Search

At present, the primary technical deterrent to the use of strawberry harvesting robots is the low harvest rate, and there is a need to improve the accuracy and real-time performance of the localization algorithms to detect the picking point on the strawberry stem. The pose estimation of the fruit target (the direction of the fruit axis) can improve the accuracy of the localization algorithm. This study proposes a novel harvesting robot for the ridge-planted strawberries as well as a fruit pose estimator called rotated YOLO (R-YOLO), which significantly improves the localization precision of the picking points. First, the lightweight network Mobilenet-V1 was used to replace the convolution neural network as the backbone network for feature extraction. The simplified network structure substantially increased the operating speed. Second, the rotation angle parameter $\alpha $ was used to label the training set and set the anchors; the rotation of the bounding boxes of the target fruits was predicted using logistic regression with the rotated anchors. The test results of a set of 100 strawberry images showed that the proposed model's average recognition rate to be 94.43% and the recall rate to be 93.46%. Eighteen frames per second (FPS) were processed on the embedded controller of the robot, demonstrating good real-time performance. Compared with several other target detection methods used for the fruit harvesting robots, the proposed model exhibited better performance in terms of real-time detection and localization accuracy of the picking points. Field test results showed that the harvesting success rate reached 84.35% in modified situations. The results of this study provide technical support for improving the target detection of the embedded controller of harvesting robots.

Gravitational search algorithm (GSA) inspired from physics emulates gravitational forces to guide particles' search. It has been successfully applied to diverse optimization problems. However, its search performance is limited by its inherent mechanism where gravitational constant plays an important role in gravitational forces among particles. To improve it, this paper uses chaotic neural oscillators to adjust its gravitational constant, named GSA-CNO. Chaotic neural oscillators can generate various chaotic states according to their parameter settings. Thus, we select four kinds of chaotic neural oscillators to form distinctive chaotic characteristics. Experimental results show that chaotic neural oscillators effectively tune the gravitational constant such that GSA-CNO has good performance and stability against four GSA variants on functions. Three real-world optimization problems demonstrate the promising practicality of GSA-CNO.

Density peaks clustering (DPC) algorithm is a novel density-based clustering algorithm, which is simple and efficient, is not necessary to specify the number of clusters in advance, and can find any nonspherical class clusters. However, DPC relies heavily on the calculation methods of the cutoff distance threshold and local density and cannot analyze complex manifold data, especially datasets with uneven density distribution and multiple peaks in the same cluster. To solve these problems, we propose an improved density peaks clustering algorithm based on the layered k-nearest neighbors and subcluster merging (LKSM_DPC). First, we redefine the local density calculation method using the layered k-nearest neighbors. To adapt to datasets with different densities, the k-nearest neighbors are divided into multiple layers. Second, for the multiple peaks in the same cluster problem, we design a new mechanism to calculate the similarity of subclusters based on the idea of shared neighbors and Newton's law of gravitation, and a subcluster merging strategy is proposed. To prove the effectiveness of our algorithm, we compare the LKSM_DPC with K-means, DBSCAN, DPC, and DPC derivatives for 24 datasets. A large number of experiments demonstrate that our algorithm can often outperform other algorithms.

Key frame extraction technology is one of the core technologies of content-based video retrieval. For video types with complex content, various scenes, and rich actions, the performance of existing key frame extraction methods is not ideal. Based on the Visual Geometry Group (VGG), this article proposes an image saliency extraction model assisted by deep prior information, and uses a large-scale data set for training on the server to obtain a trained model, and then integrates multiple features. The saliency extraction algorithm is combined with the image saliency extraction model assisted by deep prior information, and a saliency extraction algorithm based on multi-feature fusion and deep prior information is proposed. A new method for extracting key frames of motion video is introduced in detail. Taking into account that sports videos in real applications are susceptible to interference from various factors, resulting in poor picture quality, this article constructs a new visual attention model for moving targets in sports videos, which integrates images. The combination of multiple features of the bottom-level features and the skin color confidence map of the moving target overcomes the problem that a single feature cannot fully express the moving target. Since the processing object in this article is for the moving target in the video of the sports room, the extracted moving target can provide samples for video post-processing. The experimental results show that the proposed key frame extraction algorithm can quickly grasp the pedestrian information in the motion video and provide effective processing samples for the motion target for video post-processing.

This paper addresses the trajectory tracking problem for constrained high dynamic electro-hydraulic actuator in the presence of time-varying parameters, high frequency external load interference, measurement noise and some unmeasurable states. An adaptive robust optimal control scheme is proposed for the electro-hydraulic actuator in legged robot. The framework of our presented scheme is based on a linear time-varying model predictive controller (LTV-MPC) embedded with a multi-scale online estimator (MEKF). With fast- varying and slow- varying time scales, the MEKF part is used not only for measurable states filtering and unmeasurable states estimation, but also for time-varying parameters and external load interference estimation, which will be integrated into the mpc model in real time. The LTV-MPC part is a trajectory tracking controller designed by constrained MPC with an approximate high-precision real-time model and a rapidly solved cost function, which guarantees that the input and output constraints are satisfied during the receding horizon and optimal control process. Finally, with a series of highly dynamic conditions, the comparison experiment results show that the proposed controller has a simple design process, strong adaptive robust performance and trajectory tracking performance, which verifies the effectiveness of the control scheme.

As semiconductor technology develops, threedimensions integrated circuits (3-D ICs) is thought as a viable solution to further improve the performance of ICs. Throughsilicon-vias (TSVs) are the most important device in 3-D ICs. Therefore, TSVs testing is a very critical flow in 3-D ICs manufacturing. A new pre-bond TSVs test solution is proposed in this paper. The new test structure includes an improved ring oscillator and a voltage-divider structure. Compared with conventional TSV test structure, the output of new test structure is more sensitive to TSV faults. We prove the effectiveness of the new test structure by HSPICE simulation.

Brain storm optimization (BSO) is a swarm intelligence optimization algorithm which is proven to have practical values in various fields. During these years, many modifications have been facilitated to effectively improve BSO's search performance. So far, these modifications focus on improving the solution quality by applying different clustering methods and learning strategies, in which the population diversity is often neglected. However, in recent studies, population diversity plays a more significant role in designing optimization algorithm. A population that maintains its diversity in a high level can easily obtain better solutions than the one with low level of diversity. Therefore, this paper proposes a control method that evaluates the population diversity of BSO to improve its performance. Two diversity measures, which are known as distance-based diversity and fitness-based diversity, are implemented to realize the adaptation of algorithm parameters. The new algorithm is called multiple diversity-driven BSO (MDBSO). Its performance is verified by CEC2017 benchmark function suit and a neuron model training task. The results demonstrate the effectiveness and efficiency of MDBSO.

Micro-expression recognition has been an active research area in recent years, it plays an important role in psychology and public security. Due to the aspects of short duration and subtle movement, it is challenging to extract spatiotemporal features of micro-expressions. The existing methods only extract features in the three-dimensional orthogonal plane and fail to make full use of that information. To solve this problem, we propose a new Local Cubes Binary Patterns (LCBP) method for micro-expression recognition. LCBP is cascaded by the motion information LCBPdirection, the amplitude information LCBPamplitudes, and the spatial information LCBP3D to obtain the spatiotemporal features. The advantage of LCBP is its ability to preserve the spatiotemporal information and the low feature dimension. Furthermore, to increase the discrimination of features in micro-expression sequences, we apply a differential calculation energy map to find regions of interest (ROI) for getting a weighted energy map. The final micro-expression feature acquired by fusing the LCBP features and the weighted energy map are classified through the Support Vector Machine (SVM). We evaluate the proposed method on four published micro-expression databases including SMIC, CASME, CASME2, SAMM. Experimental results demonstrate that our proposed method achieves promising performance for micro-expression recognition.

Feature fusion is widely used in person re-identification (re-ID) and has been proven effective. However, it is difficult to know which features are effective to identify a specific person and how to fuse features to explore complementary information and apply the advantages of each feature. Motivated by these problems, this paper proposes a new method of person re-ID to fuse the recognition results of multiple features at the rank level. Three innovations are included in this method: first, multiple metric spaces are constructed based on the correlation of different features to generate multiple rank results; second, the most similar candidates in each corresponding rank list is converted into a graph structure by our proposed weighted center graph (WCG), and we use an adaptive value $K$ to automatically seek the most similar images of each query, thus improving the accuracy of candidate targets. Finally, to evaluate the effect of each WCG, a discriminative power coefficient is designed and used to assign a proper coefficient for each WCG according to the discriminative power of corresponding features. The result can be obtained by re-ranking the fused WCG. The extensive experiments on five datasets demonstrate the matching rate of our proposed method by comparing with several state-of-the-art methods. Our code is available at https://github.com/gengshuze/WCG.git .

As a new paradigm of information technology, the Internet of Things (IoT) is attracting increasing attention from various industrial fields. It is foreseeable that the applications of IoT will be prevalent in the public transportation system and bring changes to the system in the near future. In this paper, we analyze the impact of IoT environment on the public transportation system, propose a new framework of the intelligent public transportation system based on IoT, and present the deployment of the elements, the communication network, and the three-tier architecture of the system in detail. We also present the information flow, technical scheme, optimization model, and algorithm of the main modules of dynamic optimization of the system. The innovative points of this paper lie in: (1) a new framework for public transport system based on IoT, which integrates the scheduling problems of subway, bus, and shared taxi, is proposed for better-coordinated transfer solutions; (2) transport flow prediction methods based on periodic patterns mining is proposed for road flow analysis and passenger flow analysis, and; (3) mathematical model and DSS-based evolutionary computation algorithm are proposed for solving the dynamic bus scheduling and controlling problems. The proposed intelligent transport system based on IoT can assist the decision makers to increase the utilization rate of the transport resources, improve the efficiency of scheduling, and reduce passengers’ traveling time.

In this paper, a third-order waveguide bandpass filter (BPF) based on slotted spherical resonators with a wide spurious-free stopband is presented. The resonator consists of a spherical cavity with slots opened at the top and bottom. Compared with a non-slotted spherical resonator, the slotted resonator suppresses the two spurious modes (TM211 and TE101) whilst maintaining the fundamental TM101 mode. The unloaded quality factor of the TM101 mode is not significantly degraded. This is achieved by interrupting surface current and radiating the unwanted spurious modes with the slots. The BPF is designed at a center frequency of 10 GHz with a fractional bandwidth of 1%. Two filter prototypes are fabricated, one using metal-based selective laser melting (SLM) and the other by polymer-based stereolithography apparatus (SLA) techniques. The slots also facilitate the copper electroplating process for the SLA-printed filter. The measured results show that the average passband insertion losses of the SLM- and SLA-printed filters are 0.33 and 0.2 dB, respectively. The corresponding passband return losses are better than 22 and 20 dB. The filters demonstrate excellent passband performance and wide spurious-free stopbands up to 16 GHz with stopband rejections of over 20 dB.

With the development of the mobile Internet, novel things are constantly emerging, and among them, online car-hailing is one of the representatives. However, the rapid development of online car-hailing also brings about normative problems and safety loophole, the most prominent of which is the inconsistency between operating cars and registered drivers. Some existing algorithms based on curve similarity measurements, such as Hausdorff distance and discrete Fréchet distance, can be used to solve this problem. However, they only consider one of the characteristics of the two curves, such as the distance or the area between two curves, which does not achieve good results on this problem. On this ground, we propose a model based on curve comparison, named multi-feature fusion (MFF), which extracts the features of length, distance, and area from the GPS positioning track of car and the application mobile phone of the driver, to testify whether the car is being operated by the registered driver and thus solving the problem of mismatch between the driver and the car during the operation. Among them, the MFF model designs different algorithms for different features and fuses different features by an ensemble learning method. The experimental results prove that the model can effectively detect the mismatch between drivers and cars.

Efficient modeling method accelerates computer-aided antenna design. In this paper, a novel Gaussian process regression (GPR) modeling based on landmark isometric feature mapping (LISOMAP) for antennas is proposed to improve the accuracy of modeling. In the GPR-LISOMAP method, LISOMAP, a dimension reduction method, is used to reduce the dimension of data for eliminating useless information. GPR is utilized as the modeling method to establish the relationship between antenna design space (multiple inputs) and response space (multiple outputs). The proposed modeling method is demonstrated by a circularly polarized antenna. Numerical results show that the GPR-LISOMAP method improves the accuracy of antenna modeling.

Recently remote driving has been considered as an augmentation to autonomous driving because the autonomous driving technology is not mature enough to be used in a more challenging situation. However, the remote driving is greatly affected by network delays. When a high speed vehicle discovers a dangerous situation, the network delay may prohibit the vehicle from reacting immediately whether or not the remote driver is a human or an artificial intelligence. Thus, the network delay is a very important factor in the remote driving of the vehicle. In this paper, we systematically investigate the feasibility of remote driving in a nationwide scale by measuring the real latency to four cities in South Korea. The results show that the delay is not proportional to the geographical delay, so there are a lot of rooms to improve the latency situation in remote driving. Furthermore, we also show that different wireless technology may affect the delays, too.

As an important basic industry supporting the national economy, iron and steel industry is the industrial sector with the largest power consumption. As one of the top ten energy consumption industries, energy saving and consumption reduction has become an urgent problem in the production process of iron and steel industry. In the past, the regulation mode of iron and steel enterprises to participate in the demand response is limited, inefficient and restricted by external factors. This paper designs a method for calculating the steel demand response potential based on the AOE network. It aims to use the no-load gap in the steel process to adjust the steel load, realize the energy saving and consumption reduction of the steel enterprise itself, and reduce the fluctuation impact of the internal impact load on the power system.

Antenna and Wave Propagation course is regarded as an important course for senior undergraduates or postgraduates majoring in electrical engineering, especially communication engineering. This article presents an implementation of project-based learning in antenna and wave propagation course. A project-based learning component is developed to supplement traditional classroom learning. It motivates the students to apply the textbook theory to real-world engineering problems, allows meaningful collaborations between the students, and boosts students’ self-learning capability. Demonstrated by project results and student feedbacks, incorporating project-based learning into traditional classroom learning benefits both student learning outcomes and student personal development.

In the research field of cloud auto-scaling, controlling application-level response time through resource provision to meet the predefined threshold is vital. But there still exists many challenges in the multi-service application scenario. This paper first points out that, in a multi-service application, increasing or decreasing the instance number of one service may affect other services’ response time. This phenomena brings more complexity in designing an auto-scaling strategy as the application-level response time is constructed and affected by the time of every service in it. To hide those affections among internal services, the change in application-level response time under various services’ instance number configurations is modelled as a black-box optimization problem. Then, an improved Bayesian Optimization approach is proposed to resolve it. As the improved part, a heuristic method will dynamically and gradually expand the search space according to each service’s response time. So a group of services can be scaled simultaneously and more than one instance can be added into a service at one scaling action. The experiments results conducted on the popular kubernetes platform indicate that our method is faster than other traditional ones in controlling the application-level response time down to the predefined threshold value.

A practical question-answering (QA) system typically categorizes a new question into the frequently asked questions (FAQs) and returns the corresponding answer. Having imbalanced FAQs data is actually prevalent in general. This paper proposes a meta-learning method for imbalanced question classification. The basic idea is to generate virtual training data for zero-shot questions and then construct question prototypes for training a question classifier, thereby relieving the problem of data imbalance and improving performance of question classifier. Experiments show that the proposed method improves the overall classification performance both for English and Chinese QA tasks. Especially, the classification performance of zero annotated questions increased significantly, and the generative prototypes has minute impact on the performance of large annotated question test set.

Due to the lightweight and flexible characteristics, containers have gradually been used for the application deployment and the basic unit for resource allocation in a cloud platform recently. Reinforcement learning (RL), as a classic algorithm, is widely used in virtual machine scheduling scenarios due to its advantages of adaptability and robustness. However, most RL methods have problems in container scheduling, such as untimely scheduling, lack of accuracy in decision-making and poor dynamics that will lead to a higher SLA violation rate. In order to solve the above problems, a predictive RL algorithm A-SARSA is proposed, which combines the ARIMA model and the neural network model. This algorithm not only ensures the predictability and accuracy of the scaling strategy, but also enables the scaling decisions to adapt to the changing workloads. Through a large number of experiments, the timeliness and effectiveness of the A-SARSA algorithm for container scheduling are verified, which can reduce the SLA violation rate dramatically while keeping the resource utilization rate at a good level.

Conductor galloping is the high-amplitude, low-frequency oscillation of overhead power lines due to wind. Such movements may lead to severe damages to transmission lines, and hence pose significant risks to the power system operation. In this paper, we target to design a detection framework for conductor galloping. The difficulty comes from limited and imbalanced dataset as galloping happens rarely. By examining the impacts of data balance and data volume on the detection performance, we propose to employ proper sample adjustment methods to achieve better performance. Numerical study suggests that using only three features, together with over sampling, the SVM based detection framework achieves an F1-score of 98.9%.

Low Pressure Die Casting (LPDC) is widely used in crankcase production. Owing to the unstable production situation and the complex shape of crankcase, porosity defect usually occurs in LPDC process which leads to loss in quality and productivity. In this paper, we apply data mining methods to predict the porosity defect in advance, so that we can take actions to prevent it from reoccurring in the next production part, thereby increasing the quality and productivity. To do it, firstly, we collect production data from a real-world casting line. Secondly, we prepare the data for prediction by feature extraction and feature selection. Thirdly, we apply an ensemble algorithm named Forest of Local Trees (FLT) for defect prediction. Finally, we present a thorough experimental study of the proposed method. The results show that our method outperforms other five algorithms on five real-world datasets in terms of three indicators, recall, precision and F-measure.

In this paper, a hybrid approach which combines brain storm optimization algorithm (BSO) with sine-cosine search mechanism is proposed. BSO is a newly proposed meta-heuristic algorithm which takes inspiration from the brainstorming behavior. It can obtain good results in solving some optimization problems. However, its performance is still raw, especially in dealing with complex and multi-modal problems. Thus, in this paper, we introduce a powerful search mechanism taken from sine cosine algorithm (SCA) which has considerable capacity to enhance the search ability of BSO. The proposed algorithm is tested by CEC’17 benchmark functions and the result indicates that this hybridization has considerable merit.

As an important category of computational intelligence, meta-heuristic algorithms have always been a popular research interests over recent two decades. Teaching-learning-based optimization (TLBO) is one of nature-inspired metaheuristic algorithm which is proven to have effectiveness and efficiency in solving complex optimization problems. Although TLBO has remarkable capacity to solve different optimization problems, but the issue of trapping into local optimal is a common drawback of meta-heuristic algorithm, and TLBO is no exception. Thus we use a novel search strategy to improve the performance of TLBO by means of a new selection operation. We select twenty-nine benchmark functions of IEEE CEC2017 to testify the performance of proposed algorithm in terms of effectiveness and robustness. Experimental results exhibit that the proposed algorithm outperforms other state-of-the-art algorithms.

Because social networks have become a vital part of people’s lives, cyberbullying becomes the most common risk encountered by young people on social networking platforms and raised serious concerns in society. Over the past few decades, most existing work on cyberbullying has focused on text analysis. Yet, the cyberbullying develops into multi-objective, multi-channel, and multi-form. Traditional text analysis methods cannot satisfy the diversity of bullying data in social networks. To deal with the new type of cyberbullying, we propose a multi-modal detection framework that takes into multi-modal information(e.g., image, video, comments, time) on social networks. Specifically, we not only extract textual features but also use the hierarchical attention networks to capture the session feature in social networks and encode several media information(e.g., video, image). Based on these features, we model the multi-modal cyberbullying detection framework to solve the new form of cyberbullying. Experimental analysis on two real-world datasets shows that our framework outperforms several existing state-of-the-art models.

Dynamic vehicle routing problem with time windows(DVRPTW) is a complicated combination optimal problem which attracts most scholars and experts to study. This paper considers the customer satisfaction in dynamic vehicle routing problem. In order to solve this problem, the dynamic vehicle routing problem is decomposed into multiple static vehicle routing problems, and the corresponding model is established with the objective of maximizing customer satisfaction. The model uses the idea of transforming the vehicles driving on the road into virtual customer points. In order to reflect the quality of service, the concept of customer satisfaction is introduced. Lingo11 is used to solve the model, and results show that dynamic routing planning can serve more customer requests and improve average customer satisfaction.

A unique integrated printed circuit board winding transformer has been proposed in this paper to be used in a high efficiency, high power density capacitor-inductor-inductor-inductor-capacitor series resonant dual active bridge converter (CLLLC-SRes-DAB) and key design considerations for CLLLC-SRes-DAB are addressed. Winding structure, core arrangement of the series inductor and transformer, and the shape of heatsink are carefully designed in order to minimize core volume, transformer intra-winding capacitance (C TX ), and eddy current losses caused by fringing flux near air gaps. A 6.6kW CLLLC-SRes-DAB prototype with a 500kHz series resonant frequency has been built to evaluate the performance of the proposed transformer. 98% peak efficiency is achieved in this 6.6kW CLLLC-SRes-DAB design.

A predictive synchronous rectifier (SR) sensing and control method is proposed in this paper using a Rogowski coil with a passive integrator and an adaptive SR turn-off scheme in order to optimize series resonant (SRes) converter efficiency. Unlike other SR sensing methods used in SRes converters, the SR sensing method proposed here has high bandwidth, can be operated at high operational frequency and doesn’t have SR voltage level limitations. Therefore, this method is suitable for optimizing the efficiency of a high-frequency, high-power-density SRes converter. This paper discusses the operation principles and experimental results of the method on a 6.6-kW capacitor-inductor-inductor-inductor-capacitor (CLLLC) series resonant dual active bridge converter.

Next-generation sequencing (NGS) is now indispensable for genetics research and biomedical applications, such as disease analysis and evolution tracking [1]. However, it still takes up to a couple of days to analyze all genetic mutations (variants) of a human genome, which consists of 3 billion nucleotides, through GPU acceleration. Fig. 21.1.1 shows an overview of NGS and the data analysis workflow. The NGS technology enables sequencing hundreds of millions of DNA segments, anchored and amplified on a microarray, in parallel. In each sequencing cycle, the nucleotides (A, T, C, G) are individually detected by their unique fluorescence labels and DNA segments can then be constructed as short reads. The NGS data analysis workflow consists of Preprocessing, Short-Read Mapping (including Exact Matching and Inexact Matching), Haplotype Calling, and Variant Calling [2]. Short reads are first mapped to a reference DNA and further used to assemble the genome of the DNA sample. Preprocessing is essential for constructing the data structure for indexing the reference DNA. In Short-Read Mapping, a seeding-and-extension scheme is applied to perform both Exact and Inexact Matching. The equal-length sub-sequences (seeds) of the short reads are used to find the exact locations on the reference DNA. Then, the seeds are extended to identify the most-likely locations through global alignment, allowing mismatches and insertions/deletions [2]. Next, in Haplotype Calling, the reads mapped to a specific region are assembled to reconstruct the paternal and maternal genomes (i.e. haplotypes) of the DNA sample. Finally, in Variant Calling, the assembled haplotypes are used to determine the variants between the reference DNA and the sample DNA. The outputs of Variant Calling indicate the location and likelihood of each variant. Dedicated VLSI solutions have been developed for acceleration, but only Suffix-Array (SA) Sorting for Preprocessing and Exact Matching for Short-Read Mapping were realized on silicon [3]. This work presents a fully integrated SoC for the entire NGS data analysis process.

Community structure analysis in dynamic network is widely concerned in various fields, which mainly focus on temporal community detection and community evolution analysis. Most of the related works usually fist detect communities and then analyze evolution. This leads to a loss of evolution information on temporal community detection because block structures and evolution characteristics coexist in dynamic networks. Even thought a few modelbased approaches consider the evolution characteristics into community detection, they need to know the number of communities in advance and ignore automatic determination of the number of communities, which is a model selection problem. In the paper, we propose an model, Evolutionary Bayesian Non-negative Matrix Factorization (EvoBNMF), to model community structures with evolution characteristics for boosting the performance of temporal community detection. In detail, EvoBNMF introduces evolution behaviors, which quantify the transition relationships of communities between adjacent snapshots, to describe the evolution characteristics of community structure. Innovatively, EvoBNMF can catch the most appropriate number of communities autonomously by shrinking the corresponding evolution behaviors. Experimental results from synthetic networks and real-world networks over several state-of-the-art methods show that our approach has superior performance on temporal community detection with the virtue of autonomous determination of the number of communities.

In recent two decades, nature-inspired metaheuristic algorithms have been paid more and more attention. Although many new algorithms have been proposed, there is no quintessential difference among classic metaheuristic algorithms. Therefore, some researchers have focused on the essence of search operators in these optimizers. Spherical Evolution (SE) is one of the recent studies on the search style in metaheuristic algorithms. Contrary to other algorithms, SE adopts a spherical search instead of a hypercube search. In this paper, we focus on the advantages of the two search styles, We propose a hybrid optimizer based on the two complementary search styles, and design a rule to control their utilization. Experimental results based on 30 benchmark functions of CEC2017 show that the proposed optimizer outperforms other state-of-the-art algorithms in terms of effectiveness and robustness.

This paper reports on a simplified and cost-efficient approach for realization of air-filled self-suspended rectangular coaxial transmission lines (TLs) by means of polymer-based additive manufacturing. An X-band TL prototype is devised with a wideband filter design approach. The input and output of the TL are connectorized to interface with external circuits. Architectural highlights involving the impedance matching, the assembly of RF connectors, and the sidewall openings will be discussed. The TL is monolithically prototyped by incorporating stereolithography apparatus and copper electroplating techniques, featuring low cost, easy assembly, and free of any fastening element. The implemented TL demonstrates in 8-12.4 GHz an insertion loss of 0.4-1.1 dB (an attenuation factor of 0.06-0.26 dB/cm after the connector loss is deembedded) and a group delay of 0.23-0.32 ns with a fluctuation of around 50 ps.

During the 3-D ICs manufacturing process, TSVs are susceptible to undergo different faults. Among these faults, the leakage fault is one of the most common cases. In this paper, a new test structure based on the improved ring oscillator circuit is proposed to detect the TSV leakage fault. An accurate TSV leakage fault model extracted from three-dimensional full-wave simulation is adopted in the test structure. HSPICE Monte Carlo simulation shows that the proposed test structure can detect the weak leakage faults with no less than 0.2025um2 pin-hole area, which is a larger coverage compared with the traditional test structure.

Theoretically analyzed and experimentally demonstrated an all-fiber pressure sensor based on a microfiber coupler combined SAGNAC loop. The work of this paper proves the usability of the structure in the deep sea environment.

The main focus of this paper is on an uplink communication system with multiple single-antenna users utilizing the same frequency band and simultaneously transmitting their finite alphabet signals to one base station having a large number of antennas. It is assumed that small scale channel fading is Rayleigh fading and varies in every one time slot, and that the large scale fading coefficients are fixed and known at both the transmitter and the receiver. For such uplink non-orthogonal multiple access massive MIMO system, we aim at establishing a new criterion using a noncoherent maximum likelihood detector for collaboratively designing all such user constellations that once each received sum signal point has been recovered, all the user signal points can be uniquely determined, i.e., all the user constellations form a so called additively uniquely decomposable constellation group (AUDCG). To this end, we first derive a fast noncoherent ML detection algorithm for the received sum constellation and a corresponding closed form symbol error probability formula (SEP). Thus, two important concepts: full receiver diversity and geometrical coding gain, are introduced to quantitatively characterize how quickly SEP decays when the number of base station antennas goes to infinity. Then, the design of an optimal AUDCG is formally formulated into an optimization problem that maximizes both the receiver diversity and the geometrical coding gains subject to each user power constraint. Particularly for a two user system, with each user transmitting nonnegative binary constellation, an optimal closed form sum constellation is obtained. Computer simulations demonstrate that our proposed optimal constellation design substantially outperforms the currently available constellation designs for the same uplink massive MIMO system.

A microfiber coupler conbined SAGNAC loop is fabricated for seawater temperature and salinity sensing experiment. The experimental results show that the sensitivity is high, and its dynamic range can meet the marine environment monitoring demand.

In order to improve the accuracy of face detection, this paper proposes a method based on combination of skin color model and improved Adaboost algorithm. Using skin color model with YCbCr color space to detect the skin color, obtain the area to be detected, and then we can locate accurately the face position with the Adaboost face detection algorithm. Because the traditional Adaboost face detection algorithm needs a long time training and can not effectively distinguish feature values which are aggregated distribution, we have improved Adaboost algorithm based on two-threshold and a new method about suppression of weights updating which which prevents excessive weight gain and avoids the phenomenon of degradation during training in Adaboost.

In this paper, a new method for two-dimensional temperature distribution reconstruction using compactly supported and gaussian radial basis function is presented. And then the reconstruction performance is validated via numerical studies using temperature model. Experimental results indicate that the proposed method holds a relatively great performance of temperature distribution reconstruction and stronger anti-interference.

Good progress has been made in the microservice technology in recent years due to the development of docker container technology. Although microservice architecture can adjust the number of containers, there is a new problem. That is according to the current load pressure of services, how to adjust the number of containers accurately and quickly in real time, especially when the load pressure of services suddenly increases or decreases. In order to deal with the problem, a container scheduling strategy based on machine learning is proposed in this paper. The paper uses the data set obtained by our experiments to train random forest regression model in advance to predict the required containers of services in the next time window, according to the current load pressure of services. Large amounts of data has been collected to make the data set for the experiment. Based on the data set, random forest regression model has been trained in advance to predict the number of required containers of services in next time window. When adjusting the number of containers to balance load pressure of services, the proposed algorithm saves 50% of the time compared with traditional algorithms. In addition, the accuracy is 10%~38% higher compared with other machine learning algorithms.

This paper studies the problem of tracking control of under-actuated surface vessel (USV) with given trajectory under external disturbances. A backstepping sliding mode control method based on pre-set performance is proposed to improve the transient response performance. Firstly, by introducing the performance function, the USV error model is transformed into an equivalent conversion error model, so that the original restricted system is converted into an equivalent non-restricted system. Secondly, the position error is stabilized by a virtual velocity and a second-order integral sliding surface based on the velocity error is introduced to design the speed tracking controller. Using Lyapunov stability analysis, it can be concluded that the designed controller can ensure gradual convergence of the error signal of the whole closed-loop system. Finally, the simulation results verify the effectiveness of the design controller and robustness under external disturbances.

New age smartphones are equipped with high processing power and internet connectivity. Hence, smartphones are capable of executing applications, which were only possible by desktops or laptops until recently. Some examples of such applications are email, banking, flight booking etc. People prefer to use mobile devices for these applications due to the usability and portability of mobile devices. However, because of hardware limitations, mobiles have limited resources such as battery life, power and capacity. Researchers are constantly looking for ways to maximize the usage of these resources. The execution of any application on mobile, needs storage capacity of mobile to store, battery life of mobile to keep running and processing capacity of mobile to process. Thus, more resources are needed to run more applications on these devices. To reduce the load of applications on mobile devices and use the resources efficiently, it is necessary to move some load of applications to remote cloud server in such a way that the applications will run seamlessly. Computation offloading for mobile-edge computing MEC) is a mechanism to utilize mobile resources well by moving resource-intensive applications to cloud server at network edge. In the case of multiple users, the total computing capacity of the server needs to be taken into consideration for allocating resources to multiple users. The key to efficient computation offloading is allocating applications to mobile and remote server in such a way that minimizes transmission energy. In this paper, we formulate the computation offloading problem as graph cut problem and propose a solution based on spectral clustering computation. First, for the applications on mobile a corresponding network flow graph model is defined. Then, label propagation theory is applied on the network graph and the network graph is simplified by compressing and combining. Finally, the optimal solution is obtained by computation using spectral clustering algorithm. Experiments show that the algorithm is effective in handling programs with loosely coupled as well as highly coupled functions.

As more add-ons emerge with the flight ticket in the airline industry, the airlines not only need to design the airline bundling, but also need to set the proper bundling price. However, as the market segmentation in the airline industry becomes stronger, some airlines begin to unbundle the add-on from the flight ticket for more value-added profits. In this paper, we establish a leader-follower game model to study the unbundling of the add-on in the airline industry. The leader airline sells the unbundled add-on, and then the follower airline sells the flight ticket and the airline bundling together. The equilibrium prices of the fight ticket, add-on and airline bundling are discussed in three scenarios. Numerical experiments show that the sensitive analysis of several marketing factors on the equilibrium pricing strategy.

This paper reports on a new class of broadband fully 3-D printed E-plane rectangular-coax-to-waveguide transition. This type of transition is adopted to interconnect two E-plane rectangular waveguides, and is based on a full air-filled waveguide structure without introducing other types of transmission lines (TLs). It exhibits little dielectric loss and dispersion, and furthermore a potentially enhanced power handling capability. The transition is constructed by a section of air-filled rectangular coaxial TL cascaded in series to a broadband coax-to-waveguide probe transition. A proof-of-concept X-band back-to-back transition is designed and prototyped monolithically by incorporating stereolithography-based 3-D printing and copper electroplating techniques. The RF-measured result demonstrates a broadband and low-loss characteristic of the transition—an insertion loss of averagely 0.5 dB and a return loss of mostly better than 15 dB at the entire X band.

The fixed switching frequency method in space vector pulse width modulation strategy has been widely used in the motor speed control system. The three-phase current of the motor under this control method will generate harmonics with higher amplitude at integer multiples of the switching frequency. It is the main source of electromagnetic noise generated by the motor. Therefore, in order to suppress the current harmonics of the driver output and improve the current waveform quality, first of all, the three-phase current ripple generation mechanism based on the common topology of the three-phase motor driver is deduced theoretically and the current ripple prediction model is obtained. The results of the prediction model are then used to specifically modify the switching frequency of motor driver to reduce the amount of current harmonics during motor rotation. The experimental results show that the harmonic suppression control method based on ripple prediction model is more effective than the traditional fixed switching frequency method in reducing the motor current harmonics and improving current quality. The method in this paper has been applied in an underwater propulsion system.

This paper proposes two methods to improve the spurious-free stopband range for high-quality-factor spherical resonators and a new family of shaped spherical resonators are presented. Geometrical shaping of the proposed resonators is realized by symmetrically squeezing a spherical cavity and further opening a rectangular slot in each squeezed area. The higher order modes of the resonator are first tuned spectrally farther away from the dominant mode by the squeezing, and then are suppressed by the slotting. X-band resonator prototypes are designed, and 3-D printed by using a metallic selective laser melting technique. Quality factors of the fabricated resonators are further improved by vibration grinding process. The experiment validates effective suppression of the first higher order mode and indicates potential applications of the proposed resonators in bandpass filters to extend the spurious-free stopband bandwidths.

Due to the absence of the central administrator and the dynamic network topology of the Mobile Ad-hoc Networks (MANETS), trust management is a major issue for designing the routing protocols of the network. In this paper, to identify the malicious nodes in the ad-hoc network, a trust inference model based on recommendations is proposed. This multidimensional model is aware of the energy, the channel and history of the interactions between the nodes. The proposed trust model evaluates trust by using two main components: the direct interaction trust (Primary trust) calculated using the Bayesian statistical method and recommendations from the neighbors (secondary trust). The metrics used for calculating the primary trust are: the received signal strength, time of the each interaction, the intimacy of nodes and the frequency of interactions. This trust inference model is implemented on top of the conventional Dynamic Source Routing (DSR) protocol. The results of the simulations affirms that the proposed model enhance effectiveness of routing in existence of malicious peers in the MANETs.

Physical Unclonable Functions (PUFs) have been proposed as a tamper-resistant alternative to the traditional methods for secret key generation and challenge-response authentication. Although many different types of PUFs have been presented, the search for more efficient, reliable and secure PUF designs continues. In this paper, we introduce a new class of PUFs, called threshold PUFs. We show that, in principle, any n- input threshold logic gate can be used as a base for building an n-input PUF. This opens up the possibility of using a rich body of knowledge on threshold logic implementations for designing PUFs. As a proof of concept, we implement and evaluate binary and ternary PUFs based on recently proposed threshold logic flip-flops.

Occlusion is a challenge for accuracy of recognition and localization for picking robot in harvesting. The algorithm developed in this paper combing deep learning and random filtering, which can be effectively eliminate the disturbing of obstacle. Firstly, apple images under occluded are as training input for neural network YOLO. Recognition result was signed by rectangular after YOLO. Secondly, for eliminate the interference of occlusion by random sampling filtered the depth values of obstacle points. Experiments shown that, this algorithm can provide real-time and accurate location information for picking. The difference between real and detection is limited in 4mm by the measure range from 600mm to 1500mm. The algorithm proposed in this paper could be flexible applied in other fruits, and it has a widely application values.

In Mobile Adhoc Networks (MANETs) during the process of routing the consumption of energy remains a challenge as mobile nodes have limited battery. We propose method for increasing the lifetime of the network and minimizing the link breakages by choosing the paths for routing, with more available energy. In this paper we propose two schemes based on Adhoc On-Demand Distance Vector (AODV), a reactive routing protocol. In both these schemes, to reduce the control packets overhead, limited mobile nodes can be the part of the routing process. This limitation is based on the received signal strength. The energy efficient available path in terms of residual energy is selected either by the destination node or by intermediate node locally. The simulation results show that our proposed schemes results in the energy efficient routing as compared to traditional AODV.

The sine cosine algorithm is a newly proposed optimization algorithm and it has shown remarkable performance in solving some optimization problems. However, its search ability deteriorates when facing complex problems because of premature convergence. To mitigate this drawback, we propose a population diversity based local refinement strategy to help it maintain population diversity in a high level. Twenty-nine test functions in CEC’17 benchmark suit is implemented to evaluate its performance. The experimental results indicate the flexibility of controlling diversity and the proposed strategy is promising to be applied to other algorithms.

The online hybrid teaching mode had been used to improve learning and evaluation efficiency. The Kung-Fu style competency education with online-support laboratory system prompts students to own their learning as the pace and/or the path of learning. Student could move on to the next project only after they've mastered the core concept. To further guarantee the quality of teaching, it is necessary to provide efficient and accurate progress control for the process iteration. This paper elaborated how to build the quality assurance mechanism to 1) track students' progress, 2) store the behavior data, 3) support the quantitative data analysis, and 4) provide the teaching interaction services. The teaching assistant system could not only improve the work efficiency of the iterative process control course, but also improve the utilization of teaching resources. We used this quality assurance mechanism in the last course iteration, which effectively guarantee the quality of teaching.