Biorthogonal wavelet trees in the classification of embedded signal classes for intelligent sensors using machine learning applications

The paper deals with a method of constructing orthonormal bases of coordinates which maximize, through redundant dictionaries (frames) of biorthogonal bases, a class separability index or distances among classes. The method proposes an algorithm which consists of biorthogonal expansions over two redundant dictionaries. Embedded classes are often present in multiclassification problems. It is shown how the biorthogonality of the expansion can really help to construct a coordinate system which characterizes the classes. The algorithm is created for training wavelet networks in order to provide an efficient coordinate system maximizing the Cross Entropy function between two complementary classes. Sine and cosine wavelet packets are basis functions of the network. Thanks to their packet structure, once selected the depth of the tree, an adaptive number of basis functions is automatically chosen. The algorithm is also able to carry out centering and dilation of the basis functions in an adaptive way. The algorithm works with a preliminary extracted feature through shrinkage technique in order to reduce the dimensionality of the problem. In particular, our attention is pointed out for time-frequency monitoring, detection and classification of transients in rail vehicle systems and the outlier problem. In the former case the goal is to distinguish transients as inrush current and no inrush current and a further distinction between the two complementary classes: dangerous inrush current and no dangerous inrush current. The proposed algorithm is used on line in order to recognize the dangerous transients in real time and thus shut-down the vehicle. The algorithm can also be used in a general application of the outlier detection. A similar structure is used in developed algorithms which are currently integrated in the inferential modeling platform of the unit responsible for Advanced Control and Simulation Solutions within ABB's (Asea Brown Boveri) industry division. It is shown how impressive and rapid performances are achieved with a limited number of wavelets and few iterations. Real applications using real measured data are included to illustrate and analyze the effectiveness of the proposed method.     

Detecting ethnicity-targeted hate speech in Russian social media texts

Ethnicity-targeted hate speech has been widely shown to influence on-the-ground inter-ethnic conflict and violence, especially in such multi-ethnic societies as Russia. Therefore, ethnicity-targeted hate speech detection in user texts is becoming an important task. However, it faces a number of unresolved problems: difficulties of reliable mark-up, informal and indirect ways of expressing negativity in user texts (such as irony, false generalization and attribution of unfavored actions to targeted groups), users’ inclination to express opposite attitudes to different ethnic groups in the same text and, finally, lack of research on languages other than English. In this work we address several of these problems in the task of ethnicity-targeted hate speech detection in Russian-language social media texts. This approach allows us to differentiate between attitudes towards different ethnic groups mentioned in the same text – a task that has never been addressed before. We use a dataset of over 2,6M user messages mentioning ethnic groups to construct a representative sample of 12K instances (ethnic group, text) that are further thoroughly annotated via a special procedure. In contrast to many previous collections that usually comprise extreme cases of toxic speech, representativity of our sample secures a realistic and, therefore, much higher proportion of subtle negativity which additionally complicates its automatic detection. We then experiment with four types of machine learning models, from traditional classifiers such as SVM to deep learning approaches, notably the recently introduced BERT architecture, and interpret their predictions in terms of various linguistic phenomena. In addition to hate speech detection with a text-level two-class approach (hate, no hate), we also justify and implement a unique instance-based three-class approach (positive, neutral, negative attitude, the latter implying hate speech). Our best results are achieved by using fine-tuned and pre-trained RuBERT combined with linguistic features, with F1-hate=0.760, F1-macro=0.833 on the text-level two-class problem comparable to previous studies, and F1-hate=0.813, F1-macro=0.824 on our unique instance-based three-class hate speech detection task. Finally, we perform error analysis, and it reveals that further improvement could be achieved by accounting for complex and creative language issues more accurately, i.e., by detecting irony and unconventional forms of obscene lexicon.     

Light-driven directional ion transport for enhanced osmotic energy harvesting

Light-driven ion (proton) transport is a crucial process both for photosynthesis of green plants and solar energy harvesting of some archaea. Here, we describe use of a TiO₂/C₃N₄ semiconductor heterojunction nanotube membrane to realize similar light-driven directional ion transport performance to that of biological systems. This heterojunction system can be fabricated by two simple deposition steps. Under unilateral illumination, the TiO₂/C₃N₄ heterojunction nanotube membrane can generate a photocurrent of about 9 μA/cm², corresponding to a pumping stream of ∼5500 ions per second per nanotube. By changing the position of TiO₂ and C₃N₄, a reverse equivalent ionic current can also be realized. Directional transport of photogenerated electrons and holes results in a transmembrane potential, which is the basis of the light-driven ion transport phenomenon. As a proof of concept, we also show that this system can be used for enhanced osmotic energy generation. The artificial light-driven ion transport system proposed here offers a further step forward on the roadmap for development of ionic photoelectric conversion and integration into other applications, for example water desalination.     

Irony detection via sentiment-based transfer learning

Irony as a literary technique is widely used in online texts such as Twitter posts. Accurate irony detection is crucial for tasks such as effective sentiment analysis. A text’s ironic intent is defined by its context incongruity. For example in the phrase “I love being ignored”, the irony is defined by the incongruity between the positive word “love” and the negative context of “being ignored”. Existing studies mostly formulate irony detection as a standard supervised learning text categorization task, relying on explicit expressions for detecting context incongruity. In this paper we formulate irony detection instead as a transfer learning task where supervised learning on irony labeled text is enriched with knowledge transferred from external sentiment analysis resources. Importantly, we focus on identifying the hidden, implicit incongruity without relying on explicit incongruity expressions, as in “I like to think of myself as a broken down Justin Bieber – my philosophy professor.” We propose three transfer learning-based approaches to using sentiment knowledge to improve the attention mechanism of recurrent neural models for capturing hidden patterns for incongruity. Our main findings are: (1) Using sentiment knowledge from external resources is a very effective approach to improving irony detection; (2) For detecting implicit incongruity, transferring deep sentiment features seems to be the most effective way. Experiments show that our proposed models outperform state-of-the-art neural models for irony detection.     

A Characterisation Study on Modern Bronze Sculpture: The Artistic Patinas of Nado Canuti

Artistic patination is a traditional colouring technique for metal sculpture, employed by artists in ancient and modern times for aesthetic purposes. Today, knowledge of the artistic value and the chemistry of this superficial chromatic layer, called ‘artistic patina’, can be successfully acquired through a close collaboration between living artists, foundry artisans, and scientists. Starting from several interviews with the Italian artist Nado Canuti and foundry artisans, specific information was gathered about patination methods and the artist’s attitude towards materials restoration. Afterwards, the patinas most used by Canuti were reproduced to study their nature before any ageing or degradation. Their chromatic values, morphologies, and compositions were studied employing a range of techniques such as colour measurements, scanning electron microscopy with energy dispersive X-ray spectroscopy, and micro-Raman spectroscopy. The collected data revealed the formation of main compounds (cuprite, cassiterite, rouaite, chalcocite, isocubanite, and ferroxyhite) and additional compounds (atacamite and CN-containing compound). The scientific results, as well as the artist’s statements concerning the patinas’ significance, maintenance, and conservation, will contribute towards the future care and preservation of Canuti’s sculptures.     

意大利和国际体育法及判例制裁的比例原则

研究意大利和国际体育法判例制裁的比例原则,首先需要了解意大利(以下简称国家)和国际体育规则。其次是根据意大利与国际体育法的判例如何与归责原则连接,以及解释(和执行)方式,尤其是关于足球与反兴奋剂规则。研究的主要目的是为了验证这一原则是否在规则中被编撰和认可(通过体育法庭得到解释和执行),评估这一原则是否应用于保护体育运动的完整性(确保它的正常运作),并应当平衡要遵守体育规则和保护运动员利益二者之间的关系。     

Modelling the joint torques and loadings during squatting at the Smith machine

An analytical biomechanical model was developed to establish the relevant properties of the Smith squat exercise, and the main differences from the free barbell squat. The Smith squat may be largely patterned to modulate the distributions of muscle activities and joint loadings. For a given value of the included knee angle (θ(knee)), bending the trunk forward, moving the feet forward in front of the knees, and displacing the weight distribution towards the forefoot emphasizes hip and lumbosacral torques, while also reducing knee torque and compressive tibiofemoral and patellofemoral forces (and vice versa). The tibiofemoral shear force φ(t) displays more complex trends that strongly depend on θ(knee). Notably, for 180° ≥ θ(knee) ≥ 130°, φ(t) and cruciate ligament strain forces can be suppressed by selecting proper pairs of ankle and hip angles. Loading of the posterior cruciate ligament increases (decreases) in the range 180° ≥ θ(knee) ≥ 150° (θ(knee) ≤ 130°) with knee extension, bending the trunk forward, and moving the feet forward in front of the knees. In the range 150° > θ(knee) > 130°, the behaviour changes depending on the foot weight distribution. The conditions for the development of anterior cruciate ligament strain forces are explained. This work enables careful use of the Smith squat in strengthening and rehabilitation programmes.     

Reconfiguring confined magnetic colloids with tunable fluid transport behavior

Collective dynamics of confined colloids are crucial in diverse scenarios such as self-assembly and phase behavior in materials science, microrobot swarms for drug delivery and microfluidic control. Yet, fine-tuning the dynamics of colloids in microscale confined spaces is still a formidable task due to the complexity of the dynamics of colloidal suspension and to the lack of methodology to probe colloids in confinement. Here, we show that the collective dynamics of confined magnetic colloids can be finely tuned by external magnetic fields. In particular, the mechanical properties of the confined colloidal suspension can be probed in real time and this strategy can be also used to tune microscale fluid transport. Our experimental and theoretical investigations reveal that the collective configuration characterized by the colloidal entropy is controlled by the colloidal concentration, confining ratio and external field strength and direction. Indeed, our results show that mechanical properties of the colloidal suspension as well as the transport of the solvent in microfluidic devices can be controlled upon tuning the entropy of the colloidal suspension. Our approach opens new avenues for the design and application of drug delivery, microfluidic logic, dynamic fluid control, chemical reaction and beyond.