Drug-induced liver injury and COVID-19:Use of artificial intelligence and the updated Roussel Uclaf Causality Assessment Method in clinical practice

BACKGROUND Liver injury is a relevant condition in coronavirus disease 2019(COVID-19)inpatients.Pathophysiology varies from direct infection by virus,systemic inflammation or drug-induced adverse reaction(DILI).DILI detection and monitoring is clinically relevant,as it may contribute to poor prognosis,prolonged hospitalization and increase indirect healthcare costs.Artificial Intelligence(AI)applied in data mining of electronic medical records combining abnormal liver tests,keyword searching tools,and risk factors analysis is a relevant opportunity for early DILI detection by automated algorithms.AIM To describe DILI cases in COVID-19 inpatients detected from data mining in electronic medical records(EMR)using AI and the updated Roussel Uclaf Causality Assessment Method(RUCAM).METHODS The study was conducted in March 2021 in a hospital in southern Brazil.The NoHarm©system uses AI to support decision making in clinical pharmacy.Hospital admissions were 100523 during this period,of which 478 met the inclusion criteria.From these,290 inpatients were excluded due to alternative causes of liver injury and/or due to not having COVID-19.We manually reviewed the EMR of 188 patients for DILI investigation.Absence of clinical information excluded most eligible patients.The DILI assessment causality was possible via the updated RUCAM in 17 patients.RESULTS Mean patient age was 53 years(SD±18.37;range 22-83),most were male(70%),and admitted to the non-intensive care unit sector(65%).Liver injury pattern was mainly mixed,mean time to normalization of liver markers was 10 d,and mean length of hospitalization was 20.5 d(SD±16;range 7-70).Almost all patients recovered from DILI and one patient died of multiple organ failure.There were 31 suspected drugs with the following RUCAM score:Possible(n=24),probable(n=5),and unlikely(n=2).DILI agents in our study were ivermectin,bicalutamide,linezolid,azithromycin,ceftriaxone,amoxicillin-clavulanate,tocilizumab,piperacillin-tazobactam,and albendazole.Lack of essential clinical information excluded most patients.Although rare,DILI is a relevant clinical condition in COVID-19 patients and may contribute to poor prognostics.CONCLUSION The incidence of DILI in COVID-19 inpatients is rare and the absence of relevant clinical information on EMR may underestimate DILI rates.Prospects involve creation and validation of alerts for risk factors in all DILI patients based on RUCAM assessment causality,alterations of liver biomarkers and AI and machine learning.

Multiple Knowledge Representation of Artificial Intelligence

In the 1970s,cognitive psychology recognized that the information in the long-term memory is scene and semantic[1]and may be encoded in parallel as verbal and mental imagery[2].In 1991,I pointed out that not all verbal propositions can be derived from the verbal system,and that many can only be transformed from the imagery system[3].I have proposed the concept of visual knowledge,which consists of visual concepts,visual propositions,and visual narratives[4].Visual knowledge can simulate the various spatiotemporal operations that a person can perform on a mental imagery in his/her brain,such as the design process[5].

Prescribed Performance Tracking Control of Time-Delay Nonlinear Systems With Output Constraints

The problem of prescribed performance tracking control for unknown time-delay nonlinear systems subject to output constraints is dealt with in this paper. In contrast with related works, only the most fundamental requirements, i.e., boundedness and the local Lipschitz condition, are assumed for the allowable time delays. Moreover, we focus on the case where the reference is unknown beforehand, which renders the standard prescribed performance control designs under output constraints infeasible. To conquer these challenges, a novel robust prescribed performance control approach is put forward in this paper.Herein, a reverse tuning function is skillfully constructed and automatically generates a performance envelop for the tracking error. In addition, a unified performance analysis framework based on proof by contradiction and the barrier function is established to reveal the inherent robustness of the control system against the time delays. It turns out that the system output tracks the reference with a preassigned settling time and good accuracy,without constraint violations. A comparative simulation on a two-stage chemical reactor is carried out to illustrate the above theoretical findings.

Correction of microwave pulse reflection by digital filters in superconducting quantum circuits

Reducing the control error is vital for high-fidelity digital and analog quantum operations.In superconducting circuits,one disagreeable error arises from the reflection of microwave signals due to impedance mismatch in the control chain.Here,we demonstrate a reflection cancelation method when considering that there are two reflection nodes on the control line.We propose to generate the pre-distortion pulse by passing the envelopes of the microwave signal through digital filters,which enables real-time reflection correction when integrated into the field-programmable gate array(FPGA).We achieve a reduction of single-qubit gate infidelity from 0.67%to 0.11%after eliminating microwave reflection.Real-time correction of microwave reflection paves the way for precise control and manipulation of the qubit state and would ultimately enhance the performance of algorithms and simulations executed on quantum processors.

Parallel Implementation of the CCSDS Turbo Decoder on GPU

This paper presents a software turbo decoder on graphics processing units(GPU).Unlike previous works,the proposed decoding architecture for turbo codes mainly focuses on the Consultative Committee for Space Data Systems(CCSDS)standard.However,the information frame lengths of the CCSDS turbo codes are not suitable for flexible sub-frame parallelism design.To mitigate this issue,we propose a padding method that inserts several bits before the information frame header.To obtain low-latency performance and high resource utilization,two-level intra-frame parallelisms and an efficient data structure are considered.The presented Max-Log-Map decoder can be adopted to decode the Long Term Evolution(LTE)turbo codes with only small modifications.The proposed CCSDS turbo decoder at 10 iterations on NVIDIA RTX3070 achieves about 150 Mbps and 50Mbps throughputs for the code rates 1/6 and 1/2,respectively.

Dynamic Routing of Multiple QoS-Required Flows in Cloud-Edge Autonomous Multi-Domain Data Center Networks

The 6th generation mobile networks(6G)network is a kind of multi-network interconnection and multi-scenario coexistence network,where multiple network domains break the original fixed boundaries to form connections and convergence.In this paper,with the optimization objective of maximizing network utility while ensuring flows performance-centric weighted fairness,this paper designs a reinforcement learning-based cloud-edge autonomous multi-domain data center network architecture that achieves single-domain autonomy and multi-domain collaboration.Due to the conflict between the utility of different flows,the bandwidth fairness allocation problem for various types of flows is formulated by considering different defined reward functions.Regarding the tradeoff between fairness and utility,this paper deals with the corresponding reward functions for the cases where the flows undergo abrupt changes and smooth changes in the flows.In addition,to accommodate the Quality of Service(QoS)requirements for multiple types of flows,this paper proposes a multi-domain autonomous routing algorithm called LSTM+MADDPG.Introducing a Long Short-Term Memory(LSTM)layer in the actor and critic networks,more information about temporal continuity is added,further enhancing the adaptive ability changes in the dynamic network environment.The LSTM+MADDPG algorithm is compared with the latest reinforcement learning algorithm by conducting experiments on real network topology and traffic traces,and the experimental results show that LSTM+MADDPG improves the delay convergence speed by 14.6%and delays the start moment of packet loss by 18.2%compared with other algorithms.

The FRB-searching Pipeline of the Tianlai Cylinder Pathfinder Array

This paper presents the design,calibration,and survey strategy of the Fast Radio Burst(FRB)digital backend and its real-time data processing pipeline employed in the Tianlai Cylinder Pathfinder Array.The array,consisting of three parallel cylindrical reflectors and equipped with 96 dual-polarization feeds,is a radio interferometer array designed for conducting drift scans of the northern celestial semi-sphere.The FRB digital backend enables the formation of 96 digital beams,effectively covering an area of approximately 40 square degrees with the 3 dB beam.Our pipeline demonstrates the capability to conduct an automatic search of FRBs,detecting at quasi-realtime and classifying FRB candidates automatically.The current FRB searching pipeline has an overall recall rate of88%.During the commissioning phase,we successfully detected signals emitted by four well-known pulsars:PSR B0329+54,B2021+51,B0823+26,and B2020+28.We report the first discovery of an FRB by our array,designated as FRB 20220414A.We also investigate the optimal arrangement for the digitally formed beams to achieve maximum detection rate by numerical simulation.

Robust Consensus Tracking Control of Uncertain Multi-Agent Systems With Local Disturbance Rejection

In this paper,a new distributed consensus tracking protocol incorporating local disturbance rejection is devised for a multi-agent system with heterogeneous dynamic uncertainties and disturbances over a directed graph.It is of two-degree-of-freedom nature.Specifically,a robust distributed controller is designed for consensus tracking,while a local disturbance estimator is designed for each agent without requiring the input channel information of disturbances.The condition for asymptotic disturbance rejection is derived.Moreover,even when the disturbance model is not exactly known,the developed method also provides good disturbance-rejection performance.Then,a robust stabilization condition with less conservativeness is derived for the whole multi-agent system.Further,a design algorithm is given.Finally,comparisons with the conventional one-degree-of-freedombased distributed disturbance-rejection method for mismatched disturbances and the distributed extended-state observer for matched disturbances validate the developed method.

Detection of Worker’s Safety Helmet and Mask and Identification of Worker Using Deeplearning

This paper proposes a method for detecting a helmet for thesafety of workers from risk factors and a mask worn indoors and verifying aworker’s identity while wearing a helmet and mask for security. The proposedmethod consists of a part for detecting the worker’s helmet and mask and apart for verifying the worker’s identity. An algorithm for helmet and maskdetection is generated by transfer learning of Yolov5’s s-model and m-model.Both models are trained by changing the learning rate, batch size, and epoch.The model with the best performance is selected as the model for detectingmasks and helmets. At a learning rate of 0.001, a batch size of 32, and anepoch of 200, the s-model showed the best performance with a mAP of0.954, and this was selected as an optimal model. The worker’s identificationalgorithm consists of a facial feature extraction part and a classifier partfor the worker’s identification. The algorithm for facial feature extraction isgenerated by transfer learning of Facenet, and SVMis used as the classifier foridentification. The proposed method makes trained models using two datasets,a masked face dataset with only a masked face, and a mixed face datasetwith both a masked face and an unmasked face. And the model with the bestperformance among the trained models was selected as the optimal model foridentification when using a mask. As a result of the experiment, the model bytransfer learning of Facenet and SVM using a mixed face dataset showed thebest performance. When the optimal model was tested with a mixed dataset,it showed an accuracy of 95.4%. Also, the proposed model was evaluated asdata from 500 images of taking 10 people with a mobile phone. The resultsshowed that the helmet and mask were detected well and identification wasalso good.

Application of Blockchain Sharding Technology in Chinese Medicine Traceability System

Traditional Chinese Medicine(TCM)is one of the most promising programs for disease prevention and treatment.Meanwhile,the quality of TCM has garnered much attention.To ensure the quality of TCM,many works are based on the blockchain scheme to design the traceability scheme of TCM to trace its origin.Although these schemes can ensure the integrity,sharability,credibility,and immutability of TCM more effectively,many problems are exposed with the rapid growth of TCM data in blockchains,such as expensive overhead,performance bottlenecks,and the traditional blockchain architecture is unsuitable for TCM data with dynamic growth.Motivated by the aforementioned problems,we propose a novel and lightweight TCM traceability architecture based on the blockchain using sharding(LBS-TCM).Compared to the existing blockchain-based TCM traceability system,our architecture utilizes sharding to develop a novel traceability mechanism that supports more convenient traceability operations for TCM requirements such as uploading,querying,and downloading.Specifically,our architecture consists of a leader shard blockchain layer as its main component,which employs a sharding mechanism to conveniently TCM tracing.Empirical evaluations demonstrated that our architecture showed better performance in many aspects compared to traditional blockchain architectures,such as TCM transaction processing,TCM transaction querying,TCM uploading,etc.In our architecture,tracing TCM has become a very efficient operation,which ensures the quality of TCM and provides great convenience for subsequent TCM analysis and retrospective research.

Moving Target Landing of a Quadrotor Using Robust Optimal Guaranteed Cost Control

Dear Editor,This letter proposes a robust control strategy for the autonomous landing of a quadrotor on a moving target.Specifically,a force command that consists of a cascade dynamics estimator and an optimal guaranteed cost control law is exploited for the position-loop tracking.Then,an orientation constraint torque command is employed for the attitude-loop tracking such that the quadrotor refrains from flipping during the landing operation.

Modeling and Adaptive Neural Network Control for a Soft Robotic Arm With Prescribed Motion Constraints

This paper presents a dynamic model and performance constraint control of a line-driven soft robotic arm.The dynamics model of the soft robotic arm is established by combining the screw theory and the Cosserat theory.The unmodeled dynamics of the system are considered,and an adaptive neural network controller is designed using the backstepping method and radial basis function neural network.The stability of the closed-loop system and the boundedness of the tracking error are verified using Lyapunov theory.The simulation results show that our approach is a good solution to the motion constraint problem of the line-driven soft robotic arm.

Effects of microstructure characteristics on the tensile properties and fracture toughness of TA15 alloy fabricated by hot isostatic pressing

Powder hot isostatic pressing(HIP) is an effective method to achieve near-net-shape manufacturing of high-quality complex thinwalled titanium alloy parts, and it has received extensive attention in recent years. However, there are few reports about the microstructure characteristics on the strengthening and toughening mechanisms of powder hot isostatic pressed(HIPed) titanium alloys. Therefore, TA15powder was prepared into alloy by HIP approach, which was used to explore the microstructure characteristics at different HIP temperatures and the corresponding tensile properties and fracture toughness. Results show that the fabricated alloy has a “basket-like structure” when the HIP temperature is below 950℃, consisting of lath clusters and surrounding small equiaxed grains belts. When the HIP temperature is higher than 950℃, the microstructure gradually transforms into the Widmanstatten structure, accompanied by a significant increase in grain size. The tensile strength and elongation are reduced from 948 MPa and 17.3% for the 910℃ specimen to 861 MPa and 10% for the 970℃ specimen.The corresponding tensile fracture mode changes from transcrystalline plastic fracture to mixed fracture including intercrystalline cleavage.The fracture toughness of the specimens increases from 82.64 MPa·m^(1/2)for the 910℃ specimen to 140.18 MPa·m^(1/2)for the 970℃ specimen.Specimens below 950℃ tend to form holes due to the prior particle boundaries(PPBs), which is not conducive to toughening. Specimens above 950℃ have high fracture toughness due to the crack deflection, crack branching, and shear plastic deformation of the Widmanstatten structure. This study provides a valid reference for the development of powder HIPed titanium alloy.

Robust state of charge estimation of lithium-ion battery via mixture kernel mean p-power error loss LSTM with heap-based-optimizer

The state of charge(SOC)estimation of lithium-ion battery is an important function in the battery management system(BMS)of electric vehicles.The long short term memory(LSTM)model can be employed for SOC estimation,which is capable of estimating the future changing states of a nonlinear system.Since the BMS usually works under complicated operating conditions,i.e the real measurement data used for model training may be corrupted by non-Gaussian noise,and thus the performance of the original LSTM with the mean square error(MSE)loss may deteriorate.Therefore,a novel LSTM with mixture kernel mean p-power error(MKMPE)loss,called MKMPE-LSTM,is developed by using the MKMPE loss to replace the MSE as the learning criterion in LSTM framework,which can achieve robust SOC estimation under the measurement data contaminated with non-Gaussian noises(or outliers)because of the MKMPE containing the p-order moments of the error distribution.In addition,a meta-heuristic algorithm,called heap-based-optimizer(HBO),is employed to optimize the hyper-parameters(mainly including learning rate,number of hidden layer neuron and value of p in MKMPE)of the proposed MKMPE-LSTM model to further improve its flexibility and generalization performance,and a novel hybrid model(HBO-MKMPE-LSTM)is established for SOC estimation under non-Gaussian noise cases.Finally,several tests are performed under various cases through a benchmark to evaluate the performance of the proposed HBO-MKMPE-LSTM model,and the results demonstrate that the proposed hybrid method can provide a good robustness and accuracy under different non-Gaussian measurement noises,and the SOC estimation results in terms of mean square error(MSE),root MSE(RMSE),mean absolute relative error(MARE),and determination coefficient R2are less than 0.05%,3%,3%,and above 99.8%at 25℃,respectively.

An Edge-Fog-Cloud Computing-Based Digital Twin Model for Prognostics Health Management of Process Manufacturing Systems

The prognostics health management(PHM)fromthe systematic viewis critical to the healthy continuous operation of processmanufacturing systems(PMS),with different kinds of dynamic interference events.This paper proposes a three leveled digital twinmodel for the systematic PHMof PMSs.The unit-leveled digital twinmodel of each basic device unit of PMSs is constructed based on edge computing,which can provide real-time monitoring and analysis of the device status.The station-leveled digital twin models in the PMSs are designed to optimize and control the process parameters,which are deployed for the manufacturing execution on the fog server.The shop-leveled digital twin maintenancemodel is designed for production planning,which gives production instructions fromthe private industrial cloud server.To cope with the dynamic disturbances of a PMS,a big data-driven framework is proposed to control the three-level digital twin models,which contains indicator prediction,influence evaluation,and decisionmaking.Finally,a case study with a real chemical fiber system is introduced to illustrate the effectiveness of the digital twin model with edge-fog-cloud computing for the systematic PHM of PMSs.The result demonstrates that the three-leveled digital twin model for the systematic PHM in PMSs works well in the system’s respects.

Neural-Network-Based Adaptive Finite-Time Control for a Two-Degree-of-Freedom Helicopter System With an Event-Triggering Mechanism

Helicopter systems present numerous benefits over fixed-wing aircraft in several fields of application.Developing control schemes for improving the tracking accuracy of such systems is crucial.This paper proposes a neural-network(NN)-based adaptive finite-time control for a two-degree-of-freedom helicopter system.In particular,a radial basis function NN is adopted to solve uncertainty in the helicopter system.Furthermore,an event-triggering mechanism(ETM)with a switching threshold is proposed to alleviate the communication burden on the system.By proposing an adaptive parameter,a bounded estimation,and a smooth function approach,the effect of network measurement errors is effectively compensated for while simultaneously avoiding the Zeno phenomenon.Additionally,the developed adaptive finite-time control technique based on an NN guarantees finitetime convergence of the tracking error,thus enhancing the control accuracy of the system.In addition,the Lyapunov direct method demonstrates that the closed-loop system is semiglobally finite-time stable.Finally,simulation and experimental results show the effectiveness of the control strategy.

Cutting Force Fluctuation Suppression and Error Homogenization of Noncircular Gear Hobbing Based on the Tool Shifting Method

The current research on noncircular hobbing mainly focuses on the linkage model and motion realization.However,the intermittent cutting characteristics of hobbing would increase uncertainties in the manufacturing process.In this paper,a hobbing machining model with tool-shifting characteristics was proposed to solve the problems of cutting force fluctuation and inconsistency of tooth profile envelope accuracy at different positions of the pitch curve in noncircular gear hobbing.Based on the unit cutting force coefficient method,the undeformed chip volume generated by interrupted cutting was used to characterize the fluctuation trend of the hobbing force.The fluctuation characteristics of the cutting force generated by different hobbing models were compared and analyzed.Using the equivalent gear tooth and hob slotting numbers,an analysis model of the tooth profile envelope error of the noncircular gear was constructed.Subsequently,the tooth profile envelope errors at different positions of the pitch curve were compared and analyzed based on the constructed model.The transmission structure of the electronic gearbox was constructed based on the proposed hobbing model,and the hobbing experiment was conducted based on the selfdeveloped noncircular gear CNC hobbing system.This paper proposes a hobbing method that can effectively suppress the fluctuation of the peak and whole circumference cutting force and reduce the maximum envelope error of the whole circumference gear teeth.

Belief Propagation List Decoding for Polar Codes:Performance Analysis and Software Implementation on GPU

Belief propagation(BP)decoding outputs soft information and can be naturally used in iterative receivers.BP list(BPL)decoding provides comparable error-correction performance to the successive cancellation list(SCL)decoding.In this paper,we firstly introduce an enhanced code construction scheme for BPL decoding to improve its errorcorrection capability.Then,a GPU-based BPL decoder with adoption of the new code construction is presented.Finally,the proposed BPL decoder is tested on NVIDIA RTX3070 and GTX1060.Experimental results show that the presented BPL decoder with early termination criterion achieves above 1 Gbps throughput on RTX3070 for the code(1024,512)with 32 lists under good channel conditions.

Characterization of Memory Access in Deep Learning and Its Implications in Memory Management

Due to the recent trend of software intelligence in the Fourth Industrial Revolution,deep learning has become a mainstream workload for modern computer systems.Since the data size of deep learning increasingly grows,managing the limited memory capacity efficiently for deep learning workloads becomes important.In this paper,we analyze memory accesses in deep learning workloads and find out some unique characteristics differentiated from traditional workloads.First,when comparing instruction and data accesses,data access accounts for 96%–99%of total memory accesses in deep learning workloads,which is quite different from traditional workloads.Second,when comparing read and write accesses,write access dominates,accounting for 64%–80%of total memory accesses.Third,although write access makes up the majority of memory accesses,it shows a low access bias of 0.3 in the Zipf parameter.Fourth,in predicting re-access,recency is important in read access,but frequency provides more accurate information in write access.Based on these observations,we introduce a Non-Volatile Random Access Memory(NVRAM)-accelerated memory architecture for deep learning workloads,and present a new memory management policy for this architecture.By considering the memory access characteristics of deep learning workloads,the proposed policy improves memory performance by 64.3%on average compared to the CLOCK policy.

Self-similarity of complex networks under centrality-based node removal strategy

Real-world networks exhibit complex topological interactions that pose a significant computational challenge to analyses of such networks.Due to limited resources,there is an urgent need to develop dimensionality reduction techniques that can significantly reduce the structural complexity of initial large-scale networks.In this paper,we propose a subgraph extraction method based on the node centrality measure to reduce the size of the initial network topology.Specifically,nodes with smaller centrality value are removed from the initial network to obtain a subgraph with a smaller size.Our results demonstrate that various real-world networks,including power grids,technology,transportation,biology,social,and language networks,exhibit self-similarity behavior during the reduction process.The present results reveal the selfsimilarity and scale invariance of real-world networks from a different perspective and also provide an effective guide for simplifying the topology of large-scale networks.