Modified Dragonfly Optimization with Machine Learning Based Arabic Text Recognition

Text classification or categorization is the procedure of automatically tagging a textual document with most related labels or classes.When the number of labels is limited to one,the task becomes single-label text categorization.The Arabic texts include unstructured information also like English texts,and that is understandable for machine learning(ML)techniques,the text is changed and demonstrated by numerical value.In recent times,the dominant method for natural language processing(NLP)tasks is recurrent neural network(RNN),in general,long short termmemory(LSTM)and convolutional neural network(CNN).Deep learning(DL)models are currently presented for deriving a massive amount of text deep features to an optimum performance from distinct domains such as text detection,medical image analysis,and so on.This paper introduces aModified Dragonfly Optimization with Extreme Learning Machine for Text Representation and Recognition(MDFO-EMTRR)model onArabicCorpus.The presentedMDFO-EMTRR technique mainly concentrates on the recognition and classification of the Arabic text.To achieve this,theMDFO-EMTRRtechnique encompasses data pre-processing to transform the input data into compatible format.Next,the ELM model is utilized for the representation and recognition of the Arabic text.At last,the MDFO algorithm was exploited for optimal tuning of the parameters related to the ELM method and thereby accomplish enhanced classifier results.The experimental result analysis of the MDFO-EMTRR system was performed on benchmark datasets and attained maximum accuracy of 99.74%.

Power and Gaze in Xu Bing’s Dragonfly’s Eye

On August 18,2019,Xu exhibited“The Dragonfly’s Eye”in Today Art Museum.As a respectable writer,Xu drew attention to his elaboration to his illustration of the dragonfly through his own work through incorporating his own artistic interpretation as the new creative mode and idea in art media,further highlighting features of“The Dragonfly’s Eye”.The aesthetic feeling of human nature is emphasized in the creation of Dragonfly’s Eye.Unlike typical contemporary art video works,Dragonfly Eye delivers a whole course of illustration with exceptional production method-through the utilization of existing downloadable videos on the Internet.The project utilizes the romantic story between a young couple to comment on views of life and soul in the contemporary society.Seemingly novelty,the project ultimately centralizes at the idea of the critiquing human nature in the modern ages.

Experimental investigations of the functional morphology of dragonfly wings

Nowadays, the importance of identifying the flight mechanisms of the dragonfly, as an inspiration for designing flapping wing vehicles, is well known. An experimental approach to understanding the complexities of insect wings as organs of flight could provide significant outcomes for design purposes. In this paper, a comprehensive investigation is carried out on the morphological and microstructural features of dragonfly wings. Scanning electron microscopy （SEM） and tensile testing are used to experimentally verify the functional roles of different parts of the wings. A number of SEM images of the elements of the wings, such as the nodus, leading edge, trailing edge, and vein sections, which play dominant roles in strengthening the whole structure, are presented. The results from the tensile tests indicate that the nodus might be the critical region of the wing that is subjected to high tensile stresses. Considering the patterns of the longitudinal corrugations of the wings obtained in this paper, it can be supposed that they increase the load-bearing capacity, giving the wings an ability to tolerate dynamic loading conditions. In addition, it is suggested that the longitudinal veins, along with the leading and trailing edges, are structural mechanisms that further improve fatigue resistance by providing higher fracture toughness, preventing crack propagation, and allowing the wings to sustain a significant amount of damage without loss of strength.

Aerodynamic interaction between forewing and hindwing of a hovering dragonfly

The phase change between the forewing and hindwing is a distinct feature that sets dragonfly apart from other insects.In this paper,we investigated the aerodynamic effects of varying forewing-hindwing phase di ff erence with a60 inclined stroke plane during hovering flight.Force measurements on a pair of mechanical wing models showed that in-phase flight enhanced the forewing lift by 17%and the hindwing lift was reduced at most phase differences.The total lift of both wings was also reduced at most phase di ff erences and only increased at a phase range around in-phase.The results may explain the commonly observed behavior of the dragonfly where 0 is employed in acceleration.We further investigated the wing-wing interaction mechanism using the digital particle image velocimetry（PIV）system,and found that the forewing generated a downwash flow which is responsible for the lift reduction on the hindwing.On the other hand,an upwash flow resulted from the leading edge vortex of the hindwing helps to enhance lift on the forewing.The results suggest that the dragonflies alter the phase di ff erences to control timing of the occurrence of flow interactions to achieve certain aerodynamic effects.

A general method for large-scale fabrication of Cu nanoislands/dragonfly wing SERS flexible substrates

Noble metal nanorough surfaces that support strong surface-enhanced Raman scattering （SERS） is widely applied in the practical detection of organic molecules. A low-cost, large-area, and environment-friendly SERS-active substrate was acquired by sputtering inexpensive copper （Cu） on natural dragonfly wing （DW） with an easily controlled way of magnetron sputtering. By controlling the sputtering time of the fabrication of Cu on the DW, the performance of the SERS substrates was greatly improved. The SERS-active substrates, obtained at the optimal sputtering time （50 min）, showed a low detection limit （10-6M ） to 4-aminothiophenol （4-ATP）, a high average enhancement factor （EF, 1.98 x10^4）, excellent signal uniformity, and good reproducibility. In addition, the results of the 3D finite-difference time-domain （3D- FDTD） simulation illustrated that the SERS-active substrates provided high-density ＂hot spots＂, leading to a large SERS enhancement.

Improved Dragonfly Optimizer for Intrusion Detection Using Deep Clustering CNN-PSO Classifier

With the rapid growth of internet based services and the data generated on these services are attracted by the attackers to intrude the networking services and information.Based on the characteristics of these intruders,many researchers attempted to aim to detect the intrusion with the help of automating process.Since,the large volume of data is generated and transferred through network,the security and performance are remained an issue.IDS(Intrusion Detection System)was developed to detect and prevent the intruders and secure the network systems.The performance and loss are still an issue because of the features space grows while detecting the intruders.In this paper,deep clustering based CNN have been used to detect the intruders with the help of Meta heuristic algorithms for feature selection and preprocessing.The proposed system includes three phases such as preprocessing,feature selection and classification.In the first phase,KDD dataset is preprocessed by using Binning normalization and Eigen-PCA based discretization method.In second phase,feature selection is performed by using Information Gain based Dragonfly Optimizer(IGDFO).Finally,Deep clustering based Convolutional Neural Network(CCNN)classifier optimized with Particle Swarm Optimization(PSO)identifies intrusion attacks efficiently.The clustering loss and network loss can be reduced with the optimization algorithm.We evaluate the proposed IDS model with the NSL-KDD dataset in terms of evaluation metrics.The experimental results show that proposed system achieves better performance compared with the existing system in terms of accuracy,precision,recall,f-measure and false detection rate.

Phenoloxidase and Melanization Innate Immune Activities in Green Darner Dragonfly Nymphs (Anax junius)

Insects in the Order Odonata are highly subject to infection by gregarine parasites. However, despite the important ecological roles that insects play in every ecosystem in which they exist, little research has been devoted to the description of insect immunity. Insects rely heavily on the rapid actions of innate immune mechanisms to prevent infection. We characterized the melanization response in the hemolymph of green darner dragonfly (Anax junius) nymphs. Incubation of chymotrypsin-activated hemolymph with L-DOPA resulted in volume- and time-dependent production of dopaquinone via the phenoloxidase (PO) enzyme, with biphasic accumulation of product. The PO activity was temperature-dependent, with a stepwise increase from 20℃ - 35℃ and maximum activity measured at 35℃ - 40℃. The formation of product was also inhibited in a concentration-dependent manner by diethylcarbonate, a specific inhibitor of PO activity, which indicated that the observed activity was due to the presence of PO enzyme. The rate of formation and quantity of melanin was dependent on exposure to different titers of bacteria. This is the first characterization of both PO activity and melanization response in green darner dragonflies.

An Enhanced Dragonfly Key Exchange Protocol against Offline Dictionary Attack

Dragonfly is Password Authenticated Key Exchange protocol that uses a shared session key to authenticate parties based on pre-shared secret password. It was claimed that this protocol was secure against off-line dictionary attack, but a new research has proved its vulnerability to off-line dictionary attack and proving step was applied by using “Patched Protocol” which was based on public key validation. Unfortunately, this step caused a raise in the computation cost, which made this protocol less appealing than its competitors. We proposed an alternate enhancement to keep this protocol secure without any extra computation cost that was known as “Enhanced Dragonfly”. This solution based on two-pre-shared secret passwords instead of one and the rounds between parties had compressed into two rounds instead of four. We prove that the enhanced-Dragonfly protocol is secure against off-line dictionary attacks by analyzing its security properties using the Scyther tool. A simulation was developed to measure the execution time of the enhanced protocol, which was found to be much less than the execution time of patched Dragonfly. The off-line dictionary attack time is consumed for few days if the dictionary size is 10,000. According to this, the use of the enhanced Dragonfly is more efficient than the patched Dragonfly.

CEVA和香港应用科技研究院推出面向成本和功耗敏感LTE IoT设备的可授权NB-IoT解决方案Dragonfly NB1

专注于智能互联设备的全球领先信号处理IP授权公司CEVA和香港应用科技研究院（应科院）宣布推出Dragonfly NB1。这款成本和功耗优化的NB-IoT全面解决方案旨在精简LTE IoT设备的开发。

Dragonfly Interaction Algorithm for Optimization of Queuing Delay in Industrial Wireless Networks

In industrial wireless networks,data transmitted from source to destination are highly repetitive.This often leads to the queuing of the data,and poor management of the queued data results in excessive delays,increased energy consumption,and packet loss.Therefore,a nature-inspired-based Dragonfly Interaction Optimization Algorithm(DMOA)is proposed for optimization of the queue delay in industrial wireless networks.The term“interaction”herein used is the characterization of the“flying movement”of the dragonfly towards damselflies(female dragonflies)for mating.As a result,interaction is represented as the flow of transmitted data packets,or traffic,from the source to the base station.This includes each and every feature of dragonfly movement as well as awareness of the rival dragonflies,predators,and damselflies for the desired optimization of the queue delay.These features are juxtaposed as noise and interference,which are further used in the calculation of industrial wireless metrics:latency,error rate(reliability),throughput,energy efficiency,and fairness for the optimization of the queue delay.Statistical analysis,convergence analysis,the Wilcoxon test,the Friedman test,and the classical as well as the 2014 IEEE Congress of Evolutionary Computation(CEC)on the benchmark functions are also used for the evaluation of DMOA in terms of its robustness and efficiency.The results demonstrate the robustness of the proposed algorithm for both classical and benchmarking functions of the IEEE CEC 2014.Furthermore,the accuracy and efficacy of DMOA were demonstrated by means of the convergence rate,Wilcoxon testing,and ANOVA.Moreover,fairness using Jain’s index in queue delay optimization in terms of throughput and latency,along with computational complexity,is also evaluated and compared with other algorithms.Simulation results show that DMOA exceeds other bio-inspired optimization algorithms in terms of fairness in queue delay management and average packet loss.The proposed algorithm is also evaluated for the conflicting objectives at Pareto Front,and its analysis reveals that DMOA finds a compromising solution between the objectives,thereby optimizing queue delay.In addition,DMOA on the Pareto front delivers much greater performance when it comes to optimizing the queuing delay for industry wireless networks.

Effect of Blood Circulation in Veins on Resonance Suppression of the Dragonfly Wing Constructed by Numerical Method

To reveal the resonance suppression mechanism of the blood circulation in dragonfly wings,a numerical modeling method of dragonfly wings based on Voronoi diagrams is proposed,and the changes in mass,aerodynamic damping,and natural frequencies caused by blood circulation in veins are investigated.The equivalent mass of blood,boundary conditions,and aerodynamic damping are calculated theoretically.Modal analysis and harmonic response analysis of wing models with different blood circulation paths are performed using the finite-element method(FEM).The vibration reduction ratioδis introduced to compare the damping efficiency of different mass regions.Finally,a natural frequency testing device is constructed to measure the natural frequencies of dragonfly wings.The results indicate that the shape,mass,and natural frequencies of the dragonfly wing model constructed by numerical method agree well with reality.The mass distribution on the wing can be altered by blood circulation,thereby adjusting the natural frequencies and achieving resonance suppression.The highestδof 1.013 is observed in the C region when blood circulates solely in secondary veins,but it is still lower than theδof 1.017 when blood circulates in complete veins.The aerodynamic damping ratio(1.19–1.79%)should not be neglected in the vibration analysis of the beating wing.

Drop impact dynamic and directional transport on dragonfly wing surface

The ability of dragonflies to fly in the rain without being wetted by raindrops has motivated researchers to investigate the impact behavior of a drop on the superhydrophobic wings of dragonflies.This superhydrophobic surface is used as a reference for the design of directional surfaces and has attracted extensive attention owing to its wide applicability in microfluidics,self-cleaning,and other fields.In this study,the static contact angle and rebound process of a drop impacting a dragonfly wing surface are investigated experimentally,whereas the wetting pressure,Gibbs free energy,and Stokes number vs.coefficient of restitution are theoretically calculated to examine the dynamic and unidirectional transport behaviors of the drop.Results show that the initial inclination angle of the dragonfly wing is similar to the sliding angles along with the drop sliding.The water drop bounces from the bottom of the dragonfly wing to the distal position,demonstrating directional migration.The drop impacts the dragonfly wing surface,and the drop exhibits compression,recovery,and separation phases;in these three phases,the drop morphology evolves.As the Gibbs free energy and cross-sectional area evolve,the coefficient of restitution decreases as the drop continues to bounce,and the Stokes number increases.

Deep Convolutional Neural Networks for Accurate Classification of Gastrointestinal Tract Syndromes

Accurate detection and classification of artifacts within the gastrointestinal(GI)tract frames remain a significant challenge in medical image processing.Medical science combined with artificial intelligence is advancing to automate the diagnosis and treatment of numerous diseases.Key to this is the development of robust algorithms for image classification and detection,crucial in designing sophisticated systems for diagnosis and treatment.This study makes a small contribution to endoscopic image classification.The proposed approach involves multiple operations,including extracting deep features from endoscopy images using pre-trained neural networks such as Darknet-53 and Xception.Additionally,feature optimization utilizes the binary dragonfly algorithm(BDA),with the fusion of the obtained feature vectors.The fused feature set is input into the ensemble subspace k nearest neighbors(ESKNN)classifier.The Kvasir-V2 benchmark dataset,and the COMSATS University Islamabad(CUI)Wah private dataset,featuring three classes of endoscopic stomach images were used.Performance assessments considered various feature selection techniques,including genetic algorithm(GA),particle swarm optimization(PSO),salp swarm algorithm(SSA),sine cosine algorithm(SCA),and grey wolf optimizer(GWO).The proposed model excels,achieving an overall classification accuracy of 98.25% on the Kvasir-V2 benchmark and 99.90% on the CUI Wah private dataset.This approach holds promise for developing an automated computer-aided system for classifying GI tract syndromes through endoscopy images.

Hierarchical Dragonfly Wing： Microstructure-Biomechanical Behavior Relations

The dragonfly wing, which consists of veins and membrane, is of biological hierarchical material. We observed the cross-sections of longitudinal veins and membrane using Environmental Scanning Electron Microscopy （ESEM）. Based on the experiments and previous studies, we described the longitudinal vein and the membrane in terms of two hierarchical levels of organization of composite materials at the micro- and nano-scales. The longitudinal vein of dragonfly wing has a complex sandwich structure with two chitinous shells and a protein layer, and it is considered as the first hierarchical level of the vein. Moreover, the chitinous shells are concentric multilayered structures. Clusters of nano-fibrils grow along the circumferential orientation embedded into the protein layer. It is considered as the second level of the hierarchy. Similarly, the upper and lower epidermises of membrane constitute the first hierarchical level of organization in micro scale. Similar to the vein shell, the membrane epidermises were found to be a paralleled multilayered structure, defined as the second hierarchical level of the membrane. Combining with the mechanical behavior analysis of the dragonfly wing, we concluded that the growth orientation of the hierarchical structure of the longitudinal vein and membrane is relevant to its biomechanical behavior.

Influence of Microstructures on Aerodynamic Characteristics for Dragonfly Wing in Gliding Flight

In this paper, the functionalities of microstructures for dragonfly wing during gliding flight are investigated. Three dragonfly-mimic airfoil-shaped wings with hybrid structures were designed and fabricated as: flat wing, zigzag-edged wing and zigzag-edged wing with pillar structure. Based on the wind tunnel experiments, the zigzag-edged wing structure significantly reduces the drag force in the gliding flight. Moreover, the drag reduction is more effective on the combination of the surface pillar and zigzag-edged structure. In addition, the zigzag-edged wing structure has less influence of Karman vortex street, and the surface pillars reduce the frictional drag and stabilized the streamline in the lower vortex region. Overall, the microstructure of the dragonfly wing is an important element in the aerodynamic study. These findings can enhance the knowledge of insect-mimic wing structure and facilitate the application of Micro Air Vehicle (MAV) in the gliding flight.

The Role of Soft Vein Joints in Dragonfly Flight

Dragonflies are excellent flyers among insects and their flight ability is closely related to the architecture and material properties of their wings. The veins are main structure components of a dragonfly wing, which are found to be connected by resilin with high elasticity at some joints. A three-dimensional （3D） finite element model of dragonfly wing considering the soft vein joints is developed, with some simplifications. Passive deformation under aerodynamic loads and active flapping motion of the wing are both studied. The functions of soft vein joints in dragonfly flight are concluded. In passive deformation, the chordwise flexibility is improved by soft vein joints and the wing is cambered under loads, increasing the action area with air. In active flapping, the wing rigidity in spanwise direction is maintained to achieve the required amplitude. As a result, both the passive deformation and the active control of flapping work well in dragonfly flight. The present study may also inspire the design of biomimetic Flapping Micro Air Vehicles （FMAVs）.

ARNOLD CIRCULATION AND MULTI-OPTIMAL DYNAMIC CONTROLLING MECHANISMS IN DRAGONFLY WINGS

This paper aims to reveal the multi-optimal mechanisms for dynamic control in drag- onfly wings. By combining the Arnold circulation with such micro/nano structures as the hollow inside constructions of the pterostigma, veins and spikes, dragonfly wings can create variable mass, variable rotating inertia and variable natural frequency. This marvelous ability enables dragonflies to overcome the contradictory requirements of both light-weight-wing and heavy-weight-wing, and displays the multi-optimal mechanisms for the excellent flying ability and dynamic control capac- ity of dragonflies. These results provide new perspectives for understanding the wings＇ functions and new inspirations for bionic manufactures.

PMSM Vector Control Optimization Based on Fractional PI^(λ) of Rotational Speed Outer Loop of Dragonfly Algorithm

Aiming at the problems of slow dynamic response and weak robustness of integer-order proportional integral(PI)controller in double closed loop vector control system of permanent magnet synchronous motor(PMSM),a method of combining dragonfly algorithm with fractional order PI control is proposed for off-line parameter tuning for the outer loop of speed of the system.The parameter to be optimized is used as the spatial position of the optimal individual searching for food sources in the search space,and the error performance index integrated time and absolute error(ITAE)is used as its target fitness function.The motor speed regulation performances of traditional engineering experience setting integer order PI,particle swarm optimization algorithm tuning fractional order PI and dragonfly algorithm tuning fractional order PI are compared,respectively.Results show that the fractional order PI controller optimized by dragonfly algorithm can improve the dynamic response performance of the system,reduce overshoot and enhance robustness,which proves the feasibility and superiority of the optimization strategy.

Role of Soft Matter in the Sandwich Vein of Dragonfly Wing in Its Configuration and Aerodynamic Behaviors

The microstructure of the main longitudinal veins of the dragonfly wing and the aerodynamic behaviors of the wing were investigated in this paper. The microstructure of longitudinal vein presents two circumferential chitin layers and a protein-fiber soft layer. The dragonfly wing is corrugated due to the spatial arrangement of longitudinal veins. It was found that the corru- gation angle could significantly influence the lift/drag ratio across a range of attack angles by the wind tunnel experiments. The results of the finite element analysis indicate that the protein soft layer of vein facilitates the change of the corrugation angle by allowing substantial relative twisting deformation between two neighboring veins, which is not possible in veins without a soft sandwich layer.

Effects of Structural Characteristics of a Bionic Dragonfly Wing on Its Low Velocity Impact Resistance

The influence of the structural features of dragonfly wings, including the sandwich-type configuration of longitudinal veins and the longitudinal corrugations, on the impact response of a bio-inspired structure is investigated. According to experimental observations of the wing morphology, a novel foam-based composite structure is introduced consisting of E-glass/epoxy face-sheets bonded to a polyurethane foam core. A finite element model is employed to simulate the structural responses of the biomimetic structure under low velocity impact. The initiation and evolution of the impact-induced damage in composite skins are simulated by applying a user-defined progressive damage model together with the interracial cohesive law for intra- and inter-laminar damages, respectively. To simulate the nonlinear behavior of the foam core, a crushable plasticity model is implemented. The numerically obtained results are found to correlate with the experimentally measured ones, acquired by drop-weight testing on a bio-inspired structure. It is numerically predicted that reinforcing the structure with the veins gives the more impact load-bearing capacity and the longitudinal corrugation can increase the stiffness and damage resistance of the structure. Effects of the change in impact location, the configuration of the veins and the corrugated angle on damage resistance of the structures are fully discussed.