High-level Decision Research Articles

Privacy-preserving knowledge transfer for intrusion detection with federated deep autoencoding gaussian mixture model

Knowledge transfer is critical in making use of data from multi-source domains, but most existing techniques are not privacy-preserving. Nowadays, data leakage, together with the advancement of big-data-driven Artificial Intelligence, has raised huge concerns over data security. The neglect of privacy makes such approaches impractical. For addressing intrusion detection tasks, the Deep Autoencoding Gaussian Mixture Model (DAGMM) concatenates and jointly optimizes a compression and an estimation network in an unsupervised manner. However, DAGMM still suffers from the lack of diversely distributed intrusion samples in real-life scenarios where organizations are neither willing nor legally allowed to engage in data sharing. Given the increasing public concern over data privacy and scandals, federated learning which only allows model parameter sharing is thus proposed to enhance model performance while preserving data privacy. Moreover, it also addresses the competitive concerns on the part of organizations when sharing data with their rivals. This study proposes a Federated Deep Autoencoding Gaussian Mixture Model (F-DAGMM) to build up privacy-preserving knowledge transfer, to further support inter-organizational cooperation and high-level decision making. A two-phase federated optimization strategy is proposed to address the performance degradation caused by the significant differences in the individual clients’ data distributions. Extensive experiments demonstrate the superiority of the proposed F-DAGMM.

Predictive Analytics for Early-Stage Construction Costs Estimation

Low accuracy in the estimation of construction costs at early stages of projects has driven the research on alternative costing methods that take advantage of computing advances, however, direct implications in their use for practice is not clear. The purpose of this study was to investigate how predictive analytics could enhance cost estimation of buildings at early stages by performing a systematic literature review on predictive analytics implementations for the early-stage cost estimation of building projects. The outputs of the study are: (1) an extensive database; (2) a list of cost drivers; and (3) a comparison between the various techniques. The findings suggest that predictive analytic techniques are appropriate for practice due to their higher level of accuracy. The discussion has three main implications: (a) predictive analytics for cost estimation have not followed the best practices and standard methodologies; (b) predictive analytics techniques are ready for industry adoption; and (c) the study can be a reference for high-level decision-makers to implement predictive analytics in cost estimation. Knowledge of predictive analytics could assist stakeholders in playing a key role in improving the accuracy of cost forecast in the construction market, thus, enabling pro-active management of the project owner’s budget.

The ASSISTANT project: AI for high level decisions in manufacturing

This paper outlines the main idea and approach of the H2020 ASSISTANT (LeArning and robuSt deciSIon SupporT systems for agile mANufacTuring environments) project. ASSISTANT is aimed at the investigation of AI-based tools for adaptive manufacturing environments, and focuses on the development of a set of digital twins for integration with, management of, and decision support for production planning and control. The ASSISTANT tools are based on the approach of extending generative design, an established methodology for product design, to a broader set of manufacturing decision making processes; and to make use of machine learning, optimisation, and simulation techniques to produce executable models capable of ethical reasoning and data-driven decision making for manufacturing systems. Combining human control and accountable AI, the ASSISTANT toolsets span a wide range of manufacturing processes and time scales, including process planning, production planning, scheduling, and real-time control. They are designed to be adaptable and applicable in a both general and specific manufacturing environments.

Technology Acceptance Model in Government Context: A Systematic Review on the Implementation of IT Governance in a Government Institution

Recent trends of studies on technology acceptance in local government had recently been popular; the studies focused on identifying the predictors of human behavior in potential acceptance or rejection of technology. This study investigated the use of information technology/information system (henceforth, IT/IS) acceptance in government as a means to improve the quality of public service and strive for transparent governance. A mixed-methods (quantitative and qualitative) study was conducted, and data were collected through questionnaires involving 125 respondents, interviews, and observations. Technology Acceptance Model (TAM) is used as a theoretical framework for behavioral information systems and Smart Partial least square (Smart PLS) analysis was employed in elaborating the complex correlation between the determinants. The result showed that the perceived ease-of-use (PEOU) contributed positively to the perceived usefulness (PU) and attitude towards using technology (ATUT). Moreover, the ATUT significantly contributed to Behavioral Intention of Use (BITU); further, the BITU also contributed to actual technology use (ATU). The PU, however, possessed a negative impact on the ATUT. These results further the information regarding the quality and performance of IT/IS services that can be used as a basis for higher-level decision-making.

Globally Optimal Hierarchical Reinforcement Learning for Linearly-Solvable Markov Decision Processes

We present a novel approach to hierarchical reinforcement learning for linearly-solvable Markov decision processes. Our approach assumes that the state space is partitioned, and defines subtasks for moving between the partitions. We represent value functions on several levels of abstraction, and use the compositionality of subtasks to estimate the optimal values of the states in each partition. The policy is implicitly defined on these optimal value estimates, rather than being decomposed among the subtasks. As a consequence, our approach can learn the globally optimal policy, and does not suffer from non-stationarities induced by high-level decisions. If several partitions have equivalent dynamics, the subtasks of those partitions can be shared. We show that our approach is significantly more sample efficient than that of a flat learner and similar hierarchical approaches when the set of boundary states is smaller than the entire state space.

Transaction costs for collaboration in the watershed management of the Cuyahoga River Area of Concern

This study examines the transaction costs of collaborative watershed management in the Cuyahoga River Area of Concern (AOC)—one of the 43 geographic areas designated by the U.S. and Canada Great Lakes Water Quality Agreement (GLWQA), where significant impairment of beneficial uses has occurred as a result of human activities. The Cuyahoga River is located in Northeast Ohio, the U. S. and flows through the City of Cleveland before draining into Lake Erie—one of the five Great Lakes of North America. The watershed is degraded due to municipal and agricultural discharges, streambank erosion, and contamination from urban and industrial sources. This research explores how a diverse group of stakeholders convened under the Cuyahoga River AOC Advisory Committee to share information, coordinate activities, agree on activities that restore beneficial uses, and support strategic management actions. In this study, 23 semi-structured interviews with members of the advisory committee were conducted between January 28, 2020 and April 20, 2020, with follow-up emails and phone calls as needed to corroborate information. A review of research articles and government documents supported the interviews, including United States Environmental Protection Agency (U.S. EPA) and Ohio Environment Production Agency (OEPA) reports on the GLWQA and Cuyahoga River Remedial Action Plans. A third source of data is from direct participant observation at quarterly meetings of the advisory committee during 2017–2020, binational AOC conferences in 2017 and 2019, and other professional events geared towards restoring the Cuyahoga River AOC in 2016–2020. Results help to explain the collaborative process within the advisory committee and measure the institutional performance of the advisory committee in terms of efficiency, equitability, accountability, and adaptability. Results of this study include a set of recommendations to help guide group structure and decision-making processes, including (1) employing best available technology to organize AOC events and disseminate information; (2) supporting new members with an orientation and/or mentor to clearly define formal and informal committee rules; (3) assuring equal access to detailed information on management action plans with a real time dashboard; (4) updating voting procedures and the prioritization of management actions; and (5) better incorporating underrepresented local communities and high-level decision makers from municipalities, government agencies, and nongovernmental organizations located within the Cuyahoga River AOC.

Vital best practices for antiracist patient engagement in AYA oncology research and advocacy: A Delphi study of BIPOC AYA experts.

12136 Background: In the thick of the ongoing global crises of the COVID-19 pandemic, uprisings against anti-Black racism and police brutality, and anti-Asian racism and violence, Black, indigenous, and people of color (BIPOC) adolescent and young adult (AYA) cancer patients may be particularly vulnerable and exploited. Whilst embroiled in sociopolitical complexity, BIPOC AYAs are increasingly called upon to contribute as patient advocates in AYA oncology research and advocacy. Researchers, clinicians, and advocates in AYA oncology must dismantle long-standing racism and create meaningful structural change. The purpose of this study is to derive vital best practices for implementing antiracist patient engagement in AYA oncology research and advocacy that are co-developed by BIPOC AYA cancer patients and oncology professionals. Methods: We utilized a modified Delphi technique with a panel of BIPOC AYA cancer patients (n = 32) to build consensus opinions on professional recommendations from a prior study ( Cheung et al., 2021 ), and to generate antiracist best practices in patient engagement. The Delphi study was comprised of three consecutive and iterative survey rounds over the course of 8 months in 2021; participants were BIPOC AYAs diagnosed with cancer between ages 15-36 years. Results: Results detail best practices for the implementation of antiracist patient engagement across all research activities within the Patient-Centered Outcomes Research Institute’s (PCORI) Framework for Patient Engagement. For example, BIPOC AYAs agreed with oncology professionals’ high priority recommendation for including BIPOC AYAs at the highest levels of decision making in research topic selection. As such, a best practice is for researchers to ensure that such representatives not only hold BIPOC AYA identity, but also hold direct experience with the particular oncology diagnosis, issue, or other outcome of interest. Additionally, BIPOC AYAs concurred with oncology professionals’ high priority for “transparency, honesty, and trust” as a core principle for best practices in patient engagement. They further explained that trustworthy relationships are especially important when collaborating with teens and young adults, who are developmentally just coming into their own. When describing successful experiences of inclusion, participants ranked “build collaborative relationships with BIPOC AYA communities and listen to patients not usually heard” and “recruit a diverse range of BIPOC patients and let them give actual input into the study” as the highest priority best practices. Conclusions: Findings from this study are instructional for AYA oncology researchers, clinicians, and advocates to prevent harmful tokenism and implement genuine antiracist inclusion to advance health equity. Future research should investigate best practices within unique clinical settings.

Reactive task and motion planning for robust whole-body dynamic locomotion in constrained environments

Contact-based decision and planning methods are becoming increasingly important to endow higher levels of autonomy for legged robots. Formal synthesis methods derived from symbolic systems have great potential for reasoning about high-level locomotion decisions and achieving complex maneuvering behaviors with correctness guarantees. This study takes a first step toward formally devising an architecture composed of task planning and control of whole-body dynamic locomotion behaviors in constrained and dynamically changing environments. At the high level, we formulate a two-player temporal logic game between the multi-limb locomotion planner and its dynamic environment to synthesize a winning strategy that delivers symbolic locomotion actions. These locomotion actions satisfy the desired high-level task specifications expressed in a fragment of temporal logic. Those actions are sent to a robust finite transition system that synthesizes a locomotion controller that fulfills state reachability constraints. This controller is further executed via a low-level motion planner that generates feasible locomotion trajectories. We construct a set of dynamic locomotion models for legged robots to serve as a template library for handling diverse environmental events. We devise a replanning strategy that takes into consideration sudden environmental changes or large state disturbances to increase the robustness of the resulting locomotion behaviors. We formally prove the correctness of the layered locomotion framework guaranteeing a robust implementation by the motion planning layer. Simulations of reactive locomotion behaviors in diverse environments indicate that our framework has the potential to serve as a theoretical foundation for intelligent locomotion behaviors.

Deep Reinforcement Learning With Modulated Hebbian Plus Q-Network Architecture.

In this article, we consider a subclass of partially observable Markov decision process (POMDP) problems which we termed confounding POMDPs. In these types of POMDPs, temporal difference (TD)-based reinforcement learning (RL) algorithms struggle, as TD error cannot be easily derived from observations. We solve these types of problems using a new bio-inspired neural architecture that combines a modulated Hebbian network (MOHN) with deep Q-network (DQN), which we call modulated Hebbian plus Q-network architecture (MOHQA). The key idea is to use a Hebbian network with rarely correlated bio-inspired neural traces to bridge temporal delays between actions and rewards when confounding observations and sparse rewards result in inaccurate TD errors. In MOHQA, DQN learns low-level features and control, while the MOHN contributes to high-level decisions by associating rewards with past states and actions. Thus, the proposed architecture combines two modules with significantly different learning algorithms, a Hebbian associative network and a classical DQN pipeline, exploiting the advantages of both. Simulations on a set of POMDPs and on the Malmo environment show that the proposed algorithm improved DQN's results and even outperformed control tests with advantage-actor critic (A2C), quantile regression DQN with long short-term memory (QRDQN + LSTM), Monte Carlo policy gradient (REINFORCE), and aggregated memory for reinforcement learning (AMRL) algorithms on most difficult POMDPs with confounding stimuli and sparse rewards.

INTRAOPERATIVE PATIENT CARE KNOWLEDGE LEVELS OF OPERATING ROOM NURSES: A CASE OF AFYONKARAHISAR

OBJECTIVE: Operating rooms are work environments where the risk of making mistakes is high in health care areas, as they are areas where stress is experienced at a high level and quick decision-making is required. The ability of operating room nurses to fulfill their roles and responsibilities professionally depends on having sufficient knowledge and skills specific to the field. It is thought the fact that operating room nurses have a grasp of intraoperative period patient care will reduce the risks such as falling, pressure wound, burns, foreign body forgetting, surgical site infection, and increase the quality of the surgery. For these purposes, we aimed to determine the intraoperative patient care knowledge levels of the operating room nurses in the city of Afyonkarahisar.MATERIAL AND METHODS: This descriptive study was carried out with 60 operating room nurses working in the public and private hospitals of the city of Afyonkarahisar , after their informed verbal consent was obtained, between August and September 2014. The data were collected through a survey form consisting of two parts. In the first part, there are 6 questions about the socio-demographic characteristics of the participants. In the second part, a 3-point Likert type questionnaire consisting of 36 items designed by the researchers after the review of relevant literature and taking expert opinion was used to determine the knowledge levels of operating room nurses regarding intraoperative patient care. The SPSS for Windows 18.00 program was used in the evaluation and analysis of the data. Descriptive statistics of continuous variables were shown with mean, standard deviation, median, minimum and maximum values, while descriptive statistics of categorical variables were shown with frequency and percentage.RESULTS: Of the nurses participating in the study, the mean age was 32.03 ± 7.32 (min: 19 max: 50), 86.7% were female, 45.0% had an undergraduate degree, and 73.3% were nursing graduates. It was determined that 61.7% of them had been in the profession for more than 6 years while 53.3% working in the operating room for more than 6 years. The intraoperative period patient care knowledge mean score of the nurses was found to be 26.13 ± 5.42.CONCLUSIONS: As a result of this study, nurses working in the operating rooms of the city of Afyonkarahisar were determined to have a sufficient level of intraoperative patient care knowledge, however, there have been practices identified that need to be corrected and improved.

Goal seeking Quadratic Unconstrained Binary Optimization

The Quadratic Unconstrained Binary Optimization (QUBO) modeling and solution framework is a requirement for quantum and digital annealers. However optimality for QUBO problems of any practical size is extremely difficult to achieve. In order to incorporate the problem-specific insights, a diverse set of solutions meeting an acceptable target metric or goal is the preference in high level decision making. In this paper, we present two alternatives for goal-seeking QUBO for minimizing the deviation from a given target as well as a range of values around a target. Experimental results illustrate the efficacy of the proposed approach over Constraint Programming for quickly finding a satisficing set of solutions.

Modeling Support for Mass Collaboration in Open Innovation Initiatives—The Facilitation Process Model 2.0

Many governments and organizations recognize the potential of open innovation (OI) models to create value with large numbers of people beyond the organization. It can be challenging, however, to design an effective collaborative process for a massive group. Collaboration engineering (CE) is an approach for the design and deployment of repeatable collaborative work practices that can be executed by practitioners themselves without the ongoing support of external collaboration engineers. To manage the complexity of the design process, they use a modeling technique called facilitation process models (FPM) to capture high-level design decisions that serve different purposes, such as documenting and communicating a design, etc. FPM, however, was developed to support designs for groups of fewer than 100 people. It does not yet represent design elements that become important when designing for groups of hundreds or thousands of participants, which can be found in many OI settings. We use a design science approach to identify the limitations of the original FPM and derive requirements for extending FPM. This article contributes to the CE and to the OI literature by offering an FPM 2.0 that assists CE designers to design new OI processes, with a special focus on outside-in OI.

An FEA-Assisted Decision-Making Framework for PEMFC Gasket Material Selection

Recent research studies on industrial cyber-physical systems (ICPSs) have witnessed vast patronage with emphasis on data utility for improved design, maintenance, and high-level decision making. The design of proton-exchange membrane fuel cells (PEMFC) is geared towards improving performance and extending life cycles. More often, material selection of PEMFC components contributes a major determining factor for efficiency and durability with the seal/gasket quality being one of the most critical components. Finite element analysis (FEA) offers a simulated alternative to real-life stress analysis of components and has been employed on different rubber-like gasket materials for hydrogen fuel cells for determining an optimal strain energy density function using different hyperelastic models following uniaxial tensile testing. The results show that the Mooney–Rivlin, Ogden, and Yeoh models were the most fitting model with the best stress–strain fit following a weighted error evaluation criteria which returned 18.54%, 19.31%, and 21.96% for 25% displacement, and 22.1%, 21.7%, and 21.17% for 40% displacements, respectively. Further empirical analysis using the multi-metric regression technique for compatibility testing (curve similarity) between the hyperelastic model outputs and the tensile data reveal that the Yeoh model is the most consistent as seen in the marginal error difference amidst increasing displacement while the Arruda–Boyce model is most inconsistent as shown in the high error margin as the displacement increases from 25% to 40%. Lastly, a comparative assessment between different rubber-like materials (RLM) was presented and is expected to contribute to improved decision-making and material selection.

Information uncertainty and organizational design

This paper investigates how information uncertainty, measured through variation in the informativeness of the public information environment, shapes the organizational design choices of firms. I posit that, when faced with higher uncertainty about demand and supply, managers are more likely to establish links to customer/supplier industries through high-level hiring decisions and vertical integration, thereby facilitating access to information about these industries. Consistent with this hypothesis, I find that firms modify their hiring and, to a lesser extent, vertical integration decisions in response to variation in the informativeness of the public information environment about demand and supply, measured with two distinct empirical approaches. Further, I observe that these organizational design choices correlate with the efficiency of inventory management and investment sensitivity to growth opportunities; this finding is consistent with organizational design facilitating access to information otherwise unavailable to managers through public sources.

Active object tracking using context estimation: handling occlusions and detecting missing targets

When performing visual servoing or object tracking tasks, active sensor planning is essential to keep targets in sight or to relocate them when missing. In particular, when dealing with a known target missing from the sensor’s field of view, we propose using prior knowledge related to contextual information to estimate its possible location. To this end, this study proposes a Dynamic Bayesian Network that uses contextual information to effectively search for targets. Monte Carlo particle filtering is employed to approximate the posterior probability of the target’s state, from which uncertainty is defined. We define the robot’s utility function via information theoretic formalism as seeking the optimal action which reduces uncertainty of a task, prompting robot agents to investigate the location where the target most likely might exist. Using a context state model, we design the agent’s high-level decision framework using a Partially-Observable Markov Decision Process. Based on the estimated belief state of the context via sequential observations, the robot’s navigation actions are determined to conduct exploratory and detection tasks. By using this multi-modal context model, our agent can effectively handle basic dynamic events, such as obstruction of targets or their absence from the field of view. We implement and demonstrate these capabilities on a mobile robot in real-time.

Physics-Based Simulation and Automation of a Load-Haul-Dump Operation for an Articulated Dump Truck

Many trucks are used for a class of activities involving a sequence of basic load-haul-dump operations. The repetitiveness of this operation has been an enabler for autonomous vehicle technology in efforts to increase safety and efficiency. In this paper, we present a framework for the automation of the load-haul-dump operation in a mine setting using an articulated dump truck. A simulation environment for the testing of autonomous driving algorithms is developed and a custom mining environment is generated to adapt to our simulation settings. We also present an operational decomposition of the sequence of tasks and develop a finite state machine for high-level decision making based on this decomposition. A path tracking module that considers both bodies of the articulated truck is also developed. The resulting architecture was implemented to achieve autonomy for a load-haul-dump operation in the simulated environment within a fixed path. Experiments show that the proposed FSM-path tracking system can automate the load-haul-dump operation; and that the simulation environment can support the testing and development of autonomous driving algorithms for configurations such as an articulated truck.

Using system dynamics modelling to assess the economic efficiency of innovations in the public sector - a systematic review.

BackgroundDecision-makers for public policy are increasingly utilising systems approaches such as system dynamics (SD) modelling, which test alternative interventions or policies for their potential impact while accounting for complexity. These approaches, however, have not consistently included an economic efficiency analysis dimension. This systematic review aims to examine how, and in what ways, system dynamics modelling approaches incorporate economic efficiency analyses to inform decision-making on innovations (improvements in products, services, or processes) in the public sector, with a particular interest in health.Methods and findingsRelevant studies (n = 29) were identified through a systematic search and screening of four electronic databases and backward citation search, and analysed for key characteristics and themes related to the analytical methods applied. Economic efficiency analysis approaches within SD broadly fell into two categories: as embedded sub-models or as cost calculations based on the outputs of the SD model. Embdedded sub-models within a dynamic SD framework can reveal a clear allocation of costs and benefits to periods of time, whereas cost calculations based on the SD model outputs can be useful for high-level resource allocation decisions.ConclusionsThis systematic review reveals that SD modelling is not currently used to its full potential to evaluate the technical or allocative efficiency of public sector innovations, particularly in health. The limited reporting on the experience or methodological challenges of applying allocated efficiency analyses with SD, particularly with dynamic embedded models, hampers common learning lessons to draw from and build on. Further application and comprehensive reporting of this approach would be welcome to develop the methodology further.

Youth should decide: the principle of subsidiarity in paediatric transgender healthcare

Drawing on the principle of subsidiarity, this article develops a framework for allocating medical decision-making authority in the absence of capacity to consent and argues that decisional authority in paediatric...

Environment Classification for Robotic Leg Prostheses and Exoskeletons Using Deep Convolutional Neural Networks.

Robotic leg prostheses and exoskeletons can provide powered locomotor assistance to older adults and/or persons with physical disabilities. However, the current locomotion mode recognition systems being developed for automated high-level control and decision-making rely on mechanical, inertial, and/or neuromuscular sensors, which inherently have limited prediction horizons (i.e., analogous to walking blindfolded). Inspired by the human vision-locomotor control system, we developed an environment classification system powered by computer vision and deep learning to predict the oncoming walking environments prior to physical interaction, therein allowing for more accurate and robust high-level control decisions. In this study, we first reviewed the development of our “ExoNet” database—the largest and most diverse open-source dataset of wearable camera images of indoor and outdoor real-world walking environments, which were annotated using a hierarchical labeling architecture. We then trained and tested over a dozen state-of-the-art deep convolutional neural networks (CNNs) on the ExoNet database for image classification and automatic feature engineering, including: EfficientNetB0, InceptionV3, MobileNet, MobileNetV2, VGG16, VGG19, Xception, ResNet50, ResNet101, ResNet152, DenseNet121, DenseNet169, and DenseNet201. Finally, we quantitatively compared the benchmarked CNN architectures and their environment classification predictions using an operational metric called “NetScore,” which balances the image classification accuracy with the computational and memory storage requirements (i.e., important for onboard real-time inference with mobile computing devices). Our comparative analyses showed that the EfficientNetB0 network achieves the highest test accuracy; VGG16 the fastest inference time; and MobileNetV2 the best NetScore, which can inform the optimal architecture design or selection depending on the desired performance. Overall, this study provides a large-scale benchmark and reference for next-generation environment classification systems for robotic leg prostheses and exoskeletons.

Overtaking decision and trajectory planning in highway via hierarchical architecture of conditional state machine and chance constrained model predictive control

An overtaking trajectory planning algorithm is an essential part of autonomous vehicles, but maximizing trip efficiency (minimum travel time) while guaranteeing safety is non-trivial. In particular, to achieve optimal trajectory results in all situations using one algorithm is challenging because overtaking is a complex maneuver in which several behaviors are combined. In this paper, an overtaking algorithm that employs a finite state machine as a high-level decision maker and chance constrained model predictive control as a trajectory planner is proposed to optimize trip efficiency and ride comfort while guaranteeing safety. By combining two methods in a hierarchical structure, the proposed algorithm takes advantage of each method to realize optimality and real-time performance. Using the conditional state machine (CSM), algorithm classifies maneuver states that can ensure safety, and sets the optimal multi-vehicle constraints in each state. The chance constrained model predictive control (MPC) plans an optimal trajectory that considers the prediction uncertainty, safety, trip efficiency and ride comfort. To rigorously evaluate both trip efficiency and safety, the performance of the proposed overtaking algorithm is evaluated in a statistical manner for various level of service (LOS) scenarios. Simulation results show that the optimal trajectory was generated in a multi-vehicle situation while ensuring higher safety than the rule-based algorithm.