growth inhibition studies using SW-480 cell line. Additionally, the optimized NP formulation showed very promising blood circulation profile with elimination half-time of 7.4?h.     

Blockchain applied to the construction supply chain: A case study with threat model

The construction industry has long faced the challenge of introducing collaborative systems among multiple stakeholders. This challenge creates a high level of rigidity in terms of processing shared information related to different processes, robust holistic regulations, payment actualizations, and resource utilization across different nodes. The need for a digital platform to cross-connect all stakeholders is necessary. A blockchain-based platform is a prime candidate to improve the industry in general and the construction supply chain (CSC) in particular. In this paper, a literature review is presented to establish the main challenges that CSC faces in terms of its effects on productivity and efficiency. In addition, the effect of applying blockchain platforms on a case study is presented and analyzed from performance and security level. The analysis aims to emphasize that blockchain, as presented in this paper, is a viable solution to the challenges in the CSC regardless of the risks associated with the security and robustness of the flow of information and data protection. Moreover, a threat analysis of applying a blockchain model on the CSC industry is introduced. This model indicates potential attacks and possible countermeasures to prevent the attacks. Future work is needed to expand, quantify, and optimize the threat model and conduct simulations considering proposed countermeasures for the different blockchain attacks outlined in this study.     

An extensive experimental comparison of methods for multi-label learning

Multi-label learning has received significant attention in the research community over the past few years: this has resulted in the development of a variety of multi-label learning methods. In this paper, we present an extensive experimental comparison of 12 multi-label learning methods using 16 evaluation measures over 11 benchmark datasets. We selected the competing methods based on their previous usage by the community, the representation of different groups of methods and the variety of basic underlying machine learning methods. Similarly, we selected the evaluation measures to be able to assess the behavior of the methods from a variety of view-points. In order to make conclusions independent from the application domain, we use 11 datasets from different domains. Furthermore, we compare the methods by their efficiency in terms of time needed to learn a classifier and time needed to produce a prediction for an unseen example. We analyze the results from the experiments using Friedman and Nemenyi tests for assessing the statistical significance of differences in performance. The results of the analysis show that for multi-label classification the best performing methods overall are random forests of predictive clustering trees (RF-PCT) and hierarchy of multi-label classifiers (HOMER), followed by binary relevance (BR) and classifier chains (CC). Furthermore, RF-PCT exhibited the best performance according to all measures for multi-label ranking. The recommendation from this study is that when new methods for multi-label learning are proposed, they should be compared to RF-PCT and HOMER using multiple evaluation measures.     

Two stage architecture for multi-label learning

A common approach to solving multi-label learning problems is to use problem transformation methods and dichotomizing classifiers as in the pair-wise decomposition strategy. One of the problems with this strategy is the need for querying a quadratic number of binary classifiers for making a prediction that can be quite time consuming, especially in learning problems with a large number of labels. To tackle this problem, we propose a Two Stage Architecture (TSA) for efficient multi-label learning. We analyze three implementations of this architecture the Two Stage Voting Method (TSVM), the Two Stage Classifier Chain Method (TSCCM) and the Two Stage Pruned Classifier Chain Method (TSPCCM). Eight different real-world datasets are used to evaluate the performance of the proposed methods. The performance of our approaches is compared with the performance of two algorithm adaptation methods (Multi-Label k-NN and Multi-Label C4.5) and five problem transformation methods (Binary Relevance, Classifier Chain, Calibrated Label Ranking with majority voting, the Quick Weighted method for pair-wise multi-label learning and the Label Powerset method). The results suggest that TSCCM and TSPCCM outperform the competing algorithms in terms of predictive accuracy, while TSVM has comparable predictive performance. In terms of testing speed, all three methods show better performance as compared to the pair-wise methods for multi-label learning.