Automatic Synthesis Technology of Music Teaching Melodies Based on Recurrent Neural Network

Computer music creation boasts broad application prospects. It generally relies on artificial intelligence (AI) and machine learning (ML) to generate the music score that matches the original mono-symbol score model or memorize/recognize the rhythms and beats of the music. However, there are very few music melody synthesis models based on artificial neural networks (ANNs). Some ANN-based models cannot adapt to the transposition invariance of original rhythm training set. To overcome the defect, this paper tries to develop an automatic synthesis technology of music teaching melodies based on recurrent neural network (RNN). Firstly, a strategy was proposed to extract the acoustic features from music melody. Next, the sequence-sequence model was adopted to synthetize general music melodies. After that, an RNN was established to synthetize music melody with singing melody, such as to find the suitable singing segments for the music melody in teaching scenario. The RNN can synthetize music melody with a short delay solely based on static acoustic features, eliminating the need for dynamic features. The proposed model was proved valid through experiments.

THE AUTOMATIC SYNTHESIS OF PETRI NETS BASED ON THE FUNCTIONING OF ARTIFICIAL NEURAL NETWORK

Context. The important task was solved during the scientific research related to the development of the methods for automatic synthesis of Petri nets while tuning up of the coordinating automatic control systems. The importance of development of these methods is due to the evolution of intelligent systems. These systems provide the automation of labor intensive processes in the particular case this is the tuning of the certain type of complex control systems. Objective. The purpose of the scientific work is to minimize the time and automation of process in tuning of the multilevel coordinating automatic control systems. Method. The principle of automatic synthesis of Petri nets and the implementation of certain algorithms for tuning complex control systems based on the functioning of an artificial neural network are proposed. The mathematical description of the method for changing the coefficients in neural connections of network in the synthesis of Petri nets is presented. Results. The experiments were conducted in the Matlab\Simulink 2012a environment. These experiments were bound to the joint functioning of an artificial neural network and Petri nets. The functioning of Petri nets was presented in the Matlab \ Simulink environment using Statflow diagrams. As a result of the experiments we have obtained the temporal characteristics of the functioning of artificial neural network providing the composition of Petri nets. The fundamental suitability of using artificial neural network to provide the automatic composition of Petri nets was determined on the basis of analysis of temporal characteristics. Conclusion. The problem linked to the development of system for the joint functioning of neural network and Petri nets for the formation of algorithms and sequential calculations was solved in this work. Thus the method of automatic synthesis of Petri nets and the method of developing of the certain algorithms based on the functioning of a neural network were further developed.

From Lustre to Simulink

Model-based design is now unavoidable when building embedded systems and, more specifically, controllers. Among the available model languages, the synchronous dataflow paradigm, as implemented in languages such as MATLAB Simulink or ANSYS SCADE, has become predominant in critical embedded system industries. Both of these frameworks are used to design the controller itself but also provide code generation means, enabling faster deployment to target and easier V&V activities performed earlier in the design process, at the model level. Synchronous models also ease the definition of formal specification through the use of synchronous observers, attaching requirements to the model in the very same language, mastered by engineers and tooled with simulation means or code generation. However, few works address the automatic synthesis of MATLAB Simulink annotations from lower-level models or code. This article presents a compilation process from Lustre models to genuine MATLAB Simulink, without the need to rely on external C functions or MATLAB functions. This translation is based on the modular compilation of Lustre to imperative code and preserves the hierarchy of the input Lustre model within the generated Simulink one. We implemented the approach and used it to validate a compilation toolchain, mapping Simulink to Lustre and then C, thanks to equivalence testing and checking. This backward compilation from Lustre to Simulink also provides the ability to produce automatically Simulink components modeling specification, proof arguments, or test cases coverage criteria.

Ensuring the Correctness of Regular Expressions: A Review

Regular expressions are widely used within and even outside of computer science due to their expressiveness and flexibility. However, regular expressions have a quite compact and rather tolerant syntax that makes them hard to understand, hard to compose, and error-prone. Faulty regular expressions may cause failures of the applications that use them. Therefore, ensuring the correctness of regular expressions is a vital prerequisite for their use in practical applications. The importance and necessity of ensuring correct definitions of regular expressions have attracted extensive attention from researchers and practitioners, especially in recent years. In this study, we provide a review of the recent works for ensuring the correct usage of regular expressions. We classify those works into different categories, including the empirical study, test string generation, automatic synthesis and learning, static checking and verification, visual representation and explanation, and repairing. For each category, we review the main results, compare different approaches, and discuss their advantages and disadvantages. We also discuss some potential future research directions.

Standardization of the [68Ga]Ga-PSMA-11 Radiolabeling Protocol in an Automatic Synthesis Module: Assessments for PET Imaging of Prostate Cancer

Prostate-specific membrane antigen (PSMA) is a glycoprotein present in the prostate, that is overexpressed in prostate cancer (PCa). Recently, PSMA-directed radiopharmaceuticals have been developed, allowing the pinpointing of tumors with the Positron Emission Tomography (PET) or Single Photon Emission Computed Tomography (SPECT) imaging techniques. The aim of the present work was to standardize and validate an automatic synthesis module-based radiolabeling protocol for [68Ga]Ga-PSMA-11, as well as to produce a radiopharmaceutical for PET imaging of PCa malignancies. [68Ga]Ga-PSMA-11 was evaluated to determine the radiochemical purity (RCP), stability in saline solution and serum, lipophilicity, affinity to serum proteins, binding and internalization to lymph node carcinoma of the prostate (LNCaP) cells, and ex vivo biodistribution in mice. The radiopharmaceutical was produced with an RCP of 99.06 ± 0.10%, which was assessed with reversed-phase high-performance liquid chromatography (RP-HPLC). The product was stable in saline solution for up to 4 h (RCP > 98%) and in serum for up to 1 h (RCP > 95%). The lipophilicity was determined as −3.80 ± 0.15, while the serum protein binding (SPB) was <17%. The percentages of binding to LNCaP cells were 4.07 ± 0.51% (30 min) and 4.56 ± 0.46% (60 min), while 19.22 ± 2.73% (30 min) and 16.85 ± 1.34% (60 min) of bound material was internalized. High accumulation of [68Ga]Ga-PSMA-11 was observed in the kidneys, spleen, and tumor, with a tumor-to-contralateral-muscle ratio of >8.5 and a tumor-to-blood ratio of >3.5. In conclusion, an automatic synthesis module-based radiolabeling protocol for [68Ga]Ga-PSMA-11 was standardized and the product was evaluated, thus verifying its characteristics for PET imaging of PCa tumors in a clinical environment.