Improved organs at risk segmentation based on modified U‐Net with self‐attention and consistency regularisation

Cancer is one of the leading causes of death in the world,with radiotherapy as one of the treatment options.Radiotherapy planning starts with delineating the affected area from healthy organs,called organs at risk(OAR).A new approach to automatic OAR seg-mentation in the chest cavity in Computed Tomography(CT)images is presented.The proposed approach is based on the modified U‐Net architecture with the ResNet‐34 encoder,which is the baseline adopted in this work.The new two‐branch CS‐SA U‐Net architecture is proposed,which consists of two parallel U‐Net models in which self‐attention blocks with cosine similarity as query‐key similarity function(CS‐SA)blocks are inserted between the encoder and decoder,which enabled the use of con-sistency regularisation.The proposed solution demonstrates state‐of‐the‐art performance for the problem of OAR segmentation in CT images on the publicly available SegTHOR benchmark dataset in terms of a Dice coefficient(oesophagus-0.8714,heart-0.9516,trachea-0.9286,aorta-0.9510)and Hausdorff distance(oesophagus-0.2541,heart-0.1514,trachea-0.1722,aorta-0.1114)and significantly outperforms the baseline.The current approach is demonstrated to be viable for improving the quality of OAR segmentation for radiotherapy planning.

Guest Editorial:Special issue on advances in representation learning for computer vision

Deep learning has been a catalyst for a transformative revo-lution in machine learning and computer vision in the past decade.Within these research domains,methods grounded in deep learning have exhibited exceptional performance across a spectrum of tasks.The success of deep learning methods can be attributed to their capability to derive potent representations from data,integral for a myriad of downstream applications.These representations encapsulate the intrinsic structure,fea-tures,or latent variables characterising the underlying statistics of visual data.Despite these achievements,the challenge per-sists in effectively conducting representation learning of visual data with deep models,particularly when confronted with vast and noisy datasets.This special issue is a dedicated platform for researchers worldwide to disseminate their latest,high-quality articles,aiming to enhance readers'comprehension of the principles,limitations,and diverse applications of repre-sentation learning in computer vision.

SmartMicro Grid Energy System Management Based on Optimum Running Cost for Rural Communities in Rwanda

The governmental electric utility and the private sector are joining hands to meet the target of electrifying all households by 2024.However,the aforementioned goal is challenged by households that are scattered in remote areas.So far,Solar Home Systems(SHS)have mostly been applied to increase electricity access in rural areas.SHSs have continuous constraints to meet electricity demands and cannot run income-generating activities.The current research presents the feasibility study of electrifying Remera village with the smart microgrid as a case study.The renewable energy resources available in Remera are the key sources of electricity in that village.The generation capacity is estimated based on the load profile.The microgrid configurations are simulated with HOMER,and the genetic algorithm is used to analyze the optimum cost.By analyzing the impact of operation and maintenance costs,the results show that the absence of subsidies increases the levelized cost of electricity(COE)five times greater than the electricity price from the public utility.The microgrid made up of PV,diesel generator,and batteries proved to be the most viable solution and ensured continuous power supply to customers.By considering the subsidies,COE reaches 0.186$/kWh,a competitive price with electricity from public utilities in Rwanda.

Low profile cavity-embedded ultra-wideband UHF array antenna with end-fire beams

A low-profile,vertically polarized,ultra-wideband array antenna with end-fire beams operating in an ultra-high frequency(UHF)band is developed in this paper.The array antenna consists of 1×16 log-periodic top-hat loaded monopole antenna arrays and is feasible to embed into a shallow cavity to further reduce the array height.Capacitance is introduced in the proposed antenna element to reduce profile height and the rectangular top hats are carefully designed to minimize the transverse dimension.Simulated results show that when the antenna array operates in a frequency range of 300 MHz-900 MHz,the end-fire radiation pattern achieves±45°scanning range in the horizontal plane.Then prototypes of the proposed end-fire antenna element and a uniformly spaced linear array(1×2)are fabricated and validated.The end-fire antenna array should be suitable for airborne applications where low-profile and conformal scanning phased antenna arrays with end-fire radiations are required.This design is attractive for airborne platform applications that are used to search,discover,identify,and scout the aerial target with vertically polarized beams.

Impact of welding equipment on power quality

In an industrial facility,many electrical consumers can affect the quality of electricity.Therefore,the freedom from interference sources of these devices and equipment can be crucial for quality and uninterrupted electricity supply.Electric welding equipment is also a possible source of interference.The electrical harmonic injections created by welding equipment into the electrical network can affect the operation of other consumers connected to the given distribution points and cause unjustified overheating and shutdowns of some network components.The aim of the research is to analyse the current harmonic injection of welding equipment of different types and modes of operation connected to the internal distribution network of the industrial facility.The effectiveness of the active harmonic filter built into the welding equipment was also examined in the paper.The results showed that the built-in active harmonic filter of the DC045 laser welding equipment was ineffective because the total harmonic distortion(THD)was about three times the 8%allowed by IEEE 519−2022 standard.The current harmonic injection of MIG 320 and MM403 type welding equipment was more than five times the permissible value of 5%.The current harmonic distortion of the PLAS140 type plasma-jet cutter equipment was below the 5% value allowed in the standard,thus it complied with it.Based on the measurement results,it can be concluded that the use of protection against harmonics is also necessary for welding equipment.Finally,proposals were made in the paper to reduce the effect of harmonics.

Polariton lasing in Mie-resonant perovskite nanocavity

Deeply subwavelength lasers(or nanolasers)are highly demanded for compact on-chip bioimaging and sensing at the nanoscale.One of the main obstacles for the development of single-particle nanolasers with all three dimensions shorter than the emitting wavelength in the visible range is the high lasing thresholds and the resulting overheating.Here we ex-ploit exciton-polariton condensation and mirror-image Mie modes in a cuboid CsPbBr3 nanoparticle to achieve coherent emission at the visible wavelength of around 0.53μm from its ultra-small(≈0.007μm3 or≈λ3/20)semiconductor nanocav-ity.The polaritonic nature of the emission from the nanocavity localized in all three dimensions is proven by direct com-parison with corresponding one-dimensional and two-dimensional waveguiding systems with similar material parameters.Such a deeply subwavelength nanolaser is enabled not only by the high values for exciton binding energy(≈35 meV),re-fractive index(>2.5 at low temperature),and luminescence quantum yield of CsPbBr3,but also by the optimization of po-laritons condensation on the Mie resonances with quality factors improved by the metallic substrate.Moreover,the key parameters for optimal lasing conditions are intermode free spectral range and phonons spectrum in CsPbBr3,which govern polaritons condensation path.Such chemically synthesized colloidal CsPbBr3 nanolasers can be potentially de-posited on arbitrary surfaces,which makes them a versatile tool for integration with various on-chip systems.

A Fractional Order Fast Repetitive Control Paradigm of Vienna Rectifier for Power Quality Improvement

Due to attractive features,including high efficiency,low device stress,and ability to boost voltage,a Vienna rectifier is commonly employed as a battery charger in an electric vehicle(EV).However,the 6k±1 harmonics in the acside current of the Vienna rectifier deteriorate theTHDof the ac current,thus lowering the power factor.Therefore,the current closed-loop for suppressing 6k±1 harmonics is essential tomeet the desired total harmonic distortion(THD).Fast repetitive control(FRC)is generally adopted;however,the deviation of power grid frequency causes delay link in the six frequency fast repetitive control to become non-integer and the tracking performance to deteriorate.This paper presents the detailed parameter design and calculation of fractional order fast repetitive controller(FOFRC)for the non-integer delay link.The finite polynomial approximates the non-integer delay link through the Lagrange interpolation method.By comparing the frequency characteristics of traditional repetitive control,the effectiveness of the FOFRC strategy is verified.Finally,simulation and experiment validate the steadystate performance and harmonics suppression ability of FOFRC.

Selection of Metaheuristic Algorithm to Design Wireless Sensor Network

The deployment of sensor nodes is an important aspect in mobile wireless sensor networks for increasing network performance.The longevity of the networks is mostly determined by the proportion of energy consumed and the sensor nodes’access network.The optimal or ideal positioning of sensors improves the portable sensor networks effectiveness.Coverage and energy usage are mostly determined by successful sensor placement strategies.Nature-inspired algorithms are the most effective solution for short sensor lifetime.The primary objective of work is to conduct a comparative analysis of nature-inspired optimization for wireless sensor networks(WSNs’)maximum network coverage.Moreover,it identifies quantity of installed sensor nodes for the given area.Superiority of algorithm has been identified based on value of optimized energy.The first half of the paper’s literature on nature-inspired algorithms is discussed.Later six metaheuristics algorithms(Grey wolf,Ant lion,Dragonfly,Whale,Moth flame,Sine cosine optimizer)are compared for optimal coverage of WSNs.The simulation outcomes confirm that whale opti-mization algorithm(WOA)gives optimized Energy with improved network coverage with the least number of nodes.This comparison will be helpful for researchers who will use WSNs in their applications.

Medi-Block Record Secure Data Sharing in Healthcare System:Issues,Solutions and Challenges

With the advancements in the era of artificial intelligence,blockchain,cloud computing,and big data,there is a need for secure,decentralized medical record storage and retrieval systems.While cloud storage solves storage issues,it is challenging to realize secure sharing of records over the network.Medi-block record in the healthcare system has brought a new digitalization method for patients’medical records.This centralized technology provides a symmetrical process between the hospital and doctors when patients urgently need to go to a different or nearby hospital.It enables electronic medical records to be available with the correct authentication and restricts access to medical data retrieval.Medi-block record is the consumer-centered healthcare data system that brings reliable and transparent datasets for the medical record.This study presents an extensive review of proposed solutions aiming to protect the privacy and integrity of medical data by securing data sharing for Medi-block records.It also aims to propose a comprehensive investigation of the recent advances in different methods of securing data sharing,such as using Blockchain technology,Access Control,Privacy-Preserving,Proxy Re-Encryption,and Service-On-Chain approach.Finally,we highlight the open issues and identify the challenges regarding secure data sharing for Medi-block records in the healthcare systems.

Controlled LED Lighting for Horticulture: A Review

As energy gradually becomes a more valuable commodity, the desire for reduced energy losses strengthens. Lighting is a critical field on this matter, as it accounts for a large percentage of the global electricity consumption and modern lighting systems are greatly more efficient than incandescent, discharge, and fluorescent lights. Previous research has proven that plants do not require the entire visible spectrum but react only to specific wavelengths, making it possible to control their growth and yield via artificial lighting. The flexibility of control of Light Emitting Diode (LED) lights allows for the combination of great energy losses reduction and controlled plant growth, achieving the improvement of two major parameters in a single action. This review paper summarizes the current research on the effect different light wavelengths have on specific plant species and discusses the applications of LED lighting for horticulture, yield storage, and disease protection.

Design and Implementation of Smart Power Voltage and Frequency Synchroniser in Power Distribution System

Voltage and frequency are usually considered and assessed independently in the design and operation of electrical networks. However, these two are linked. Each and every malfunctioning electrical system has an impact on both voltage and frequency. This paper presents the opportunity for monitoring the distributed electrical energy by means of a system that monitors, controls, and provides a breakpoint based on high or low voltage and frequency tripping mechanism that avoids any damage to the load. The designed system comprised a switch mode power supply (SMPS), a direct digital synthesizer (DDS), and PIC16F876A microcontroller techniques for stable voltage and frequency outputs. Proteus design suite version 8.11 software and Benchcope SDS1102CN were used for modeling and simulation. The hardware prototype was implemented at a telecom cell site for data capturing and analysis. Test results showed that the implementation of the prototype provided stable and constant outputs of 222 V/50 Hz and 112 V/60 Hz which constituted 99% and 99.8% efficiency for voltage and frequency performance respectively. The paper also discusses different technologies that can be adopted by the system to mitigate voltage and frequency effects on customer appliances.

利用近似解加速求解SAT问题的启发式完全算法

结合DPLL完全算法能够证明可满足性(SAT)问题的不可满足性和局部搜索算法快速的优点,提出利用近似解加速求解SAT问题的启发式完全算法.首先利用局部搜索算法快速地得到一个近似解,并将该近似解作为完全算法的初始输入,用于其中分支变量的相位决策.该算法引导完全算法优先搜索近似解所在的子空间,加速解决器找到可满足解的过程,为SAT问题的求解提供了一种新的有效途径.实验结果表明,该算法有效地提高了决策的精度和SAT解决器的效率,对很多实例非常有效.

干涉型光纤传感器阵列消PIF技术的研究

针对低双折射光纤双光束干涉型传感器两臂偏振态随机变化引起的信号衰落 ,提出了一种新型消偏振方式 ,它可以在可见度略有下降的情况下 ,较好地消除偏振态变化引起的干涉信号可见度的随机变化。该方案是通过相互正交的两个偏振态来补偿由于其中一个偏振态变化导致的干涉信号衰落。通过自动增益控制电路可以使传感信号稳定 ,能够在信噪比有所下降的情况下消除偏振衰落的影响 。

Angle estimation in bistatic MIMO radar using improved reduced dimension Capon algorithm

This paper discusses the problem of direction of departure （DOD） and direction of arrival （DOA） estimation for a bistatic multiple input multiple output （MIMO） radar, and proposes an improved reduced-dimension Capon algorithm therein. Compared with the reduced-dimension Capon algorithm which requires pair matching between the two-dimensional angle estimation, the pro- posed algorithm can obtain automatically paired DOD and DOA estimation without debasing the performance of angle estimation in bistatic MIMO radar. Furthermore, the proposed algorithm has a lower complexity than the reduced-dimension Capon algorithm, and it is suitable for non-uniform linear arrays. The complexity of the proposed algorithm is analyzed and the Cramer-Rao bound （CRB） is also derived. Simulation results verify the usefulness of the proposed algorithm.

External Characteristics and Internal Flow Features of a Centrifugal Pump during Rapid Startup

Centrifugal pumps always work under steady conditions,and many researches focus on the steady operation.But transient conditions,such as sudden startup and shutdown,are inevitable.The researches on the inner flow of centrifugal pumps under transient conditions have been done,and they show that the transient operation is different from the steady operation.In order to research the evolution of unsteady flow in a centrifugal pump under transient conditions,and to investigate the mechanism of transient effects by analyzing the unsteady flow in a centrifugal pump,the external characteristic experiment and the internal flow numerical calculation of the centrifugal pump with an open impeller during startup is presented.The relationships of the rotation speed,capacity and head between start-time are obtained by the external characteristics experiment.The numerical calculations under startup process are carried out by using the k-e model and N-S equation.The distribution of velocity and pressure in the inner channel of the tested pump was obtained by choosing fourteen start-time points and twelve geometrical points in the impeller channel during startup.The calculation results show that the velocity and the pressure increase linearly with the start-time before rotation＇s speed gets steady,then changes almost horizontally after rotation speed becomes steady,then fluctuates until being steady.The internal flow characteristics are in good agreement with the external characteristic experimental results and numerical calculation.The simulation methods and results make the basis for the diagnosis and optimization of under flow in the centrifugal pump during transient operation.

A realizable quantum encryption algorithm for qubits

A realizable quantum encryption algorithm for qubits is presented by employing bit-wise quantum computation. System extension and bit-swapping are introduced into the encryption process, which makes the ciphertext space expanded greatly. The security of the proposed algorithm is analysed in detail and the schematic physical implementation is also provided. It is shown that the algorithm, which can prevent quantum attack strategy as well as classical attack strategy, is effective to protect qubits. Finally, we extend our algorithm to encrypt classical binary bits and quantum entanglements.

A distributed VSG control method for a battery energy storage system with a cascaded H-bridge in a grid-connected mode

With the high penetration of renewable energy,new challenges,such as power fluctuation suppression and inertial support capability,have arisen in the power sector.Battery energy storage systems play an essential role in renewable energy integration.In this paper,a distributed virtual synchronous generator(VSG)control method for a battery energy storage system(BESS)with a cascaded H-bridge converter in a grid-connected mode is proposed.The VSG is developed without communication dependence,and state-of-charge(SOC)balancing control is achieved using the distributed average algorithm.Owing to the low varying speed of SOC,the bandwidth of the distributed communication networks is extremely slow,which decreases the cost.Therefore,the proposed method can simultaneously provide inertial support and accurate SOC balancing.The stability is also proved using root locus analysis.Finally,simulations under different conditions are carried out to verify the effectiveness of the proposed method.

Sliding Mode Control in Power Converters and Drives: A Review

Sliding mode control(SMC)has been studied since the 1950s and widely used in practical applications due to its insensitivity to matched disturbances.The aim of this paper is to present a review of SMC describing the key developments and examining the new trends and challenges for its application to power electronic systems.The fundamental theory of SMC is briefly reviewed and the key technical problems associated with the implementation of SMC to power converters and drives,such chattering phenomenon and variable switching frequency,are discussed and analyzed.The recent developments in SMC systems,future challenges and perspectives of SMC for power converters are discussed.

Fault Diagnosis for Aero-engine Applying a New Multi-class Support Vector Algorithm

Hierarchical Support Vector Machine （H-SVM） is faster in training and classification than other usual multi-class SVMs such as ＂1-V-R＂and ＂1-V-1＂. In this paper, a new multi-class fault diagnosis algorithm based on H-SVM is proposed and applied to aero-engine. Before SVM training, the training data are first clustered according to their class-center Euclid distances in some feature spaces. The samples which have close distances are divided into the same sub-classes for training, and this makes the H-SVM have reasonable hierarchical construction and good generalization performance. Instead of the common C-SVM, the v-SVM is selected as the binary classifier, in which the parameter v varies only from 0 to 1 and can be determined more easily. The simulation results show that the designed H-SVMs can fast diagnose the multi-class single faults and combination faults for the gas path components of an aero-engine. The fault classifiers have good diagnosis accuracy and can keep robust even when the measurement inputs are disturbed by noises.

A secure identification system using coherent states

A quantum identification system based on the transformation of polarization of a mesoscopic coherent state is proposed. Physically, an initial polarization state which carries the identity information is transformed into an arbitrary elliptical polarization state, To verify the identity of a communicator, a reverse procedure is performed by the receiver, For simply describing the transformation procedure, the analytical methods of Poincaré sphere and quaternion are adopted. Since quantum noise provides such a measurement uncertainty for the eavesdropping that the identity information cannot be retrieved from the elliptical polarization state, the proposed scheme is secure.