Large sequence models for sequential decision-making:a survey

Transformer architectures have facilitated the development of large-scale and general-purpose sequence models for prediction tasks in natural language processing and computer vision,e.g.,GPT-3 and Swin Transformer.Although originally designed for prediction problems,it is natural to inquire about their suitability for sequential decision-making and reinforcement learning problems,which are typically beset by long-standing issues involving sample efficiency,credit assignment,and partial observability.In recent years,sequence models,especially the Transformer,have attracted increasing interest in the RL communities,spawning numerous approaches with notable effectiveness and generalizability.This survey presents a comprehensive overview of recent works aimed at solving sequential decision-making tasks with sequence models such as the Transformer,by discussing the connection between sequential decision-making and sequence modeling,and categorizing them based on the way they utilize the Transformer.Moreover,this paper puts forth various potential avenues for future research intending to improve the effectiveness of large sequence models for sequential decision-making,encompassing theoretical foundations,network architectures,algorithms,and efficient training systems.

Evolutionary Decision-Making and Planning for Autonomous Driving Based on Safe and Rational Exploration and Exploitation

Decision-making and motion planning are extremely important in autonomous driving to ensure safe driving in a real-world environment.This study proposes an online evolutionary decision-making and motion planning framework for autonomous driving based on a hybrid data-and model-driven method.First,a data-driven decision-making module based on deep reinforcement learning(DRL)is developed to pursue a rational driving performance as much as possible.Then,model predictive control(MPC)is employed to execute both longitudinal and lateral motion planning tasks.Multiple constraints are defined according to the vehicle’s physical limit to meet the driving task requirements.Finally,two principles of safety and rationality for the self-evolution of autonomous driving are proposed.A motion envelope is established and embedded into a rational exploration and exploitation scheme,which filters out unreasonable experiences by masking unsafe actions so as to collect high-quality training data for the DRL agent.Experiments with a high-fidelity vehicle model and MATLAB/Simulink co-simulation environment are conducted,and the results show that the proposed online-evolution framework is able to generate safer,more rational,and more efficient driving action in a real-world environment.

Optimized sequential therapy vs 10- and 14-d concomitant therapy for eradicating Helicobacter pylori: A randomized clinical trial

BACKGROUND A cure for Helicobacter pylori(H.pylori)remains a problem of global concern.The prevalence of antimicrobial resistance is widely rising and becoming a challenging issue worldwide.Optimizing sequential therapy seems to be one of the most attractive strategies in terms of efficacy,tolerability and cost.The most common sequential therapy consists of a dual therapy[proton-pump inhibitors(PPIs)and amoxicillin]for the first period(5 to 7 d),followed by a triple therapy for the second period(PPI,clarithromycin and metronidazole).PPIs play a key role in maintaining a gastric pH at a level that allows an optimal efficacy of antibiotics,hence the idea of using new generation molecules.This open-label prospective study randomized 328 patients with confirmed H.pylori infection into three groups(1:1:1):The first group received quadruple therapy consisting of twice-daily(bid)omeprazole 20 mg,amoxicillin 1 g,clarith-romycin 500 mg and metronidazole 500 mg for 10 d(QT-10),the second group received a 14 d quadruple therapy following the same regimen(QT-14),and the third group received an optimized sequential therapy consisting of bid rabe-prazole 20 mg plus amoxicillin 1 g for 7 d,followed by bid rabeprazole 20 mg,clarithromycin 500 mg and metronidazole 500 mg for the next 7 d(OST-14).AEs were recorded throughout the study,and the H.pylori eradication rate was determined 4 to 6 wk after the end of treatment,using the 13C urea breath test.RESULTS In the intention-to-treat and per-protocol analysis,the eradication rate was higher in the OST-14 group compared to the QT-10 group:(93.5%,85.5%P=0.04)and(96.2%,89.5%P=0.03)respectively.However,there was no statist-ically significant difference in eradication rates between the OST-14 and QT-14 groups:(93.5%,91.8%P=0.34)and(96.2%,94.4%P=0.35),respectively.The overall incidence of AEs was significantly lower in the OST-14 group(P=0.01).Furthermore,OST-14 was the most cost-effective among the three groups.CONCLUSION The optimized 14-d sequential therapy is a safe and effective alternative.Its eradication rate is comparable to that of the 14-d concomitant therapy while causing fewer AEs and allowing a gain in terms of cost.

Toluene Processed All-Polymer Solar Cells with 18%Efficiency and Enhanced Stability Enabled by Solid Additive:Comparison Between Sequential-Processing and Blend-Casting

The emergence of polymerized small molecule acceptors(PSMAs)has significantly improved the performance of all-polymer solar cells(all-PSCs).However,the pace of device engineering lacks behind that of materials development,so that a majority of the PSMAs have not fulfilled their potentials.Furthermore,most high-performance all-PSCs rely on the use of chloroform as the processing solvent.For instance,the recent highperformance PSMA,named PJ1-γ,with high LUMO,and HOMO levels,could only achieve a PCE of 16.1%with a high-energy-level donor(JD40)using chloroform.Herein,we present a methodology combining sequential processing(SqP)with the addition of 0.5%wt PC_(71)BM as a solid additive(SA)to achieve an impressive efficiency of 18.0%for all-PSCs processed from toluene,an aromatic hydrocarbon solvent.Compared to the conventional blend-casting(BC)method whose best efficiency(16.7%)could only be achieved using chloroform,the SqP method significantly boosted the device efficiency using toluene as the processing solvent.In addition,the donor we employ is the classic PM6 that has deeper energy levels than JD40,which provides low energy loss for the device.We compare the results with another PSMA(PYF-T-o)with the same method.Finally,an improved photostability of the SqP devices with the incorporation of SA is demonstrated.

Effect of sequential nursing care combined with communication intervention on visual recovery and pain after cataract ultrasound emulsification

BACKGROUND Cataracts are a common ophthalmic disease and postoperative vision recovery is crucial to patient quality of life.Rational and efficient care models play an impor-tant role in promoting vision recovery.AIM To evaluate the clinical effectiveness of procedural nursing care combined with communication intervention in vision recovery after cataract ultrasound emulsi-fication.METHODS A randomized controlled study was conducted on 100 patients with cataracts who underwent ultrasound emulsification surgery.They were randomly assigned to an experimental group or a control group.The experimental group received procedural nursing combined with Connect,Introduce,Communicate,Ask,Respond,Exit(CICARE)communication intervention,whereas the control group received conventional nursing.The effectiveness of the nursing model was assessed by comparing differences in vision recovery,pain scores,and mental health status between the two groups.RESULTS It was found that over time the visual acuity of patients in both groups gradually recovered and patients in the experimental group had lower pain scores and superior mental health status than the control group(P<0.05).CONCLUSION Procedural nursing combined with CICARE communication intervention has positive effects on vision recovery in patients after cataract ultrasound emulsification.

Accelerated Sequential Deposition Reaction via Crystal Orientation Engineering for Low-Temperature,High-Efficiency Carbon-Electrode CsPbBr_(3) Solar Cells

Low-temperature,ambient processing of high-quality CsPbBr_(3)films is demanded for scalable production of efficient,low-cost carbon-electrode perovskite solar cells(PSCs).Herein,we demonstrate a crystal orientation engineering strategy of PbBr_(2)precursor film to accelerate its reaction with CsBr precursor during two-step sequential deposition of CsPbBr_(3)films.Such a novel strategy is proceeded by adding CsBr species into PbBr_(2)precursor,which can tailor the preferred crystal orientation of PbBr_(2)film from[020]into[031],with CsBr additive staying in the film as CsPb_(2)Br_(5)phase.Theoretical calculations show that the reaction energy barrier of(031)planes of PbBr_(2)with CsBr is lower about 2.28 eV than that of(O2O)planes.Therefore,CsPbBr_(3)films with full coverage,high purity,high crystallinity,micro-sized grains can be obtained at a low temperature of 150℃.Carbon-electrode PSCs with these desired CsPbBr_(3)films yield the record-high efficiency of 10.27%coupled with excellent operation stability.Meanwhile,the 1 cm^(2)area one with the superior efficiency of 8.00%as well as the flexible one with the champion efficiency of 8.27%and excellent mechanical bending characteristics are also achieved.

An Overview of Sequential Approximation in Topology Optimization of Continuum Structure

This paper offers an extensive overview of the utilization of sequential approximate optimization approaches in the context of numerically simulated large-scale continuum structures.These structures,commonly encountered in engineering applications,often involve complex objective and constraint functions that cannot be readily expressed as explicit functions of the design variables.As a result,sequential approximation techniques have emerged as the preferred strategy for addressing a wide array of topology optimization challenges.Over the past several decades,topology optimization methods have been advanced remarkably and successfully applied to solve engineering problems incorporating diverse physical backgrounds.In comparison to the large-scale equation solution,sensitivity analysis,graphics post-processing,etc.,the progress of the sequential approximation functions and their corresponding optimizersmake sluggish progress.Researchers,particularly novices,pay special attention to their difficulties with a particular problem.Thus,this paper provides an overview of sequential approximation functions,related literature on topology optimization methods,and their applications.Starting from optimality criteria and sequential linear programming,the other sequential approximate optimizations are introduced by employing Taylor expansion and intervening variables.In addition,recent advancements have led to the emergence of approaches such as Augmented Lagrange,sequential approximate integer,and non-gradient approximation are also introduced.By highlighting real-world applications and case studies,the paper not only demonstrates the practical relevance of these methods but also underscores the need for continued exploration in this area.Furthermore,to provide a comprehensive overview,this paper offers several novel developments that aim to illuminate potential directions for future research.

Orientation and Decision-Making for Soccer Based on Sports Analytics and AI:A Systematic Review

Due to ever-growing soccer data collection approaches and progressing artificial intelligence(AI) methods, soccer analysis, evaluation, and decision-making have received increasing interest from not only the professional sports analytics realm but also the academic AI research community. AI brings gamechanging approaches for soccer analytics where soccer has been a typical benchmark for AI research. The combination has been an emerging topic. In this paper, soccer match analytics are taken as a complete observation-orientation-decision-action(OODA) loop.In addition, as in AI frameworks such as that for reinforcement learning, interacting with a virtual environment enables an evolving model. Therefore, both soccer analytics in the real world and virtual domains are discussed. With the intersection of the OODA loop and the real-virtual domains, available soccer data, including event and tracking data, and diverse orientation and decisionmaking models for both real-world and virtual soccer matches are comprehensively reviewed. Finally, some promising directions in this interdisciplinary area are pointed out. It is claimed that paradigms for both professional sports analytics and AI research could be combined. Moreover, it is quite promising to bridge the gap between the real and virtual domains for soccer match analysis and decision-making.

Attribute Reduction Method Based on Sequential Three-Branch Decision Model

Attribute reduction is a research hotspot in rough set theory. Traditional heuristic attribute reduction methods add the most important attribute to the decision attribute set each time, resulting in multiple redundant attribute calculations, high time consumption, and low reduction efficiency. In this paper, based on the idea of sequential three-branch decision classification domain, attributes are treated as objects of three-branch division, and attributes are divided into core attributes, relatively necessary attributes, and unnecessary attributes using attribute importance and thresholds. Core attributes are added to the decision attribute set, unnecessary attributes are rejected from being added, and relatively necessary attributes are repeatedly divided until the reduction result is obtained. Experiments were conducted on 8 groups of UCI datasets, and the results show that, compared to traditional reduction methods, the method proposed in this paper can effectively reduce time consumption while ensuring classification performance.

Toward Trustworthy Decision-Making for Autonomous Vehicles:A Robust Reinforcement Learning Approach with Safety Guarantees

While autonomous vehicles are vital components of intelligent transportation systems,ensuring the trustworthiness of decision-making remains a substantial challenge in realizing autonomous driving.Therefore,we present a novel robust reinforcement learning approach with safety guarantees to attain trustworthy decision-making for autonomous vehicles.The proposed technique ensures decision trustworthiness in terms of policy robustness and collision safety.Specifically,an adversary model is learned online to simulate the worst-case uncertainty by approximating the optimal adversarial perturbations on the observed states and environmental dynamics.In addition,an adversarial robust actor-critic algorithm is developed to enable the agent to learn robust policies against perturbations in observations and dynamics.Moreover,we devise a safety mask to guarantee the collision safety of the autonomous driving agent during both the training and testing processes using an interpretable knowledge model known as the Responsibility-Sensitive Safety Model.Finally,the proposed approach is evaluated through both simulations and experiments.These results indicate that the autonomous driving agent can make trustworthy decisions and drastically reduce the number of collisions through robust safety policies.

Proposal for sequential Stern-Gerlach experiment with programmable quantum processors

The historical significance of the Stern–Gerlach(SG)experiment lies in its provision of the initial evidence for space quantization.Over time,its sequential form has evolved into an elegant paradigm that effectively illustrates the fundamental principles of quantum theory.To date,the practical implementation of the sequential SG experiment has not been fully achieved.In this study,we demonstrate the capability of programmable quantum processors to simulate the sequential SG experiment.The specific parametric shallow quantum circuits,which are suitable for the limitations of current noisy quantum hardware,are given to replicate the functionality of SG devices with the ability to perform measurements in different directions.Surprisingly,it has been demonstrated that Wigner’s SG interferometer can be readily implemented in our sequential quantum circuit.With the utilization of the identical circuits,it is also feasible to implement Wheeler’s delayed-choice experiment.We propose the utilization of cross-shaped programmable quantum processors to showcase sequential experiments,and the simulation results demonstrate a strong alignment with theoretical predictions.With the rapid advancement of cloud-based quantum computing,such as BAQIS Quafu,it is our belief that the proposed solution is well-suited for deployment on the cloud,allowing for public accessibility.Our findings not only expand the potential applications of quantum computers,but also contribute to a deeper comprehension of the fundamental principles underlying quantum theory.

Ethical Decision-Making Framework Based on Incremental ILP Considering Conflicts

Humans are experiencing the inclusion of artificial agents in their lives,such as unmanned vehicles,service robots,voice assistants,and intelligent medical care.If the artificial agents cannot align with social values or make ethical decisions,they may not meet the expectations of humans.Traditionally,an ethical decision-making framework is constructed by rule-based or statistical approaches.In this paper,we propose an ethical decision-making framework based on incremental ILP(Inductive Logic Programming),which can overcome the brittleness of rule-based approaches and little interpretability of statistical approaches.As the current incremental ILP makes it difficult to solve conflicts,we propose a novel ethical decision-making framework considering conflicts in this paper,which adopts our proposed incremental ILP system.The framework consists of two processes:the learning process and the deduction process.The first process records bottom clauses with their score functions and learns rules guided by the entailment and the score function.The second process obtains an ethical decision based on the rules.In an ethical scenario about chatbots for teenagers’mental health,we verify that our framework can learn ethical rules and make ethical decisions.Besides,we extract incremental ILP from the framework and compare it with the state-of-the-art ILP systems based on ASP(Answer Set Programming)focusing on conflict resolution.The results of comparisons show that our proposed system can generate better-quality rules than most other systems.

Sequential Inverse Optimal Control of Discrete-Time Systems

This paper presents a novel sequential inverse optimal control(SIOC)method for discrete-time systems,which calculates the unknown weight vectors of the cost function in real time using the input and output of an optimally controlled discrete-time system.The proposed method overcomes the limitations of previous approaches by eliminating the need for the invertible Jacobian assumption.It calculates the possible-solution spaces and their intersections sequentially until the dimension of the intersection space decreases to one.The remaining one-dimensional vector of the possible-solution space’s intersection represents the SIOC solution.The paper presents clear conditions for convergence and addresses the issue of noisy data by clarifying the conditions for the singular values of the matrices that relate to the possible-solution space.The effectiveness of the proposed method is demonstrated through simulation results.

Stroke Risk Assessment Decision-Making Using a Machine Learning Model:Logistic-AdaBoost

Stroke is a chronic cerebrovascular disease that carries a high risk.Stroke risk assessment is of great significance in preventing,reversing and reducing the spread and the health hazards caused by stroke.Aiming to objectively predict and identify strokes,this paper proposes a new stroke risk assessment decision-making model named Logistic-AdaBoost(Logistic-AB)based on machine learning.First,the categorical boosting(CatBoost)method is used to perform feature selection for all features of stroke,and 8 main features are selected to form a new index evaluation system to predict the risk of stroke.Second,the borderline synthetic minority oversampling technique(SMOTE)algorithm is applied to transform the unbalanced stroke dataset into a balanced dataset.Finally,the stroke risk assessment decision-makingmodel Logistic-AB is constructed,and the overall prediction performance of this new model is evaluated by comparing it with ten other similar models.The comparison results show that the new model proposed in this paper performs better than the two single algorithms(logistic regression and AdaBoost)on the four indicators of recall,precision,F1 score,and accuracy,and the overall performance of the proposed model is better than that of common machine learning algorithms.The Logistic-AB model presented in this paper can more accurately predict patients’stroke risk.

Research on Maneuver Decision-Making of Multi-Agent Adversarial Game in a Random Interference Environment

The strategy evolution process of game players is highly uncertain due to random emergent situations and other external disturbances.This paper investigates the issue of strategy interaction and behavioral decision-making among game players in simulated confrontation scenarios within a random interference environment.It considers the possible risks that random disturbances may pose to the autonomous decision-making of game players,as well as the impact of participants’manipulative behaviors on the state changes of the players.A nonlinear mathematical model is established to describe the strategy decision-making process of the participants in this scenario.Subsequently,the strategy selection interaction relationship,strategy evolution stability,and dynamic decision-making process of the game players are investigated and verified by simulation experiments.The results show that maneuver-related parameters and random environmental interference factors have different effects on the selection and evolutionary speed of the agent’s strategies.Especially in a highly uncertain environment,even small information asymmetry or miscalculation may have a significant impact on decision-making.This also confirms the feasibility and effectiveness of the method proposed in the paper,which can better explain the behavioral decision-making process of the agent in the interaction process.This study provides feasibility analysis ideas and theoretical references for improving multi-agent interactive decision-making and the interpretability of the game system model.

Enhancement of vertical phase separation in sequentially deposited organic photovoltaics through the independent processing of additives

Herein,the impact of the independent control of processing additives on vertical phase separation in sequentially deposited (SD) organic photovoltaics (OPVs) and its subsequent effects on charge carrier kinetics at the electron donor-acceptor interface are investigated.The film morphology exhibits notable variations,significantly depending on the layer to which 1,8-diiodooctane (DIO) was applied.Grazing incidence wide-angle X-ray scattering analysis reveals distinctly separated donor/acceptor phases and vertical crystallinity details in SD films.Time-of-flight secondary ion mass spectrometry analysis is employed to obtain component distributions in diverse vertical phase structures of SD films depending on additive control.In addition,nanosecond transient absorption spectroscopy shows that DIO control significantly affects the dynamics of separated charges in SD films.In SD OPVs,DIO appears to act through distinct mechanisms with minimal restriction,depending on the applied layer.This study emphasizes the significance of morphological optimization in improving device performance and underscores the importance of independent additive control in the advancement of OPV technology.

Efficacy and safety of Xileisan combined with mesalazine for ulcerative colitis:A meta-analysis and trial sequential analysis

BACKGROUND The benefits and risks of Xileisan(XLS)in the treatment of ulcerative colitis(UC)remain unclear.AIM The present study aimed to evaluate the efficacy and safety of the combination of XLS and mesalazine when treating UC.METHODS We searched eight databases for clinical trials evaluating the combination of XLS and mesalazine in the treatment of UC,up to January 2024.Meta-analysis and trial sequential analysis(TSA)were performed using Revman 5.3 and TSA 0.9.5.10 beta,respectively.RESULTS The present study included 13 clinical studies involving 990 patients,of which 501 patients received XLS combined with mesalazine while 489 patients received mesalazine alone.The meta-analysis showed that,in terms of efficacy,the combination of XLS and mesalazine significantly improved the clinical efficacy rate by 22%[risk ratio(RR)=1.22;95%CI:1.15–1.28;P<0.00001]and mucosal improvement rate by 25%(RR=1.25;95%CI:1.12–1.39;P=0.0001),while significantly reducing the duration of abdominal pain by 2.25 days[mean difference(MD)=-2.25;95%CI:-3.35 to-1.14;P<0.0001],diarrhea by 2.06 days(MD=-2.06;95%CI:-3.92 to-0.20;P=0.03),hematochezia by 2.32 days(MD=-2.32;95%CI:-4.02 to-0.62;P=0.008),tumor necrosis factor alpha by 16.25 ng/mL(MD=-16.25;95%CI:-20.48 to-12.01;P<0.00001),and interleukin-6 by 14.14 ng/mL(MD=-14.14;95%CI:-24.89 to-3.39;P=0.01).The TSA indicated conclusiveness in the meta-analysis of the efficacy endpoints.In terms of safety,the meta-analysis revealed that the combination of XLS and mesalazine did not increase the occurrence of total and gastrointestinal adverse events,abdominal distension,and erythema(P>0.05).The TSA showed non conclusive findings in the meta-analysis of the safety endpoints.Harbord’s test showed no publication bias(P=0.734).CONCLUSION Treatment with XLS alleviated the clinical symptoms,intestinal mucosal injury,and inflammatory response in patients with UC,while demonstrating good safety.

Determination of the best materials for development and designing product using a multi-criteria decision-making

Purpose–Material selection,driven by wide and often conflicting objectives,is an important,sometimes difficult problem in material engineering.In this context,multi-criteria decision-making(MCDM)methodologies are effective.An approach of MCDM is needed to cater to criteria of material assortment simultaneously.More firms are now concerned about increasing their productivity using mathematical tools.To occupy a gap in the previous literature this research recommends an integrated MCDM and mathematical Bi-objective model for the selection of material.In addition,by using the Technique for Order Preference by Similarity to Ideal Solution(TOPSIS),the inherent ambiguities of decision-makers in paired evaluations are considered in this research.It goes on to construct a mathematical bi-objective model for determining the best item to purchase.Design/methodology/approach–The entropy perspective is implemented in this paper to evaluate the weight parameters,while the TOPSIS technique is used to determine the best and worst intermediate pipe materials for automotive exhaust system.The intermediate pipes are used to join the components of the exhaust systems.The materials usually used to manufacture intermediate pipe are SUS 436LM,SUS 430,SUS 304,SUS 436L,SUH 409 L,SUS 441 L and SUS 439L.These seven materials are evaluated based on tensile strength(TS),hardness(H),elongation(E),yield strength(YS)and cost(C).A hybrid methodology combining entropy-based criteria weighting,with the TOPSIS for alternative ranking,is pursued to identify the optimal design material for an engineered application in this paper.This study aims to help while filling the information gap in selecting the most suitable material for use in the exhaust intermediate pipes.After that,the authors searched for and considered eight materials and evaluated them on the following five criteria:(1)TS,(2)YS,(3)H,(4)E and(5)C.The first two criteria have been chosen because they can have a lot of influence on the behavior of the exhaust intermediate pipes,on their performance and on the cost.In this structure,the weights of the criteria are calculated objectively through the entropy method in order to have an unbiased assessment.This essentially measures the quantity of information each criterion contribution,indicating the relative importance of these criteria better.Subsequently,the materials were ranked using the TOPSIS method in terms of their relative performance by measuring each material from an ideal solution to determine the best alternative.The results show that SUS 309,SUS 432L and SUS 436 LM are the first three materials that the exhaust intermediate pipe optimal design should consider.Findings–The material matrix of the decision presented in Table 3 was normalized through Equation 5,as shown in Table 5,and the matrix was multiplied with weighting criteriaß_j.The obtained weighted normalized matrix V_ij is presented in Table 6.However,the ideal,worst and best value was ascertained by employing Equation 7.This study is based on the selection of material for the development of intermediate pipe using MCDM,and it involves four basic stages,i.e.method of translation criteria,screening process,method of ranking and search for methods.The selection was done through the TOPSIS method,and the criteria weight was obtained by the entropy method.The result showed that the top three materials are SUS 309,SUS 432L and SUS 436 LM,respectively.For the future work,it is suggested to select more alternatives and criteria.The comparison can also be done by using different MCDM techniques like and Choice Expressing Reality(ELECTRE),Decision-Making Trial and Evaluation Laboratory(DEMATEL)and Preference Ranking Organization Method for Enrichment Evaluation(PROMETHEE).Originality/value–The results provide important conclusions for material selection in this targeted application,verifying the employment of mutual entropy-TOPSIS methodology for a series of difficult engineering decisions in material engineering concepts that combine superior capacity with better performance as well as cost-efficiency in various engineering design.

Exploring Sequential Feature Selection in Deep Bi-LSTM Models for Speech Emotion Recognition

Machine Learning(ML)algorithms play a pivotal role in Speech Emotion Recognition(SER),although they encounter a formidable obstacle in accurately discerning a speaker’s emotional state.The examination of the emotional states of speakers holds significant importance in a range of real-time applications,including but not limited to virtual reality,human-robot interaction,emergency centers,and human behavior assessment.Accurately identifying emotions in the SER process relies on extracting relevant information from audio inputs.Previous studies on SER have predominantly utilized short-time characteristics such as Mel Frequency Cepstral Coefficients(MFCCs)due to their ability to capture the periodic nature of audio signals effectively.Although these traits may improve their ability to perceive and interpret emotional depictions appropriately,MFCCS has some limitations.So this study aims to tackle the aforementioned issue by systematically picking multiple audio cues,enhancing the classifier model’s efficacy in accurately discerning human emotions.The utilized dataset is taken from the EMO-DB database,preprocessing input speech is done using a 2D Convolution Neural Network(CNN)involves applying convolutional operations to spectrograms as they afford a visual representation of the way the audio signal frequency content changes over time.The next step is the spectrogram data normalization which is crucial for Neural Network(NN)training as it aids in faster convergence.Then the five auditory features MFCCs,Chroma,Mel-Spectrogram,Contrast,and Tonnetz are extracted from the spectrogram sequentially.The attitude of feature selection is to retain only dominant features by excluding the irrelevant ones.In this paper,the Sequential Forward Selection(SFS)and Sequential Backward Selection(SBS)techniques were employed for multiple audio cues features selection.Finally,the feature sets composed from the hybrid feature extraction methods are fed into the deep Bidirectional Long Short Term Memory(Bi-LSTM)network to discern emotions.Since the deep Bi-LSTM can hierarchically learn complex features and increases model capacity by achieving more robust temporal modeling,it is more effective than a shallow Bi-LSTM in capturing the intricate tones of emotional content existent in speech signals.The effectiveness and resilience of the proposed SER model were evaluated by experiments,comparing it to state-of-the-art SER techniques.The results indicated that the model achieved accuracy rates of 90.92%,93%,and 92%over the Ryerson Audio-Visual Database of Emotional Speech and Song(RAVDESS),Berlin Database of Emotional Speech(EMO-DB),and The Interactive Emotional Dyadic Motion Capture(IEMOCAP)datasets,respectively.These findings signify a prominent enhancement in the ability to emotional depictions identification in speech,showcasing the potential of the proposed model in advancing the SER field.

Embryo Transfer Strategies for Women with Recurrent Implantation Failure During the Frozen-thawed Embryo Transfer Cycles:Sequential Embryo Transfer or Double-blastocyst Transfer?

Objective Both sequential embryo transfer(SeET)and double-blastocyst transfer(DBT)can serve as embryo transfer strategies for women with recurrent implantation failure(RIF).This study aims to compare the effects of SeET and DBT on pregnancy outcomes.Methods Totally,261 frozen-thawed embryo transfer cycles of 243 RIF women were included in this multicenter retrospective analysis.According to different embryo quality and transfer strategies,they were divided into four groups:group A,good-quality SeET(GQ-SeET,n=38 cycles);group B,poor-quality or mixed-quality SeET(PQ/MQ-SeET,n=31 cycles);group C,good-quality DBT(GQ-DBT,n=121 cycles);and group D,poor-quality or mixed-quality DBT(PQ/MQ-DBT,n=71 cycles).The main outcome,clinical pregnancy rate,was compared,and the generalized estimating equation(GEE)model was used to correct potential confounders that might impact pregnancy outcomes.Results GQ-DBT achieved a significantly higher clinical pregnancy rate(aOR 2.588,95%CI 1.267–5.284,P=0.009)and live birth rate(aOR 3.082,95%CI 1.482–6.412,P=0.003)than PQ/MQ-DBT.Similarly,the clinical pregnancy rate was significantly higher in GQ-SeET than in PQ/MQ-SeET(aOR 4.047,95%CI 1.218–13.450,P=0.023).The pregnancy outcomes of GQ-SeET were not significantly different from those of GQ-DBT,and the same results were found between PQ/MQ-SeET and PQ/MQ-DBT.Conclusion SeET relative to DBT did not seem to improve pregnancy outcomes for RIF patients if the embryo quality was comparable between the two groups.Better clinical pregnancy outcomes could be obtained by transferring good-quality embryos,no matter whether in SeET or DBT.Embryo quality plays a more important role in pregnancy outcomes for RIF patients.