Efficient Deep Learning Framework for Fire Detection in Complex Surveillance Environment

To prevent economic,social,and ecological damage,fire detection and management at an early stage are significant yet challenging.Although computationally complex networks have been developed,attention has been largely focused on improving accuracy,rather than focusing on real-time fire detection.Hence,in this study,the authors present an efficient fire detection framework termed E-FireNet for real-time detection in a complex surveillance environment.The proposed model architecture is inspired by the VGG16 network,with significant modifications including the entire removal of Block-5 and tweaking of the convolutional layers of Block-4.This results in higher performance with a reduced number of parameters and inference time.Moreover,smaller convolutional kernels are utilized,which are particularly designed to obtain the optimal details from input images,with numerous channels to assist in feature discrimination.In E-FireNet,three steps are involved:preprocessing of collected data,detection of fires using the proposed technique,and,if there is a fire,alarms are generated and transmitted to law enforcement,healthcare,and management departments.Moreover,E-FireNet achieves 0.98 accuracy,1 precision,0.99 recall,and 0.99 F1-score.A comprehensive investigation of various Convolutional Neural Network(CNN)models is conducted using the newly created Fire Surveillance SV-Fire dataset.The empirical results and comparison of numerous parameters establish that the proposed model shows convincing performance in terms of accuracy,model size,and execution time.

Robust Distributed Model Predictive Control for Formation Tracking of Nonholonomic Vehicles

Dear Editor,This letter proposes a robust distributed model predictive control(MPC) strategy for formation tracking of a group of wheeled vehicles subject to constraints and disturbances. Formation control has attracted significant interest because of its applications in searching and exploration [1], [2].

Sequestration of helium and xenon via iron-halide compounds in early Earth

The terrestrial abundance anomalies of helium and xenon suggest the presence of deep-Earth reservoirs of these elements,which has led to great interest in searching for materials that can host these usually unreactive elements.Here,using an advanced crystal structure search approach in conjunction with first-principles calculations,we show that several Xe/He-bearing iron halides are thermodynamically stable in a broad region of P–T phase space below 60 GPa.Our results present a compelling case for sequestration of He and Xe in the early Earth and may suggest their much wider distribution in the present Earth than previously believed.These findings offer insights into key material-based and physical mechanisms for elucidating major geological phenomena.

Evolutionary Neural Architecture Search and Its Applications in Healthcare

Most of the neural network architectures are based on human experience,which requires a long and tedious trial-and-error process.Neural architecture search(NAS)attempts to detect effective architectures without human intervention.Evolutionary algorithms(EAs)for NAS can find better solutions than human-designed architectures by exploring a large search space for possible architectures.Using multiobjective EAs for NAS,optimal neural architectures that meet various performance criteria can be explored and discovered efficiently.Furthermore,hardware-accelerated NAS methods can improve the efficiency of the NAS.While existing reviews have mainly focused on different strategies to complete NAS,a few studies have explored the use of EAs for NAS.In this paper,we summarize and explore the use of EAs for NAS,as well as large-scale multiobjective optimization strategies and hardware-accelerated NAS methods.NAS performs well in healthcare applications,such as medical image analysis,classification of disease diagnosis,and health monitoring.EAs for NAS can automate the search process and optimize multiple objectives simultaneously in a given healthcare task.Deep neural network has been successfully used in healthcare,but it lacks interpretability.Medical data is highly sensitive,and privacy leaks are frequently reported in the healthcare industry.To solve these problems,in healthcare,we propose an interpretable neuroevolution framework based on federated learning to address search efficiency and privacy protection.Moreover,we also point out future research directions for evolutionary NAS.Overall,for researchers who want to use EAs to optimize NNs in healthcare,we analyze the advantages and disadvantages of doing so to provide detailed guidance,and propose an interpretable privacy-preserving framework for healthcare applications.

Cooperative UAV search strategy based on DMPC-AACO algorithm in restricted communication scenarios

Improvement of integrated battlefield situational awareness in complex environments involving dynamic factors such as restricted communications and electromagnetic interference(EMI)has become a contentious research problem.In certain mission environments,due to the impact of many interference sources on real-time communication or mission requirements such as the need to implement communication regulations,the mission stages are represented as a dynamic combination of several communication-available and communication-unavailable stages.Furthermore,the data interaction between unmanned aerial vehicles(UAVs)can only be performed in specific communication-available stages.Traditional cooperative search algorithms cannot handle such situations well.To solve this problem,this study constructed a distributed model predictive control(DMPC)architecture for a collaborative control of UAVs and used the Voronoi diagram generation method to re-plan the search areas of all UAVs in real time to avoid repetition of search areas and UAV collisions while improving the search efficiency and safety factor.An attention mechanism ant-colony optimization(AACO)algorithm is proposed for UAV search-control decision planning.The search strategy is adaptively updated by introducing an attention mechanism for regular instruction information,a priori information,and emergent information of the mission to satisfy different search expectations to the maximum extent.Simulation results show that the proposed algorithm achieves better search performance than traditional algorithms in restricted communication constraint scenarios.

Searching scheme in P2P system based on semantic overlay network

In consideration of the limitation of super-peer overlay network, the semantic information was introduced into the super-peers＇ organization. A novel P2P （peer-to-peer） searching model, SSP2P, was put forward. The peers in the model were organized in a natural area autonomy system （AAS） based on the smallworld theory. A super-peer was selected in each AAS based on power law; and all the super-peers formed different super-peer semantic networks. Thus, a hierarchical super-peer overlay network was formed. The results show that the model reduces the communication cost and enhances the search efficiency while ensuring the system expansibility. It proves that the introduction of semantic information in the construction of a super-peer overlay is favorable to P2P system capability.

一种基于CatBoost优化的光伏阵列故障诊断模型

大部分光伏电站地处偏僻、地形复杂的区域,受到外界环境的影响,易发生各种故障.而传统的光伏阵列故障诊断方法存在精度不高以及光伏数据利用率低等问题.针对以上问题,本文先是通过引入Levy飞行策略和步长因子动态调整策略改进麻雀搜索算法(Sparrow Search Algorithm,SSA),降低SSA算法陷入局部最优的风险,提升SSA算法的寻优能力.然后采用改进的Levy步长调整麻雀搜索算法(Levy Adjustment Sparrow Search Algorithm,LASSA)对CatBoost模型关键超参数进行寻优,提出了一种基于CatBoost并以LASSA为优化策略的光伏阵列故障诊断模型LASSA-CatBoost,以实现光伏阵列的短路、开路、老化和阴影遮挡故障的精确诊断.实验结果表明,LASSA-CatBoost模型的故障诊断准确率为99.7%,相较于优化前的CatBoost模型,准确率提高了3.6%.与现有的光伏阵列故障诊断模型相比,LASSA-CatBoost模型的准确性和稳定性更高.

Semantic overlay network for searching taxonomy-based data sources

Distributed data sources which employ taxonomy hierarchy to describe the contents of their objects are considered, and a super-peer-based semantic overlay network （SSON） is proposed for sharing and searching their data objects. In SSON, peers are dynamically clustered into many semantic clusters based on the semantics of their data objects and organized in the semantic clusters into a semantic overlay network. Each semantic cluster consists of a super-peer and more peers, and is only responsible for answering queries in its semantic subspace. A query is first routed to the appropriate semantic clusters by an efficient searching algorithm, and then it is forwarded to the specific peers that hold the relevant data objects. Experimental results indicate that SSON has good scalability and achieves a competitive trade-off between search efficiency and costs.

AMachine Learning Approach to User Profiling for Data Annotation of Online Behavior

The user’s intent to seek online information has been an active area of research in user profiling.User profiling considers user characteristics,behaviors,activities,and preferences to sketch user intentions,interests,and motivations.Determining user characteristics can help capture implicit and explicit preferences and intentions for effective user-centric and customized content presentation.The user’s complete online experience in seeking information is a blend of activities such as searching,verifying,and sharing it on social platforms.However,a combination of multiple behaviors in profiling users has yet to be considered.This research takes a novel approach and explores user intent types based on multidimensional online behavior in information acquisition.This research explores information search,verification,and dissemination behavior and identifies diverse types of users based on their online engagement using machine learning.The research proposes a generic user profile template that explains the user characteristics based on the internet experience and uses it as ground truth for data annotation.User feedback is based on online behavior and practices collected by using a survey method.The participants include both males and females from different occupation sectors and different ages.The data collected is subject to feature engineering,and the significant features are presented to unsupervised machine learning methods to identify user intent classes or profiles and their characteristics.Different techniques are evaluated,and the K-Mean clustering method successfully generates five user groups observing different user characteristics with an average silhouette of 0.36 and a distortion score of 1136.Feature average is computed to identify user intent type characteristics.The user intent classes are then further generalized to create a user intent template with an Inter-Rater Reliability of 75%.This research successfully extracts different user types based on their preferences in online content,platforms,criteria,and frequency.The study also validates the proposed template on user feedback data through Inter-Rater Agreement process using an external human rater.

Target acquisition performance in the presence of JPEG image compression

This paper presents an investigation on the effect of JPEG compression on the similarity between the target image and the background,where the similarity is further used to determine the degree of clutter in the image.Four new clutter metrics based on image quality assessment are introduced,among which the Haar wavelet-based perceptual similarity index,known as HaarPSI,provides the best target acquisition prediction results.It is shown that the similarity between the target and the background at the boundary between visually lossless and visually lossy compression does not change significantly compared to the case when an uncompressed image is used.In future work,through subjective tests,it is necessary to check whether this presence of compression at the threshold of just noticeable differences will affect the human target acquisition performance.Similarity values are compared with the results of subjective tests of the well-known target Search_2 database,where the degree of agreement between objective and subjective scores,measured through linear correlation,reached a value of 90%.

Optimal search path planning of UUV in battlefeld ambush scene

Aiming at the practical application of Unmanned Underwater Vehicle(UUV)in underwater combat,this paper proposes a battlefield ambush scene with UUV considering ocean current.Firstly,by establishing these mathematical models of ocean current environment,target movement,and sonar detection,the probability calculation methods of single UUV searching target and multiple UUV cooperatively searching target are given respectively.Then,based on the Hybrid Quantum-behaved Particle Swarm Optimization(HQPSO)algorithm,the path with the highest target search probability is found.Finally,through simulation calculations,the influence of different UUV parameters and target parameters on the target search probability is analyzed,and the minimum number of UUVs that need to be deployed to complete the ambush task is demonstrated,and the optimal search path scheme is obtained.The method proposed in this paper provides a theoretical basis for the practical application of UUV in the future combat.

Enhanced Differentiable Architecture Search Based on Asymptotic Regularization

In differentiable search architecture search methods,a more efficient search space design can significantly improve the performance of the searched architecture,thus requiring people to carefully define the search space with different complexity according to various operations.Meanwhile rationalizing the search strategies to explore the well-defined search space will further improve the speed and efficiency of architecture search.With this in mind,we propose a faster and more efficient differentiable architecture search method,AllegroNAS.Firstly,we introduce a more efficient search space enriched by the introduction of two redefined convolution modules.Secondly,we utilize a more efficient architectural parameter regularization method,mitigating the overfitting problem during the search process and reducing the error brought about by gradient approximation.Meanwhile,we introduce a natural exponential cosine annealing method to make the learning rate of the neural network training process more suitable for the search procedure.Moreover,group convolution and data augmentation are employed to reduce the computational cost.Finally,through extensive experiments on several public datasets,we demonstrate that our method can more swiftly search for better-performing neural network architectures in a more efficient search space,thus validating the effectiveness of our approach.

A Lightweight, Searchable, and Controllable EMR Sharing Scheme

Electronic medical records (EMR) facilitate the sharing of medical data, but existing sharing schemes suffer fromprivacy leakage and inefficiency. This article proposes a lightweight, searchable, and controllable EMR sharingscheme, which employs a large attribute domain and a linear secret sharing structure (LSSS), the computationaloverhead of encryption and decryption reaches a lightweight constant level, and supports keyword search andpolicy hiding, which improves the high efficiency of medical data sharing. The dynamic accumulator technologyis utilized to enable data owners to flexibly authorize or revoke the access rights of data visitors to the datato achieve controllability of the data. Meanwhile, the data is re-encrypted by Intel Software Guard Extensions(SGX) technology to realize resistance to offline dictionary guessing attacks. In addition, blockchain technology isutilized to achieve credible accountability for abnormal behaviors in the sharing process. The experiments reflectthe obvious advantages of the scheme in terms of encryption and decryption computation overhead and storageoverhead, and theoretically prove the security and controllability in the sharing process, providing a feasible solutionfor the safe and efficient sharing of EMR.

Risk assessment of rockburst using SMOTE oversampling and integration algorithms under GBDT framework

Rockburst is a common geological disaster in underground engineering,which seriously threatens the safety of personnel,equipment and property.Utilizing machine learning models to evaluate risk of rockburst is gradually becoming a trend.In this study,the integrated algorithms under Gradient Boosting Decision Tree(GBDT)framework were used to evaluate and classify rockburst intensity.First,a total of 301 rock burst data samples were obtained from a case database,and the data were preprocessed using synthetic minority over-sampling technique(SMOTE).Then,the rockburst evaluation models including GBDT,eXtreme Gradient Boosting(XGBoost),Light Gradient Boosting Machine(LightGBM),and Categorical Features Gradient Boosting(CatBoost)were established,and the optimal hyperparameters of the models were obtained through random search grid and five-fold cross-validation.Afterwards,use the optimal hyperparameter configuration to fit the evaluation models,and analyze these models using test set.In order to evaluate the performance,metrics including accuracy,precision,recall,and F1-score were selected to analyze and compare with other machine learning models.Finally,the trained models were used to conduct rock burst risk assessment on rock samples from a mine in Shanxi Province,China,and providing theoretical guidance for the mine's safe production work.The models under the GBDT framework perform well in the evaluation of rockburst levels,and the proposed methods can provide a reliable reference for rockburst risk level analysis and safety management.

Spatial search weighting information contained in cell velocity distribution

Cell migration plays a significant role in physiological and pathological processes.Understanding the characteristics of cell movement is crucial for comprehending biological processes such as cell functionality,cell migration,and cell–cell interactions.One of the fundamental characteristics of cell movement is the specific distribution of cell speed,containing valuable information that still requires comprehensive understanding.This article investigates the distribution of mean velocities along cell trajectories,with a focus on optimizing the efficiency of cell food search in the context of the entire colony.We confirm that the specific velocity distribution in the experiments corresponds to an optimal search efficiency when spatial weighting is considered.The simulation results indicate that the distribution of average velocity does not align with the optimal search efficiency when employing average spatial weighting.However,when considering the distribution of central spatial weighting,the specific velocity distribution in the experiment is shown to correspond to the optimal search efficiency.Our simulations reveal that for any given distribution of average velocity,a specific central spatial weighting can be identified among the possible central spatial weighting that aligns with the optimal search strategy.Additionally,our work presents a method for determining the spatial weights embedded in the velocity distribution of cell movement.Our results have provided new avenues for further investigation of significant topics,such as relationship between cell behavior and environmental conditions throughout their evolutionary history,and how cells achieve collective cooperation through cell-cell communication.

Bridge Bidding via Deep Reinforcement Learning and Belief Monte Carlo Search

Contract Bridge,a four-player imperfect information game,comprises two phases:bidding and playing.While computer programs excel at playing,bidding presents a challenging aspect due to the need for information exchange with partners and interference with communication of opponents.In this work,we introduce a Bridge bidding agent that combines supervised learning,deep reinforcement learning via self-play,and a test-time search approach.Our experiments demonstrate that our agent outperforms WBridge5,a highly regarded computer Bridge software that has won multiple world championships,by a performance of 0.98 IMPs(international match points)per deal over 10000 deals,with a much cost-effective approach.The performance significantly surpasses previous state-of-the-art(0.85 IMPs per deal).Note 0.1 IMPs per deal is a significant improvement in Bridge bidding.

Q-Learning-Assisted Meta-Heuristics for Scheduling Distributed Hybrid Flow Shop Problems

The flow shop scheduling problem is important for the manufacturing industry.Effective flow shop scheduling can bring great benefits to the industry.However,there are few types of research on Distributed Hybrid Flow Shop Problems(DHFSP)by learning assisted meta-heuristics.This work addresses a DHFSP with minimizing the maximum completion time(Makespan).First,a mathematical model is developed for the concerned DHFSP.Second,four Q-learning-assisted meta-heuristics,e.g.,genetic algorithm(GA),artificial bee colony algorithm(ABC),particle swarm optimization(PSO),and differential evolution(DE),are proposed.According to the nature of DHFSP,six local search operations are designed for finding high-quality solutions in local space.Instead of randomselection,Q-learning assists meta-heuristics in choosing the appropriate local search operations during iterations.Finally,based on 60 cases,comprehensive numerical experiments are conducted to assess the effectiveness of the proposed algorithms.The experimental results and discussions prove that using Q-learning to select appropriate local search operations is more effective than the random strategy.To verify the competitiveness of the Q-learning assistedmeta-heuristics,they are compared with the improved iterated greedy algorithm(IIG),which is also for solving DHFSP.The Friedman test is executed on the results by five algorithms.It is concluded that the performance of four Q-learning-assisted meta-heuristics are better than IIG,and the Q-learning-assisted PSO shows the best competitiveness.

Even Search in a Promising Region for Constrained Multi-Objective Optimization

In recent years, a large number of approaches to constrained multi-objective optimization problems(CMOPs) have been proposed, focusing on developing tweaked strategies and techniques for handling constraints. However, an overly finetuned strategy or technique might overfit some problem types,resulting in a lack of versatility. In this article, we propose a generic search strategy that performs an even search in a promising region. The promising region, determined by obtained feasible non-dominated solutions, possesses two general properties.First, the constrained Pareto front(CPF) is included in the promising region. Second, as the number of feasible solutions increases or the convergence performance(i.e., approximation to the CPF) of these solutions improves, the promising region shrinks. Then we develop a new strategy named even search,which utilizes the non-dominated solutions to accelerate convergence and escape from local optima, and the feasible solutions under a constraint relaxation condition to exploit and detect feasible regions. Finally, a diversity measure is adopted to make sure that the individuals in the population evenly cover the valuable areas in the promising region. Experimental results on 45 instances from four benchmark test suites and 14 real-world CMOPs have demonstrated that searching evenly in the promising region can achieve competitive performance and excellent versatility compared to 11 most state-of-the-art methods tailored for CMOPs.

A Reverse Path Planning Approach for Enhanced Performance of Multi-Degree-of-Freedom Industrial Manipulators

In the domain of autonomous industrial manipulators,precise positioning and appropriate posture selection in path planning are pivotal for tasks involving obstacle avoidance,such as handling,heat sealing,and stacking.While Multi-Degree-of-Freedom(MDOF)manipulators offer kinematic redundancy,aiding in the derivation of optimal inverse kinematic solutions to meet position and posture requisites,their path planning entails intricate multiobjective optimization,encompassing path,posture,and joint motion optimization.Achieving satisfactory results in practical scenarios remains challenging.In response,this study introduces a novel Reverse Path Planning(RPP)methodology tailored for industrial manipulators.The approach commences by conceptualizing the manipulator’s end-effector as an agent within a reinforcement learning(RL)framework,wherein the state space,action set,and reward function are precisely defined to expedite the search for an initial collision-free path.To enhance convergence speed,the Q-learning algorithm in RL is augmented with Dyna-Q.Additionally,we formulate the cylindrical bounding box of the manipulator based on its Denavit-Hartenberg(DH)parameters and propose a swift collision detection technique.Furthermore,the motion performance of the end-effector is refined through a bidirectional search,and joint weighting coefficients are introduced to mitigate motion in high-power joints.The efficacy of the proposed RPP methodology is rigorously examined through extensive simulations conducted on a six-degree-of-freedom(6-DOF)manipulator encountering two distinct obstacle configurations and target positions.Experimental results substantiate that the RPP method adeptly orchestrates the computation of the shortest collision-free path while adhering to specific posture constraints at the target point.Moreover,itminimizes both posture angle deviations and joint motion,showcasing its prowess in enhancing the operational performance of MDOF industrial manipulators.

Research on intelligent search-and-secure technology in accelerator hazardous areas based on machine vision

Prompt radiation emitted during accelerator operation poses a significant health risk,necessitating a thorough search and securing of hazardous areas prior to initiation.Currently,manual sweep methods are employed.However,the limitations of manual sweeps have become increasingly evident with the implementation of large-scale accelerators.By leveraging advancements in machine vision technology,the automatic identification of stranded personnel in controlled areas through camera imagery presents a viable solution for efficient search and security.Given the criticality of personal safety for stranded individuals,search and security processes must be sufficiently reliable.To ensure comprehensive coverage,180°camera groups were strategically positioned on both sides of the accelerator tunnel to eliminate blind spots within the monitoring range.The YOLOV8 network model was modified to enable the detection of small targets,such as hands and feet,as well as larger targets formed by individuals near the cameras.Furthermore,the system incorporates a pedestrian recognition model that detects human body parts,and an information fusion strategy is used to integrate the detected head,hands,and feet with the identified pedestrians as a cohesive unit.This strategy enhanced the capability of the model to identify pedestrians obstructed by equipment,resulting in a notable improvement in the recall rate.Specifically,recall rates of 0.915 and 0.82were obtained for Datasets 1 and 2,respectively.Although there was a slight decrease in accuracy,it aligned with the intended purpose of the search-and-secure software design.Experimental tests conducted within an accelerator tunnel demonstrated the effectiveness of this approach in achieving reliable recognition outcomes.