Search results

Automatic modulation recognition (AMR) is a challenging problem in intelligent communication systems and has wide application prospects. At present, although many AMR methods based on deep learning have been proposed, the methods proposed by these works cannot be directly applied to the actual wireless communication scenario, because there are usually two kinds of dilemmas when recognizing the real modulated signal, namely, long sequence and noise. This paper aims to effectively process in-phase quadrature (IQ) sequences of very long signals interfered by noise.

This paper proposes a general model for a modulation classifier based on a two-layer nested structure of long short-term memory (LSTM) networks, called a two-layer nested structure (TLN)-LSTM, which exploits the time sensitivity of LSTM and the ability of the nested network structure to extract more features, and can achieve effective processing of ultra-long signal IQ sequences collected from real wireless communication scenarios that are interfered by noise.

Experimental results show that our proposed model has higher recognition accuracy for five types of modulation signals, including amplitude modulation, frequency modulation, gaussian minimum shift keying, quadrature phase shift keying and differential quadrature phase shift keying, collected from real wireless communication scenarios. The overall classification accuracy of the proposed model for these signals can reach 73.11%, compared with 40.84% for the baseline model. Moreover, this model can also achieve high classification performance for analog signals with the same modulation method in the public data set HKDD_AMC36.

At present, although many AMR methods based on deep learning have been proposed, these works are based on the model’s classification results of various modulated signals in the AMR public data set to evaluate the signal recognition performance of the proposed method rather than collecting real modulated signals for identification in actual wireless communication scenarios. The methods proposed in these works cannot be directly applied to actual wireless communication scenarios. Therefore, this paper proposes a new AMR method, dedicated to the effective processing of the collected ultra-long signal IQ sequences that are interfered by noise.

Compared with traditional methods relying on manual teaching or system modeling, data-driven learning methods, such as deep reinforcement learning and imitation learning, show more promising potential to cope with the challenges brought by increasingly complex tasks and environments, which have become the hot research topic in the field of robot skill learning. However, the contradiction between the difficulty of collecting robot–environment interaction data and the low data efficiency causes all these methods to face a serious data dilemma, which has become one of the key issues restricting their development. Therefore, this paper aims to comprehensively sort out and analyze the cause and solutions for the data dilemma in robot skill learning.

First, this review analyzes the causes of the data dilemma based on the classification and comparison of data-driven methods for robot skill learning; Then, the existing methods used to solve the data dilemma are introduced in detail. Finally, this review discusses the remaining open challenges and promising research topics for solving the data dilemma in the future.

This review shows that simulation–reality combination, state representation learning and knowledge sharing are crucial for overcoming the data dilemma of robot skill learning.

To the best of the authors’ knowledge, there are no surveys that systematically and comprehensively sort out and analyze the data dilemma in robot skill learning in the existing literature. It is hoped that this review can be helpful to better address the data dilemma in robot skill learning in the future.

Music sentiment analysis helps to promote the diversification of music information retrieval methods. Traditional music emotion classification tasks suffer from high manual workload and low classification accuracy caused by difficulty in feature extraction and inaccurate manual determination of hyperparameter. In this paper, the authors propose an optimized convolution neural network-random forest (CNN-RF) model for music sentiment classification which is capable of optimizing the manually selected hyperparameters to improve the accuracy of music sentiment classification and reduce labor costs and human classification errors.

A CNN-RF music sentiment classification model is designed based on quantum particle swarm optimization (QPSO). First, the audio data are transformed into a Mel spectrogram, and feature extraction is conducted by a CNN. Second, the music features extracted are processed by RF algorithm to complete a preliminary emotion classification. Finally, to select the suitable hyperparameters for a CNN, the QPSO algorithm is adopted to extract the best hyperparameters and obtain the final classification results.

The model has gone through experimental validations and achieved a classification accuracy of 97 per cent for different sentiment categories with shortened training time. The proposed method with QPSO achieved 1.2 and 1.6 per cent higher accuracy than that with particle swarm optimization and genetic algorithm, respectively. The proposed model had great potential for music sentiment classification.

The dual contribution of this work comprises the proposed model which integrated two deep learning models and the introduction of a QPSO into model optimization. With these two innovations, the efficiency and accuracy of music emotion recognition and classification have been significantly improved.

Full adder cells are building blocks of arithmetic circuits and affect the performance of the entire digital system. The purpose of this study is to provide a low-power and high-performance full adder cell.

Approximate computing is a novel paradigm that is used to design low-power and high-performance circuits. In this paper, a novel 1-bit approximate full adder cell is presented using the combination of complementary metal-oxide-semiconductor, transmission gate and pass transistor logic styles.

Simulation results confirm the superiority of the proposed design in terms of power consumption and power–delay product (PDP) criteria compared to state-of-the-art circuits. Also, the proposed full adder cell is applied in an 8-bit ripple carry adder to accomplish image processing applications including image blending, motion detection and edge detection. The results confirm that the proposed cell has premier compromise and outperforms its counterparts.

The proposed cell consists of only 11 transistors and decreases the switching activity remarkably. Therefore, it is a low-power and low-PDP cell.

The present work highlights the outstanding properties of Cannabis sativa that can be harnessed for various utilitarian functions and its climate friendly properties.

In this paper, the authors reviewed current research on all possible utilities from household work to manufacturing of various products that are environmentally sustainable. The authors have presented some of their research on this materials and also exploration of hemp as an archaeological material based on the findings from wall paintings of Ellora caves.

There are references of hemp use in mixing with earthen/lime plaster of western Indian monuments. Around 1,500 years of Ellora’s earthen plaster, despite harsh climatic conditions, survived due to the presence of hemp in the plaster that adds durability, fibrosity and its capacity to ward off insects and control humidity. Furthermore, the outstanding quality of Cannabis as carbon sequestrant was harnessed by Indians of ancient times in Ellora mural paintings.

This work discusses some relevant literature on the potential use of hempcrete aligned with Agenda 2030 of sustainable development goals.

There are several research going on in producing sustainable materials using hemp that have the least environmental impact and can provide eco-friendly solutions.

The authors impress upon the readers about multifarious utility of the hemp and advices for exploration of this material to address many environmental issues.

This paper presents both review of the existing papers and some components coming directly from their laboratory investigations.

The design, fabrication and experimental validation of defected microstrip structure (DMS) are proposed to address the problem of near-end crosstalk (NEXT) and far-end crosstalk (FEXT) between the microstrip transmission lines in a printed circuit board.

The proposed DMS evolved with the combination of spur line (L-shaped DMS) and U-shaped DMS topologies. This technique reduces the strength of electromagnetic coupling and suppresses crosstalk by optimizing the capacitive and inductive coupling ratio between the linked microstrip lines. The practical inductance value is much more significant in DMS than in defected ground structures (DGS), but the capacitance value remains the same.

A DMS unit is etched on the aggressor microstrip line instead of the DGS circuit. Because there is no leakage via the ground plane and the circuit size is far smaller than with DGS, the enclosure issue is disregarded. DMS structures have a larger effective inductance and are resistant to electromagnetic interference. A tightly coupled transmission line structure with minimal separation between the coupled microstrip line is designed using DMS. Further research must be conducted to improve the NEXT, FEXT and spacing between the transmission lines.

Simulation and actual measurement results show that the proposed DMS structure can effectively suppress crosstalk by analysing the S-parameters, namely, S_12, S_13 and S_14, with measured values of 1.48 dB, 20.65 dB and 21.099 dB, respectively. The data rate is measured to be 1.34 Gbps as per the eye diagram characterization. The results show that the NEXT and FEXT are reduced by approximately 20 dB in the frequency range of 1–11 GHz for mixed signals. The substantial measured results in the vector network analyser coincide with the computer simulation technology microwave studio suite simulation results.

Diffusion studies investigate the propagation of behavior, attitudes, or beliefs across a networked population. Some behavior is binary, e.g., whether or not to install solar panels, while other behavior is continuous, e.g., wastefulness with plastic. Similarly, attitudes and beliefs often allow nuance, but can become practically binary in polarized environments. We argue that this property of behavior and attitudes – whether they are binary or continuous – should critically affect whether a population becomes homogenous in its adoption of that behavior. Models show that only continuous behavior converges across a network. Specifically, binary behavior allows local convergence, as multiple states can be local majorities. Continuous behavior becomes uniform across the network through a logic of communicating vessels. We present a model comparing the diffusion of both types of behavior and report on a laboratory experiment that tests it. In the model, actors have to distribute an investment over two options, while a majority receives information that points to the optimal option and a minority receives misguided information that points toward the other option. We predict that when adjacent persons receive misguided information this can hinder convergence toward optimal investment behavior in small networked groups, especially when subjects cannot split their investment, i.e., binary choice. Results falsify our theoretical predictions: Although investment decisions are significantly negatively affected by local majorities only in the binary condition, this difference with the continuous condition is not itself significant. Binary and continuous behavior therefore achieve comparable incidences of optimal investment in the experiment. The failure of the theoretical predictions appears due to a substantial level of error in decision-making, which prevents local majorities from locking in on a suboptimal behavior.

The construction industries at present are focusing on designing sustainable concrete with less carbon footprint. Considering this aspect, a Fibre-Reinforced Geopolymer Concrete (FGC) was developed with 8 and 10 molarities (M). At elevated temperatures, concrete experiences deterioration of its mechanical properties which is in some cases associated with spalling, leading to the building collapse.

In this study, six geopolymer-based mix proportions are prepared with crimped steel fibre (SF), polypropylene fibre (PF), basalt fibre (BF), a hybrid mixture consisting of (SF + PF), a hybrid mixture with (SF + BF), and a reference specimen (without fibres). After temperature exposure, ultrasonic pulse velocity, physical characteristics of damaged concrete, loss of compressive strength (CS), split tensile strength (TS), and flexural strength (FS) of concrete are assessed. A polynomial relationship is developed between residual strength properties of concrete, and it showed a good agreement.

The test results concluded that concrete with BF showed a lower loss in CS after 925 °C (i.e. 60 min of heating) temperature exposure. In the case of TS, and FS, the concrete with SF had lesser loss in strength. After 986 °C and 1029 °C exposure, concrete with the hybrid combination (SF + BF) showed lower strength deterioration in CS, TS, and FS as compared to concrete with PF and SF + PF. The rate of reduction in strength is similar to that of GC-BF in CS, GC-SF in TS and FS.

Performance evaluation under fire exposure is necessary for FGC. In this study, we provided the mechanical behaviour and physical properties of SF, PF, and BF-based geopolymer concrete exposed to high temperatures, which were evaluated according to ISO standards. In addition, micro-structural behaviour and linear polynomials are observed.

The purpose of this study is to evaluate the 3D printability of a multimaterial, fully self-supporting auxetic structure. This will contribute to expanding the application of additive manufacturing (AM) to new products, such as automotive suspensions.

An experimental approach for sample fabrication on a multiextruder 3D printer and characterization by compression testing was conducted along with numerical simulations, which were used to support the design of different auxetic configurations for the jounce bumper.

The effect of stacking different auxetic cell modules was discussed, and the findings demonstrated that a one-piece printed structure has a better performance than one composed of multiple single modules stacked on top of each other.

The quality of the 3D printing process affected the performance of the final components and reproducibility of the results. Therefore, researchers are encouraged to further study component fabrication optimization to achieve a more reliable process.

This research work can help improve the manufacturing and functionality of a critical element of automotive suspension systems, such as the jounce bumper, which can efficiently reduce noise, vibration and harshness by absorbing impact energy.

In previous research, auxetic structures for the application of jounce bumpers have already been suggested. However, to the best of the authors’ knowledge, in this work, an AM approach was used for the first time to fabricate multimaterial auxetic structures, not only by co-printing a flexible thermoplastic polymer with a stiffer one but also by continuously extruding multilevel structures of auxetic cell modules.

In a packaging olives manufacturing system, the drained weight of the product plays a decisive role in customer’s satisfaction as well as in financial saving for the organization. The purpose of this study is to minimize the variation of the drained weight of olives in the production system to avoid the negative consequences.

The research develops a practical implementation step-by-step of Six Sigma define, measure, analyze, improve and control (DMAIC) in reducing the variation of the drained weight of olives.

Data analysis was used at various phases of the project to identify the root causes of rejection and rework. As a result of the necessary interventions and actions to optimize the manufacturing process, the standard deviation of drained weight was significantly reduced by 51.02%, with a 99.97% decrease in the number of parts per million defectives. Thus, the yield of the production process was improved by 8.24%. The estimated annual savings from this project were US$ 228,000 resulting from reduced rejection and rework.

This research may be used in packaging olives production systems as a tool for managers and engineers planning to increase productivity and efficiency while also improving product quality. The study also provided the organization with helpful actions that will be used to guide future Six Sigma operations management on the system. Thus, practical guidelines and solutions are provided.

In this project, for the first time, the Six Sigma methodology has been applied to solve a real-world problem in the packaging olives manufacturing system and to show that the DMAIC approach may assist to improve the efficiency of their operations and hence contribute to their quest toward continuous improvement.