Search

Artificial intelligence (AI) has great potential to transform the clinical workflow of radiotherapy. Since the introduction of deep neural networks (DNNs), many AI-based methods have been proposed to address challenges in different aspects of radiotherapy. Commercial vendors have started to release AI-based tools that can be readily integrated to the established clinical workflow. To show the recent progress in AI-aided radiotherapy, we have reviewed AI-based studies in five major aspects of radiotherapy, including image reconstruction, image registration, image segmentation, image synthesis, and automatic treatment planning. In each section, we summarized and categorized the recently published methods, followed by a discussion of the challenges, concerns, and future development. Given the rapid development of AI-aided radiotherapy, the efficiency and effectiveness of radiotherapy in the future could be substantially improved through intelligent automation of various aspects of radiotherapy.

Resting-state fMRI studies have suggested that autism spectrum disorder (ASD) is associated with aberrant dynamic changes. However, existing research either has difficulty showing the brain's dynamic characteristics or cannot obtain stable results. We examined the `two-group cross-location hidden Markov model' of each region of interest (ROI) to identify possible pathogenic features of ASD. Specifically, we selected resting-state fMRI data with complete scales and good quality from Autism Brain Imaging Data Exchange (ABIDEI). Eligible data included 145 ASD and 157 control (CON). Two groups of subjects were separated to train Hidden Markov models representing respective populations. Then, we used each model to estimate the likelihood values of all participants. Using the likelihood value as features, we tested the significant differences of 200 ROIs and finally identified ROIs with common significant differences in the two types of models. Additionally, we investigated the relationship between likelihood values of significantly different ROIs and clinical scales. some ROIs were negatively correlated with the Autism Diagnostic Observation Schedule and positively correlated with full IQ. Finally, we constructed a support vector machine to classify ASD and CON. Overall, our findings suggested that the abnormal areas in the frontopolar area, orbitofrontal area, inferior temporal gyrus, middle temporal gyrus and fusiform gyrus are prominent features of ASD and are closely related to clinical functional decline. The average accuracy rate reached 74.9% after ten cross-validations. This `two-group cross-localized Hidden Markov Model' provides a robust and powerful framework for understanding the dysfunctional brain architecture of ASD.

Recently, a novel technology for noninvasive deep brain stimulation (NDBS) with temporally interfering electric fields was developed. This noninvasive technology is able to perform one-point temporal interference (TI) stimulation and stimulates the hippocampus without affecting the overlying cortex in mice. In this study, we introduce the concept of multi-point temporal interference (MTI) stimulation, which can simultaneously stimulate multiple nodes in the brain network to modulate its function. For the sake of realizing MTI stimulation, we proposed the scheme with each electrode carrying different frequency currents, which has higher usability with respect to the scheme by adding more electrode pairs. Additionally, to optimize the MTI stimulation, we selected the proper current frequencies and amplitudes, which were verified by geometrical model, magnetic resonance imaging (MRI) human head model, and tissue phantom. Finally, we tested the independence between the two stimulation points in MTI stimulation. The MTI stimulation can be generated by our method with proper parameters in geometrical model, MRI human head model, and tissue phantom. The stimulation points in MTI stimulation are all steerable, and furthermore can be controlled independently. Our results suggest that MTI stimulation can be used to simultaneously stimulate multiple target nodes of the brain network in deep brain areas noninvasively, which paves the way for the modulation of the brain in research and clinical neurobiology.

Objective: Evidence greatly lacks regarding evaluation of the effect of circuit based gait and balance training in comparison to virtual reality based gait and balance training. Therefore aim of the current study was to compare the effect of both interventions in rehabilitation of stroke outpatients.Methods: Consecutive stroke patients falling on the set criterion were evaluated and recruited from outpatient Rehabilitation Department of Railway General Hospital, Pakistan. Patients were divided into two groups; circuit training group (CTG) (n=19) and exer-gaming/ virtual reality training group (VTG) (n=18) by sealed envelope method. Each group received a training session of 50 minutes for 5 days a week; till 6 weeks. Gait and balance were assessed using Berg Balance Scale (BBS) and Timed UP and Go Test (TUG). Informed consent was signed by patients before participation and the study was approved by the Ethical Committee of Riphah College of Rehabilitation Sciences, Pakistan.Results: Final analysis was conducted on 30 stroke patients, 15 in circuit training group (age: 51.53 ± 7.6, male: 8, female: 7, right hemiplegic: 9 and left hemiplegic: 6) and 15 in virtual reality training group (age: 52.40 ± 7.4, male: 11, female: 4, right hemiplegic: 11 and left hemiplegic: 4). Patients improved the score for both outcomes measures from baseline to 6 weeks of intervention (BBS: CTG 36.00 ± 9.9 to 48.60 ± 8.7, VTG 32.73 ± 4.6 to 42.60 ± 8.5; TUG: CTG 26.01 ± 8.5 to 16.57 ± 7.1, VTG 29.80 ± 13.4 to 21.36 ± 9.9). Within group analysis showed significant result in every 2 weeks for both groups except the last two weeks in virtual reality training group.Conclusion: The results of the current study suggest no supremacy of either of the two interventions i.e. virtual reality and circuit class training. Both techniques are equally effective and can improve stroke rehabilitation outcomes in term of gait and balance.

In order to solve the problem of insufficient effectiveness of traditional college students' innovation and entrepreneurship education, this paper proposes a new method of College Students' innovation and Entrepreneurship Education under the background of big data. In order to achieve more effective innovation and entrepreneurship education of College Students under the background of big data, K-means clustering method is needed to deeply mine the innovation and entrepreneurship data of college students. Mining more accurate entrepreneurial data of college students, based on the above mining entrepreneurial data of college students as the basis of index construction, the maximum eigenvalue of College Students' entrepreneurial risk evaluation index is calculated, and the consistency test of evaluation index is completed according to the calculation results. According to the test results, calculate the correlation degree of College Students' entrepreneurial risk evaluation index, screen out the evaluation index of College Students' entrepreneurial risk, and construct the evaluation function of College Students' entrepreneurial risk according to the evaluation index. The experimental results show that, compared with the traditional methods, the proposed method can achieve higher accuracy of data mining for college students' entrepreneurship, and the risk evaluation results are more accurate.

Due to the low power of electromagnetic radiation (EMR), EM convert channel has been widely considered as a short-range attack that can be easily mitigated by shielding. This paper overturns this common belief by demonstrating how covert EM signals leaked from typical laptops, desktops and servers are decoded from hundreds of meters away, or penetrate aggressive shield previously considered as sufficient to ensure emission security. We achieve this by designing EMLoRa – a super resilient EM covert channel that exploits memory as a LoRa-like radio. EMLoRa represents the first attempt of designing an EM covert channel using state-of-the-art spread spectrum technology. It tackles a set of unique challenges, such as handling complex spectral characteristics of EMR, tolerating signal distortions caused by CPU contention, and preventing adversarial detectors from demodulating covert signals. Experiment results show that EMLoRa boosts communication range by 20x and improves attenuation resilience by up to 53 dB when compared with prior EM covert channels at the same bit rate. By achieving this, EMLoRa allows an attacker to circumvent security perimeter, breach Faraday cage, and localize air-gapped devices in a wide area using just a small number of inexpensive sensors. To countermeasure EMLoRa, we further explore the feasibility of uncovering EMLoRa's signal using energy- and CNN-based detectors. Experiments show that both detectors suffer limited range, allowing EMLoRa to gain a significant range advantage. Our results call for further research on the countermeasure against spread spectrum-based EM covert channels.

Humour is valued by people for its many positive social functions, which is also of great merit for computing exploration. Especially in this era, many advanced computing science and technologies allow new perspectives to address this topic. Among them, creative computing, which aims to offer new and surprising computing solutions, can lend its theoretical and technical supports to humour generation and exploitation. Based on it, the proposed research first raises the concept of the humour degree to bridge the more qualitative topic of humour with the quantitative nature of computing, so as to build a new basis for the following computing work. Secondly, a creative system is designed to calculate the humour degree for utterances. Thirdly, the experiment is conducted to validate the effectiveness of the system. The results show that it is feasible and significant to calculate the humour degree for utterances through a creative computing approach.

A new absorbing structure based on a planar spiral antenna is designed to deal with multipath propagation in a complex urban environment. Firstly, a multipath propagation model is introduced, and then a specific size metal ring structure is designed for multipath signals, and the final wave-absorbing structure is obtained through improvement and optimization. In this paper, emphasis on the value of the phase and the root mean square error of the antenna received by multipath signals of different angles and frequencies under the absorbing structure. The simulation results verify its effectiveness.

A high gain and broadband dipole antenna is designed by optimizing reflector and using a Partially Reflective Meta Surface (PRMS) structure. By optimizing the distance between PRMS structure and the antenna and the size of PRMS structure, the performance of the antenna has achieved a high Gain (9.2dBi) and a wide impedance bandwidth (61.2%). The antenna we designed is beneficial to compose a high gain array antenna used in urban environment. The Simulated result confirmed this method is effective to improve the performance of the antenna.

This paper defined the concept of military theory, conducted the analysis of the current state of military theoretical research based on knowledge maps, data cleansing and analysis of military theoretical research literature. Through multidimensional scale analysis, Co-word analysis, social network graph analysis, centrality analysis and factor analysis, this paper carried out knowledge map research on the status of military theoretical research. On this basis, summarized the current situation of military theoretical research, which includes great development potential, relatively limited research, generalization of content, lack of quantitative analysis, and insufficient basic conditions. The research conclusions have certain reference value for further development of military theoretical research and practical application.

State of charge (SOC) is one of the key indices for battery management system (BMS). Accurate estimation of SOC can greatly improve battery safety performance and service life. Due to the complex electrochemical reaction inside the battery, SOC is highly nonlinear and cannot be directly measured. This paper proposes a SOC estimation method based on recurrent neural network (RNN). The input current and terminal voltage are selected as input parameters to predict SOC. The information transfer of RNN is mainly divided into two steps: from the input layer to the hidden layer and from the hidden layer to the output layer. To identify the internal parameters of RNN, RNN is firstly opened the feedback loop, and then closed the feedback loop after the training using the improved gauss-newton backpropagation algorithm. Through the cycle charge and discharge experiment of Lithium-ion battery, this paper trained 8 neural networks based on different training sets and predicted them with corresponding verification sets respectively. It was found that the experimental data were consistent with the predicted data, which verified the effectiveness of the method.

With the development of modern technology, virtual reality technology has gradually risen. At present, foreign clinical psychologists have applied virtual reality technology to the treatment of various psychological disorders such as anxiety disorders, PTSD, eating disorders, and schizophrenia, and have achieved certain results. In addition, virtual reality has certain applications in psychological evaluation, especially in the evaluation of executive functions. This article mainly introduces the application of virtual reality technology in clinical psychology practice and puts forward its limitations and future development prospects.

The bolster is one of the key components of a train. It is subjected to the complicated alternating load such as tensile, compression, torsion in various directions in practical application, and the fatigue crack initiation and propagation is the major failure mode of the bolster. In this paper, it is taken that the bolster of CRH2046 train after a period of service as the research object. Based on the fracture mechanics, the residual life prediction method of the bolster with the pre-existing cracks is researched. First, three-dimensional solid modeling and finite element strength analysis are carried out on the integral structure of the bolster with surrounding components to determine the stress distribution characteristics of the critical region of the bolster. Second, the sub-model technique is applied to establish the equivalent finite element model of the critical region. The function of stress intensity factor changing with crack morphology and relative crack depth is obtained. At last, the process of predicting the residual life the bolster under the two stage of the crack propagation is presented.

In the last few decades we have witnessed how the pheromone of social insect has become a rich inspiration source of swarm robotics. By utilising the virtual pheromone in physical swarm robot system to coordinate individuals and realise direct/indirect inter-robot communications like the social insect, stigmergic behaviour has emerged. However, many studies only take one single pheromone into account in solving swarm problems, which is not the case in real insects. In the real social insect world, diverse behaviours, complex collective performances and flexible transition from one state to another are guided by different kinds of pheromones and their interactions. Therefore, whether multiple pheromone based strategy can inspire swarm robotics research, and inversely how the performances of swarm robots controlled by multiple pheromones bring inspirations to explain the social insects’ behaviours will become an interesting question. Thus, to provide a reliable system to undertake the multiple pheromone study, in this paper, we specifically proposed and realised a multiple pheromone communication system called ColCOS $\Phi$. This system consists of a virtual pheromone sub-system wherein the multiple pheromone is represented by a colour image displayed on a screen, and the micro-robots platform designed for swarm robotics applications. Two case studies are undertaken to verify the effectiveness of this system: one is the multiple pheromone based on an ant’s forage and another is the interactions of aggregation and alarm pheromones. The experimental results demonstrate the feasibility of ColCOS $\Phi$ and its great potential in directing swarm robotics and social insects research.

In this paper, a CPW-fed ultrawideband antenna with switchable notched stop bands is proposed. The antenna radiating patch which is embedded within a rectangular slot consisting of two parts: a slotted feed and a slotted octagonal patch. It has two slots to provide two switchable notched stop bands. The impedance bandwidth ranges from 3 GHz to 10.6 GHz. The modified fence-shaped slot is created in a radiating patch to create band-notched properties in the 5G WiFi band (5 GHz - 6 GHz). In the meanwhile, a meandering slot connection is created in the feed to obtain band-notched properties in the WiMAX band (3.3 GHz - 3.8 GHz). These two slots all can be switched on or off.

Magnetic resonance (MR) simulators have recently gained popularity; it avoids the unnecessary radiation exposure associated with Computed Tomography (CT) when used for radiation therapy planning. We propose a method for pseudo CT estimation from MR images based on joint dictionary learning. Patient-specific anatomical features were extracted from the aligned training images and adopted as signatures for each voxel. The most relevant and informative features were identified to train the joint dictionary learning-based model. The well-trained dictionary was used to predict the pseudo CT of a new patient. This prediction technique was validated with a clinical study of 12 patients with MR and CT images of the brain. The mean absolute error (MAE), peak signal-to-noise ratio (PSNR), normalized cross correlation (NCC) indexes were used to quantify the prediction accuracy. We compared our proposed method with a state-of-the-art dictionary learning method. Overall our proposed method significantly improves the prediction accuracy over the state-of-the-art dictionary learning method. We have investigated a novel joint dictionary Iearning- based approach to predict CT images from routine MRIs and demonstrated its reliability. This CT prediction technique could be a useful tool for MRI-based radiation treatment planning or attenuation correction for quantifying PET images for PET/MR imaging.

This paper proposes a novel electric vehicle (EV) charging scheduling mechanism by controlling active and reactive charging power of EVs to provide joint voltage and frequency regulation (JVFR) in the distribution network. The objective of the scheduling problem is to minimize the net cost of the distribution system operator (DSO) for operating the distribution grid in the presence of both wind-based renewable generation and EV charging stations. We test the method on a 34-bus radial distribution network for different levels of VAR requirements of wind DG units to demonstrate the feasibility and performance of the proposed JVFR approach. The simulation results show that this JVFR greatly reduces the cost of DSO in comparison with Volt-VAR Optimization (VVO) technique, which is traditionally used to optimize voltage and minimize losses of a distribution network.

Distributed energy resources (DERs) such as renewable generation, energy storage and flexible loads have been acknowledged as the key drivers to transform the passive distribution networks into proactive players in the electricity market. In order to reduce the communication and computational complexity of integrating the huge number of DERs into the power system operation, the distribution system operator (DSO) is considered as the central controller to take charge of the dispatch of all the DERs within a distribution network. Through the exchange of boundary power flows and control signals, the independent system operator (ISO) coordinates all the DSOs to achieve certain social objective. In this paper, we study the interactions between the ISO and all the DSOs in both the day-ahead market and the real-time balancing market. Particularly, we identify that the locational marginal price (LMP) based real-time market is unfair and discourages the integration of DERs. To achieve a win-win solution for both the ISO and the DSOs, we propose a real-time coordination mechanism to determine the power dispatch and the corresponding charge/payments via a Nash bargaining problem. Numerical results show that our proposed mechanism guarantees that the ISO and all the DSOs can cooperatively maximize the social welfare and share the benefits fairly due to the cooperation.

The developments of robotics inform research across a broad range of disciplines. In this paper, we will study and compare two collision selective neuron models via a vision-based autonomous micro robot. In the locusts' visual brain, two Lobula Giant Movement Detectors (LGMDs), i.e. LGMD1 and LGMD2, have been identified as looming sensitive neurons responding to rapidly expanding objects, yet with different collision selectivity. Both neurons have been modeled and successfully applied in robotic vision system for perceiving potential collisions in an efficient and reliable manner. In this research, we conduct binocular neuronal models, for the first time combining the functionalities of LGMD1 and LGMD2 neurons, in the visual modality of a ground mobile robot. The results of systematic on-line experiments demonstrated three contributions of this research: (1) The arena tests involving multiple robots verified the effectiveness and robustness of a reactive motion control strategy via integrating a bilateral pair of LGMD1 and LGMD2 models for collision detection in dynamic scenarios. (2) We pinpointed the different collision selectivity between LGMD1 and LGMD2 neuron models, which fulfill corresponding biological research. (3) The utilized micro robot may also benefit researches on other embedded vision systems as well as swarm robotics.

Demand side management (DSM) exploits flexibility of the end-user side to help improve the performance of the power grid. However, how to model and evaluate the multi-dimensional flexibility (MDF) of the energy consumers (such as the flexibilities in terms of energy, power, time period and locations, etc.) is an important and challenging issue. To handle this, we propose a day-ahead market design for the MDF services. In this market, the MDF aggregators need to submit the characteristics of their virtual battery models and parametric reward functions, which represent the aggregate load flexibilities and the required remunerations, respectively. One key feature of this new market is that the system operator is allowed to accept only a portion of every bid instead of the whole of them. This can bring more flexibilities for the operator to minimize the total system cost. With various case studies on a 6-bus transmission network, we show that this market can help flatten the locational marginal prices (LMPs) across the peak load period. Moreover, we show that even if the MDF bids at different buses are the same, the clearing results can be quite different, which reflect the practical values of different load flexibilities from the perspective of the system operator.

When the eyes were given maximum disparity, a good relationship was found between visual fatigue and the static or dynamic parameters of vergence and accommodation, as well as physiological signals and subjective evaluation value. The common experimental paradigm of asthenopia is to give the dynamic and repetitive stimulus. Therefore, the current research was proposed to devise a static and sustained stimulus of prism-induced diplopia and projected an experiment to induce visual fatigue by diplopia. Subjects put on the based-out prism whose degree could be adjusted by two pulleys on top of it, they wear their correctional glasses and adjusted slowly the degree of prism until the eyes were diplopia. This state should last for ten minutes in total, of which two minutes as a trial and had an intermediate rested for 30 seconds. The electroencephalogram (EEG) data and critical fusion frequency of 13 subjects were recorded for closed eyes before and after fatigue. In brain occipital, parietal, temporal and frontal lobe, ratio algorithms (α+θ)/β were significantly increased, while gravity frequency (GF) and power spectral entropy (PSE) were significantly reduced, and decline in the critical fusion frequency (CFF) also exists a significant difference. CFF also had a significant difference in the Spearman correlation with PSE, so EEG has a strong correlation with visual fatigue and EEG power spectral components might be a useful method to evaluate the degree of ocular fatigue.

As a frequently used query operation for online applications, secure k-nearest neighbors (k-NN) computation on encrypted cloud data has received much attention. In this paper, we focus on the problem of supporting efficient k-NN computation over encrypted cloud data while data owner cannot share his secret keys with query users. We give a security analysis of the scheme proposed by Zhu et al. [16], and the analysis shows the scheme cannot provide query privacy at all. And we design a new efficient construction to support efficient k-NN computation over encrypted cloud data without key sharing. Additionally, security analysis is presented to demonstrate the new scheme can provide data privacy and query privacy in the Known Ciphertext Model.

The basic framework for reactive ancillary services under power market that views the reactive power as a compensatory consumption is investigated in this paper. In the given scenarios the Distributed Generators (DGs) are motivated and utilized as sources of reactive power and optimizing the overall distribution operation which takes into account the costs of reactive power delivery. The basic framework for reactive ancillary services under power market that views the reactive power as a compensatory consumption is investigated in this paper. In the given scenarios the Distributed Generators (DGs) are motivated and utilized as sources of reactive power and optimizing the overall distribution operation which takes into account the costs of reactive power delivery. The case indicated that the model proposed can reduce the loss of the lines and the cost of reactive power and improve the voltage profile in distribution network.

Dipole inversion is the final step of the QSM algorithm. In this step, the zero cone surface in the dipole kernel makes the field-to-susceptibility inverse problem ill-posed. Current solutions are mostly based on the Bayesian approach. Compared to the L1-norm, which has been used in previous techniques, the L2-norm converges faster. Therefore, we propose to employ a reweighted L2-norm using weights that are renewed after each iteration such that the multiplication of weights and the susceptibility gradient satisfy the Gaussian distribution. This is considered to be consistent with the a priori knowledge of the L2-norm. Results of phantom and in vivo experiments demonstrate that this novel Distribution Specified Dipole Inversion (DSDI) method enhances the quality of QSM reconstruction image and shortens calculation time remarkably.