TransCode: Uncovering COVID-19 transmission patterns via deep learning.

BACKGROUND: The heterogeneity of COVID-19 spread dynamics is determined by complex spatiotemporal transmission patterns at a fine scale, especially in densely populated regions. In this study, we aim to discover such fine-scale transmission patterns via deep learning. METHODS: We introduce the notion of TransCode to characterize fine-scale spatiotemporal transmission patterns of COVID-19 caused by metapopulation mobility and contact behaviors. First, in Hong Kong, China, we construct the mobility trajectories of confirmed cases using their visiting records. Then we estimate the transmissibility of individual cases in different locations based on their temporal infectiousness distribution. Integrating the spatial and temporal information, we represent the TransCode via spatiotemporal transmission networks. Further, we propose a deep transfer learning model to adapt the TransCode of Hong Kong, China to achieve fine-scale transmission characterization and risk prediction in six densely populated metropolises: New York City, San Francisco, Toronto, London, Berlin, and Tokyo, where fine-scale data are limited. All the data used in this study are publicly available. RESULTS: The TransCode of Hong Kong, China derived from the spatial transmission information and temporal infectiousness distribution of individual cases reveals the transmission patterns (e.g., the imported and exported transmission intensities) at the district and constituency levels during different COVID-19 outbreaks waves. By adapting the TransCode of Hong Kong, China to other data-limited densely populated metropolises, the proposed method outperforms other representative methods by more than 10% in terms of the prediction accuracy of the disease dynamics (i.e., the trend of case numbers), and the fine-scale spatiotemporal transmission patterns in these metropolises could also be well captured due to some shared intrinsically common patterns of human mobility and contact behaviors at the metapopulation level. CONCLUSIONS: The fine-scale transmission patterns due to the metapopulation level mobility (e.g., travel across different districts) and contact behaviors (e.g., gathering in social-economic centers) are one of the main contributors to the rapid spread of the virus. Characterization of the fine-scale transmission patterns using the TransCode will facilitate the development of tailor-made intervention strategies to effectively contain disease transmission in the targeted regions.

Economic Analysis of Border Control Policies during COVID-19 Pandemic: A Modelling Study to Inform Cross-Border Travel Policy between Singapore and Thailand.

With countries progressing towards high COVID-19 vaccination rates, strategies for border reopening are required. This study focuses on Thailand and Singapore, two countries that share significant tourism visitation, to illustrate a framework for optimizing COVID-19 testing and quarantine policies for bilateral travel with a focus on economic recovery. The timeframe is the month of October 2021, when Thailand and Singapore were preparing to reopen borders for bilateral travel. This study was conducted to provide evidence for the border reopening policy decisions. Incremental net benefit (INB) compared to the pre-opening period was quantified through a willingness-to-travel model, a micro-simulation COVID-19 transmission model and an economic model accounting for medical and non-medical costs/benefits. Multiple testing and quarantine policies were examined, and Pareto optimal (PO) policies and the most influential components were identified. The highest possible INB for Thailand is US $125.94 million, under a PO policy with no quarantine but with antigen rapid tests (ARTs) pre-departure and upon arrival to enter both countries. The highest possible INB for Singapore is US $29.78 million, under another PO policy with no quarantine on both sides, no testing to enter Thailand, and ARTs pre-departure and upon arrival to enter Singapore. Tourism receipts and costs/profits of testing and quarantine have greater economic impacts than that from COVID-19 transmission. Provided healthcare systems have sufficient capacity, great economic benefits can be gained for both countries by relaxing border control measures.

Optimal Network of General Hospitals in Slovenia.

This article explores how the minimum number of general hospital locations can be determined with optimal population coverage. Due to the increasing financial problems of hospitals and the poor organization of general hospital healthcare, Slovenia is currently working to reform the healthcare system. Defining the optimal network of hospital providers is one of the key elements in reforming the healthcare system. To define the optimal network of general hospitals, the allocation-location model was used, and the maximize attendance model was used as the central method. The chief purpose of maximize attendance model is to optimize the demand attendance with respect to distance and time spent getting to the point of demand. In the analysis of optimal locations and the number of Slovenian general hospitals, we used data on the locations of settlements with their number of inhabitants and data on the Slovenian road network, based on which we defined average travel speeds on the categorized road network. The hypothetical locations of general hospitals and the number of optimally located general hospitals that provide access to the nearest provider were determined in three different time intervals. We found that the same accessibility to hospital services as provided by the existing network of general hospitals can be achieved with only ten optimally located general hospitals within a 30-min time interval. This means that two general hospitals could be rationalized or reorganized, which would bring significant savings in the field of hospital activity, which creates a large loss in the health system in Slovenia.

Comparing Travel Distance to Care and Staging of Parotid Gland Malignancies in South Dakota and Surrounding States.

BACKGROUND: Parotid gland malignancies are difficult to characterize in terms of incidence and risk factors due to their relatively rare occurrence. Common cancers often present more aggressively in rural areas, albeit occurring less frequently. Some previous studies have found increased distance to care has been linked to more advanced malignancies. This study hypothesized decreased access to parotid gland malignancy specialists (otolaryngologists or dermatologists), evaluated as longer travel distances, would be associated with more advanced staging of parotid gland malignancies. METHODS: A retrospective chart review of the Sanford Health system electronic medical record in South Dakota and surrounding states from 2008-2018 was conducted to obtain data of parotid gland malignancies, respective staging, and patient home addresses to assess distance, both driving and straight-line, to the nearest parotid gland malignancy specialist, including outreach clinics. Travel distance was categorized (0-20 miles, 20-40 miles, and 40+ miles) and compared to categorized tumor stage (early 0/I, late II/III/IV) using a Fisher's Exact test. RESULTS: Overall, chart review yielded 134 patients with parotid gland malignancies from 2008-2018 in the Sanford Health system and associated data was gathered. The malignancies were categorically organized as 52.3 percent in early stage (0/I) vs. 47.7 percent in late (II/III/IV). When comparing parotid malignancy stage to driving distance, no significant association was found when outreach clinics were excluded (p=0.938) or included (p=0.327). When comparing parotid malignancy stage to straight-line distance, no significant association was found when outreach clinics were excluded (p=0.801) or included (p=0.874). CONCLUSIONS: Although no association was established between travel distance and parotid gland malignancy staging, further studies are needed to evaluate at population levels the incidence of parotid gland malignancies in rural communities and if there are specific risk factors in these areas for these malignancies which is currently unknown.

Gender Differences in Adventure Tourists Who Practice Kayaking in Extremadura.

Adventure tourism is among the sectors that has experienced the greatest growth in participation in recent years. In addition, it provides a unique opportunity to generate different benefits for rural populations as well as for the preservation of their environment. The objective of this study was to analyze gender differences in the profile, estimated expenditure, perception of economic impact and satisfaction of adventure tourists visiting the Valle del Jerte (Extremadura, Spain) for kayaking activities. The sample was composed of 511 tourists who kayaked in the Valle del Jerte. Gender differences were analyzed by the Mann-Whitney U test in continuous variables and Pearson's chi-square test in categorical variables. The predominant profile of the kayaking tourist is Spanish, married, employed, with university education, lives with their partner with children at home, chooses a rural home for accommodation, travels with companions, uses their own car for transportation, spends 550 euros on average, has good perceptions of the economic impact of the activity on the destination and is satisfied with the kayak service received. This information is relevant for public and private organizations as well as for the local community to be able to offer services more oriented to the tourist who engages in these activities, as well as to attract more tourists.

Health and Wellness Tourists' Motivation and Behavior Intention: The Role of Perceived Value.

In recent years, with the rapid change of people's health concept, health and wellness tourism has shown a vigorous development trend. However, existing literature has been lacking on travelers' behavioral intentions, influenced by their motivation in health and wellness tourism. To fill in this gap, we designed scales of tourists' behavioral intention and motivation in health and wellness tourism and investigated the aforementioned effects, with a sample of 493 visitors who have traveled in health and wellness tourism. Factor analysis and structural equation models were applied to explore the relations among motivation, perceived value, and behavioral intention in health and wellness tourism. The results indicate that health and wellness tourists' motivation significantly positively predicts their behavior intentions. Travelers' perceived value of health and wellness tourism significantly partially mediates the associations between their behavioral intention and escape motivation, attractive motivation, environmental motivation, as well as interpersonal motivation. No empirical evidence supports the mediating role of perceived value in the correlation between consumption motivation and behavioral intention. Health and wellness tourism industries are encouraged to meet the intrinsic motivation of travelers and make them perceive the value of this kind of tourism, which in turn promotes tourists' choice, evaluation, and satisfaction of health and wellness tourism.

Epidemic Diffusion Network of Spain: A Mobility Model to Characterize the Transmission Routes of Disease.

Human mobility drives the geographical diffusion of infectious diseases at different scales, but few studies focus on mobility itself. Using publicly available data from Spain, we define a Mobility Matrix that captures constant flows between provinces by using a distance-like measure of effective distance to build a network model with the 52 provinces and 135 relevant edges. Madrid, Valladolid and Araba/Álaba are the most relevant nodes in terms of degree and strength. The shortest routes (most likely path between two points) between all provinces are calculated. A total of 7 mobility communities were found with a modularity of 63%, and a relationship was established with a cumulative incidence of COVID-19 in 14 days (CI14) during the study period. In conclusion, mobility patterns in Spain are governed by a small number of high-flow connections that remain constant in time and seem unaffected by seasonality or restrictions. Most of the travels happen within communities that do not completely represent political borders, and a wave-like spreading pattern with occasional long-distance jumps (small-world properties) can be identified. This information can be incorporated into preparedness and response plans targeting locations that are at risk of contagion preventively, underscoring the importance of coordination between administrations when addressing health emergencies.

The Effect of Travel-Chain Complexity on Public Transport Travel Intention: A Mixed-Selection Model.

With urban expansion and traffic environment improvement, travel chains continue to grow, and the combination of travel purposes and modes becomes more complex. The promotion of mobility as a service (MaaS) has positive effects on facilitating the public transport traffic environment. However, public transport service optimization requires an accurate understanding of the travel environment, selection preferences, demand prediction, and systematic dispatch. Our study focused on the relationship between the trip-chain complexity environment and travel intention, combining the Theory of Planned Behavior (TPB) with travelers' preferences to construct a bounded rationality theory. First, this study used K-means clustering to transform the characteristics of the travel trip chain into the complexity of the trip chain. Then, based on the partial least squares structural equation model (PLS-SEM) and the generalized ordered Logit model, a mixed-selection model was established. Finally, the travel intention of PLS-SEM was compared with the travel sharing rate of the generalized ordered Logit model to determine the trip-chain complexity effects for different public transport modes. The results showed that (1) the proposed model, which transformed travel-chain characteristics into travel-chain complexity using K-means clustering and adopted a bounded rationality perspective, had the best fit and was the most effective with comparison to the previous prediction approaches. (2) Compared with service quality, trip-chain complexity negatively affected the intention of using public transport in a wider range of indirect paths. Gender, vehicle ownership, and with children/without children had significant moderating effects on certain paths of the SEM. (3) The research results obtained by PLS-SEM indicated that when travelers were more willing to travel by subway, the subway travel sharing rate corresponding to the generalized ordered Logit model was only 21.25-43.49%. Similarly, the sharing rate of travel by bus was only 32-44% as travelers were more willing to travel by bus obtained from PLS-SEM. Therefore, it is necessary to combine the qualitative results of PLS-SEM with the quantitative results of generalized ordered Logit. Moreover, when service quality, preferences, and subjective norms were based on the mean value, with each increase in trip-chain complexity, the subway travel sharing rate was reduced by 3.89-8.30%, while the bus travel sharing rate was reduced by 4.63-6.03%.

Reducing the burden of TB among migrants to low TB incidence countries.

BACKGROUND: International migrants to low TB incidence countries are disproportionately affected by TB compared to the native population: migrants are at increased risk for TB transmission and TB disease due to a variety of personal, environmental and socio-economic determinants experienced during the four phases of migration (pre-departure, transit, arrival and early settlement, return travel).OBJECTIVE: To provide an up-to-date overview of the determinants that drive the TB burden among migrants, as well as effective and feasible interventions to address this for each migration phase.METHODS: We conducted a literature review by searching PubMed and the grey literature for articles and reports on determinants and interventions addressing migrant health and TB.RESULTS: Lowering the risk of TB transmission and TB disease among migrants would be most effective by improving the socio-economic position of migrants pre-, during and after migration, ensuring universal health coverage, and providing tailored and migrant-sensitive care and prevention activities.CONCLUSION: In addition to migrant-sensitive health services and cross-border collaboration between low TB incidence countries, there is a need for international financial and technical support for endemic countries.

Topics and destinations in comments on YouTube tourism videos during the Covid-19 pandemic.

This study examines the comments posted on tourism-related YouTube videos during the Covid-19 pandemic to establish sustainable development strategies in destinations. Its objectives were: (i) to identify the topics of discussion, (ii) to establish the perceptions of tourism in a pandemic crisis, and (iii) to identify the destinations mentioned. The data was collected between January and May 2020. 39,225 comments were extracted in different languages and globally through the YouTube API. The data processing was carried out using the word association technique. The results show that the most discussed topics were: "people," "country," "tourist," "place," "tourism," "see," "visit," "travel," "covid-19," "life," and "live," which are the focus of the comments made on the perceptions found and represent the attraction factors shown by the videos and the emotions perceived in the comments. The findings show that users' perceptions are related to risks since the "Covid-19" pandemic is associated with the impact on tourism, people, destinations, and affected countries. The destinations in the comments were: India, Nepal, China, Kerala, France, Thailand, and Europe. The research has theoretical implications concerning tourists' perceptions of destinations since new perceptions associated with destinations during the pandemic are shown. Such concerns involve tourist safety and work at the destinations. This research has practical implications since, during the pandemic, companies can develop prevention plans. Also, governments could implement sustainable development plans that contain measures so that tourists can make their trips during a pandemic.

Personality variation is eroded by simple social behaviours in collective foragers.

The movement of groups can be heavily influenced by 'leader' individuals who differ from the others in some way. A major source of differences between individuals is the repeatability and consistency of their behaviour, commonly considered as their 'personality', which can influence both position within a group as well as the tendency to lead. However, links between personality and behaviour may also depend upon the immediate social environment of the individual; individuals who behave consistently in one way when alone may not express the same behaviour socially, when they may be conforming with the behaviour of others. Experimental evidence shows that personality differences can be eroded in social situations, but there is currently a lack of theory to identify the conditions where we would expect personality to be suppressed. Here, we develop a simple individual-based framework considering a small group of individuals with differing tendencies to perform risky behaviours when travelling away from a safe home site towards a foraging site, and compare the group behaviours when the individuals follow differing rules for aggregation behaviour determining how much attention they pay to the actions of their fellow group-members. We find that if individuals pay attention to the other members of the group, the group will tend to remain at the safe site for longer, but then travel faster towards the foraging site. This demonstrates that simple social behaviours can result in the repression of consistent inter-individual differences in behaviour, giving the first theoretical consideration of the social mechanisms behind personality suppression.

Identification of social groups and waiting pedestrians at railway platforms using trajectory data.

To investigate the impact of social groups on waiting behaviour of passengers at railway platforms a method to identify social groups through the monitoring of distances between pedestrians and the stability of those distances over time is introduced. The method allows the recognition of groups using trajectories only and thus opens up the possibility of studying crowds in public places without constrains caused by privacy protection issues. Trajectories from a railway platform in Switzerland were used to analyse the waiting behaviour of passengers in dependence of waiting time as well as the size of social groups. The analysis of the trajectories shows that the portion of passengers travelling in groups reaches up to 10% during the week and increases to 20% on the weekends. 60% of the groups were pairs, larger groups were less frequent. With increasing group size, the mean speed of the members decreases. Individuals and pairs often choose waiting spots at the sides of the stairs and in vicinity of obstacles, while larger groups wait close to the platform entries. The results indicate that passengers choose waiting places according to the following criteria and ranking: shortest ways, direction of the next intended action, undisturbed places and ensured communication. While individual passengers often wait in places where they are undisturbed and do not hinder others, the dominating comfort criterion for groups is to ensure communication. The results regarding space requirements of waiting passengers could be used for different applications. E.g. to enhance the level of service concept assessing the comfort of different types of users, to avoid temporary bottlenecks to improve the boarding and alighting process or to increase the robustness of the performance of railway platforms during peak loads by optimising the pedestrian distribution.

Contagion of coronavirus disease-the first family cluster of Pakistan: a case series.

Coronavirus Disease has resulted in public health crisis all over the world. We describe the case series of a family, who travelled together to a mass gathering in Iraq, toured Syria, Lebanon, and Doha and returned to Karachi. The data describes the demographic and clinical features of these six members. There were three males and three females. One developed severe disease and died. Incubation period was between 8-14 days. Four patients were symptomatic, had diabetes mellitus and hypertension; and presented with fever. They also had bilateral airspace opacifications on chest X-ray. Our study describes familial clustering of SARS-CoV-2 and its person-to-person transmission.

Hospital Access Patterns of Children With Technology Dependence.

OBJECTIVES: We studied hospital utilization patterns among children with technology dependence (CTD). We hypothesized that increasing pediatric healthcare concentration requires those caring for CTD to selectively navigate healthcare systems and travel greater distances for care. METHODS: Using 2017 all-encounter datasets from 6 US states, we identified CTD visits defined by presence of a tracheostomy, gastrostomy, or intraventricular shunt. We calculated pediatric Hospital Capability Indices for hospitals and mapped distances between patient residence, nearest hospital, and encounter facility. RESULTS: Thirty-five percent of hospitals never saw CTD. Of 37 108 CTD encounters within the remaining 543 hospitals, most emergency visits (70.0%) and inpatient admissions (85.3%) occurred within 34 (6.3%) high capability centers. Only 11.7% of visits were to the closest facility, as CTD traveled almost 4 times further to receive care. When CTD bypassed nearer facilities, they were 10 times more likely to travel to high-capability centers (95% confidence interval: 9.43-10.8), but even those accessing low-capability facilities bypassed less capable, geographically closer hospitals. Transfer was more likely in nearest and low-capability facility encounters. CTD with Medicaid insurance, Black race, or from lower socioeconomic communities had lower odds of encounters at high-capability centers and of bypassing a closer institution than those with white race, private insurance, or from advantaged communities. CONCLUSIONS: Children with technology dependence routinely bypass closer hospitals to access care in facilities with higher pediatric capability. This access behavior leaves many hospitals unfamiliar with CTD, which results in greater travel but less transfers and may be influenced by sociodemographic factors.

Mpox outbreak in the Netherlands, 2022: public health response, characteristics of the first 1,000 cases and protection of the first-generation smallpox vaccine.

In early May 2022, a global outbreak of mpox started among persons without travel history to regions known to be enzootic for monkeypox virus (MPXV). On 8 August 2022, the Netherlands reported its 1,000th mpox case, representing a cumulative incidence of 55 per million population, one of the highest cumulative incidences worldwide. We describe characteristics of the first 1,000 mpox cases in the Netherlands, reported between 20 May and 8 August 2022, within the context of the public health response. These cases were predominantly men who have sex with men aged 31-45 years. The vast majority of infections were acquired through sexual contact with casual partners in private or recreational settings including LGBTQIA+ venues in the Netherlands. This indicates that, although some larger upsurges occurred from point-source and/or travel-related events, the outbreak was mainly characterised by sustained transmission within the Netherlands. In addition, we estimated the protective effect of first-generation smallpox vaccine against moderate/severe mpox and found a vaccine effectiveness of 58% (95% CI: 17-78%), suggesting moderate protection against moderate/severe mpox symptoms on top of any possible protection by this vaccine against MPXV infection and disease. Communication with and supporting the at-risk population in following mitigation measures remains essential.

Active travel to school: a longitudinal millennium cohort study of schooling outcomes.

OBJECTIVES: Assess longitudinal associations between active travel during the school commute and later educational outcomes. SETTING: England, Wales and Northern Ireland. PARTICIPANTS: 6778 children, surveyed at ages 7, 11, 14 and 17. PRIMARY AND SECONDARY OUTCOMES: School-leaver General Certificate of Secondary Education exam scores summed to provide a single measure of educational success. RESULTS: Controlling a range of sociodemographic and health variables, using active versus passive travel modes during a child's commute to school during earlier years predicted differences in school-leaver exam performance at age 16. These effects were mediated through changes in self-esteem, emotional difficulties and behavioural difficulties. Examples include: being driven to school at 11 was associated with improved exam performance at 16 mediated through enhanced self-esteem at 14 (ab=0.08, 95% CI=0.01 to 0.20, p=0.05) and cycling at 14 was associated with better exam scores at 16 mediated through reduced emotional difficulty at 16 (ab=0.10, 95% CI=0.01 to 0.30, p=0.05). The relationship between travel mode and exam performance was moderated by household income quintile, most notably with poorer exam performance seen in high-income children who were driven to school. Importantly, although our model predicted 21% of variance in exam performance, removing travel mode barely reduced its ability to predict exam scores (ΔR 2=-0.005, F 20,6469 = 2.50, p<0.001). CONCLUSION: There are differences in school-leaver exam performance linked to travel mode choices earlier in the school career, but these differences are extremely small. There appears to be no realistic educational disadvantage from any given travel mode, strengthening the case for cleaner, healthier modes to become the default.

Associations of parents' and adolescents' active travel behavior across various destinations - a sex/gender analysis.

BACKGROUND: Active travel behavior such as walking and cycling is associated with several health benefits. Especially the family environment seems to be important for active travel in children and adolescents. Currently, little is known regarding travel behavior in leisure time and associations of travel behavior within parent-adolescent dyads. METHODS: The present analysis is based on the German ARRIVE study (Active tRavel behavioR in the famIly enVironmEnt), which incorporated a large scale, representative cross-sectional online survey including 517 parent-child dyads consisting of adolescents (N = 517; boys = 263, girls = 254) aged 11-15 years and one of their parents (N = 517; fathers = 259, mothers = 258). Based on that survey which took place in June 2021 (during the COVID-19 pandemic), we calculated the prevalence of active travel to four commonly visited destinations (school/work, friends/relatives, shopping stores and recreational activities) using an adapted version of the travel to school questionnaire by Segura-Diaz JM, Rojas-Jimenez A, Barranco-Ruiz Y, Murillo-Pardo B, Saucedo-Araujo RG, Aranda-Balboa MJ, et al. (Int J Environ Res Public Health 17(14), 2020). In addition, we investigated the associations between parents' and adolescents' travel behavior using scores for school/work, leisure time (friends/relatives, shopping stores and recreational activities) and overall (school/work and leisure time). RESULTS: Across all destinations, prevalence of active travel in adolescents (63.08%) was higher than in parents (29.21%). Active travel to school (47.33%) as well as to work (20.43%) indicated the lowest prevalence. Linear regression models revealed significant associations in overall active travel between mothers and adolescents (girls: ß = 0.308, p < 0.001; boys: ß = 0.302, p = 0.001) and in leisure time active travel behavior between mothers and daughters (ß = 0.316, p < 0.001). Related to school/work active travel there were no associations between parents and adolescents. CONCLUSION: The associations between adolescents' and parents' travel behavior differ depending on gender: they are solely seen in mother-adolescents dyads. Furthermore, our findings conclude that travel is a routine and independent of the destination.

Mobility and ART retention among men in Malawi: a mixed-methods study.

INTRODUCTION: Mobility is associated with worse outcomes across the HIV treatment cascade, especially among men. However, little is known about the mechanisms that link mobility and poor HIV outcomes and what types of mobility most increase the risk of treatment interruption among men in southern Africa. METHODS: From August 2021 to January 2022, we conducted a mixed-methods study with men living with HIV (MLHIV) but not currently receiving antiretroviral therapy (ART) in Malawi. Data collection was embedded within two larger trials (ENGAGE and IDEaL trials). We analysed baseline survey data of 223 men enrolled in the trials who reported being mobile (defined as spending ≥14 nights away from home in the past 12 months) using descriptive statistics and negative binomial regressions. We then recruited 32 men for in-depth interviews regarding their travel experiences and ART utilization. We analysed qualitative data using constant comparative methods. RESULTS: Survey data showed that 34% of men with treatment interruptions were mobile, with a median of 60 nights away from home in the past 12 months; 69% of trips were for income generation. More nights away from home in the past 12 months and having fewer household assets were associated with longer periods out of care. In interviews, men reported that travel was often unplanned, and men were highly vulnerable to exploitive employer demands, which led to missed appointments and ART interruption. Men made major efforts to stay in care but were often unable to access care on short notice, were denied ART refills at non-home facilities and/or were treated poorly by providers, creating substantial barriers to remaining in and returning to care. Men desired additional multi-month dispensing (MMD), the ability to refill treatment at any facility in Malawi, and streamlined pre-travel refills at home facilities. CONCLUSIONS: Men prioritize ART and struggle with the trade-offs between their own health and providing for their families. Mobility is an essential livelihood strategy for MLHIV in Malawi, but it creates conflict with ART retention, largely due to inflexible health systems. Targeted counselling and peer support, access to ART services anywhere in the country, and MMD may improve outcomes for mobile men.

Dynamic sub-route-based self-adaptive beam search Q-learning algorithm for traveling salesman problem.

In this paper, a dynamic sub-route-based self-adaptive beam search Q-learning (DSRABSQL) algorithm is proposed that provides a reinforcement learning (RL) framework combined with local search to solve the traveling salesman problem (TSP). DSRABSQL builds upon the Q-learning (QL) algorithm. Considering its problems of slow convergence and low accuracy, four strategies within the QL framework are designed first: the weighting function-based reward matrix, the power function-based initial Q-table, a self-adaptive ε-beam search strategy, and a new Q-value update formula. Then, a self-adaptive beam search Q-learning (ABSQL) algorithm is designed. To solve the problem that the sub-route is not fully optimized in the ABSQL algorithm, a dynamic sub-route optimization strategy is introduced outside the QL framework, and then the DSRABSQL algorithm is designed. Experiments are conducted to compare QL, ABSQL, DSRABSQL, our previously proposed variable neighborhood discrete whale optimization algorithm, and two advanced reinforcement learning algorithms. The experimental results show that DSRABSQL significantly outperforms the other algorithms. In addition, two groups of algorithms are designed based on the QL and DSRABSQL algorithms to test the effectiveness of the five strategies. From the experimental results, it can be found that the dynamic sub-route optimization strategy and self-adaptive ε-beam search strategy contribute the most for small-, medium-, and large-scale instances. At the same time, collaboration exists between the four strategies within the QL framework, which increases with the expansion of the instance scale.