Explainable, Domain-Adaptive, and Federated Artificial Intelligence in Medicine

Artificial intelligence(AI)continues to transform data analysis in many domains.Progress in each domain is driven by a growing body of annotated data,increased computational resources,and technological innovations.In medicine,the sensitivity of the data,the complexity of the tasks,the potentially high stakes,and a requirement of accountability give rise to a particular set of challenges.In this review,we focus on three key methodological approaches that address some of the particular challenges in AI-driven medical decision making.1)Explainable AI aims to produce a human-interpretable justification for each output.Such models increase confidence if the results appear plausible and match the clinicians expectations.However,the absence of a plausible explanation does not imply an inaccurate model.Especially in highly non-linear,complex models that are tuned to maximize accuracy,such interpretable representations only reflect a small portion of the justification.2)Domain adaptation and transfer learning enable AI models to be trained and applied across multiple domains.For example,a classification task based on images acquired on different acquisition hardware.3)Federated learning enables learning large-scale models without exposing sensitive personal health information.Unlike centralized AI learning,where the centralized learning machine has access to the entire training data,the federated learning process iteratively updates models across multiple sites by exchanging only parameter updates,not personal health data.This narrative review covers the basic concepts,highlights relevant corner-stone and stateof-the-art research in the field,and discusses perspectives.

3D Grid of Carbon Tubes with Mn3O4-NPs/CNTs Filled in their Inner Cavity as Ultrahigh-Rate and Stable Lithium Anode

Transition metal oxides are regarded as promising candidates of anode for next-generation lithium-ion batteries(LIBs)due to their ultrahigh theoretical capacity and low cost,but are restricted by their low conductivity and large volume expansion during Li^(+)intercalation.Herein,we designed and constructed a structurally integrated 3D carbon tube(3D-CT)grid film with Mn_(3)O_(4)nanoparticles(Mn_(3)O_(4)-NPs)and carbon nanotubes(CNTs)filled in the inner cavity of CTs(denoted as Mn_(3)O_(4)-NPs/CNTs@3D-CT)as high-performance free-standing anode for LIBs.The Mn_(3)O_(4)-NPs/CNTs@3D-CT grid with Mn_(3)O_(4)-NPs filled in the inner cavity of 3D-CT not only afford sufficient space to overcome the damage caused by the volume expansion of Mn_(3)O_(4)-NPs during charge and discharge processes,but also achieves highly efficient channels for the fast transport of both electrons and Li+during cycling,thus offering outstanding electrochemical performance(865 mAh g^(-1)at 1 A g^(-1)after 300 cycles)and excellent rate capability(418 mAh g^(-1)at 4 A g^(-1))based on the total mass of electrode.The unique 3D-CT framework structure would open up a new route to the highly stable,high-capacity,and excellent cycle and high-rate performance free-standing electrodes for highperformance Li-ion storage.

A Privacy-Preserving System Design for Digital Presence Protection

A person’s privacy has become a growing concern,given the nature of an expansive reliance on real-time video activities with video capture,stream,and storage.This paper presents an innovative system design based on a privacy-preserving model.The proposed system design is implemented by employing an enhanced capability that overcomes today’s single parameterbased access control protection mechanism for digital privacy preservation.The enhanced capability combines multiple access control parameters:facial expression,resource,environment,location,and time.The proposed system design demonstrated that a person’s facial expressions combined with a set of access control rules can achieve a person’s privacy-preserving preferences.The findings resulted in different facial expressions successfully triggering a person’s face to be blurred and a person’s privacy when using a real-time video conferencing service captured from a webcam or virtual webcam.A comparison analysis of capabilities between existing designs and the proposed system design shows enhancement of the capabilities of the proposed system.A series of experiments exercising the enhanced,real-time multi-parameterbased system was shown as a viable path forward for preserving a person’s privacy while using a webcam or virtual webcam to capture,stream,and store videos.

Air/CO2 cooling garment: Description and benefits of use for subjects exposed to a hot and humid climate during physical activities

The severity of the hot and humid conditions to which miners are exposed increases as the depth of the work site increases.This can cause heat stress that can greatly affect the health and safety of workers.To resolve this,a cooling garment has been developed that uses an atmospheric discharge of liquid CO2 to create a cool microclimate with an average temperature of 12.5(±0.4)℃ beneath the garment.To evaluate the garment's cooling efficiency,19 male subjects participated in an experimental procedure.The two modes,cooling on and off,were compared.Significant physiological differences were found between the two modes after minute 27(p<0.05)until the end of the recovery phase for the heart rate(maximum difference of 10 beats per minute)and the internal body temperature(maximum difference of 0.33℃).It was found that the modes also affected the subjects'perceptions.The ON-mode was associated with better well-being and thermal comfort,and reduced humidity sensation.Perceptions of exertion were lower in the ON-mode condition from minute 2.The findings provide strong evidence of the ability of this cooling garment to reduce heat stress in hot and humid conditions similar to those encountered in deep mines.

Collision Vehicle Detection System Based on GPS/INS Integration

Continuous vehicle tracking as well as detecting accidents, are significant services that are needed by many industries including insurance and vehicle rental companies. The main goal of this paper is to provide methods to detect the position of car accident. The models consider GPS/INS-based navigation algorithm, calibration of navigational sensors, a de-nosing method as long as vehicle accident, expressed by a set of raw measurements which are obtained from various environmental sensors. In addition, the location-based accident detection model is tested in different scenarios. The results illustrate that under harsh environments with no GPS signal, location of accident can be detected. Also results confirm that calibration of sensors has an important role in position correction algorithm. Finally, the results present that the proposed accident detection algorithm can recognize accidents and related its positions.

Low-Cost GPSIINS Integrated Land-Vehicular Navigation System for Harsh Environments Using Hybrid Mamdani AFISIKF Model

Nowadays, GPS （global positioning system） receivers are aided by INS （inertial navigation systems） to achieve more precision and stability in land-vehicular navigation. KF （Kalman filter） is a conventional method which is used for the navigation system to estimate the navigational parameters, when INS measurements are fused with GPS data. However, new generation of INS, which relies on MEMS （micro-electro-mechanical systems） based low-cost IMUs （inertial measurement units） for the land navigation systems, decreases the accuracy and the robustness of navigation system due to their inherent errors. This paper provides a new method for fusing the low-cost IMU and GPS measurements. The proposed method is based on KF aided by AF1S （adaptive fuzzy inference systems） as a promising solution to overcome the mentioned problems. The results of this study show the efficiency of the proposed method to reduce the navigation system errors in comparison with KF alone.

Constant-Stress Accelerated Degradation Life Test of an Organic Light-Emitting Diode Display under Violet Light

The lifetime of commercial OLED display devices increases, so does the need for an accelerated lifetime testing method. The present work proposes a simple and accurate blackbox testing approach for commercial PMOLED display lifetime assessment using violet light-induced accelerated aging. Maximum likelihood estimations using lognormal distributions are performed based on datasets acquired from samples exposed to six different degrees of violet irradiance and accelerated life model is shown to accurately fit experimental data using an inverse power law. Based on these results, weighted average of the logarithmic standard deviation, the average life and median life can then be obtained for specific conditions of operation of the devices. As this method relies exclusively on violet light-induced degradation at room-temperature, this minimally-invasive testing procedure requires no significant modification to the display hardware architecture.

Single Platform Integration Environment for Turbine Rotor Design and Analysis

The present article covers briefly state of the art software interoperability technical solutions and the development of the first module of a new single platform D ＆ A （design ＆ analysis） tool for simulation and prediction of stress and burst behavior of turbine rotating disc a preliminary design stage. This platform singularity requires integration of multiple CAD （computer assisted design） ＆ FEA （finite element analysis） tools processing in batch mode and driven from a SPIE （single platform integration environment）. This first module is also to demonstrate, for an axial turbine disc hub axi-symmetric component, feasibility and usefulness of such a platform at preliminary design stage. Expected benefits of the D ＆ A single platform are to improve output accuracy, reduce cycle time, improve process quality and improve resource productivity.

Parameterization Modeling of a Gas Turbine Coverplate

In order to reduce product development cycle time, aerospace companies tend to develop various correlations integrating geometric and performance parameters. This paper covers the development of a parameterization modeling, to be used in the preliminary design phase, for the turbine cover plate of an aero-engine. The parameterization modeling of the turbine cover plate is achieved by using commercial CAD （computer aided design） software processing in batch mode. Two main approaches are presented the outer face and the skeleton models. These models can then be integrated into an iterative process for designing optimal shapes. Both models are capable of reproducing existing cover plate with reasonable accuracy in relatively shorter time periods. However, the skeleton approach provides probably the best results in terms of flexibility and accuracy, but increases programming complexity and requires greater run times.

Engineering Fe‑N_(4)Electronic Structure with Adjacent Co‑N_(2)C_(2)and Co Nanoclusters on Carbon Nanotubes for Efficient Oxygen Electrocatalysis

Regulating the local configuration of atomically dispersed transition-metal atom catalysts is the key to oxygen electrocatalysis performance enhancement.Unlike the previously reported singleatom or dual-atom configurations,we designed a new type of binary-atom catalyst,through engineering Fe-N_(4)electronic structure with adjacent Co-N_(2)C_(2)and nitrogen-coordinated Co nanoclusters,as oxygen electrocatalysts.The resultant optimized electronic structure of the Fe-N_(4)active center favors the binding capability of intermediates and enhances oxygen reduction reaction(ORR)activity in both alkaline and acid conditions.In addition,anchoring M-N-C atomic sites on highly graphitized carbon supports guarantees of efficient charge-and mass-transports,and escorts the high bifunctional catalytic activity of the entire catalyst.Further,through the combination of electrochemical studies and in-situ X-ray absorption spectroscopy analyses,the ORR degradation mechanisms under highly oxidative conditions during oxygen evolution reaction processes were revealed.This work developed a new binary-atom catalyst and systematically investigates the effect of highly oxidative environments on ORR electrochemical behavior.It demonstrates the strategy for facilitating oxygen electrocatalytic activity and stability of the atomically dispersed M-N-C catalysts.

Leveraging UAV-assisted communications to improve secrecy for URLLC in 6G systems

Unmanned Aerial Vehicles(UAVs)will be essential to support mission-critical applications of Ultra Reliable Low Latency Communication(URLLC)in futuristic Sixth-Generation(6G)networks.However,several security vulnerabilities and attacks have plagued previous generations of communication systems;thus,physical layer security,especially against eavesdroppers,is vital,especially for upcoming 6G networks.In this regard,UAVs have appeared as a winning candidate to mitigate security risks.In this paper,we leverage UAVs to propose two methods.The first method utilizes a UAV as Decode-and-Forward(DF)relay,whereas the second method utilizes a UAV as a jammer to mitigate eavesdropping attacks for URLLC between transmitter and receiver devices.Moreover,we present a low-complexity algorithm that outlines the two aforementioned methods of mitigating interception,i.e.increasing secrecy rate,and we compare them with the benchmark null method in which there is a direct communication link between transmitter and receiver without the UAV DF relay.Additionally,simulation results show the effectiveness of such methods by improving the secrecy rate and its dependency on UAV height,blocklength,decoding error probability and transmitter-receiver separation distance.Lastly,we recommend the best method to enhance the secrecy rate in the presence of an eavesdropper based on our simulations.

Seamless morphing trailing edge flaps for UAS-S45 using high-fidelity aerodynamic optimization

The seamless trailing edge morphing flap is investigated using a high-fidelity steady-state aerodynamic shape optimization to determine its optimum configuration for different flight conditions,including climb,cruise,and gliding descent.A comparative study is also conducted between a wing equipped with morphing flap and a wing with conventional hinged flap.The optimization is performed by specifying a certain objective function and the flight performance goal for each flight condition.Increasing the climb rate,extending the flight range and endurance in cruise,and decreasing the descend rate,are the flight performance goals covered in this study.Various optimum configurations were found for the morphing wing by determining the optimum morphing flap deflection for each flight condition,based on its objective function,each of which performed better than that of the baseline wing.It was shown that by using optimum configuration for the morphing wing in climb condition,the required power could be reduced by up to 3.8%and climb rate increases by 6.13%.The comparative study also revealed that the morphing wing enhances aerodynamic efficiency by up to 17.8%and extends the laminar flow.Finally,the optimum configuration for the gliding descent brought about a 43%reduction in the descent rate.

Analytical and Experimental Studies of Liquid and Gas Leaks through Micro and Nano-Porous Gaskets

The reliability of industrial installation requires minimum leakage of pressurized sealed joints during operation. At the design stage, the leakage behavior of the gasket must be one of the most important parameter in the gasket selection. The objective of the work presented in this paper is to develop an analytical leak rate prediction methodology used in gasketed joints. A pseudo analytical-experimental innovative approach was used to estimate the characteristics of the porous structure for the purpose of predicting accurate leak rate through gaskets with different fluids under conditions similar to those of operation. The analytical model assumes the flow to be continuum but employs a slip boundary condition on the leak path wall to determine the porosity parameters of the gasket. The analytical model results are validated and confronted against experimental data which were conducted under various conditions of fluid media, pressure, gasket stress and temperature. Two experimental test rigs fully automate that accurately reproduces the real leakage behavior of the gasketed joint have been developed to analyze the mechanical and thermal effects on the gasket flow regime. The gas leaks were measured with multi-gas mass spectrometers while liquid leaks were measure using a sophisticated detection system based on the pressure rise method.

Experimental and Finite Element Analysis of a T-Joint Welding

This paper presents the Finite Element （FE） modeling of a two-seam welding process for a T-joint with a V chamfer preparation： The aim of the model is to predict the deformations, distortions and residual stresses resulting from the welding of the plates and experiments have been carried out in order to compare to the FE model. The ＂birth and death＂ method is used in ANSYS to simulate the filler metal deposition and the heat generation and weld pool simulation are conducted accordingly with the double ellipsoid configuration as proposed by Goldak et al. The model takes into consideration the temperature dependent non-linear material properties and uses a new formulation to compute the temperature dependent combined coefficient of heat loss. Improvements in the calculation are achieved by combining two types of meshing. The FE simulation is divided into two consecutive parts： the thermal simulation followed by the structural simulation. The results of the numerical model are compared to experiments.

Ultrafine and fine particle emission in turning titanium metal matrix composite(Ti-MMC)

Titanium metal matrix composite(Ti-MMC)has excellent features and capabilities which can be considered a potential candidate to replace commercial titanium and superalloys within an extensive range of products and industrial sectors.Regardless of the superior features in Ti-MMC,however,referring to several factors including high unit cost and existence of rigid and abrasive ceramic particles in the generated matrices of the work part,the Ti-MMC is grouped as extremely difficult to cut with a poor level of machinability.Furthermore,adequate process parameters for machining Ti-MMCs under several lubrication methods are rarely studied.Therefore,adequate knowledge of this regard is strongly demanded.Among machinability attributes,ultrafine particles(UFPs)and fine particles(FPs)have been selected as the main machinability attributes and the factors leading to minimized emission have been studied.According to experimental observations,despite the type of coating used,the use of higher levels of flow rate led to less UFPs,while no significant effects were observed on UFPs.Under similar cutting conditions,higher levels of FPs were recorded under the use of uncoated inserts.Moreover,cutting speed had no significant influence on UFPs;nevertheless,it significantly affects the FPs despite the type of insert used.

Value Generation through Integrated Teams： A Socio-Cognitive Approach

Value generation is defined as meeting client requirements while minimizing waste. Researchers concur on the issues related to sequential design in handling client requirements, and suggest the use of an integrated design approach as an alternative. Little has been said, however, about the impact of adopting integrated design＇s work organization to traditional design practice, processes and tools, nor about the importance of breaking down socio-cognitive barriers related to mental model fragmentation between design professionals, clients and users. This may result in cognitive inertia, a major source of waste. The objective of this research is to develop and test the introduction of boundary objects, such as new technologies, to the context of integrated teams and organizations to break the cognitive inertia that hinders value generation. The research is conclusive about the effectiveness of using boundary objects to transform practices in construction. This research also contributes to a better understanding of the new purposes of construction projects by framing its context and process dimensions within a theoretical framework, as well as to the evolution of practices in construction - and of practices that could be applicable to other fields.

Driving Behavior Assessment Using Fuzzy Inference System and Low-Cost Inertial Sensors

Continuous vehicle tracking as well as monitoring driving behaviour, is significant services that are needed by manyindustries including insurance and vehicle rental companies. The main goal of this paper is to provide methods to model the quality ofthe driving behaviour based on FIS （fuzzy inference systems）. The models consider vehicle dynamics as long as the human behaviourparameters, expressed by a set of raw measurements which are obtained from various environmental sensors. In addition,assessment-driving behaviour model is simulated and tested by two different FISs： Mamdani and Sugeno-TSK. The simulation resultsillustrate the critical distinctions between the two FISs using the proposed driving behaviour models. These differences are based onvarious processing times, robust behaviour of the FISs, outputs MFs （membership functions）, fuzzification-techniques, flexibility inthe systems design and computational efficiency.

A taxonomy of built asset information coupling

The digital transformation of the built asset industry is moving toward closer integration of physical and digital assets and resources.Within the framework of Cyber-Physical Systems(CPSs)and Digital Twins(DTs),an increasing number of studies focus on the technical aspects of CPS and DT.However,a unified framework describing the dimensions and characteristics essential for integrating lifecycle information remains elusive.To leverage these concepts effectively,it is necessary to develop new frameworks to classify and put into relationship various components that comprise the lifecycle information integration of physical and digital assets and resources.This paper addresses these gaps by proposing a taxonomy of Built Asset Lifecycle Information Couples,which outlines the dimensions and characteristics crucial for the lifecycle information integration of built assets and resources.The proposed taxonomy contributes to the efforts aimed at organizing the knowledge domain of lifecycle information management in the built environment.

Batteries for electric vehicles:Technical advancements,environmental challenges,and market perspectives

The rapid evolution of electric vehicles(EVs)highlights the critical role of bat-tery technology in promoting sustainable transportation.This review offers a comprehensive introduction to the diverse landscape of batteries for EVs.In particular,it examines the impressive array of available battery technologies,focusing on the predominance of lithium-based batteries,such as lithium-ion and lithium-metal variants.Additionally,it explores battery technologies beyond lithium(“post-lithium”),including aluminum,sodium,and magnesium batter-ies.The potential of solid-state batteries is also discussed,along with the current status of various battery types in EV applications.The review further addresses end-of-life treatment strategies for EV batteries,including reuse,remanufactur-ing,and recycling,which are essential for mitigating the environmental impact of batteries and ensuring sustainable lifecycle management.Finally,market per-spectives and potential future research directions for battery technologies in EVs are also discussed.

Optimization and design of an aircraft's morphing wing-tip demonstrator for drag reduction at low speed, Part Ⅰ–Aerodynamic optimization using genetic, bee colony and gradient descent algorithms

In this paper, an ‘in-house＇ genetic algorithm is described and applied to an optimization problem for improving the aerodynamic performances of an aircraft wing tip through upper surface morphing. The algorithm＇s performances were studied from the convergence point of view, in accordance with design conditions. The algorithm was compared to two other optimization methods,namely the artificial bee colony and a gradient method, for two optimization objectives, and the results of the optimizations with each of the three methods were plotted on response surfaces obtained with the Monte Carlo method, to show that they were situated in the global optimum region. The optimization results for 16 wind tunnel test cases and 2 objective functions were presented. The 16 cases used for the optimizations were included in the experimental test plan for the morphing wing-tip demonstrator, and the results obtained using the displacements given by the optimizations were evaluated.