As the interest in regulating energy usage and in the demand-response market is growing, new energy management algorithms emerge. In this paper, we propose a formalization of "the sourcing problem" and its a...
详细信息
ISBN:
(纸本)9789897581984
As the interest in regulating energy usage and in the demand-response market is growing, new energy management algorithms emerge. In this paper, we propose a formalization of "the sourcing problem" and its application to a multisource elevator. We propose a linear formulation that, coupled with a low level rule-based controller, can solve this problem. We show in the experiments that a compromise between reducing consumption peaks and minimizing the energy bill has to be reached.
The paper presents the methodology and results of a pilot stage of semi-automatic adjective mapping between plWordNet and Princeton WordNet. Two types of rule-based algorithms aimed at generation of automatic prompts ...
详细信息
ISBN:
(纸本)9783319240336;9783319240329
The paper presents the methodology and results of a pilot stage of semi-automatic adjective mapping between plWordNet and Princeton WordNet. Two types of rule-based algorithms aimed at generation of automatic prompts are proposed. Both capitalise on the existing network of intra and inter-lingual relations as well as on lemma filtering by a cascade dictionary. The results of their implementation are juxtaposed with the results of manual mapping. The highest precision is achieved in a hybrid approach relying on both synset and lexical unit relations.
Multiple-instance learning (MIL) is a supervised learning technique that addresses the problem of classifying bags of instances instead of single instances. In this paper, we introduce a rule-based MIL algorithm, call...
详细信息
Multiple-instance learning (MIL) is a supervised learning technique that addresses the problem of classifying bags of instances instead of single instances. In this paper, we introduce a rule-based MIL algorithm, called mi-DS, and compare it with 21 existing MIL algorithms on 26 commonly used data sets. The results show that mi-DS performs on par with or better than several well-known algorithms and generates models characterized by balanced values of precision and recall. Importantly, the introduced method provides a framework that can be used for converting other rule-based algorithms into MIL algorithms.
Algorithmic decision making has proliferated and now impacts our daily lives in both mundane and consequential ways. Machine learning practitioners use a myriad of algorithms for predictive models in applications as d...
详细信息
Algorithmic decision making has proliferated and now impacts our daily lives in both mundane and consequential ways. Machine learning practitioners use a myriad of algorithms for predictive models in applications as diverse as movie recommendations, medical diagnoses, and parole recommendations without delving into the reasons driving specific predictive decisions. The algorithms in such applications are often chosen for their superior performance among a pool of competing algorithms;however, popular choices such as random forest and deep neural networks fail to provide an interpretable understanding of the model's predictions. In recent years, rule-based algorithms have provided a valuable alternative to address this issue. Previous work established an or-of-and (disjunctive normal form) based classification technique that allows for classification rule mining of a single class in a binary classification. In this work, we extend this idea to provide classification rules for both classes simultaneously. That is, we provide a distinct set of rules for each of the positive and negative classes. We also present a novel and complete taxonomy of classifications that clearly capture and quantify the inherent ambiguity of noisy binary classifications in the real world. We show that this approach leads to a more granular formulation of the likelihood model and a simulated annealing-based optimization achieves classification performance competitive with comparable techniques. We apply our method to synthetic and real-world data sets for comparison with other related methods to demonstrate the utility of our contribution.
Mobile health (mHealth) apps can be an evidence-based approach to improve health behavior and outcomes. Prior literature has highlighted the need for more research on mHealth personalization, including in diabetes and...
详细信息
Mobile health (mHealth) apps can be an evidence-based approach to improve health behavior and outcomes. Prior literature has highlighted the need for more research on mHealth personalization, including in diabetes and pregnancy. Critical gaps exist on the impact of personalization of mHealth apps on patient engagement, and in turn, health behaviors and outcomes. Evidence regarding how personalization, engagement, and health outcomescould be aligned when designing mHealth for underserved populations is much needed, given the historical oversights with mHealth design in these populations. This viewpoint is motivated by our experience from designing a personalized mHealth solution focused on Medicaid-enrolled pregnant individuals with uncontrolled type 2 diabetes, many of whom also experience a high burden of social needs. We describefundamental components of designing mHealth solutions that are both inclusive and personalized, forming the basis of an evidence-based framework for future mHealth design in other disease states with similar contexts.
暂无评论