An investigation into the deep learning approach in sentimental analysis using graph-based theories

Sentiment analysis is a branch of natural language analytics that aims to correlate what is expressed which comes normally within unstructured format with what is believed and learnt. Several attempts have tried to address this gap (i.e., Naive Bayes, RNN, LSTM, word embedding, etc.), even though the deep learning models achieved high performance, their generative process remains a “black-box” and not fully disclosed due to the high dimensional feature and the non-deterministic weights assignment. Meanwhile, graphs are becoming more popular when modeling complex systems while being traceable and understood. Here, we reveal that a good trade-off transparency and efficiency could be achieved with a Deep Neural Network by exploring the Credit Assignment Paths theory. To this end, we propose a novel algorithm which alleviates the features’ extraction mechanism and attributes an importance level of selected neurons by applying a deterministic edge/node embeddings with attention scores on the input unit and backward path respectively. We experiment on the Twitter Health News dataset were the model has been extended to approach different approximations (tweet/aspect and tweets’ source levels, frequency, polarity/subjectivity), it was also transparent and traceable. Moreover, results of comparing with four recent models on same data corpus for tweets analysis showed a rapid convergence with an overall accuracy of ≈83% and 94% of correctly identified true positive sentiments. Therefore, weights can be ideally assigned to specific active features by following the proposed method. As opposite to other compared works, the inferred features are conditioned through the users’ preferences (i.e., frequency degree) and via the activation’s derivatives (i.e., reject feature if not scored). Future direction will address the inductive aspect of graph embeddings to include dynamic graph structures and expand the model resiliency by considering other datasets like SemEval task7, covid-19 tweets, etc.

Formation of highly concentrated heterogeneous flows during plasma deposition of powder materials

Most industrial installations for plasma spraying of powder materials are equipped by nozzles with local (radial) powder input into the thermal plasma jet generated by the plasma torch. Such a local input of the sprayed material significantly perturbs the flow of the plasma jet, and causes dispersion of temperature and velocity of the particles of the sprayed powder materials. This work presents study of high-temperature heterogeneous flows generated by the electric arc plasma torch PNK - 50 with an annular (circular) input unit of powder materials with their gas-dynamic focusing developed at ITAM SB RAS. The performed experiments proved that the annular injection of a powder material guarantees the stable formation of a highly concentrated flow of thermal plasma with particles of sprayed powder materials. The comparative analysis clearly showed the advantages of annular powder input unit with its gas-dynamic focusing. In contrast to local point injection, axisymmetric annular injection practically does not disturb the jet of thermal plasma and, thus, significantly increases the efficiency of interphase exchange.

FCNN: An Efficient Intrusion Detection Method Based on Raw Network Traffic

When traditional machine learning methods are applied to network intrusion detection, they need to rely on expert knowledge to extract feature vectors in advance, which incurs lack of flexibility and versatility. Recently, deep learning methods have shown superior performance compared with traditional machine learning methods. Deep learning methods can learn the raw data directly, but they are faced with expensive computing cost. To solve this problem, a preprocessing method based on multipacket input unit and compression is proposed, which takes m data packets as the input unit to maximize the retention of information and greatly compresses the raw traffic to shorten the data learning and training time. In our proposed method, the CNN network structure is optimized and the weights of some convolution layers are assigned directly by using the Gabor filter. Experimental results on the benchmark data set show that compared with the existing models, the proposed method improves the detection accuracy by 2.49% and reduces the training time by 62.1%. In addition, the experiments show that the proposed compression method has obvious advantages in detection accuracy and computational efficiency compared with the existing compression methods.

Spiking Neural Membrane Computing Models

As third-generation neural network models, spiking neural P systems (SNP) have distributed parallel computing capabilities with good performance. In recent years, artificial neural networks have received widespread attention due to their powerful information processing capabilities, which is an effective combination of a class of biological neural networks and mathematical models. However, SNP systems have some shortcomings in numerical calculations. In order to improve the incompletion of current SNP systems in dealing with certain real data technology in this paper, we use neural network structure and data processing methods for reference. Combining them with membrane computing, spiking neural membrane computing models (SNMC models) are proposed. In SNMC models, the state of each neuron is a real number, and the neuron contains the input unit and the threshold unit. Additionally, there is a new style of rules for neurons with time delay. The way of consuming spikes is controlled by a nonlinear production function, and the produced spike is determined based on a comparison between the value calculated by the production function and the critical value. In addition, the Turing universality of the SNMC model as a number generator and acceptor is proved.

An Analysis of On-Bord High-Voltage Converters of Single-Phase Alternating Current with Increased Miroelectric Power Factor

The power circuit arrangements of on-board high-voltage static converters fed from a 3000 V AC single-phase network that in the general case produce multi-channel AC and DC output voltages are considered. The basic technical requirements posed to such converters are formulated. The general structural diagram of high-voltage converters with improved electric power consumption quality is given. Possible power circuit arrangements for the high-voltage converter input unit based on single-phase input current correction devices are considered. A classification and criteria for comparative evaluation of the possible power circuit arrangements of these devices are proposed. The information presented in the article will be of interest for specialists engaged in designing on-board electrical systems involving high-voltage converters that must comply with strict requirements for the quality of consumed single-phase input current.

Energy efficient biomorphic pulse information coding in electronic neurons for the entrance unit of the neuroprocessor

This article studies the implementation of some well-known principles of information work of biological systems in the input unit of the neuroprocessor, including spike coding of information used in models of neural networks of the latest generation.<br> The development of modern neural network IT gives rise to a number of urgent tasks at the junction of several scientific disciplines. One of them is to create a hardware platform&nbsp;— a neuroprocessor for energy-efficient operation of neural networks. Recently, the development of nanotechnology of the main units of the neuroprocessor relies on combined memristor super-large logical and storage matrices. The matrix topology is built on the principle of maximum integration of programmable links between nodes. This article describes a method for implementing biomorphic neural functionality based on programmable links of a highly integrated 3D logic matrix.<br> This paper focuses on the problem of achieving energy efficiency of the hardware used to model neural networks. The main part analyzes the known facts of the principles of information transfer and processing in biological systems from the point of view of their implementation in the input unit of the neuroprocessor. The author deals with the scheme of an electronic neuron implemented based on elements of a 3D logical matrix. A pulsed method of encoding input information is presented, which most realistically reflects the principle of operation of a sensory biological neural system. The model of an electronic neuron for selecting ranges of technological parameters in a real 3D logic matrix scheme is analyzed. The implementation of disjunctively normal forms is shown, using the logic function in the input unit of a neuroprocessor as an example. The results of modeling fragments of electric circuits with memristors of a 3D logical matrix in programming mode are presented.<br> The author concludes that biomorphic pulse coding of standard digital signals allows achieving a high degree of energy efficiency of the logic elements of the neuroprocessor by reducing the number of valve operations. Energy efficiency makes it possible to overcome the thermal limitation of the scalable technology of three-dimensional layout of elements in memristor crossbars.

Semantic Labeling of natural Scene Images Using Color Features

Scene image classification systems firstly need to locate the objects, and then classify the whole image. The color feature is importance to describe the properties of an image surface. The paper presents a framework for scene images to label local regions using color features. The paper uses maker-controlled watershed algorithm to segment the input image into regions. This paper uses the segmented regions as a basic input unit, and then extract Color Histogram (CH) and Color Moment (CM) features in HSV space. This system performs labeling using 3-layer Feed Forward Neural Network (FFNN) classifier. The system tests accuracy on public Microsoft Research Cambridge (MSRC) 9-class dataset.

Thermodynamic Performance and Optimization Analysis of a Modified Organic Flash Cycle for the Recovery of Low-Grade Heat

The recently proposed organic flash cycle (OFC) has the potential for the efficient recovery of low-grade heat, mainly due to the reduction of irreversibilities in the heat input unit. In the present study, a modified OFC (OFCM) employing a two-phase expander (TPE) and regeneration is proposed and thermodynamic and optimization analysis on this cycle is conducted compared with the basic OFC (OFCB). Six substances are considered as the working fluids. Influences of flash temperature, source temperature, and working fluid are systemically investigated on the system performance. Results showed that OFCM is superior to OFCB in the aspects of power production, thermal, and second-law efficiencies.

MEMS Variable Area Capacitor for Room Temperature Electrometry

This paper introduces a new way to detect charge using MEMS variable capacitors for extremely sensitive, room temperature electrometry. It is largely based on the electrometers introduced by Riehl et al. [1] except variable capacitance is created by a changing area, not a changing gap. The new scheme will improve MEMS electrometers by eliminating the effects of squeeze-film damping and by theoretically increasing the maximum charge resolution by 70%. The charge conversion gain (the increase in output voltage per input unit charge) for this system is derived. The result show good agreement with MATLAB calculations.