Conversion Scenarios Research Articles

Energy efficiency of hydrogen for vehicle propulsion: On- or off-board H2 to electricity conversion?

If hydrogen fuel is available to support the transportation sector decarbonization, its usage can be placed either directly onboard in a fuel cell vehicle, or indirectly, off-board, by using a fuel cell power station to produce electricity to charge a battery electric vehicle. Therefore, in this work, the direct and indirect conversion scenarios of hydrogen to vehicle propulsion were investigated regarding energy efficiency. Thus, in the first scenario, hydrogen is the fuel for the onboard electricity production to propel a fuel cell vehicle while in the second, hydrogen is the electricity source to charge the battery electric vehicle. When simulated for a drive cycle, results have shown that the scenario with the onboard fuel cell consumed about 20% less hydrogen, demonstrating higher energy efficiency in terms of driving range. However, energy efficiency depends on the outside temperature when heat loss utilization is considered. For outside temperatures of −5 °C or higher, the system composed of the battery electric vehicle fueled with electricity from the off-board fuel cell was shown to be more energy-efficient. For lower temperatures, the system composed of the onboard fuel cell again presented higher total (heat + electricity) efficiency. Therefore, the results provide valuable insights into how hydrogen fuel can be used for vehicle propulsion, supporting the hydrogen economy development.

Distinct response of Asian summer monsoon circulation and precipitation to orbital forcing during six Heinrich events

Climatic fingerprint of Heinrich (H) events was characterized by widespread megadroughts over the Asian summer monsoon (ASM) region accompanied by systemic weakening of the ASM. However, recent studies of hydroclimate proxies suggest huge spatial discrepancies in precipitation over the ASM region during some H events, characterized by increased precipitation in the Yangtze River Valley contrasting with the prevalent megadroughts across the whole ASM region. The mechanism responsible for the spatial discrepancies in precipitation and the relationship between local precipitation and the ASM intensity remain elusive. In this study, we investigate the response of the ASM circulation and precipitation to orbital forcing during six H events based on simulations with a coupled atmosphere-ocean general circulation model. The results show that changes in insolation alone can induce spatial discrepancies in precipitation over the ASM region during the H events. During the H1, 3, 4, 5, 6 events, the amplification of the land-sea pressure contrast in response to a positive interhemispheric insolation gradient (30°N-30°S) during boreal summer intensifies moisture transport from the adjacent oceans to the ASM region. The ensuing moisture divergence, combined with anomalous downdrafts, results in decreased precipitation in the South Asian Summer Monsoon (SASM) region, but converse scenario for the East Asian Summer Monsoon (EASM) region. During the H2 event, the increased precipitation across the Yangtze River Valley sharply contrasts the widespread drought over the ASM region, attributing to an anticyclone anomaly over the subtropical Western North Pacific and a cyclone anomaly over Japan and Korea. Moisture budget analysis shows that the dynamic effect, especially the vertical term, rather than the thermodynamic effect, is the dominant control of precipitation changes over the ASM region. Our results also suggest that despite the synchronous variation in the strength of the EASM and SASM in response to orbital forcing, the EASM should not be regarded as an eastward and northward extension of the SASM. Furthermore, our model simulates a weak correlation between the monsoon intensity and precipitation in the SASM region in response to orbital forcing, calling for caution in employing precipitation to reconstruct SASM intensity on orbital time scale.

EAV: EEG-Audio-Video Dataset for Emotion Recognition in Conversational Contexts

Understanding emotional states is pivotal for the development of next-generation human-machine interfaces. Human behaviors in social interactions have resulted in psycho-physiological processes influenced by perceptual inputs. Therefore, efforts to comprehend brain functions and human behavior could potentially catalyze the development of AI models with human-like attributes. In this study, we introduce a multimodal emotion dataset comprising data from 30-channel electroencephalography (EEG), audio, and video recordings from 42 participants. Each participant engaged in a cue-based conversation scenario, eliciting five distinct emotions: neutral, anger, happiness, sadness, and calmness. Throughout the experiment, each participant contributed 200 interactions, which encompassed both listening and speaking. This resulted in a cumulative total of 8,400 interactions across all participants. We evaluated the baseline performance of emotion recognition for each modality using established deep neural network (DNN) methods. The Emotion in EEG-Audio-Visual (EAV) dataset represents the first public dataset to incorporate three primary modalities for emotion recognition within a conversational context. We anticipate that this dataset will make significant contributions to the modeling of the human emotional process, encompassing both fundamental neuroscience and machine learning viewpoints.

Considerable energy crop production potentials in the Russian Far East

High-latitude regions are not traditionally considered for energy crop production due to unfavorable production conditions, e.g., low temperatures and short growing seasons. However, with increasing pressures on land use in warmer regions, rising global food demands, and climate change, shifting energy crop production to cold climate regions has become a desirable alternative. Increasing attempts have been made in recent decades to cultivate cold-tolerant energy crops in high latitudes. This study aims to assess the potential biomass and bioenergy productivities of willow, poplar, and miscanthus over the Russian Far East (RFE) federal district, with a yield-predicting model built on newly published data from high latitude. We evaluated the potentials of energy crop production and greenhouse gas mitigation in RFE under three land use scenarios. Our analysis reveals that the RFE has the potential to produce 1.3 × 109 Mg of biomass per year on 215 Mha of spare land with an average yield of 6 Mg ha−1 under the most extensive land conversion scenario, which can be converted to 24 EJ of bioenergy and thus lead to a net mitigation of 4.1 × 108 Mg CO2e greenhouse gas emissions. The productivity and mitigation potential remain substantial (78 % of the most extensive land conversion scenario) under the scenario that all the RFE's existing croplands and forests are preserved. Our assessment offers valuable insights into the potential of energy crop development in the RFE and other high-latitude regions globally, presenting a novel land-use solution for a low-carbon future.

Modelling the opportunity for cost-savings or patient access with biosimilar adalimumab and tocilizumab: a European perspective

Objectives Biosimilars improve patient access by providing cost-effective treatment options. This study assessed the potential for savings and expanded patient access with increased use of two biosimilar disease modifying anti-rheumatic drugs (DMARDs): (a) approved adalimumab biosimilars and (b) the first tocilizumab biosimilar, representing an established biosimilar field and a recent biosimilar entrant in France, Germany, Italy, Spain, and the United Kingdom (UK). Methods Separate ex-ante analyses were conducted for each country, parameterized using country-specific list prices, unit volumes annually, and market shares for each therapy. Discounting scenarios of 10%, 20%, and 30% were tested for tocilizumab. Outputs included direct cost-savings associated with drug acquisition or the incremental number of patients that could be treated if savings were redirected. Two biosimilar conversion scenarios were tested. Results Savings associated with a 100% conversion to adalimumab biosimilar ranged from €10.5 to €187 million (UK and Germany, respectively), or an additional 1,096 to 19,454 patients that could be treated using the cost-savings. Introduction of a tocilizumab biosimilar provided savings up to €29.3 million in the most conservative scenario. Exclusive use of tocilizumab biosimilars (at a 30% discount) could increase savings to €28.8 to €113 million or expand access to an additional 43% of existing tocilizumab users across countries. Conclusion This study demonstrates the benefits that can be realized through increased biosimilar adoption, not only in an untapped tocilizumab market, but also through incremental increases in well-established markets such as adalimumab. As healthcare budgets continue to face downwards pressure globally, strategies to increase biosimilar market share could prove useful to help manage financial constraints.

A Power System Study on Hydrogen Conversion Pathways for Gas Turbine Power Plants in Vietnam towards Net Zero Target

The potential applications of hydrogen in various fields of the energy sector are attracting attention worldwide, including the use of hydrogen for decarbonizing power systems. In Vietnam, hydrogen is considered to gradually replace natural gas in power generation to achieve the country’s net zero target by 2050 but there is a lack of research about this new subject. This study focuses on the computational simulation of the evolution of Vietnam’s power system in the period 2030–2050 according to non-conversion and slow, moderate, and accelerated scenarios of natural gas-to-hydrogen conversion at gas turbine power plants. Based on a total power system generation capacity of 150.5 GW in 2030, the modeling results show that the system capacity range of the scenarios is between 568.7 GW and 584.6 GW. In terms of economic performance, the slow conversion scenario has the lowest system cost of USD 1269.0 billion, and the accelerated scenario represents the highest system cost of USD 1283.2 billion. As for CO2 emissions of the power system, the accelerated scenario has the lowest cumulative CO2 emissions in the studied period while the non-conversion appears highest, 2933 and 3212 million tons, respectively. Based on the study results, the possible pathway recommendation of natural gas-to-hydrogen conversion for Vietnam’s power system is proposed.

Configuring circular by-product supply networks through public-private partnerships – A case study of rice straw stubble agri-waste in Punjab

The use of production by-products as feedstock offers benefits in terms of circularity, waste reduction, and enhanced local value-add. In this paper, we examine the institutional and supply network collaborations required to shift from global to near-sourcing using by-products of previously unrelated production activities. The case study of straw stubble agri-waste is examined as it exhibits multiple product-process valorisation opportunities, generates social welfare gains for farmers, and addresses a critical societal need of reducing pollution. Drawing on circular economy and supply network configuration literature, the research involved the consideration of local resource availability, product-production process technology options, partnering arrangements, and network governance. The results reveal multiple feedstock product-process conversion scenarios, each representing potential intermediate and end-use products/markets. Two pathways were identified offering industrial-scale valorisation, namely straw-stubble as a feedstock for i) building products and ii) energy purposes. Circular supply network design parameters emerge from cross-case analysis suggesting alignment across feedstock network structure, product-processing pathways, and the configuration of public-private partnerships is necessary. This paper develops supply network configuration design approaches and related partnering models by providing a structured framework for identifying commerically viable by-product driven supply networks that leverage the proximity of non-traditional suppliers exploiting local resources. This research contributes to the design of circular supply networks and partnership configurations for the valorisation of by-products.

How does shrimp farming impact agricultural production and food security in coastal Bangladesh? Evidence from farmer perception and remote sensing approach

Shrimp farming poses a significant challenge to agriculture in coastal Bangladesh, compounded by climate change and natural disasters. Therefore, the study aims to assess the impact of shrimp farming on food security among marginal farmers using Structural Equation Modeling (SEM). Additionally, we investigate scenarios of agriculture land conversion (1990–2022) in the southwestern coastal regions of Bangladesh through remote sensing techniques. To achieve the study objectives, we collected 672 respondents' opinions from the study regions through a self-administered questionnaire survey. The results indicate that a majority (60%) of the participants believe that rice yields have significantly decreased on their farms in the past ten years, with 70% attributing this decline to increased shrimp cultivation. SEM reveals that shrimp farming has a significant negative impact on farmers' income and dietary habits. Land use and land cover analyses indicate that the area dedicated to aquaculture has nearly doubled from 391.37 km2 in 1990 to 739.93 km2 in 2022.In contrast, agricultural land has decreased by 321.83 km2 over more than thirty years. Our analysis demonstrates that shrimp farming negatively impacts traditional agricultural practices and the sustainability of coastal agriculture by increasing soil salinity, thereby impacting marginalized farmers' food security through income reduction. This study provides valuable insights for policymakers worldwide to implement appropriate laws and regulations to control unplanned shrimp aquaculture in different coastal settings, thus contributing to sustainable development goals and food sovereignty.

Introducing CASUX: A Standardized Scale for Measuring the User Experience of Artificial Intelligence Based Conversational Agents

Conversational agents are growing in popularity, and as such they must provide a good user experience and meet the needs of the users. Yet, how to measure the user experience in the conversational AI scenario remains an open and urgent question to be solved, which may hinder further empirical studies on human-agent interactions. In fact, there have been very few studies that explore how users perceive interacting with these conversational agents, which is important to ensure their sustainability. Accordingly, in this work, we used a subjective technique by following a measurement approach to develop a standardized measurement instrument/scale called the Conversational Agent Scale for User Experience. In terms of the methodology, we used a mixed-method approach involving an iterative process spanning across six different user studies (three qualitative and three quantitative) at different points of time for the purpose of dimension identification, item generation and subsequent item refinements. As a part of the qualitative studies we conducted a Systematic Literature Review, semi-structured interviews with users of conversational agents, and expert interviews. For the quantitative studies a lab-based experiment was performed for the pre-test, followed by two online surveys as a part of pilot testing and scale development. The qualitative studies initially identified a total of 13 distinct user experience dimensions and 418 measurement items. Finally, the Exploratory Factor Analysis as a part of the main survey resulted in 9 user experience dimensions (practicality perception, proficiency, humanness, sentiment, robustness, etiquette & mannerism, personality, anthropomorphism, and ease of use) and 34 measurement items. This was supplemented by conducting another Confirmatory Factor Analysis for establishing the reliability and validity of the proposed scale, together with checking the model-fit indices. All the 9 dimensions had sufficient validity, and a reasonable level of statistical reliability. Some of the user experience dimensions like humanness, personality, anthropomorphism, and etiquette & mannerism show the uniqueness of the conversational AI scenario from the traditional usage factors used commonly while evaluating graphical user interface-based systems. This work fills the gap of a lack of research on how to classify and measure the conversational experience of users and provides a reference for practitioners and designers in developing these agents and continuously improving the usage experience.

A Contrastive Analysis of Linguistic Features of Chinese and American Compliments

Compliments are an integral component of social etiquette and play a significant role in everyday interpersonal communication. This study examines the influence of distinct phonetic characteristics in Chinese and English on the moods and sentiments conveyed through compliments. Through an analysis of compliment strategies and their linguistic functions in common situations, this study compares the differences in vocabulary selection and expression methods between Chinese and American compliments. It also discusses the underlying reasons for these differences from the perspectives of cultural variations, social norms, and thinking patterns. Furthermore, the study analyzes and compares the similarities between Chinese and American compliments in terms of their purposes, topics, and stylistic changes. Overall, despite differences in phonetics, vocabulary selection, and expression methods, Chinese and American compliments exhibit convergence in their macroscopic purposes, themes, and styles due to the constraints imposed by specific conversational scenarios.

Cost, market, and policy constraints on mitigating climate change through afforestation in China

Afforestation is a promising nature-based climate solution for mitigating climate change, but it is subject to a complex web of biophysical, cost-benefit, market, and policy processes. Although its biophysical feasibility has been established, the cost, market, and policy constraints that affect climate change mitigation through afforestation are still unclear. Here, we estimate such cost, market, and policy constraints on the basis of biophysical feasibility. Our findings reveal that implementation costs are a more relevant constraint than opportunity costs on mitigating climate change through afforestation. The China Certified Emission Reduction market currently provides only a 0.308 % incentive for climate change mitigation through afforestation, due to market access constraints. The current market prices of China Certified Emission Reduction, China Carbon Emissions Trading Exchange, and Nature Based Carbon Offset in Voluntary Carbon Market constrain 88.15 %, 87.95 %, and 85.75 % of CO2 removal actions through afforestation, compared to the carbon price scenario (US$62.97 tCO2-1) of the EU Emissions Trading System. Moreover, land policy under the scenarios of prohibiting conversion of cultivated land to forest and forest restoration in degraded areas exhibit 8.87–29.59 % and 65.16–74.10 % constraints, respectively, on mitigating climate change through afforestation compared to land-use freedom conversion scenarios from 2020 to 2060. Thus, enhancing the incentive price of CO2 removal, addressing the market access barrier, strengthening cooperation between global carbon markets, and exploring carbon–neutral and food multi-oriented land policies can be valuable sources of mitigation efforts over the next 40 years.

Constraining axion-like particles dark matter in Coma Berenices with FAST

Axions and axion-like particles (ALPs) appear in many extensions of the Standard Model and are being investigated as promising dark matter (DM) candidates. One viable methodology for their detection involves the investigation of the line-like radio emissions from the dwarf spheroidal galaxy, potentially originating from the radiative decay of ALPs or the conversion of ALPs in the magnetic field. In this work, we constrain the properties of ALPs using the 2-hour radio observation of Coma Berenices through the Five-hundred-meter Aperture Spherical radio Telescope (FAST). The 95% upper limits of the ALP-photon coupling are calculated for the ALP decay and conversion scenarios, respectively. Note that the sensitive ALP masses for FAST range from ∼μeV to tens of μeV, where ALP can explain the DM abundance naturally. However, our limits are weaker than those of the CAST helioscope, which can provide an independent and complementary check on the ALP non-detection for ground experiments. Furthermore, we evaluate the expected sensitivity on the ALP of FAST with its full designed bandwidth (70 MHz - 3 GHz) for 100 hours of observation time. Our results indicate that, even with the exceptional sensitivity of the FAST, it is challenging to surpass the existing experimental constraints on ALP DM using radio observation of dSphs, unless the possible enhancements of ALP signals by compact stars in dSphs are considered.

Large language models driven BIM-based DfMA method for free-form prefabricated buildings: framework and a usefulness case study

ABSTRACT The escalating demand for free-form buildings presents a formidable technological hurdle in the realm of prefabrication manufacturing and assembly. This research draws inspiration from recent advancements in large language models (LLMs) and seeks to harness their transformative potential in tandem with Building Information Modeling (BIM) to advance the Design for Manufacture and Assembly (DfMA) method. The ultimate aim is to catapult the prefabrication industry into an era characterized by unparalleled design freedom and heightened efficiency. The research includes contributions from the following four areas: (1) A review of the literature on DfMA theories, specifically fabrication and construction. (2) The development of a BIM-based DfMA method framework, including the methodological basis, Design for Manufacturing (DfM), and Design for Assembly (DfA). (3) A pipeline for LLMs driven BIM-based DfMA method framework and a validation using the Decathlon Solar Team design-build practice at the University of Washington’s Lotus House. (4) An evaluation of 692 conversation scenarios to verify the feasibility of our proposal. We get a 91.1% user agreement on average based on GPT4. The research results could guide the workflow in building a lifecycle for DfMA practices in the future smart manufacturing era.

Multi-Task Learning with Sequential Dependence Toward Industrial Applications: A Systematic Formulation

Multi-task learning (MTL) is widely used in the online recommendation and financial services for multi-step conversion estimation, but current works often overlook the sequential dependence among tasks. In particular, sequential dependence multi-task learning (SDMTL) faces challenges in dealing with complex task correlations and extracting valuable information in real-world scenarios, leading to negative transfer and a deterioration in the performance. Herein, a systematic learning paradigm of the SDMTL problem is established for the first time, which applies to more general multi-step conversion scenarios with longer conversion paths or various task dependence relationships. Meanwhile, an SDMTL architecture, named Task-Aware Feature Extraction (TAFE), is designed to enable the dynamic task representation learning from a sample-wise view. TAFE selectively reconstructs the implicit shared information corresponding to each sample case and performs the explicit task-specific extraction under dependence constraints, which can avoid the negative transfer, resulting in more effective information sharing and joint representation learning. Extensive experiment results demonstrate the effectiveness and applicability of the proposed theoretical and implementation frameworks. Furthermore, the online evaluations at MYbank showed that TAFE had an average increase of 9.22% and 3.76% in various scenarios on the post-view click-through & conversion rate (CTCVR) estimation task. Currently, TAFE is deployed in an online platform to provide various traffic services.

Phase shift control of dual active bridge DC‐DC converter based on feedforward compensation and transient optimization strategy

SummaryIn the context of the dual active bridge (DAB) bidirectional DC‐DC converter using the traditional dual‐phase‐shift (DPS) control method, a transient DC bias occurs during power co‐direction and commutation conversion. This bias negatively impacts the converter's transient performance and can lead to harsh effects, such as hard switching problems, resulting in power loss and excessive current stress. In a closed‐loop control system, poor transient response may destroy the stability of the converter. In this paper, the transient‐optimized‐dual‐phase‐shift (TODPS) control strategy is proposed to eliminate the transient DC bias and to maintain soft switching during transient states. It reduces power loss, eliminates excessive current stress, and allows for smooth transitions between single‐phase‐shift (SPS) and DPS control strategies without introducing DC bias. A closed‐loop control system based on TODPS control is established with feed‐forward compensation to adjust the primary‐side current and modify transmission power. This adjustment enhances the transient performance of the DAB converter. The proposed strategy is versatile and applicable to various power conversion scenarios involving DAB converters. It enables quick switching of the magnitude and direction of the primary‐side current during transient states, resulting in a smooth transient effect without noticeable overshoot or oscillation. The experiment results verify the effectiveness of the proposed transient optimization strategy.

Latitudinal responses of wetland soil nitrogen pools to plant invasion and subsequent aquaculture reclamation along the southeastern coast of China

The impact of invasive species and land use change on soil nitrogen pools in coastal wetlands has been reported at local scale, but uncertainty persists for regional pattern due to geographical variability and limited field data. This study measured the top soil (upper 20 cm) organic nitrogen (SON), inorganic nitrogen (SIN) and total nitrogen (STN) concentrations and stocks across 21 coastal wetland sites in China (20°42′N-31°51′ N) that had undergone the same sequence of transformation from mudflats (MFs) to invasive Spartina alterniflora marshes (SAs) then to earthen aquaculture ponds (APs). Results showed that the conversion of MF to SA significantly increased SON and SIN concentrations and stocks by 37.7–86.1%, but subsequent conversion to APs significantly decreased them by 13.5–34.6%. SON/SIN ratio decreased upon invasion by S. alterniflora and it had a negative effect on STN accumulation, whereas conversion of SAs to APs showed the opposite trends. The change rates of SON, SIN and STN stocks showed clear decreasing trends with increasing latitude in the MF-to-SA conversion scenario, reflecting the strong influence of environmental temperatures, but weaker or insignificant trends were observed in the SA-to-AP conversion scenario, likely because of mitigating anthropogenic activities in aquaculture ponds. Our findings can be used to inform strategies to control invasive species and reduce the greenhouse gas nitrous oxide (N2O) emissions, and support global N model for climate change in response to habitat modifications in coastal wetlands.

A novel and dynamic land use/cover change research framework based on an improved PLUS model and a fuzzy multiobjective programming model

Spatial reconstruction and scenario simulation of historical processes and future trends of land use/cover change (LUCC) can help to reveal the historical background of land conversion and the spatial distribution of future land. Moreover, there is a close relationship between the spatiotemporal dynamics of land use/cover and changes in different ecosystem services (ESs). Using this relationship to simulate future land use scenarios is important. In this study, an LUCC dynamic analysis framework (LSTM-PLUS-FMOP) was constructed based on a deep learning time series forecasting model (LSTM), a parallelized urban land use simulation (PLUS) model and a fuzzy multiobjective programming (FMOP) model. The PLUS model was used to analyze the driving mechanism of land expansion and explore the land conversion pattern. In addition, three land conversion scenarios were established: natural land expansion (NLE), economic development priority (EDP) and regional sustainable development (RSD). The FMOP model and the relationship between LUCC and ES were used to perform a spatial simulation of land conversion. The uncertainty parameters in the model were treated by intuitionistic fuzzy numbers (IFSs). This study applied the constructed framework to the Yellow River Basin of Shaanxi Province (YRB-SX). The results showed that (1) from 2000 to 2020, the cropland area of the YRB-SX continuously decreased by 12.67 × 104 ha, while the built-up area continuously increased by 28.25 × 104 ha. The net reduction in woodland and grassland area was 13.90 × 104 ha. (2) The relative error range of land prediction using the LSTM model was 0.0003– 0.0042. This model had better accuracy than the Markov chain prediction model. (3) The cropland area decreased by 0.26% (NLE), 0.85% (EDP) and 1.68% (RSD) under the three scenarios. The built-up area increased by 25.01%, 32.76% and 14.72%, respectively. The RSD scenario followed the principles of ecological protection and spatial constraints, which mitigated the degradation of the ecosystem to some extent. This coupled simulation framework will help to obtain land allocation schemes that meet the requirements of ecological protection and provide solutions for rational land management.

Dynamic evaluation of the electrical primary energy factor for building energy performance: Insights from 2022 Italian data

The primary energy factor (PEF) represents a fundamental concept for converting a final energy carrier into primary energy. Among its many areas of application, building industry is of particular interest, since primary energy demand is a representative and widespread indicator for evaluating a building’s whole energy performance. This paper starts by exploring the critical issues related to the use of PEF, which is often evaluated through outdated, static values. Through the application of one of the methods of the UNI EN 17423:2021 standard, the hourly trend of the primary energy factor for the electric carrier in Italy during the year 2022 was evaluated. Results show the strong dynamicity of the PEF and the existing relationships between its renewable and non-renewable shares, which are strongly influenced by pro-duction, import and export strategies. The obtained PEFs were applied to a case study of a residential building, evaluating the primary energy needs under different final energy conversion scenarios. This work highlights the need for an update of the PEF to dynamic values consistent with the energy context of a country to facilitate the energy transition, as well as to reduce the supply and demand mismatch, and reward the use of renewable energy.

Reciprocity, Inequality, and Unsuccessful Rescues

AbstractForced choices between rescuing imperilled persons are subject to a presumption of equality. Unless we can point to a morally relevant difference between these persons' imperilments, each should get an equal chance of rescue. Sometimes, this presumption is overturned. For example, when one imperilled person has wrongfully caused the forced choice, most think that this person (rather than an innocent person) should bear the harm. The converse scenario, in which a forced choice resulted from the supererogatory action of one of the imperilled people, has received little attention in distributive ethics. I argue that, sometimes, we need not offer equal chances in these cases either. When the supererogatory act places the initially imperilled person under a reciprocal duty to bear risks for the supererogatory agent's sake in the forced choice, we may fulfil this duty for them if they are unable to do it themselves, by favouring the supererogatory agent.

Intelligent Diagnostic System Development based on Artificial Intelligence Technology

Intelligent diagnosis is an important scenario in smart healthcare, with conversational diagnostic scenarios being the most common. The process of collecting symptom information through conversations with users and inferring diseases based on symptoms. Through a dialogue based diagnostic system, it can meet some of the medical consultation needs of residents, thereby freeing doctors from some basic consultations and greatly alleviating the shortage of medical resources. In the actual diagnosis process, the symptoms reported by patients are often insufficient to support accurate diagnosis. It is necessary to ask the user if they have any other symptoms through dialogue to form a diagnostic conclusion. Existing research mainly adopts reinforcement learning methods, which gradually learn the dialogue process between traditional Chinese medicine students and patients in real medical scenarios, and obtain strategies for symptom inquiry and disease diagnosis. Despite the advantages of reinforcement learning in dealing with temporal decision problems, the diagnostic accuracy is still low and data dependency is strong. In this article, a medical dialogue robot architecture based on medical dialogue diagnosis technology, medical knowledge graph technology, and "inference machine" technology is proposed to build an intelligent diagnosis architecture. Secondly, in terms of algorithm, this article proposes a disease diagnosis algorithm based on Naive Bayes Classification and a symptom screening algorithm based on symptom set differences for symptom query process, This algorithm increases the interpretability of diagnostic results by simulating the questioning and diagnostic process of doctors, and combines it with the medical dialogue robot architecture to achieve intelligent diagnosis throughout the entire process.