This paper introduces a novel parameter automation strategy for the particle swarm algorithm and two further extensions to improve its performance after predefined number of generations. Initially, efficiently control local search convergence global optimum solution, time-varying acceleration coefficients (TVAC) are introduced in addition inertia weight factor optimization (PSO). From basis TVAC, new strategies discussed PSO. First, concept "mutation" is along with TVAC (MPSO-TVAC), by...

The growing self-organizing map (GSOM) has been presented as an extended version of the (SOM), which significant advantages for knowledge discovery applications. In this paper, GSOM algorithm is in detail and effect a spread factor, can be used to measure control GSOM, investigated. factor independent dimensionality data such controlling generating maps with different dimensionality, then compared analyzed better accuracy. also method achieving hierarchical clustering set GSOM. Such allows...

Abstract Motivation: In light of the increasing adoption targeted resequencing (TR) as a cost-effective strategy to identify disease-causing variants, robust method for copy number variation (CNV) analysis is needed maximize value this promising technology. Results: We present CNV detection TR data, including whole-exome capture data. Our calls gains and losses each target region based on normalized depth coverage. key strategies include use base-level log-ratios remove GC-content bias,...

Quantitative gait assessment is important in diagnosis and management of Parkinson's disease (PD); however, characteristics a cohort are dispersed by patient physical properties including age, height, body mass, gender, as well walking speed, which may limit capacity to discern some pathological features. The aim this study was twofold. First, use multiple regression normalization strategy that accounts for subject self-selected speed identify differences spatial-temporal features between PD...

Fuzzy rough theory can describe real-world situations in a mathematically effective and interpretable way, while evolutionary neural networks be utilized to solve complex problems. Combining them with these complementary capabilities may lead fuzzy network the interpretability prediction capability. In this article, we propose modifications existing models of then develop powerful framework for by inheriting merits both aforementioned systems. We first introduce neurons enhance consequence...

Electric vehicles (EVs) are an eco-friendly alternative to with internal combustion engines. Despite their environmental benefits, the massive electricity demand imposed by anticipated proliferation of EVs could jeopardize secure and economic operation power grid. Hence, proper strategies for charging coordination will be indispensable future Coordinated EV schemes can implemented as centralized, decentralized, hierarchical systems, last two, referred distributed control systems. This paper...

Cooperative co-evolution (CC) is an evolutionary computation framework that can be used to solve high-dimensional optimization problems via a "divide-and-conquer" mechanism. However, the main challenge when using this lies in problem decomposition. That is, deciding how allocate decision variables particular subproblem, especially interacting variables. Existing decomposition methods are typically computationally expensive. In paper, we propose new method, which call recursive differential...

Energy storage systems have the potential to deliver value in multiple ways, and these must be traded off against one another. An operational strategy that aims maximize returned of such a system can often significantly improved with use forecasting - demand, generation, pricing but consideration battery degradation is important too. This paper proposes stochastic dynamic programming approach optimally operate an energy across receding horizon. The method operates asset maximal lifetime...

Data-driven analysis methods, such as the information content of a fitness sequence, characterize discrete landscape by quantifying its smoothness, ruggedness, or neutrality. However, enhancements to method are required when dealing with continuous landscapes. One typically employed adaptation is sample using random walks variable step size. this has significant limitations: may produce biased samples, and uncertainty added because distance between observations not accounted for. In paper,...

Here, a novel energy trading system is proposed for demand-side management of neighborhood area network (NAN) consisting shared storage (SES) provider, users with non-dispatchable generation, and an electricity retailer. In leader-follower Stackelberg game, the SES provider first maximizes their revenue by setting price signal grid. Then, following provider's actions, retailer minimizes social cost users, i.e., sum total users' when they interact supplying grid to users. A pricing strategy,...

Cooperative co-evolution is a framework that can be used to effectively solve large scale optimization problems. This approach employs divide and conquer strategy, which decomposes the problem into sub-components are optimized separately. However, solution quality relies heavily on decomposition method used. Ideally, interacting decision variables should assigned same sub-component interdependency between kept minimum. Differential grouping, recently proposed method, has high accuracy across...

Using whole exome sequencing to predict aberrations in tumours is a cost effective alternative genome sequencing, however predominantly used for variant detection and infrequently utilised of somatic copy number variation. We propose new method infer genotypes using data from paired tumour/normal samples. Our algorithm uses two Hidden Markov Models computationally resolves polyploidy/aneuploidy, normal cell contamination signal baseline shift. makes explicit on chromosome arm level events,...

Regional solar power forecasting, which involves predicting the total generation from all rooftop photovoltaic (PV) systems in a region holds significant importance for various stakeholders energy sector to ensure stable electricity supply. However, vast amount of and weather time series geographically dispersed locations that need be considered forecasting process makes accurate regional challenging. Therefore, previous studies have limited focus either single (i.e., aggregated series) is...

The ever-increasing demand for the cloud computing paradigm has resulted in widespread deployment of multiple datacenters, operations which consume very high levels energy. carbon footprint resulting from these threatens environmental sustainability while increased energy costs have a direct impact on profitability providers. Using renewable sources to satisfy demands datacenters emerged as viable approach overcome aforementioned issues. problem scheduling workflows across multi-cloud...

We present a comparison of two constraint-handling methods used in the application particle swarm optimization (PSO) to constrained nonlinear problems (CNOPs). A brief review techniques for evolutionary algorithms (EAs) is given, followed by direct existing enforcing constraints using PSO. The considered are nonstationary multistage penalty functions and preservation feasible solutions. Five benchmark comparison, results examined assess performance each method terms accuracy rate...

Recent advances and automation in DNA sequencing technology has created a vast amount of sequence data. This increasing growth data demands better efficient analysis methods. Identifying genes this newly accumulated is an important issue bioinformatics, it requires the prediction complete gene structure. Accurate identification splice sites sequences plays one central roles structural eukaryotes. Effective detection knowledge characteristics, dependencies, relationship nucleotides site...