Adaptive Information Research Articles

Aligning Correlation Information for Domain Adaptation in Action Recognition.

Domain adaptation (DA) approaches address domain shift and enable networks to be applied to different scenarios. Although various image DA approaches have been proposed in recent years, there is limited research toward video DA. This is partly due to the complexity in adapting the different modalities of features in videos, which includes the correlation features extracted as long-range dependencies of pixels across spatiotemporal dimensions. The correlation features are highly associated with action classes and proven their effectiveness in accurate video feature extraction through the supervised action recognition task. Yet correlation features of the same action would differ across domains due to domain shift. Therefore, we propose a novel adversarial correlation adaptation network (ACAN) to align action videos by aligning pixel correlations. ACAN aims to minimize the distribution of correlation information, termed as pixel correlation discrepancy (PCD). Additionally, video DA research is also limited by the lack of cross-domain video datasets with larger domain shifts. We, therefore, introduce a novel HMDB-ARID dataset with a larger domain shift caused by a larger statistical difference between domains. This dataset is built in an effort to leverage current datasets for dark video classification. Empirical results demonstrate the state-of-the-art performance of our proposed ACAN for both existing and the new video DA datasets.

Adaptive information fusion network for multi‐modal personality recognition

AbstractPersonality recognition is of great significance in deepening the understanding of social relations. While personality recognition methods have made significant strides in recent years, the challenge of heterogeneity between modalities during feature fusion still needs to be solved. This paper introduces an adaptive multi‐modal information fusion network (AMIF‐Net) capable of concurrently processing video, audio, and text data. First, utilizing the AMIF‐Net encoder, we process the extracted audio and video features separately, effectively capturing long‐term data relationships. Then, adding adaptive elements in the fusion network can alleviate the problem of heterogeneity between modes. Lastly, we concatenate audio‐video and text features into a regression network to obtain Big Five personality trait scores. Furthermore, we introduce a novel loss function to address the problem of training inaccuracies, taking advantage of its unique property of exhibiting a peak at the critical mean. Our tests on the ChaLearn First Impressions V2 multi‐modal dataset show partial performance surpassing state‐of‐the‐art networks.

The Attachment-Caregiving Questionnaire as a Personality Inventory Sensitive to Psychological Vulnerabilities: A Pilot Study

Evolution enabled the human species to form attachment relationships, where a caregiver looks after a needy attacher. In early-life interactions with a parent-caregiver, the child-attacher acquires adaptive durable information—the attachment dimensions—which become part of their personality. As such, the dimensions affect vulnerability to psychological conditions, but the precise nature of this link remains controversial. With this pilot study, we addressed this issue. Considering a sample of 67 psychotherapy patients, we tested (H1) the expected connections between dimensions and specific vulnerability to psychological conditions and (H2) the capability of a self-report to detect such links. We relied on the Attachment-Caregiving Questionnaire (ACQ) to measure seven dimensions and test the hypotheses by (1) investigating the correlation between the patients’ dimensions and their symptoms and (2) building logistic regression models to test whether the dimensions can predict vulnerability to specific symptoms. Our analysis demonstrated that almost all expected dimensions could predict vulnerability to related symptoms. Given the limited sample size, one dimension could not be connected to any symptoms. This study provides preliminary support for the connections between attachment dimensions and vulnerability to clinical conditions and the ACQ’s capability in detecting such links. Further testing is required.

Measurement of body size parameters and body weight prediction in beef cattle based on image analysis

The body size parameter of cattle is an important index reflecting the growth and development and health condition of cattle. The traditional manual contact measurement is not only a large workload and difficult to measure, but also prone to problems such as affecting the normal life habits of cattle. In this paper, we address this problem by proposing a contactless body size measurement method for cattle based on machine vision. Firstly, the cattle is confined to a fixed space using a position-limiting device, and images of the body of the cattle are taken from three directions: top, left, and right, using multiple cameras. Secondly, the image is segmented using a fuzzy clustering algorithm based on neighborhood adaptive local spatial information improvement, and the image is processed to extract the contour images of the top view and side view. The key points of body measurements were extracted using interval division and curvature calculation for the side view images, and the key point information was extracted using skeleton extraction and pruning for the top view images, which realized the measurements of body height(BH), rump height(RH), body slanting length(BSL), and abdominal circumference(AC) parameters of the cattle. The correlation between body size and weight data obtained by contactless methods was investigated and the modeled using one-factor linear regression, one-factor nonlinear regression, multivariate stepwise regression, RBF network fitting, BP neural network fitting, support vector machine, and particle swarm optimization-based support vector machine methods, respectively. Information on body size parameters was collected from 137 cattles, and the results showed that the maximum errors between the measured and actual values of BH, RH, BSL and AC were 5.0%, 4.4%, 3.6%, and 5.5%, respectively. Correlation of BH, RH, BSL and AC with weight obtained by non-contact methods was > 0.75. The BH parameter can be selected in the single-factor growth monitoring. The multi-body scale can reflect the growth status of cattle more comprehensively, in which RH, BSL and AC are important detection parameter; the multi-factor nonlinear model can reflect the growth characteristics of cattle more comprehensively. The contactless measurement method proposed in the paper can effectively improve the work efficiency and reduce the stress reaction of cattle, which is a long-term and effective monitoring method, and is of great significance in promoting accurate and welfare cattle rearing.

In vivo EPID-based daily treatment error identification for volumetric-modulated arc therapy in head and neck cancers with a hierarchical convolutional neural network: a feasibility study.

We proposed a deep learning approach to classify various error types in daily VMAT treatment of head and neck cancer patients based on EPID dosimetry, which could provide additional information to support clinical decisions for adaptive planning. 146 arcs from 42 head and neck patients were analyzed. Anatomical changes and setup errors were simulated in 17,820 EPID images of 99 arcs obtained from 30 patients using in-house software for model training, validation, and testing. Subsequently, 141 clinical EPID images from 47 arcs belonging to the remaining 12 patients were utilized for clinical testing. The hierarchical convolutional neural network (HCNN) model was trained to classify error types and magnitudes using EPID dose difference maps. Gamma analysis with 3%/2mm (dose difference/distance to agreement) criteria was also performed. The F1 score, a combination of precision and recall, was utilized to evaluate the performance of the HCNN model and gamma analysis. The adaptive fractioned doses were calculated to verify the HCNN classification results. For error type identification, the overall F1 score of the HCNN model was 0.99 and 0.91 for primary type and subtype identification, respectively. For error magnitude identification, the overall F1 score in the simulation dataset was 0.96 and 0.70 for the HCNN model and gamma analysis, respectively; while the overall F1 score in the clinical dataset was 0.79 and 0.20 for the HCNN model and gamma analysis, respectively. The HCNN model-based EPID dosimetry can identify changes in patient transmission doses and distinguish the treatment error category, which could potentially provide information for head and neck cancer treatment adaption.

Strangers like me: birds respond equally to a familiar and an unfamiliar sentinel species' alarm calls, but respond less to non‐core and non‐sentinel's alarm calls

Alarm signals have evolved to communicate imminent threats to conspecifics but animals may also perceive other species' alarm displays to obtain adaptive information. In birds, mixed‐species foraging flocks are often structured around a focal sentinel species, which produces reliable alarm calls that inform eavesdropping non‐sentinel heterospecifics about predation risk. Ongoing work has revealed that several species can recognize the alarm calls of certain sentinel species even without prior encounters, including when these are from distant biogeographic regions. Similar work has yet to examine whether naive subjects' responses to unfamiliar sentinel alarm calls differ from responses to non‐sentinel alarm calls. Here we played the alarm calls of three subtropical Asian bird species that participate in mixed species flocks, to temperate North American birds. Birds responded most to the alarm call of an allopatric core sentinel and a local sympatric sentinel control species, less so to an allopatric non‐core sentinel, and least so to an allopatric non‐sentinel and a negative control stimulus. These patterns provide evidence that broad phylogenetic and geographic recognition is a pertinent aspect of sentinel alarm calls in general.

Eye Movement Desensitisation and Reprocessing (EMDR) therapy for prolonged grief: theory, research, and practice.

Prolonged Grief Disorder occurs within 7-10% of the bereaved population and is a more complicated and persistent form of grief which has been associated with suicidality, mental health disorders, sleep disturbance, poor health behaviors, and work and social impairment. EMDR is a fitting treatment option for those with Prolonged Grief, focusing on processing past memories, blocks, current triggers, future fears, and preparing the person for living life beyond the loss in line with the Adaptive Information Processing Model and grief frameworks. This paper discusses the theory, research regarding the application of EMDR with prolonged grief, and gives insight and guidance to clinicians working in this area including a case example.

Beyond fitness: The information imparted in population states by selection throughout lifecycles

We approach the questions, what part of evolutionary change results from selection, and what is the adaptive information flow into a population undergoing selection, as a problem of quantifying the divergence of typical trajectories realized under selection from the expected dynamics of their counterparts under a null stochastic-process model representing the absence of selection. This approach starts with a formulation of adaptation in terms of information and from that identifies selection from the genetic parameters that generate information flow; it is the reverse of a historical approach that defines selection in terms of fitness, and then identifies adaptive characters as those amplified in relative frequency by fitness. Adaptive information is a relative entropy on distributions of histories computed directly from the generators of stochastic evolutionary population processes, which in large population limits can be approximated by its leading exponential dependence as a large-deviation function. We study a particular class of generators that represent the genetic dependence of explicit transitions around reproductive cycles in terms of stoichiometry, familiar from chemical reaction networks. Following Smith (2023), which showed that partitioning evolutionary events among genetically distinct realizations of lifecycles yields a more consistent causal analysis through the Price equation than the construction from units of selection and fitness, here we show that it likewise yields more complete evolutionary information measures.

What do vegetable farmers expect from climate services to adapt to climate change by 2060? A case study from the Parisian region

Climate services are an important tool providing information for many sectors to adapt to climate change. For agriculture, the impacts of climate change vary between regions and between crops, and farmers' needs for climate information are also determined by local context. The purpose of this paper is to identify the climate information needs of vegetable farmers, and to discuss these needs within the specific context of the Parisian region. Based on participatory workshops in three areas of the Parisian region, and using regional downscaled data from the French climate services, this study addresses the following question: what do vegetable farmers of a peri-urban area expect from climate services to adapt to climate change by 2060? Participatory workshops with agricultural expert allowed us to build a preliminary set of climate variables based on crops' vulnerability to high temperatures, mild temperature in winter, late frost, low relative air humidity, low precipitation, and climate extremes such as drought, heat waves and floods. Based on this set of variables climate projection on monthly, seasonal, and annual scales were provided to farmers for the near (2021–2040) and distant (2041–2060) future, as well as for past period (1990–2020) and discussed during 3 participatory workshops. Based on farmer’s feedbacks, we made a synthesis of climate information required by farmers which was validated and further discussed in a last round of workshops involving farmers and agricultural advisers. Three main findings emerge from this participatory study. Our first finding shows the need for both climate and non-climate information for vegetable farming adaptation. Specific needs include information on wind speed peaks and directions, soil moisture, climate analogous spaces (or sites), and urban planning regulations (constraining the possibility to build greenhouses or tunnels to adapt to climate change). Our second finding is that farmers expect from climate services to visualise a comprehensive climatic situation, that is, a whole conjunction of several inter-related variables, rather than precise and detailed variations of a single one. Seasonal and annual time scales seem to be the most relevant for farmers’ adaptation strategies (except for frost requiring more precise information). Our third finding is that these needs remain context-specific and depend on water access, the market demand (here Parisian), and the peri-urban location.

Transfer learning under the Cox model with interval‐censored data

AbstractTransfer learning, focusing on information borrowing to address limited sample size issues, has gained increasing attention in recent years. Our method aims to utilize data from other population groups as a complement to enhance risk factor discernment and failure time prediction among underrepresented subgroups. However, a literature gap exists in effective knowledge transfer from the source to the target for risk assessment with interval‐censored data while accommodating population incomparability and privacy constraints. Our objective is to bridge this gap by developing a transfer learning approach under the Cox proportional hazards model. We introduce the tuning‐free Trans‐Cox‐MIC algorithm, enabling adaptable information sharing in regression coefficients and baseline hazards, while ensuring computational efficiency. Our approach accommodates covariate distribution shifts, coefficient variations, and baseline hazard discrepancies. Extensive simulations showcase the method's accuracy, robustness, and efficiency. Application to the prostate cancer screening data demonstrates enhanced risk estimation precision and predictive performance in the African American population.

A cyberattack resilient model for battery electric bus transit fleets using real-time adaptive system information

This paper aims to assess and tackle the cyber–physical security threats stemming from vulnerabilities of battery-based electric bus (BEB) fleets to cyberattacks. An optimization model is adopted for scheduling the battery swapping in BEB fleets and is utilized for cybersecurity assessments. New methods are proposed for detection of false data injection attacks (FDIAs) against the information of the BEB scheduling model. A supervised machine learning-based method is used for identification of potential cyberattacks against the system parameters that govern the operation of the BEB transit fleet. The proposed cybersecurity model is integrated with the BEB scheduling model to form a cyberattack-resilient scheduling framework for the BEB transit fleet. Two categories of data are considered for the simulation of attack scenarios and assessment of the proposed cybersecurity framework: Type 1 – Signals that are received from sources local to the battery swapping station (BSS), and Type 2 – Signals that are received from sources external to the BSS which can be intercepted and tampered by the attacker. The simulation results are presented to evaluate potential disruptions in the BEB transit operation due to FDIAs against the system’s operating parameters. It is demonstrated that a soft cyberattack mildly deviating the fleet operating parameters, e.g., the bus arrival time by up to 10 min or battery SoC by 5%, does not cause a considerable impact on the scheduling parameters or the financial metrics. A moderate or aggressive attack, however, affecting the fleet operating parameters considerably, can adversely impact the scheduling information and the fleet financial metrics.

OASL: Orientation-aware adaptive sampling learning for arbitrary oriented object detection

Arbitrary oriented object detection (AOOD) is a fundamental task in aeiral image interpretation, which is commonly implemented by optimizing three subtasks: classification, localization, and orientation. The consistency of classification, localization, and orientation is crucial for achieving high performance of AOOD detectors. However, independent prediction between subtasks and differences in quality metrics for task-specific samples reduces the accuracy of high-precision detection. In this paper, we propose a novel dense anchor-free detector Orientation-aware Adaptive Sampling Learning (OASL) that includes two core modules: Orientation-aware Structured Information Extraction Module (O-SIEM) and Weights adaptive Sample Information Richness Metric (W-SIRM). Specifically, O-SIEM applies the global and local receptive fields of objects to explicitly extract spatial contextual features of oriented and densely distributed objects, which helps to strike a balance between capturing task-interactive and task-specific features, ultimately leading to learning common patterns between subtasks. W-SIRM integrates information from three subtasks and achieves dynamic evaluation of sample quality and adaptive adjustment of sample weights based on the information richness of samples. Extensive experiments demonstrate that the proposed OASL method can effectively handle the consistency problem and enhance the validity of the sample quality metric.

Fusion information refresh rate improvement based on adaptive visual tracking in vehicle augmented reality sightseeing interactive system

AbstractThis paper proposes a dynamic information fusion interactive system with a transparent display applied in the vehicle. The dynamic information fusion interactive system integrates three leading technologies: relative position acquisition, fusion information mapping, and visual field tracking adaptive information generation. For visual field tracking adaptive information generation, the position of fusion information changes as the observer's field of view varies to help observers use this system more comfortably and intuitively. The frame rate of the dynamic virtual information display can be increased from 10 to 20 Hz without increasing the AI computing power and providing observers with a better observer experience. Integrating those technologies could achieve an AR‐based interactive system on a direct‐view transparent display. Such a system can provide passengers with location‐based interactive virtual and real integration information in the mobile field.

Representation modeling learning with multi-domain decoupling for unsupervised skeleton-based action recognition

Skeleton-based action recognition is one of the basic researches in computer vision. In recent years, the unsupervised contrastive learning paradigm has achieved great success in skeleton-based action recognition. However, previous work often treated input skeleton sequences as a whole when performing comparisons, lacking fine-grained representation contrast learning. Therefore, we propose a contrastive learning method for Representation Modeling with Multi-domain Decoupling (RMMD), which extracts the most significant representations from input skeleton sequences in the temporal domain, spatial domain and frequency domain, respectively. Specifically, in the temporal and spatial domains, we propose a multi-level spatiotemporal mining reconstruction module (STMR) that iteratively reconstructs the original input skeleton sequences to highlight spatiotemporal representations under different actions. At the same time, we introduce position encoding and a global adaptive attention matrix, balancing both global and local information, and effectively modeling the spatiotemporal dependencies between joints. In the frequency domain, we use the discrete cosine transform (DCT) to achieve temporal-frequency conversion, discard part of the interference information, and use the frequency self-attention (FSA) and multi-level aggregation perceptron (MLAP) to deeply explore the frequency domain representation. The fusion of the temporal domain, spatial domain and frequency domain representations makes our model more discriminative in representing different actions. Besides, we verify the effectiveness of the model on the NTU RGB+D and PKU-MMD datasets. Extensive experiments show that our method outperforms existing unsupervised methods and achieves significant performance improvements in downstream tasks such as action recognition and action retrieval.

Data privacy protection health status assessment for rotating machinery with dual-task feature fusion framework

Accurately assessing health status of rotating machinery is essential in reliable operation and predictive maintenance. Recently, health status assessment (HSA) of rotating machinery has acquired significant progress, particularly with the increasing popularity of deep learning. However, most methods regard HSA as a combination of isolated tasks, ignoring the hierarchical relationships between tasks in predictive maintenance. Also, they fail to learn multi-source features adequately. Besides, due to data silos and conflict of interests, the collaborative model training poses a strong demand for privacy protection. Thus, this paper proposes a data privacy protection HSA framework with dual-task feature fusion learning. First, we consider HSA of machinery as an integral dual-task process and synchronously obtain assessment results. The proposed framework constructs hierarchical health labels to ensure assessment accuracy, and utilizes adaptive information exchange channels to maintain balance between the dual tasks. Next, we design a feature fusion network based on channel independence and patch mechanisms to enhance the utilization of correlation information in multi-source signals. Finally, by employing decentralized swarm learning, achieve privacy-preserving joint training to address data silos. Experimental results validate the effectiveness and superiority of the proposed framework.

Slimming Neural Networks Using Adaptive Connectivity Scores.

In general, deep neural network (DNN) pruning methods fall into two categories: 1) weight-based deterministic constraints and 2) probabilistic frameworks. While each approach has its merits and limitations, there are a set of common practical issues such as trial-and-error to analyze sensitivity and hyper-parameters to prune DNNs, which plague them both. In this work, we propose a new single-shot, fully automated pruning algorithm called slimming neural networks using adaptive connectivity scores (SNACS). Our proposed approach combines a probabilistic pruning framework with constraints on the underlying weight matrices, via a novel connectivity measure, at multiple levels to capitalize on the strengths of both approaches while solving their deficiencies. In SNACS, we propose a fast hash-based estimator of adaptive conditional mutual information (ACMI), that uses a weight-based scaling criterion, to evaluate the connectivity between filters and prune unimportant ones. To automatically determine the limit up to which a layer can be pruned, we propose a set of operating constraints that jointly define the upper pruning percentage limits across all the layers in a deep network. Finally, we define a novel sensitivity criterion for filters that measures the strength of their contributions to the succeeding layer and highlights critical filters that need to be completely protected from pruning. Through our experimental validation, we show that SNACS is faster by over 17× the nearest comparable method and is the state-of-the-art single-shot pruning method across four standard Dataset-DNN pruning benchmarks: CIFAR10-VGG16, CIFAR10-ResNet56, CIFAR10-MobileNetv2, and ILSVRC2012-ResNet50.

Smart chiral liquid crystal elastomers: Design, properties and application

AbstractSmart chiral liquid crystal elastomers are a class of soft photonic crystals with periodic nanostructures. There are two kinds of chiral liquid crystal elastomers with structural colors: cholesteric liquid crystal elastomers with a one‐dimensional helical nanostructure and blue‐phase liquid crystal elastomers with a three‐dimensional photonic crystal nanostructure. The self‐assembled nanostructure of chiral liquid crystal elastomers can be dynamically controlled under external stimulation, and the reflected color can be adjusted throughout the visible light range. Along with the development of innovative material systems and cutting‐edge manufacturing technologies, researchers have proposed diverse strategies to design and synthesize chiral liquid crystal elastomers and have thoroughly investigated their properties and potential applications. Here, we provide a systematic review of the progress in the design and fabrication of smart chiral liquid crystal elastomers, focusing on the cholesteric liquid crystal elastomers via surface‐enforced alignment, bar coating, 3D printing, anisotropic deswelling methods as well as the three‐dimensional self‐assembly of blue‐phase liquid crystal elastomers without additional alignment. Smart chiral liquid crystal elastomers are able to respond quickly to external stimuli and have a wide range of applications in areas such as adaptive optics, color‐changing camouflage, soft robotics, and information encryption. This review concludes with a perspective on the opportunities and challenges for the future development of smart chiral liquid crystal elastomers.

COMMUNICATION STRATEGIES IN THE MANAGEMENT OF SOCIO-CULTURAL ACTIVITIES: ANALYSIS AND OPTIMIZATION OF THE IMPACT OF GLOBALIZATION ON REGIONAL DEVELOPMENT IN UKRAINE

This study investigates into the complex interplay among communication strategies, globalization, and socio-economic factors within the context of regional development, with a specific focus on Ukraine. Employing a mixed-methods approach, it seeks to investigate the profound impact of effective communication strategies on socio-cultural management and their contribution to regional growth in the era of globalization. The study combines quantitative data from regional development reports with stakeholders across various Ukrainian regions. A theoretical model, based on game theory and the Prisoner's Dilemma, is employed to examine strategic choices in communication, globalization integration, socioeconomic focus, infrastructure development, and cultural initiatives.Through an extensive analysis combining quantitative data derived from regional development reports with insights from stakeholders representing diverse Ukrainian regions, this research reveals that cooperative communication strategies, characterized by robust engagement, a balanced approach to globalization, equitable socio-economic development, strategic infrastructure investment, and active promotion of cultural initiatives, yield the most favourable outcomes for regional development.The key takeaway from this study is the paramount significance of inclusive and participatory approaches, effective communication strategies, and harmonious integration of globalization to foster sustainable regional development. Notably, tailored communication strategies exhibit a significant correlation with the success of socio-cultural initiatives, consequently exerting a positive influence on regional development. These encompass community engagement, cultural sensitivity, and adaptive information dissemination. In conclusion, comprehending and optimizing communication strategies emerge as critical imperatives for harnessing the benefits of globalization in the realm of regional development in Ukraine and analogous contexts.

Designing a course for pre-service science teachers using ChatGPT: what ChatGPT brings to the table

ABSTRACT ChatGPT holds significant potential for enhancing learning through integration into education as an advanced chatbot. With the goal of harnessing this potential, our research focused on exploring the utilization of ChatGPT in designing a course plan for pre-service science teachers. We adopted a qualitative research approach and employed ChatGPT as an assistant to create a course plan for classroom assessment in science education. Our conversation to create this plan served as our data source for document analysis. We conducted interpretive analysis for qualitative data. The findings emphasized the benefits of ChatGPT in developing an implementable course plan, delivering adaptable information, and time saving. However, there were limitations to consider. These challenges encompassed issues such as communicating out of ChatGPT and the possibility of miscommunication. Despite these limitations, the research findings clearly demonstrate that ChatGPT is highly effective in developing a course plan. As researchers who have personally experienced the process of creating a course plan using ChatGPT, we believe that its potential needs to be maximally utilized. We suggest its application across different subjects and disciplines to thoroughly examine its strengths and weaknesses in depth.

A New Multi-Target Three-Way Threat Assessment Method with Heterogeneous Information and Attribute Relevance

Target threat assessment provides support for combat decision making. The multi-target threat assessment method based on a three-way decision can obtain threat classification while receiving threat ranking, thus avoiding the limitation of traditional two-way decisions. However, the heterogeneous situation information, attribute relevance, and adaptive information processing needs in complex battlefield environment bring challenges to existing methods. Therefore, this paper proposes a new multi-target three-way threat assessment method with heterogeneous information and attribute relevance. Firstly, dynamic assessment information is represented by heterogeneous information, and attribute weights are calculated by heterogeneous Criteria Importance Through Intercriteria Correlation (CRITIC). Then, the conditional probability is calculated by the heterogeneous weighted Technique for Order Preference by Similarity to Ideal Solution (TOPSIS), and the adaptive risk avoidance coefficients are constructed by calculating the uncertainty of the assessment value, and then the relative loss function matrices are constructed. Finally, the comprehensive loss function matrices are obtained by the weighted Heronian mean (HM) operator, and the comprehensive thresholds are calculated to obtain the three-way rules. The case study shows that compared with the existing methods, the proposed method can effectively handle the heterogeneous information and attribute relevance, and obtain the risk avoidance coefficients without presetting or field subjective settings, which is more suitable for the complex mission environment.