Devil in the details: how can we avoid potential pitfalls of CATS regression when our data do not follow a Poisson distribution?

Background Community assembly by trait selection (CATS) allows for the detection of environmental filtering and estimation of the relative role of local and regional (meta-community-level) effects on community composition from trait and abundance data without using environmental data. It has been shown that Poisson regression of abundances against trait data results in the same parameter estimates. Abundance data do not necessarily follow a Poisson distribution, and in these cases, other generalized linear models should be fitted to obtain unbiased parameter estimates. Aims This paper discusses how the original algorithm for calculating the relative role of local and regional effects has to be modified if Poisson model is not appropriate. Results It can be shown that the use of the logarithm of regional relative abundances as an offset is appropriate only if a log-link function is applied. Otherwise, the link function should be applied to the product of local total abundance and regional relative abundances. Since this product may be outside the domain of the link function, the use of log-link is recommended, even if it is not the canonical link. An algorithm is also suggested for calculating the offset when data are zero-inflated. The relative role of local and regional effects is measured by Kullback-Leibler R2. The formula for this measure presented by Shipley (2014) is valid only if the abundances follow a Poisson distribution. Otherwise, slightly different formulas have to be applied. Beyond theoretical considerations, the proposed refinements are illustrated by numerical examples. CATS regression could be a useful tool for community ecologists, but it has to be slightly modified when abundance data do not follow a Poisson distribution. This paper gives detailed instructions on the necessary refinement.

Analysis of Brand Visual Design Based on Collaborative Filtering Algorithm

With the continuous development of China’s social economy, the competitiveness of brand market is gradually increasing. In order to improve their own level in brand building, major enterprises gradually explore and study visual communication design. Brand visual design has also received more and more attention. Building a complete and rich visual design system can improve the brand level and attract users to consume. Based on the abovementioned situation, this paper proposes to use collaborative filtering algorithm to analyze and study brand visual design. Firstly, a solution is proposed to solve the problem of low accuracy of general recommendation algorithm in brand goods. Collaborative filtering algorithm is used to analyze the visual communication design process of enterprise brand. Research on personalized image design according to consumers’ trust and recognition of brand design is conducted. In traditional craft brand visual design, we mainly study the impact of image design on consumer behavior. The brand loyalty model is used to predict and analyze the visual design effect. Also, the user’s evaluation coefficient is taken as the expression of brand visual design recognition. Finally, the collaborative filtering algorithm is optimized to improve the consumer similarity based on the original algorithm. The results show that the brand visual design using collaborative filtering algorithm can help enterprises obtain greater benefits in their own brand construction. It provides effective data help in the development of traditional craft brands.

Recursive Identification for MIMO Fractional-Order Hammerstein Model Based on AIAGS

In this paper, adaptive immune algorithm based on a global search strategy (AIAGS) and auxiliary model recursive least square method (AMRLS) are used to identify the multiple-input multiple-output fractional-order Hammerstein model. The model’s nonlinear parameters, linear parameters, and fractional order are unknown. The identification step is to use AIAGS to find the initial values of model coefficients and order at first, then bring the initial values into AMRLS to identify the coefficients and order of the model in turn. The expression of the linear block is the transfer function of the differential equation. By changing the stimulation function of the original algorithm, adopting the global search strategy before the local search strategy in the mutation operation, and adopting the parallel mechanism, AIAGS further strengthens the original algorithm’s optimization ability. The experimental results show that the proposed method is effective.

Proximal policy optimization with model-based methods

Model-free reinforcement learning methods have successfully been applied to practical applications such as decision-making problems in Atari games. However, these methods have inherent shortcomings, such as a high variance and low sample efficiency. To improve the policy performance and sample efficiency of model-free reinforcement learning, we propose proximal policy optimization with model-based methods (PPOMM), a fusion method of both model-based and model-free reinforcement learning. PPOMM not only considers the information of past experience but also the prediction information of the future state. PPOMM adds the information of the next state to the objective function of the proximal policy optimization (PPO) algorithm through a model-based method. This method uses two components to optimize the policy: the error of PPO and the error of model-based reinforcement learning. We use the latter to optimize a latent transition model and predict the information of the next state. For most games, this method outperforms the state-of-the-art PPO algorithm when we evaluate across 49 Atari games in the Arcade Learning Environment (ALE). The experimental results show that PPOMM performs better or the same as the original algorithm in 33 games.

Automated Aircraft Dent Inspection via a Modified Fourier Transform Profilometry Algorithm

The search for dents is a consistent part of the aircraft inspection workload. The engineer is required to find, measure, and report each dent over the aircraft skin. This process is not only hazardous, but also extremely subject to human factors and environmental conditions. This study discusses the feasibility of automated dent scanning via a single-shot triangular stereo Fourier transform algorithm, designed to be compatible with the use of an unmanned aerial vehicle. The original algorithm is modified introducing two main contributions. First, the automatic estimation of the pass-band filter removes the user interaction in the phase filtering process. Secondly, the employment of a virtual reference plane reduces unwrapping errors, leading to improved accuracy independently of the chosen unwrapping algorithm. Static experiments reached a mean absolute error of ∼0.1 mm at a distance of 60 cm, while dynamic experiments showed ∼0.3 mm at a distance of 120 cm. On average, the mean absolute error decreased by ∼34%, proving the validity of the proposed single-shot 3D reconstruction algorithm and suggesting its applicability for future automated dent inspections.

IN-IDRIS: MODIFICATION OF IDRIS STEMMING ALGORITHM FOR INDONESIAN TEXT

Stemming has an important role in text processing. Stemming of each language is different and strongly affected by the type of text language. Besides that, each language has different rules in the use of words with an affix. A large number of the words used in the Indonesian language are formed by combining root words with affixes and other combining forms. One of the problems in Indonesian stemming is having different types of affixes, and also having some prefixes that changes according to the first letters of the root words. Implementing Idris stemmer for Indonesian text is of interest because Indonesia and Malaysia have the same language root. However, the results do not always produce the actual word, because the Idris algorithm first removes the prefix according to Rule 2. This elimination directly affected the Idris stemmer result when implemented to Indonesian text. In this study, we focus on a modified Idris stemmer (from Malay) to IN-Indris with Indonesia context. In order to test the proposed modification to the original algorithm, Indonesian online novels excerpts are used to measure the performance of IN-Idris.test was conducted to compare the proposed algorithm with other stemmers. From the experiment result, IN-Idris had an accuracy of approximately 82.81%. There was an increased accuracy up to 5.25% when compared to Idris accuracy. Moreover, the proposed stemmer is also running faster than Idris with a gap of speed of around 0.25 seconds. ABSTRAK: Stemming mempunyai peranan penting dalam pemprosesan teks. Stem setiap bahasa adalah berbeza dan sangat dipengaruhi oleh jenis bahasa teks. Selain itu, setiap bahasa mempunyai peraturan yang berbeza dalam penggunaan kata dengan awalan. Sebilangan besar kata-kata yang digunakan dalam bahasa Indonesia dibentuk dengan menggabungkan kata akar dengan afiks dan bentuk gabungan lain. Salah satu masalah dalam bahasa Indonesia adalah mempunyai pelbagai jenis awalan, dan juga mempunyai beberapa awalan yang berubah sesuai dengan huruf pertama kata dasar. Menerapkan stemder Idris untuk teks Indonesia adalah minat kerana Indonesia dan Malaysia mempunyai akar bahasa yang sama. Namun, hasilnya tidak selalu menghasilkan kata yang sebenarnya, kerana algoritma Idris pertama kali menghapus awalan menurut Peraturan 2. Penghapusan ini secara langsung mempengaruhi hasil batang Idris ketika diterapkan ke teks Indonesia. Dalam kajian ini, kami memfokuskan pada stemmer Idris yang diubahsuai (dari bahasa Melayu) ke IN-Indris dengan konteks Indonesia. Untuk menguji cadangan pengubahsuaian pada algoritma asli, petikan novel dalam talian Indonesia digunakan untuk mengukur prestasi IN-Idris. Ujian dilakukan untuk membandingkan algoritma yang dicadangkan dengan stemmer lain. Dari hasil eksperimen, IN-Idris mempunyai ketepatan sekitar 82,81%, ada peningkatan ketepatan hingga 5,25% dibandingkan dengan ketepatan Idris. Selain itu, stemmer yang dicadangkan juga berjalan lebih cepat daripada Idris dengan jurang kelajuan sekitar 0.25 saat.

Modelling of hemodynamics in bifurcation lesions of coronary arteries before and after myocardial revascularization

Modelling of patient-specific hemodynamics for a clinical case of severe coronary artery disease with the bifurcation stenosis was carried out with allowance for standard angiographic data obtained before and after successfully performed myocardial revascularization by stenting of two arteries. Based on a non-Newtonian fluid model and an original algorithm for fluid dynamics computation operated with a limited amount of initial data, key characteristics of blood flow were determined to analyse the features of coronary disease and the consequences of its treatment. The results of hemodynamic modelling near bifurcation sites are presented with an emphasis on physical, physiological and clinical phenomena to demonstrate the feasibility of the proposed approach. The main limitations and ways to minimize them are the subjects of discussion as well. This article is part of the theme issue ‘Transport phenomena in complex systems (part 2)’.

Research on dynamic routing algorithm based on gaussian mixture model

In this paper, based on the method of environmental sound detection, a neural network model based on capsule network and Gaussian mixture model is proposed. The model proposed in this paper mainly aims at the disadvantages of dynamic routing algorithm in the capsule network, and proposes a dynamic routing algorithm based on Gaussian mixture model. The improved dynamic routing algorithm assumes that the characteristics of the data conform to the multi-dimensional Gaussian distribution, so the model can learn the distribution of data features by building distribution functions of different classes. The information entropy is used as the activation value of the salient degree of the feature. Through experiments, the accuracy of the proposed algorithm on Urbansound8K data set is more than 92%, which is 4.8% higher than the original algorithm.

The Important Role of Global State for Multi-Agent Reinforcement Learning

Environmental information plays an important role in deep reinforcement learning (DRL). However, many algorithms do not pay much attention to environmental information. In multi-agent reinforcement learning decision-making, because agents need to make decisions combined with the information of other agents in the environment, this makes the environmental information more important. To prove the importance of environmental information, we added environmental information to the algorithm. We evaluated many algorithms on a challenging set of StarCraft II micromanagement tasks. Compared with the original algorithm, the standard deviation (except for the VDN algorithm) was smaller than that of the original algorithm, which shows that our algorithm has better stability. The average score of our algorithm was higher than that of the original algorithm (except for VDN and COMA), which shows that our work significantly outperforms existing multi-agent RL methods.

Software Optimisation of Lightweight Klein Encryption in IoT

The Internet of Things (IoT) and Wireless Sensor Network (WSN) devices are prone to security vulnerabilities, especially when they are resource-constrained. Lightweight cryptography is a promising encryption concept for IoT and WSN devices, that can mitigate these vulnerabilities. For example, Klein encryption is a lightweight block cipher, which has achieved popularity for the trade-off between performance and security. In this paper, we propose one novel method to enhance the efficiency of the Klein block cipher and the effects on the Central Processing Unit (CPU), memory usage, and processing time. Furthermore, we evaluate another approach on the performance of the Klein encryption iterations. These approaches were implemented in the Python language and ran on the Raspberry PI 3. We evaluated and analyzed the results of two modified encryption algorithms and confirmed that two enhancing techniques lead to significantly improved performance compared to the original algorithm