Search

Resident combustion of solid fuel has been widely acknowledged as a high potential for pollutant reduction. However, there is a marked asymmetry between more pollutant emission and less burned volatiles of biomass and coal in the combustion process. To study the solid fuel optimum combustion form in a household stove, both the pollution reduction and energy efficient utilization of crop straws and coals were investigated. Taking the molding pressure and clay addition ratio as variable process conditions, the research of bio-coal briquette (made from the mixture of anthracite and biomass) was implemented in the range of 15~35 MP and 5~15%, respectively. Biomass and coal work complementarily for each other’s combustion property development. In particular, the pyrolysis gas produced by biomass low-temperature devolatilization is featured with low ignition point and is distributed in the bio-coal briquette. Its own combustion provides energy for anthracite particle combustion. Consequently, a positive effect was identified when bio-coal briquettes were used as residential fuel, and further improvement manifested in reducing more than 90% of particle matter (PM) and achieving about twice the thermal efficiencies (TEs) compared with the mass-weighted average values of coal briquettes and biomass briquettes. 88.8 ± 11.8%, 136.7 ± 13.7% and 81.4 ± 17.7% more TEs were provided by wheat straw–coal briquettes, rice straw–coal briquettes and maize straw–coal briquettes. 93.3 ± 3.1% (wheat straw–coal), 97.6 ± 0.2% (rice straw–coal) and 90.4 ± 2.2% (maize straw–coal) in terms of PM2.5 emission factors (EFs) was reduced. For bio-coal briquette, a 25 MPa and 10% addition were determined as the optimum molding pressure and clay addition ratio. Bio-coal briquettes with higher TEs and lower PM EFs will bring about substantial benefits for air quality promotion, human health and energy saving.

Over the past four decades, the prophecy from computer pundits and prognosticators pointed to the looming arrival of the paperless office era. However, forty years later, physical paper documents are still playing a significant role due to the ease of use, superior readability, and availability. The drawbacks of paper sheets are that they are hard to modify and retrieve, have limited space, and are environmentally unfriendly. Augmenting paper documents with digital information from mobile devices extends the two-dimensional space of physical paper documents. Various camera-based recognition and detection devices have been proposed to augment paper documents with digital information. However, there are still some limitations that exist in these systems. This paper presents a novel, low cost, spatially aware, mobile system called Ultrasonic PhoneLens. The Ultrasonic PhoneLens adopts two-dimensional dynamic image presentation and ultrasonic sound positioning techniques. It consists of two ultrasonic sound sensors, one Arduino mini-controller board, and one android mobile device. Based on the location of the mobile device over the physical paper, Ultrasonic PhoneLens can retrieve pre-saved digital information from a mobile database for the object (such as a text, a paragraph, or an image) in a paper document. An empirical study was conducted to evaluate the system performance. The results indicate that our system has a better performance in tasks such as browsing multivalent documents and sharing digital information than the Wiimote PhoneLens system.

In this paper, we proposed a scheme that Injects artificial noise from the tag end (IANT) to enhance the physical layer security of the ambient backscatter communication (ABC) system. The difference between the ABC system and the traditional radio frequency identification system is whether it uses the radio frequency (RF) signals in the environment to supply energy and modulation information for passive tags. In the IANT scheme, we select the best tag to communicate with the reader according to the channel quality between tags and reader, and at the same time select another tag to generate artificial noise that affects the receiving effect of the eavesdropper. This paper uses the method of generating noise copies in the reader to reduce the interference of artificial noise on the signal received by the reader. The simulation results show that with the increase in channel quality between tags and reader and the increase in the number of tags, the proposed IANT scheme is significantly superior to the contrast scheme in terms of system achievable secrecy rate, effectively enhancing the physical layer security of the ABC system.

Most of the papers published so far in literature have focused on the theoretical phenomena underlying the formation of chaos, rather than on the investigation of potential applications of chaos to the real world. This paper aims to bridge the gap between chaos theory and chaos applications by presenting a survey of very recent applications of chaos. In particular, the manuscript covers the last three years by describing different applications of chaos as reported in the literature published during the years 2018 to 2020, including the matter related to the symmetry properties of chaotic systems. The topics covered herein include applications of chaos to communications, to distributed sensing, to robotic motion, to bio-impedance modelling, to hardware implementation of encryption systems, to computing and to random number generation.

Recent years have seen a growing call for use of big data analytics techniques to support the realisation of symmetries and simulations in digital twins and smart factories, in which data quality plays an important role in determining the quality of big data analytics products. Although data quality affecting big data analytics has received attention in the smart factory research field, to date a systematic review of the topic of interest for understanding the present state of the art is not available, which could help reveal the trends and gaps in this area. This paper therefore presents a systematic literature review of research articles about data quality affecting big data analytics in smart factories that have been published up to 2020. We examined 31 empirical studies from our selection of papers to identify the research themes in this field. The analysis of these studies links data quality issues toward big data analytics with data quality dimensions and methods used to address these issues in the smart factory context. The findings of this systematic review also provide implications for practitioners in addressing data quality issues to better use big data analytics products to support digital symmetry in the context of smart factory.

This paper presents a computational tool for estimating energy generated by low-power photovoltaic systems based on the specific conditions of the study region since the characteristic energy equation can be obtained considering the main climatological factors affecting these systems in terms of the symmetry or skewness of the random distribution of the generated energy. Furthermore, this paper is aimed at determining any correlation that exists between meteorological variables with respect to the energy generated by 5-kW solar systems in the specific climatic conditions of the Republic of Cuba. The paper also presents the results of the influence of each climate factor on the distribution symmetry of the generated energy of the solar system. Studying symmetry in statistical models is important because they allow us to establish the degree of symmetry (or skewness), which is the probability distribution of a random variable, without having to make a graphical representation of it. Statistical skewness reports the degree to which observations are distributed evenly and proportionally above and below the center (highest) point of the distribution. In the case when the mentioned distribution is balanced, it is called symmetric.

The plastic modifications in synaptic connectivity is primarily from changes triggered by neuromodulated dopamine signals. These activities are controlled by neuromodulation, which is itself under the control of the brain. The subjective brain’s self-modifying abilities play an essential role in learning and adaptation. The artificial neural networks with neuromodulated plasticity are used to implement transfer learning in the image classification domain. In particular, this has application in image detection, image segmentation, and transfer of learning parameters with significant results. This paper proposes a novel approach to enhance transfer learning accuracy in a heterogeneous source and target, using the neuromodulation of the Hebbian learning principle, called NDHTL (Neuromodulated Dopamine Hebbian Transfer Learning). Neuromodulation of plasticity offers a powerful new technique with applications in training neural networks implementing asymmetric backpropagation using Hebbian principles in transfer learning motivated CNNs (Convolutional neural networks). Biologically motivated concomitant learning, where connected brain cells activate positively, enhances the synaptic connection strength between the network neurons. Using the NDHTL algorithm, the percentage of change of the plasticity between the neurons of the CNN layer is directly managed by the dopamine signal’s value. The discriminative nature of transfer learning fits well with the technique. The learned model’s connection weights must adapt to unseen target datasets with the least cost and effort in transfer learning. Using distinctive learning principles such as dopamine Hebbian learning in transfer learning for asymmetric gradient weights update is a novel approach. The paper emphasizes the NDHTL algorithmic technique as synaptic plasticity controlled by dopamine signals in transfer learning to classify images using source-target datasets. The standard transfer learning using gradient backpropagation is a symmetric framework. Experimental results using CIFAR-10 and CIFAR-100 datasets show that the proposed NDHTL algorithm can enhance transfer learning efficiency compared to existing methods.

This paper focuses on preventing forms of social dysfunction such as invasions of privacy and stalking by understanding the diversified situation of the rapidly increasing number of social media users who use social media services, which are various types of social networking services. To prevent these problems, we aim to identify mutual relationships by layering the relationships between social media users. In other words, in social media that has a relationship with the subject, the subject user is yet another object, so the appearance of the object viewed by the subject user and the correlation between the subjects and objects must be visualized. At this time, because the subject is an object that has changed over time, it is necessary to perform symmetrical and mutual correlation analysis based on relationship through objective layering viewed from a computer. In this paper, the mutual relationship between the subject user and the object user was defined and visualized to apply it to the deep learning model through a software program. Among various types of social media that are mainly used, user information data is gathered through the popular social media site called Instagram and our target community platforms. Consequently, it was processed again to represent user interactions among other users. Finally, three stages of mutual relationship visualization were represented through simulation and tests, and 120,000 data sets were processed, classified, and proved through the simulation results.

The dataset distribution of actual logging is asymmetric, as most logging data are unlabeled. With the traditional classification model, it is hard to predict the oil and gas reservoir accurately. Therefore, a novel approach to the oil layer recognition model using the improved whale swarm algorithm (WOA) and semi-supervised support vector machine (S3VM) is proposed in this paper. At first, in order to overcome the shortcomings of the Whale Optimization Algorithm applied in the parameter-optimization of the S3VM model, such as falling into a local optimization and low convergence precision, an improved WOA was proposed according to the adaptive cloud strategy and the catfish effect. Then, the improved WOA was used to optimize the kernel parameters of S3VM for oil layer recognition. In this paper, the improved WOA is used to test 15 benchmark functions of CEC2005 compared with five other algorithms. The IWOA–S3VM model is used to classify the five kinds of UCI datasets compared with the other two algorithms. Finally, the IWOA–S3VM model is used for oil layer recognition. The result shows that (1) the improved WOA has better convergence speed and optimization ability than the other five algorithms, and (2) the IWOA–S3VM model has better recognition precision when the dataset contains a labeled and unlabeled dataset in oil layer recognition.

Cloud based healthcare computing have changed the face of healthcare in many ways. The main advantages of cloud computing in healthcare are scalability of the required service and the provision to upscale or downsize the data storge, collaborating Artificial Intelligence (AI) and machine learning. The current paper examined various research studies to explore the utilization of intelligent techniques in health systems and mainly focused into the security and privacy issues in the current technologies. Despite the various benefits related to cloud-computing applications for healthcare, there are different types of management, technology handling, security measures, and legal issues to be considered and addressed. The key focus of this paper is to address the increased demand for cloud computing and its definition, technologies widely used in healthcare, their problems and possibilities, and the way protection mechanisms are organized and prepared when the company chooses to implement the latest evolving service model. In this paper, we focused on a thorough review of current and existing literature on different approaches and mechanisms used in e-Health to deal with security and privacy issues. Some of these approaches have strengths and weaknesses. After selecting original articles, the literature review was carried out, and we identified several models adopted in their solutions. We arrived at the reviewed articles after comparing the models used.

This paper presents a novel approach for an Intrusion Detection System (IDS) based on one kind of asymmetric optimization which use any three already well-known IDS algorithms and Triple Modular Redundancy (TMR) algorithm together. Namely, a variable threshold which indicates an attack on an observed and protected network is determined by using all three values obtained with three known IDS algorithms i.e., on previously recorded data by making a decision by majority. For these algorithms authors used algorithm of k-nearest neighbors, cumulative sum algorithm, and algorithm of exponentially weighted moving average. Using a proposed method we can get a threshold that is more precisely determined than in the case of any method individual. Practically, using TMR we obtain a dynamically threshold adjustment of IDS software, which reduces the existence of false alarms and undetected attacks, so the efficiency of such IDS software is notably higher and can get better results. Today, Denial of Service attacks (DoS) are one of the most present type of attacks and the reason for the special attention paid to them in this paper. In addition, the authors of the proposed method for IDS software used a known CIC-DDoS2019 dataset, which contains various data recordings of such attacks. Obtained results with the proposed solution showed better characteristics than each individual used algorithm in this solution. IDS software with the proposed method worked precisely and timely, which means alarms were triggered properly and efficiently.

This paper presents research focusing on visualization and pattern recognition based on computer science. Although deep neural networks demonstrate satisfactory performance regarding image and voice recognition, as well as pattern analysis and intrusion detection, they exhibit inferior performance towards adversarial examples. Noise introduction, to some degree, to the original data could lead adversarial examples to be misclassified by deep neural networks, even though they can still be deemed as normal by humans. In this paper, a robust diversity adversarial training method against adversarial attacks was demonstrated. In this approach, the target model is more robust to unknown adversarial examples, as it trains various adversarial samples. During the experiment, Tensorflow was employed as our deep learning framework, while MNIST and Fashion-MNIST were used as experimental datasets. Results revealed that the diversity training method has lowered the attack success rate by an average of 27.2 and 24.3% for various adversarial examples, while maintaining the 98.7 and 91.5% accuracy rates regarding the original data of MNIST and Fashion-MNIST.

Automated brain tumor segmentation based on 3D magnetic resonance imaging (MRI) is critical to disease diagnosis. Moreover, robust and accurate achieving automatic extraction of brain tumor is a big challenge because of the inherent heterogeneity of the tumor structure. In this paper, we present an efficient semantic segmentation 3D recurrent multi-fiber network (RMFNet), which is based on encoder–decoder architecture to segment the brain tumor accurately. 3D RMFNet is applied in our paper to solve the problem of brain tumor segmentation, including a 3D recurrent unit and 3D multi-fiber unit. First of all, we propose that recurrent units segment brain tumors by connecting recurrent units and convolutional layers. This quality enhances the model’s ability to integrate contextual information and is of great significance to enhance the contextual information. Then, a 3D multi-fiber unit is added to the overall network to solve the high computational cost caused by the use of a 3D network architecture to capture local features. 3D RMFNet combines both advantages from a 3D recurrent unit and 3D multi-fiber unit. Extensive experiments on the Brain Tumor Segmentation (BraTS) 2018 challenge dataset show that our RMFNet remarkably outperforms state-of-the-art methods, and achieves average Dice scores of 89.62%, 83.65% and 78.72% for the whole tumor, tumor core and enhancing tumor, respectively. The experimental results prove our architecture to be an efficient tool for brain tumor segmentation accurately.

The paper proposes composite materials for the manufacturing of parts of the car body structure, namely a door. This work aims to analyze the possibility of replacing the metal door of a vehicle with a door made of composite materials. Specific issues related to this replacement are analyzed in the paper. Test specimens were made of composite materials of different sizes, using several types of constituents to determine which material might be most suitable to replace metal in the manufacturing of the door. The choice of materials for the car door was made starting from the characteristics of the analyzed composite materials, but also taking into account the manufacturing possibilities and other engineering limitations. The behavior of the automotive structure as analyzed, using the finite element method for determining the stresses in the structure. Experimental verifications were performed on an experimental stand which has been specially designed for this purpose, to validate the proposed model.

In the field of cognitive science, much research has been conducted on the diverse applications of artificial intelligence (AI). One important area of study is machines imitating human thinking. Although there are various approaches to development of thinking machines, we assume that human thinking is not always optimal in this paper. Sometimes, humans are driven by emotions to make decisions that are not optimal. Recently, deep learning has been dominating most machine learning tasks in AI. In the area of optimal decisions involving AI, many traditional machine learning methods are rapidly being replaced by deep learning. Therefore, because of deep learning, we can expect the faster growth of AI technology such as AlphaGo in optimal decision-making. However, humans sometimes think and act not optimally but emotionally. In this paper, we propose a method for building thinking machines imitating humans using Bayesian decision theory and learning. Bayesian statistics involves a learning process based on prior and posterior aspects. The prior represents an initial belief in a specific domain. This is updated to posterior through the likelihood of observed data. The posterior refers to the updated belief based on observations. When the observed data are newly added, the current posterior is used as a new prior for the updated posterior. Bayesian learning such as this also provides an optimal decision, thus, this is not well-suited to the modeling of thinking machines. Therefore, we study a new Bayesian approach to developing thinking machines using Bayesian decision theory. In our research, we do not use a single optimal value expected by the posterior, instead, we generate random values from the last updated posterior to be used for thinking machines that imitate human thinking.

Climate change and air pollution are among the key drivers of energy transition worldwide. The adoption of renewable resources can act as a peacemaker and give stability regarding the damaging effects of fossil fuels challenging public health as well as the tension made between countries in global prices of oil and gas. Understanding the potential and capabilities to produce renewable energy resources is a crucial pre-requisite for countries to utilize them and to scale up clean and stable sources of electricity generation. This paper presents a hybrid methodology that combines the data envelopment analysis (DEA) Window model, and fuzzy technique for order of preference by similarity to ideal solution (FTOPSIS) in order to evaluate the capabilities of 42 countries in terms of renewable energy production potential. Based on three inputs (population, total energy consumption, and total renewable energy capacity) and two outputs (gross domestic product and total energy production), DEA window analysis chose the list of potential countries, including Norway, United Kingdom, Kuwait, Australia, Netherlands, United Arab Emirates, United States, Japan, Colombia, and Italy. Following that, the FTOPSIS model pointed out the top three countries (United States, Japan, and Australia) that have the greatest capabilities in producing renewable energies based on five main criteria, which are available resources, energy security, technological infrastructure, economic stability, and social acceptance. This paper aims to offer an evaluation method for countries to understand their potential of renewable energy production in designing stimulus packages for a cleaner energy future, thereby accelerating sustainable development.

Feature-based pedestrian detection method is currently the mainstream direction to solve the problem of pedestrian detection. In this kind of method, whether the appropriate feature can be extracted is the key to the comprehensive performance of the whole pedestrian detection system. It is believed that the appearance of a pedestrian can be better captured by the combination of edge/local shape feature and texture feature. In this field, the current method is to simply concatenate HOG (histogram of oriented gradient) features and LBP (local binary pattern) features extracted from an image to produce a new feature with large dimension. This kind of method achieves better performance at the cost of increasing the number of features. In this paper, Choquet integral based on the signed fuzzy measure is introduced to fuse HOG and LBP descriptors in parallel that is expected to improve accuracy without increasing feature dimensions. The parameters needed in the whole fusion process are optimized by a training algorithm based on genetic algorithm. This architecture has three advantages. Firstly, because the fusion of HOG and LBP features is parallel, the dimensions of the new features are not increased. Secondly, the speed of feature fusion is fast, thus reducing the time of pedestrian detection. Thirdly, the new features after fusion have the advantages of HOG and LBP features, which is helpful to improve the detection accuracy. The series of experimentation with the architecture proposed in this paper reaches promising and satisfactory results.

Artificial Neural Networks (ANNs) were created inspired by the neural networks in the human brain and have been widely applied in speech processing. The application areas of ANN include: Speech recognition, speech emotion recognition, language identification, speech enhancement, and speech separation, amongst others. Likewise, given that speech processing performed by humans involves complex cognitive processes known as auditory attention, there has been a growing amount of papers proposing ANNs supported by deep learning algorithms in conjunction with some mechanism to achieve symmetry with the human attention process. However, while these ANN approaches include attention, there is no categorization of attention integrated into the deep learning algorithms and their relation with human auditory attention. Therefore, we consider it necessary to have a review of the different ANN approaches inspired in attention to show both academic and industry experts the available models for a wide variety of applications. Based on the PRISMA methodology, we present a systematic review of the literature published since 2000, in which deep learning algorithms are applied to diverse problems related to speech processing. In this paper 133 research works are selected and the following aspects are described: (i) Most relevant features, (ii) ways in which attention has been implemented, (iii) their hypothetical relationship with human attention, and (iv) the evaluation metrics used. Additionally, the four publications most related with human attention were analyzed and their strengths and weaknesses were determined.

This paper presents the results of the development of a technology for manufacturing electro-optical Mach–Zehnder modulators based on InP. The key features of the technology are the use of one SiNx double-patterned dielectric mask with two sequential inductively coupled plasma (ICP) etchings of the heterostructure for the simultaneous formation of active and passive sections of the modulator’s optical waveguides. This prevents misalignment errors at the borders. The planarization of the wafer surface was performed using photosensitive benzocyclobutene (BCB) films in a combined scheme. Windows in the BCB film to the bottom ohmic contact and at the die boundaries were formed by lithography, and then the excess thickness of the BCB film was removed by ICP etching until the p-InGaAs contact regions of the p-i-n heterostructure were exposed. The deposition and annealing of the top ohmic contact Ti/Pt/Au (50/25/400 nm) to p-InGaAs was carried out after the surface planarization, with the absence of both deformation and cracking of the planarizing film. A new approach to the division of the wafers into single dies is presented in this paper. The division was carried out in two stages: first, grooves were formed by dicing or deep wet etching, and then cleaving was performed along the formed grooves. The advantages of these techniques are that it allows the edges of the waveguides at the optical input/outputs to be formed and the antireflection coating to be deposited simultaneously on all dies on the wafer, before it is divided.

Over the past few years, the study of environmental sound classification (ESC) has become very popular due to the intricate nature of environmental sounds. This paper reports our study on employing various acoustic features aggregation and data enhancement approaches for the effective classification of environmental sounds. The proposed data augmentation techniques are mixtures of the reinforcement, aggregation, and combination of distinct acoustics features. These features are known as spectrogram image features (SIFs) and retrieved by different audio feature extraction techniques. All audio features used in this manuscript are categorized into two groups: one with general features and the other with Mel filter bank-based acoustic features. Two novel and innovative features based on the logarithmic scale of the Mel spectrogram (Mel), Log (Log-Mel) and Log (Log (Log-Mel)) denoted as L2M and L3M are introduced in this paper. In our study, three prevailing ESC benchmark datasets, ESC-10, ESC-50, and Urbansound8k (Us8k) are used. Most of the audio clips in these datasets are not fully acquired with sound and include silence parts. Therefore, silence trimming is implemented as one of the pre-processing techniques. The training is conducted by using the transfer learning model DenseNet-161, which is further fine-tuned with individual optimal learning rates based on the discriminative learning technique. The proposed methodologies attain state-of-the-art outcomes for all used ESC datasets, i.e., 99.22% for ESC-10, 98.52% for ESC-50, and 97.98% for Us8k. This work also considers real-time audio data to evaluate the performance and efficiency of the proposed techniques. The implemented approaches also have competitive results on real-time audio data.

Mass media not only reflect the activities of state bodies but also shape the informational context, sentiment, depth, and significance level attributed to certain state initiatives and social events. Multilateral and quantitative (to the practicable extent) assessment of media activity is important for understanding their objectivity, role, focus, and, ultimately, the quality of the society’s “fourth power”. The paper proposes a method for evaluating the media in several modalities (topics, evaluation criteria/properties, classes), combining topic modeling of the text corpora and multiple-criteria decision making. The evaluation is based on an analysis of the corpora as follows: the conditional probability distribution of media by topics, properties, and classes is calculated after the formation of the topic model of the corpora. Several approaches are used to obtain weights that describe how each topic relates to each evaluation criterion/property and to each class described in the paper, including manual high-level labeling, a multi-corpora approach, and an automatic approach. The proposed multi-corpora approach suggests assessment of corpora topical asymmetry to obtain the weights describing each topic’s relationship to a certain criterion/property. These weights, combined with the topic model, can be applied to evaluate each document in the corpora according to each of the considered criteria and classes. The proposed method was applied to a corpus of 804,829 news publications from 40 Kazakhstani sources published from 01 January 2018 to 31 December 2019, to classify negative information on socially significant topics. A BigARTM model was derived (200 topics) and the proposed model was applied, including to fill a table of the analytical hierarchical process (AHP) and all of the necessary high-level labeling procedures. Experiments confirm the general possibility of evaluating the media using the topic model of the text corpora, because an area under receiver operating characteristics curve (ROC AUC) score of 0.81 was achieved in the classification task, which is comparable with results obtained for the same task by applying the BERT (Bidirectional Encoder Representations from Transformers) model.

In this paper, we consider the matrix expression of convolution, and its generalized continuous form. The matrix expression of convolution is effectively applied in convolutional neural networks, and in this study, we correlate the concept of convolution in mathematics to that in convolutional neural network. Of course, convolution is a main process of deep learning, the learning method of deep neural networks, as a core technology. In addition to this, the generalized continuous form of convolution has been expressed as a new variant of Laplace-type transform that, encompasses almost all existing integral transforms. Finally, we would, in this paper, like to describe the theoretical contents as detailed as possible so that the paper may be self-contained.

To improve the efficiency, accuracy, and intelligence of target detection and recognition, multi-sensor information fusion technology has broad application prospects in many aspects. Compared with single sensor, multi-sensor data contains more target information and effective fusion of multi-source information can improve the accuracy of target recognition. However, the recognition capabilities of different sensors are different during target recognition, and the complementarity between sensors needs to be analyzed during information fusion. This paper proposes a multi-sensor fusion recognition method based on complementarity analysis and neutrosophic set. The proposed method mainly has two parts: complementarity analysis and data fusion. Complementarity analysis applies the trained multi-sensor to extract the features of the verification set into the sensor, and obtain the recognition result of the verification set. Based on recognition result, the multi-sensor complementarity vector is obtained. Then the sensor output the recognition probability and the complementarity vector are used to generate multiple neutrosophic sets. Next, the generated neutrosophic sets are merged within the group through the simplified neutrosophic weighted average (SNWA) operator. Finally, the neutrosophic set is converted into crisp number, and the maximum value is the recognition result. The practicality and effectiveness of the proposed method in this paper are demonstrated through examples.

Fire monitoring in local urban markets within East Africa (EA) has been seriously neglected for a long time. This has culminated in a severe destruction of life and property worth millions. These rampant fires are attributed to electrical short circuits, fuel spillages, etc. Previous research proposes single smoke detectors. However, they are prone to false alarm rates and are inefficient. Also, satellite systems are expensive for developing countries. This paper presents a fuzzy model for early fire detection and control as symmetry’s core contribution to fuzzy systems design and application in computer and engineering sciences. We utilize a fuzzy logic technique to simulate the performance of the model using MATLAB, using six parameters: temperature, humidity, flame, CO, CO2 and O2 vis-à-vis the Estimated Fire Intensity Prediction (EFIP). Results show that, using fuzzy logic, a significant improvement in fire detection is observed with an overall accuracy rate of 95.83%. The paper further proposes an IoT-based fuzzy prediction model for early fire detection with a goal of minimizing extensive damage and promote intermediate fire suppression and control through true fire incidences. This solution provides for future public safety monitoring, and control of fire-related situations among the market community. Hence, fire safety monitoring is significant in providing future fire safety planning, control and management by putting in place appropriate fire safety laws, policies, bills and related fire safety practices or guidelines to be applied in public buildings, market centers and other public places.

This paper investigates the energy-efficient communications and user capacity in the cognitive multiple input multiple output (MIMO) symmetric system of underlay mode. The advantage of the improved energy efficiency provided by the orthogonal slot allocation for time division multiple access (TDMA) has a side effect of restricting the number of users accessing the system. To tackle the above problem, this paper proposes a nonorthogonal time resource allocation method with sparse code multiple access (SCMA), which allows one to convert the orthogonal slot units of TDMA into non-orthogonal shared slot units for multiple secondary users (SUs). The method of adding virtual users is adopted, wherein each SU is treated as multiple SUs who occupy a shared unit, to facilitate the packet access. Finally, the greedy algorithm is applied to optimize the time slot allocation of unoccupied shared slot units. The simulation results show that SCMA-based nonorthogonal slot allocation can reduce not only the energy consumption by nearly 40%, but also the average power interference from SUs to primary users by nearly 2 dB if their number is relatively high. Moreover, in the case of satisfying the rate requirement of the users, the system user capacity increased by more than 50%.

The Traffic Alert and Collision Avoidance System (TCAS) is recognized worldwide as the last resort for avoiding midair collisions. The existing TCAS can solve pairwise conflict effectively, but cannot manage multi-aircraft conflict satisfactorily, and more seriously, can even trigger domino conflicts in some situation. In response to the increasingly frequent multi-aircraft conflicts, especially three-aircraft conflicts, it is necessary to improve the ability of TCAS. This paper studies the collision avoidance of multi-aircraft scenarios and innovatively proposes a collaborative optimization of a collision avoidance system (CAS) based on the state prediction of the aircraft. In the process, not only invading aircraft but also potential invading aircraft are considered in the plan for an optimal conflict resolution program. From the perspective of mathematics, the collaborative multi-aircraft conflict detection and resolution algorithm is described in detail in this paper. In the end, this paper conducts a comparative experiment to prove the feasibility of the algorithm in three-aircraft scenarios using InCAS software and Gmas simulation software based on graphical modeling of complex systems. The experimental results show that the CAS proposed in this paper can efficiently prevent the occurrence of domino conflicts and guide each aircraft to avoid conflict areas and return to their origin trajectories. In contrast, the existing TCAS will cause the target aircraft to intensify the conflict with the potential invading aircraft when avoiding intruder aircraft. The research greatly remedies the gaps in the area of multi-aircraft collision avoidance and greatly improves the ability and efficiency of TCAS.

Digital image watermarking aims to protect the information in an image without significantly affecting visual quality. In this paper, a new image watermarking technique has been proposed that uses Gaussian filters and first-order partial differential matrix to extort the edge surface of a host image. This paper influence on the edge surface curvelet coefficients as human eyes are not equally sensitive to a smooth and an edged surface. To preserve the quality of the artwork and to increase the resistance against attacks, the author utilizes the edge surface area of an image, coarse levels of curvelet transform, and strength parameters. The selection of host coefficients are conforming to the human visual system (HVS) is the uniqueness of the research. The exploitation of the Gaussian filters and first-order partial differential coarse curvelet coefficients and the watermark strength parameter offers robustness against image processing attacks. The standard visual quality perception of HVS evaluation metrics are used to measure the superiority of the presented work.

Various defects are formed on the workpiece surface during the production process. Workpiece surface defects are classified according to various characteristics, which includes a bumped surface, scratched surface and pit surface. Suppliers analyze the cause of workpiece surface defects through the defect types and thus determines the subsequent processing. Therefore, the correct classification is essential regarding workpiece surface defects. In this paper, a multi-classifier decision-level fusion classification model for workpiece surface defects based on a convolutional neural network (CNN) was proposed. In the proposed model, the histogram of oriented gradient (HOG) was used to extract the features of the second fully connected layer of the CNN, and the features of the HOG were further extracted by using the local binary patterns (LBP), which was called the HOG&ndash, LBP feature extraction. Finally, this paper designed a symmetry ensemble classifier, which was used to classify the features of the last fully connected layer of the CNN and the features of the HOG&ndash, LBP. The comprehensive decision was made by fusing the classification results of the symmetry structure channels. The experiments were carried out, and the results showed that the proposed model could improve the accuracy of the workpiece surface defect classification.

In the real world, multi-objective optimization problems always change over time in most projects. Once the environment changes, the distribution of the optimal solutions would also be changed in decision space. Sometimes, such change may obey the law of symmetry, i.e., the minimum of the objective function in such environment is its maximum in another environment. In such cases, the optimal solutions keep unchanged or vibrate in a small range. However, in most cases, they do not obey the law of symmetry. In order to continue the search that maintains previous search advantages in the changed environment, some prediction strategy would be used to predict the operation position of the Pareto set. Because of this, the segment and multi-directional prediction is proposed in this paper, which consists of three mechanisms. First, by segmenting the optimal solutions set, the prediction about the changes in the distribution of the Pareto front can be ensured. Second, by introducing the cloud theory, the distance error of direction prediction can be offset effectively. Third, by using extra angle search, the angle error of prediction caused by the Pareto set nonlinear variation can also be offset effectively. Finally, eight benchmark problems were used to verify the performance of the proposed algorithm and compared algorithms. The results indicate that the algorithm proposed in this paper has good convergence and distribution, as well as a quick response ability to the changed environment.

In recent years, the common algorithms for image super-resolution based on deep learning have been increasingly successful, but there is still a large gap between the results generated by each algorithm and the ground-truth. Even some algorithms that are dedicated to image perception produce more textures that do not exist in the original image, and these artefacts also affect the visual perceptual quality of the image. We believe that in the existing perceptual-based image super-resolution algorithm, it is necessary to consider Super-Resolution (SR) image quality, which can restore the important structural parts of the original picture. This paper mainly improves the Enhanced Super-Resolution Generative Adversarial Networks (ESRGAN) algorithm in the following aspects: adding a shallow network structure, adding the dual attention mechanism in the generator and the discriminator, including the second-order channel mechanism and spatial attention mechanism and optimizing perceptual loss by adding second-order covariance normalization at the end of feature extractor. The results of this paper ensure image perceptual quality while reducing image distortion and artefacts, improving the perceived similarity of images and making the images more in line with human visual perception.

The protection of video data has become a hot topic of research. Researchers have proposed a series of coding algorithms to ensure the safe and efficient transmission of video information. We propose an encryption scheme that can protect video information with higher security by combining the video coding algorithm with encryption algorithm. The H.264/AVC encoding algorithm encodes the video into multiple slices, and the slices are independent of each other. With this feature, we encrypt each slice while using the cipher feedback (CFB) mode of the advanced encryption standard (AES) with the dynamic key. The key is generated by the pseudo-random number generator (PRNG) and updated in real time. The encryption scheme goes through three phases: constructing plaintext, encrypting plaintext, and replacing the original bitstream. In our scheme, we encrypt the code stream after encoding, so it does not affect the coding efficiency. The purpose of the CFB mode while using the AES encryption algorithm is to maintain the exact same bit rate and produce a format compatible bitstream. This paper proposes a new four-dimensional (4-D) hyperchaotic algorithm to protect data privacy in order to further improve the security of video encryption. Symmetric encryption requires that the same key is used for encryption and decoding. In this paper, the symmetry method is used to protect the privacy of video data due to the large amount of video encrypted data. In the experiment, we evaluated the proposed algorithm while using different reference video sequences containing motion, texture, and objects.

In this paper, a hybrid neural network (HNN) that combines a convolutional neural network (CNN) and long short-term memory neural network (LSTM) is proposed to extract the high-level characteristics of materials for critical temperature (Tc) prediction of superconductors. Firstly, by obtaining 73,452 inorganic compounds from the Materials Project (MP) database and building an atomic environment matrix, we obtained a vector representation (atomic vector) of 87 atoms by singular value decomposition (SVD) of the atomic environment matrix. Then, the obtained atom vector was used to implement the coded representation of the superconductors in the order of the atoms in the chemical formula of the superconductor. The experimental results of the HNN model trained with 12,413 superconductors were compared with three benchmark neural network algorithms and multiple machine learning algorithms using two commonly used material characterization methods. The experimental results show that the HNN method proposed in this paper can effectively extract the characteristic relationships between the atoms of superconductors, and it has high accuracy in predicting the Tc.

This paper concerns several important topics of the Symmetry journal, namely, pattern recognition, computer-aided design, diversity and similarity. We also take advantage of the symmetric structure of a membership function. Searching for the (sub) optimal subset of features is an NP-hard problem. In this paper, a binary swallow swarm optimization (BSSO) algorithm for feature selection is proposed. To solve the classification problem, we use a fuzzy rule-based classifier. To evaluate the feature selection performance of our method, BSSO is compared to induction without feature selection and some similar algorithms on well-known benchmark datasets. Experimental results show the promising behavior of the proposed method in the optimal selection of features.

With the development of mobile network technology, the continuous increase of mobile traffic has put forward higher requirements for quality of service (QoS) issues such as asymmetric transmission delay. The paper mainly studies the energy distribution problem on the migration data link from the terminal device to the edge node in the mobile edge network. Multiple data service packages are set up at each hop on the migration data link, and these data service packages compete with each other, and ultimately only one terminal provides and stores energy for this hop. The migration strategy of the data service package is affected by the edge node, and the edge node changes the migration strategy according to the migration strategy of the data service package. The paper is based on the formation of nodes between the data service packages of different nodes on the 5G network data link to jointly control the migration strategy, coordinate the migration strategy formulated, and better coordinate the migration strategy. In this competitive game model, the optimal migration strategy of nodes is found out according to the terminal equipment access requirements. Then according to the node stability rules, the composition of nodes when the nodes are stable is obtained, the migration strategy of stable nodes and the migration and spectrum strategies of operators are obtained, and the migration strategy of joint control provides energy for edge nodes.

Plant diseases pose a severe threat to crop yield. This necessitates the rapid identification of diseases affecting various crops using modern technologies. Many researchers have developed solutions to the problem of identifying plant diseases, but it is still considered a critical issue due to the lack of infrastructure in many parts of the world. This paper focuses on detecting and classifying diseases present in the leaf images by adopting a hybrid learning model. The proposed hybrid model uses k-means clustering for detecting the disease area from the leaf and a Convolutional Neural Network (CNN) for classifying the type of disease based on comparison between sampled and testing images. The images of leaves under consideration may be symmetrical or asymmetrical in shape. In the proposed methodology, the images of various leaves from diseased plants were first pre-processed to filter out the noise present to get an enhanced image. This improved image enabled detection of minute disease-affected regions. The infected areas were then segmented using k-means clustering algorithm that locates only the infected (diseased) areas by masking the leaves’ green (healthy) regions. The grey level co-occurrence matrix (GLCM) methodology was used to fetch the necessary features from the affected portions. Since the number of fetched features was insufficient, more synthesized features were included, which were then given as input to CNN for training. Finally, the proposed hybrid model was trained and tested using the leaf disease dataset available in the UCI machine learning repository to examine the characteristics between trained and tested images. The hybrid model proposed in this paper can detect and classify different types of diseases affecting different plants with a mean classification accuracy of 92.6%. To illustrate the efficiency of the proposed hybrid model, a comparison was made against the following classification approaches viz., support vector machine, extreme learning machine-based classification, and CNN. The proposed hybrid model was found to be more effective than the other three.

Service fulfillment for clients increasingly involves cooperation between information technology (IT) systems. Designing such solutions requires an architectural approach that ensures symmetry between the communicating parties. For the design of such systems, the author introduces the 1+5 architectural views model. The model contains three new architectural views. For business process modeling, it ensures the integrated processes view. Integration aspects cover two additional views: integrated services, and contracts. Moreover, new stereotypes and tagged values have been added to the unified modeling language (UML). The author has introduced two profiles: UML profile for integration flows, and UML profile for distributed ledger deployment. Communication between systems requires flows that arrange mediation mechanisms. The paper describes an integration flow diagram that extends a UML activity diagram. In the case of blockchain, the author has proposed the smart contract design pattern. The paper describes three case studies that have employed the model to design various solutions. The 1+5 model has proven to be well suited for designing both centralized integration environments with enterprise service bus (ESB) and distributed blockchain solutions with peer-to-peer (P2P) connections.

Ptychography is a lensless imaging technology that is validated from hard X-rays to terahertz spectral range. It is most attractive for extreme ultraviolet (EUV) and X-rays as optical elements are expensive and often not available. Typically, the set up involves coherently illuminated object that directs the scattered radiation normally to detector which is parallel to the object plane. Computer processing of diffraction patterns obtained when scanning the object gives the image, more precisely, the distribution of intensity and phase on its surface. However, this scheme is inefficient for EUV and X-rays due to poor reflectivity and low penetration in all materials. Reflection mode ptychography solves the problem if illumination angles do not exceed the critical angle of object material. Changing the geometry of experiment changes physical and mathematical model of image formation. Including: diffraction integral describing beam propagation from object to detector, inverse problem, optimization of object illumination angle, position and orientation of detector, choosing size and grid of coordinate and frequency computer domains. This paper considers the wavefield scattered to detector by obliquely illuminated object and determines a domain for processing of obtained scans. Solution of inverse problem with phase retrieval and resulting numerical images will be presented in the next paper.

Several researchers are considering the plausibility of being able to rapidly launch a mission to an asteroid, which would fly in close proximity of the asteroid to deliver an impulse in a particular direction so as to deflect the asteroid from its current orbit. Planetary motion, in general, and the motion of asteroids, in particular, are subject to planetary influences that are characterised by a kind of natural symmetry, which results in an asteroid orbiting in a stable and periodic or almost periodic orbit exhibiting a number of natural orbital symmetries. Tracking and following an asteroid, in close proximity, is the subject of this paper. In this paper, the problem of synthesizing an optimal trajectory to a NEO such as an asteroid is considered. A particular strategy involving the optimization of a co-planar trajectory segment that permits the satellite to approach and fly alongside the asteroid is chosen. Two different state space representations of the Hill–Clohessy–Wiltshire (HCW) linearized equations of relative motion are used to obtain optimal trajectories for a spacecraft approaching an asteroid. It is shown that by using a state space representation of HCW equations where the secular states are explicitly represented, the optimal trajectories are not only synthesized rapidly but also result in lower magnitudes of control inputs which must be applied continuously over extended periods of time. Thus, the solutions obtained are particularly suitable for low thrust control of the satellites orbit which can be realized by electric thrusters.

Blockchain networks are based on cryptographic notions that include asymmetric-key encryption, hash functions and consensus protocols. Despite their popularity, mainstream protocols, such as Proof of Work or Proof of Stake still have drawbacks. Efforts to enhance these protocols led to the birth of alternative consensus protocols, catering to specific areas, such as medicine or transportation. These protocols remain relatively unknown despite having unique merits worth investigating. Although past reviews have been published on popular blockchain consensus protocols, they do not include most of these lesser-known protocols. Highlighting these alternative consensus protocols contributes toward the advancement of the state of the art, as they have design features that may be useful to academics, blockchain practitioners and researchers. In this paper, we bridge this gap by providing an overview of alternative consensus protocols proposed within the past 3 years. We evaluate their overall performance based on metrics such as throughput, scalability, security, energy consumption, and finality. In our review, we examine the trade-offs that these consensus protocols have made in their attempts to optimize scalability and performance. To the best of our knowledge, this is the first paper that focuses on these alternative protocols, highlighting their unique features that can be used to develop future consensus protocols.

Deepfake is one of the applications that is deemed harmful. Deepfakes are a sort of image or video manipulation in which a person’s image is changed or swapped with that of another person’s face using artificial neural networks. Deepfake manipulations may be done with a variety of techniques and applications. A quintessential countermeasure against deepfake or face manipulation is deepfake detection method. Most of the existing detection methods perform well under symmetric data distributions, but are still not robust to asymmetric datasets variations and novel deepfake/manipulation types. In this paper, for the identification of fake faces in videos, a new multistream deep learning algorithm is developed, where three streams are merged at the feature level using the fusion layer. After the fusion layer, the fully connected, Softmax, and classification layers are used to classify the data. The pre-trained VGG16 model is adopted for transferred CNN1stream. In transfer learning, the weights of the pre-trained CNN model are further used for training the new classification problem. In the second stream (transferred CNN2), the pre-trained VGG19 model is used. Whereas, in the third stream, the pre-trained ResNet18 model is considered. In this paper, a new large-scale dataset (i.e., World Politicians Deepfake Dataset (WPDD)) is introduced to improve deepfake detection systems. The dataset was created by downloading videos of 20 different politicians from YouTube. Over 320,000 frames were retrieved after dividing the downloaded movie into little sections and extracting the frames. Finally, various manipulations were performed to these frames, resulting in seven separate manipulation classes for men and women. In the experiments, three fake face detection scenarios are investigated. First, fake and real face discrimination is studied. Second, seven face manipulations are performed, including age, beard, face swap, glasses, hair color, hairstyle, smiling, and genuine face discrimination. Third, performance of deepfake detection system under novel type of face manipulation is analyzed. The proposed strategy outperforms the prior existing methods. The calculated performance metrics are over 99%.

Specific emitter identification involves extracting the fingerprint features that represent the individual differences of the emitter through processing the received signals. By identifying the extracted fingerprint features, one can also identify the emitter to which the received signals belong. Due to differences in transmitter hardware, this fingerprint cannot be duplicated. Therefore, SEI plays an important role in the field of information security and can reduce the information leakages caused by key theft. This method can also be used in the military field to support communication countermeasures via emitter individual identification. In this paper, empirical mode decomposition is carried out for each radar pulse signal, and then the bispectral features are extracted. Dimensionality reduction is carried out according to the symmetry of the bispectral features. The features after dimensionality reduction are input into a one-dimensional LeNet neural network as the fingerprint features of the emitter, and the identification of 10 radar emitter sources is completed. Based on the verification of real signals, the SEI identification strategy in this paper achieved a recognition rate of 96.4% for 10 radar signals, 98.9% for 10 data emitter signals, and 88.93% for 5 communication radio signals.

This paper deals with the flow shop scheduling problem. To find the optimal solution is an NP-hard problem. The paper reviews some algorithms from the literature and applies a benchmark dataset to evaluate their efficiency. In this research work, the discrete bacterial memetic evolutionary algorithm (DBMEA) as a global searcher was investigated. The proposed algorithm improves the local search by applying the simulated annealing algorithm (SA). This paper presents the experimental results of solving the no-idle flow shop scheduling problem. To compare the proposed algorithm with other researchers’ work, a benchmark problem set was used. The calculated makespan times were compared against the best-known solutions in the literature. The proposed hybrid algorithm has provided better results than methods using genetic algorithm variants, thus it is a major improvement for the memetic algorithm family solving production scheduling problems.

Text, voice, images and videos can express some intentions and facts in daily life. By understanding these contents, people can identify and analyze some behaviors. This paper focuses on the commodity trade declaration process and identifies the commodity categories based on text information on customs declarations. Although the technology of text recognition is mature in many application fields, there are few studies on the classification and recognition of customs declaration goods. In this paper, we proposed a classification framework based on machine learning (ML) models for commodity trade declaration that reaches a high rate of accuracy. This paper also proposed a symmetrical decision fusion method for this task based on convolutional neural network (CNN) and transformer. The experimental results show that the fusion model can make up for the shortcomings of the two original models and some improvements have been made. In the two datasets used in this paper, the accuracy can reach 88% and 99%, respectively. To promote the development of study of customs declaration business and Chinese text recognition, we also exposed the proprietary datasets used in this study.

The internet of things (IoT) refers to all the smart objects that are connected to other objects, devices or servers and that are able to collect and share data, in order to &ldquo, learn&rdquo, and improve their functionalities. Smart objects suffer from lack of memory and computational power, since they are usually lightweight. Moreover, their security is weakened by the fact that smart objects can be placed in unprotected environments, where adversaries are able to play with the symmetric-key algorithm used and the device on which the cryptographic operations are executed. In this paper, we focus on a family of white-box symmetric ciphers substitution&ndash, permutation network (SPN)box, extending and improving our previous paper on the topic presented at WIDECOM2019. We highlight the importance of white-box cryptography in the IoT context, but also the need to have a fast black-box implementation (server-side) of the cipher. We show that, modifying an internal layer of SPNbox, we are able to increase the key length and to improve the performance of the implementation. We measure these improvements (a) on 32/64-bit architectures and (b) in the IoT context by encrypting/decrypting 10,000 payloads of lightweight messaging protocol Message Queuing Telemetry Transport (MQTT).

Energy efficiency and renewable energy are the two main research topics for sustainable energy. In the past ten years, countries around the world have invested a lot of manpower into new energy research. However, in addition to new energy development, energy efficiency technologies need to be emphasized to promote production efficiency and reduce environmental pollution. In order to improve power production efficiency, an integrated solution regarding the issue of electric power load forecasting was proposed in this study. The solution proposed was to, in combination with persistence and search algorithms, establish a new integrated ultra-short-term electric power load forecasting method based on the adaptive-network-based fuzzy inference system (ANFIS) and back-propagation neural network (BPN), which can be applied in forecasting electric power load in Taiwan. The research methodology used in this paper was mainly to acquire and process the all-day electric power load data of Taiwan Power and execute preliminary forecasting values of the electric power load by applying ANFIS, BPN and persistence. The preliminary forecasting values of the electric power load obtained therefrom were called suboptimal solutions and finally the optimal weighted value was determined by applying a search algorithm through integrating the above three methods by weighting. In this paper, the optimal electric power load value was forecasted based on the weighted value obtained therefrom. It was proven through experimental results that the solution proposed in this paper can be used to accurately forecast electric power load, with a minimal error.

Fine-grained image classification is a challenging problem because of its large intra-class differences and low inter-class variance. Bilinear pooling based models have been shown to be effective at fine-grained classification, while most previous approaches neglect the fact that distinctive features or modeling distinguishing regions usually have an important role in solving the fine-grained problem. In this paper, we propose a novel convolutional neural network framework, i.e., attention bilinear pooling, for fine-grained classification with attention. This framework can learn the distinctive feature information from the channel or spatial attention. Specifically, the channel and spatial attention allows the network to better focus on where the key targets are in the image. This paper embeds spatial attention and channel attention in the underlying network architecture to better represent image features. To further explore the differences between channels and spatial attention, we propose channel attention bilinear pooling (CAB), spatial attention bilinear pooling (SAB), channel spatial attention bilinear pooling (CSAB), and spatial channel attention bilinear pooling (SCAB) as four alternative frames. A variety of experiments on several datasets show that our proposed method has a very impressive performance compared to other methods based on bilinear pooling.

The spatial constrained Fuzzy C-means clustering (FCM) is an effective algorithm for image segmentation. Its background information improves the insensitivity to noise to some extent. In addition, the membership degree of Euclidean distance is not suitable for revealing the non-Euclidean structure of input data, since it still lacks enough robustness to noise and outliers. In order to overcome the problem above, this paper proposes a new kernel-based algorithm based on the Kernel-induced Distance Measure, which we call it Kernel-based Robust Bias-correction Fuzzy Weighted C-ordered-means Clustering Algorithm (KBFWCM). In the construction of the objective function, KBFWCM algorithm comprehensively takes into account that the spatial constrained FCM clustering algorithm is insensitive to image noise and involves a highly intensive computation. Aiming at the insensitivity of spatial constrained FCM clustering algorithm to noise and its image detail processing, the KBFWCM algorithm proposes a comprehensive algorithm combining fuzzy local similarity measures (space and grayscale) and the typicality of data attributes. Aiming at the poor robustness of the original algorithm to noise and outliers and its highly intensive computation, a Kernel-based clustering method that includes a class of robust non-Euclidean distance measures is proposed in this paper. The experimental results show that the KBFWCM algorithm has a stronger denoising and robust effect on noise image.

In this paper, our goal is to improve the recognition accuracy of battlefield target aggregation behavior while maintaining the low computational cost of spatio-temporal depth neural networks. To this end, we propose a novel 3D-CNN (3D Convolutional Neural Networks) model, which extends the idea of multi-scale feature fusion to the spatio-temporal domain, and enhances the feature extraction ability of the network by combining feature maps of different convolutional layers. In order to reduce the computational complexity of the network, we further improved the multi-fiber network, and finally established an architecture—3D convolution Two-Stream model based on multi-scale feature fusion. Extensive experimental results on the simulation data show that our network significantly boosts the efficiency of existing convolutional neural networks in the aggregation behavior recognition, achieving the most advanced performance on the dataset constructed in this paper.

Supervised monocular depth estimation methods based on learning have shown promising results compared with the traditional methods. However, these methods require a large number of high-quality corresponding ground truth depth data as supervision labels. Due to the limitation of acquisition equipment, it is expensive and impractical to record ground truth depth for different scenes. Compared to supervised methods, the self-supervised monocular depth estimation method without using ground truth depth is a promising research direction, but self-supervised depth estimation from a single image is geometrically ambiguous and suboptimal. In this paper, we propose a novel semi-supervised monocular stereo matching method based on existing approaches to improve the accuracy of depth estimation. This idea is inspired by the experimental results of the paper that the depth estimation accuracy of a stereo pair as input is better than that of a monocular view as input in the same self-supervised network model. Therefore, we decompose the monocular depth estimation problem into two sub-problems, a right view synthesized process followed by a semi-supervised stereo matching process. In order to improve the accuracy of the synthetic right view, we innovate beyond the existing view synthesis method Deep3D by adding a left-right consistency constraint and a smoothness constraint. To reduce the error caused by the reconstructed right view, we propose a semi-supervised stereo matching model that makes use of disparity maps generated by a self-supervised stereo matching model as the supervision cues and joint self-supervised cues to optimize the stereo matching network. In the test, the two networks are able to predict the depth map directly from a single image by pipeline connecting. Both procedures not only obey geometric principles, but also improve estimation accuracy. Test results on the KITTI dataset show that this method is superior to the current mainstream monocular self-supervised depth estimation methods under the same condition.

In this paper, a novel fractional-order fusion model (FFM) is presented for low-light image enhancement. Existing image enhancement methods don&rsquo, t adequately extract contents from low-light areas, suppress noise, and preserve naturalness. To solve these problems, the main contributions of this paper are using fractional-order mask and the fusion framework to enhance the low-light image. Firstly, the fractional mask is utilized to extract illumination from the input image. Secondly, image exposure adjusts to visible the dark regions. Finally, the fusion approach adopts the extracting of more hidden contents from dim areas. Depending on the experimental results, the fractional-order differential is much better for preserving the visual appearance as compared to traditional integer-order methods. The FFM works well for images having complex or normal low-light conditions. It also shows a trade-off among contrast improvement, detail enhancement, and preservation of the natural feel of the image. Experimental results reveal that the proposed model achieves promising results, and extracts more invisible contents in dark areas. The qualitative and quantitative comparison of several recent and advance state-of-the-art algorithms shows that the proposed model is robust and efficient.