Using AI and ML to predict shipment times of therapeutics, diagnostics and vaccines in e-pharmacy supply chains during COVID-19 pandemic

PurposeThis paper aims to address the pressing problem of prediction concerning shipment times of therapeutics, diagnostics and vaccines during the ongoing COVID-19 pandemic using a novel artificial intelligence (AI) and machine learning (ML) approach.Design/methodology/approachThe present study used organic real-world therapeutic supplies data of over 3 million shipments collected during the COVID-19 pandemic through a large real-world e-pharmacy. The researchers built various ML multiclass classification models, namely, random forest (RF), extra trees (XRT), decision tree (DT), multilayer perceptron (MLP), XGBoost (XGB), CatBoost (CB), linear stochastic gradient descent (SGD) and the linear Naïve Bayes (NB) and trained them on striped datasets of (source, destination, shipper) triplets. The study stacked the base models and built stacked meta-models. Subsequently, the researchers built a model zoo with a combination of the base models and stacked meta-models trained on these striped datasets. The study used 10-fold cross-validation (CV) for performance evaluation.FindingsThe findings reveal that the turn-around-time provided by therapeutic supply logistics providers is only 62.91% accurate when compared to reality. In contrast, the solution provided in this study is up to 93.5% accurate compared to reality, resulting in up to 48.62% improvement, with a clear trend of more historic data and better performance growing each week.Research limitations/implicationsThe implication of the study has shown the efficacy of ML model zoo with a combination of base models and stacked meta-models trained on striped datasets of (source, destination and shipper) triplets for predicting the shipment times of therapeutics, diagnostics and vaccines in the e-pharmacy supply chain.Originality/valueThe novelty of the study is on the real-world e-pharmacy supply chain under post-COVID-19 lockdown conditions and has come up with a novel ML ensemble stacking based model zoo to make predictions on the shipment times of therapeutics. Through this work, it is assumed that there will be greater adoption of AI and ML techniques in shipment time prediction of therapeutics in the logistics industry in the pandemic situations.

The Precautionary Principles of the Potential Risks of Compound Events in Danish Municipalities

The risk of compound events describes potential weather and climate events in which the combination of multiple drivers and hazards consolidate, resulting in extreme socio-economic impacts. Compound events affecting exposed societies can therefore be deemed a crucial security risk. Designing appropriate preparation proves difficult, as compound events are rarely documented. This paper explores the understanding and practices of climate risk management related to compound events in specific Danish municipalities vulnerable to flood hazards (i.e., Odense, Hvidovre, and Vejle). These practices illuminate that different understandings of compound events steer risk attitudes and consequently decisions regarding the use of different policy instruments. Through expert interviews supported by policy documents, we found that the municipalities understand compound events as either a condition or situation and develop precautionary strategies to some extent. Depending on their respective geographical surroundings, they observe compound events either as no clear trend (Odense), a trend to be critically watched (Hvidovre), or already as a partial reality (Vejle). They perceive flood drivers and their combinations as major physical risks to which they adopt different tailor-made solutions. By choosing a bottom-up approach focusing on local governance structures, it demonstrated that the mismatch between responsibility and capacity and the ongoing separation of services related to climatic risks in the Danish municipality context need to be critically considered. The findings highlight that the complex challenge of compound events cannot be solved by one (scientific) discipline alone. Thus, the study advocates a broader inclusion of scientific practices and increased emphasis on local focus within compound event research to foster creative thinking, better preparation, and subsequently more effective management of their risks.

ONLINE-TICS: Internet-Delivered Behavioral Treatment for Patients with Chronic Tic Disorders

Comprehensive Behavioral Intervention for Tics (CBIT) is considered a first-line therapy for tics. However, availability of CBIT is extremely limited due to a lack of qualified therapists. This study is a multicenter (n = 5), randomized, controlled, observer-blind trial including 161 adult patients with chronic tic disorders (CTD) to provide data on efficacy and safety of an internet-delivered, completely therapist-independent CBIT intervention (iCBIT Minddistrict®) in the treatment of tics compared to placebo and face-to-face (f2f) CBIT. Using a linear mixed model with the change to baseline of Yale Global Tic Severity Scale-Total Tic Score (YGTSS-TTS) as a dependent variable, we found a clear trend towards significance for superiority of iCBIT (n = 67) over placebo (n = 70) (−1.28 (−2.58; 0.01); p = 0.053). In addition, the difference in tic reduction between iCBIT and placebo increased, resulting in a significant difference 3 (−2.25 (−3.75; −0.75), p = 0.003) and 6 months (−2.71 (−4.27; −1.16), p < 0.001) after the end of treatment. Key secondary analysis indicated non-inferiority of iCBIT in comparison to f2f CBIT (n = 24). No safety signals were detected. Although the primary endpoint was narrowly missed, it is strongly suggested that iCBIT is superior compared to placebo. Remarkably, treatment effects of iCBIT even increased over time.

Long-Term Ice Conditions in Yingkou, a Coastal Region Northeast of the Bohai Sea, between 1951/1952 and 2017/2018: Modeling and Observations

Bohai Sea ice creates obstacles for maritime navigation and offshore activities. A better understanding of ice conditions is valuable for sea-ice management. The evolution of 67 years of seasonal ice thickness in a coastal region (Yingkou) in the Northeast Bohai Sea was simulated by using a snow/ice thermodynamic model, using local weather-station data. The model was first validated by using seasonal ice observations from field campaigns and a coastal radar (the season of 2017/2018). The model simulated seasonal ice evolution well, particularly ice growth. We found that the winter seasonal mean air temperature in Yingkou increased by 0.33 °C/decade slightly higher than air temperature increase (0.27 °C/decade) around Bohai Sea. The decreasing wind-speed trend (0.05 m/s perdecade) was a lot weaker than that averaged (0.3 m/s per decade) between the early 1970s and 2010s around the entire Bohai Sea. The multi-decadal ice-mass balance revealed decreasing trends of the maximum and average ice thickness of 2.6 and 0.8 cm/decade, respectively. The length of the ice season was shortened by 3.7 days/decade, and ice breakup dates were advanced by 2.3 days/decade. All trends were statistically significant. The modeled seasonal maximum ice thickness is highly correlated (0.83, p < 0.001) with the Bohai Sea Ice Index (BoSI) used to quantify the severity of the Bohai Sea ice condition. The freezing-up date, however, showed a large interannual variation without a clear trend. The simulations indicated that Bohai ice thickness has grown continuously thinner since 1951/1952. The time to reach 0.15 m level ice was delayed from 3 January to 21 January, and the ending time advanced from 6 March to 19 February. There was a significant weakening of ice conditions in the 1990s, followed by some recovery in 2000s. The relationship between large-scale climate indices and ice condition suggested that the AO and NAO are strongly correlated with interannual changes in sea-ice thickness in the Yingkou region.

Investigation of the current usage of BIM capabilities by large-sized building contractors in Kenya based on theory of innovation diffusion

Purpose This study aims to focus on the four user characteristics of innovation diffusion (availability, observability and trialability [AOT], simplicity, relative advantage [RA] and interoperability) to observe their influence on building information modelling (BIM) usage. This study focuses on the Kenyan construction industry, specifically the building contractors. Design/methodology/approach This study uses purposive sampling and specifically focusses on active construction sites that met requirements needed for BIM usage to thrive. Data was collected manually using questionnaires (N = 62). Findings This paper contributes to the analysis of the current state of BIM usage by the Kenyan construction industry specifically among building contractors and confirms that Kenya is at the early majority adopters’ stage of diffusion characterised by low BIM usage. In terms of correlation, this study found out that AOT had a strong positive correlation with usage, RA had a moderate positive correlation with usage, simplicity had a weak positive correlation with usage and interoperability had no correlation with usage. Practical implications This study gives a clear trend on BIM usage among building contractors to assist potential BIM users make informed decision. The recommendations in this study can be adopted by any late adopter jurisdiction whose structure of the construction industry is similar to Kenya’s. Originality/value This paper highlights variables that enable or subdue BIM usage. It goes further to localise and contextualise the barriers for deeper understanding of what makes these barriers be major hindrances towards BIM usage and giving practical solutions to these barriers.

Controlling Agents by Constrained Policy Updates

Learning the optimal behavior is the ultimate goal in reinforcement learning. This can be achieved by many different approaches, the most successful of them are policy gradient methods. However, they can suffer from undesirably large updates of policies, leading to poor performance. In recent years there has been a clear trend toward designing more reliable algorithms. This paper addresses to examine different restriction strategies applied to the widely used Proximal Policy Optimization (PPO-Clip) technique. We also question whether the analyzed methods are able to adapt not only to low-dimensional tasks but also to complex, high-dimensional problems in control and robotic domains. The analysis of the learned behavior shows that these methods can lead to better performance compared to the original PPO-Clip algorithm, moreover, they are also able to achieve complex behavior and policies in high-dimensional environments.

Antibody-free profiling of transcription factor occupancy during early embryogenesis by FitCUT&RUN

Key transcription factors (TFs) play critical roles in zygotic genome activation (ZGA) during early embryogenesis, while genome-wide occupancies of only a few factors have been profiled during ZGA due to the limitation of cell numbers or the lack of high-quality antibodies. Here, we present FitCUT&RUN, a modified CUT&RUN method, in which an Fc fragment of immunoglobulin G is used for tagging, to profile TF occupancy in an antibody-free manner and demonstrate its reliability and robustness using as few as five thousand K562 cells. We applied FitCUT&RUN to zebrafish undergoing embryogenesis to generate reliable occupancy profiles of three known activators of zebrafish ZGA: Nanog, Pou5f3 and Sox19b. By profiling the time-series occupancy of Nanog during zebrafish ZGA, we observed a clear trend toward a gradual increase in Nanog occupancy and found that Nanog occupancy prior to the major phase of ZGA is critical for the activation of a significant proportion of early transcribed genes. Our results further suggested that the sequential binding of Nanog may be controlled by replication timing and the presence of Nanog motifs.

Analysis on Spatio-Temporal Characteristics and Influencing Factors of Industrial Green Innovation Efficiency—From the Perspective of Innovation Value Chain

Green innovation has become an important combination of high-quality economic growth and ecological sustainability. In this paper, the super-efficiency network SBM model was used to measure the two-stage green innovation efficiency of the industrial technology research and development (R&D) stage and achievement transformation stage in China (30 provinces and cities) from 2009 to 2019. The results show the following points. Firstly, in terms of temporal series, the efficiency of technology R&D and achievement transformation has experienced three stages of “upward-declining-revitalized period”. Secondly, in terms of spatial trend, the industrial green innovation efficiency gradually increases from northwest to southeast. The high-efficiency areas are still concentrated in the eastern coastal region, with a clear trend towards balanced development in the central and western regions. Finally, openness, industrial structure, government technical expenditures, enterprise scale, and environmental regulation all have different degrees of impact on the efficiency of green innovation in the two stages. Based on the above, this paper is helpful for the government to formulate laws and regulations and coordinate the level of regional economic development and clarify the spatio-temporal characteristics and influencing factors of the efficiency of green innovation.

Searching for a fingerprint of global warming in the Asian summer monsoon

This study investigates possible trends in several large scale indices that describe the Asian summer monsoon. Results from recent atmospheric general circulation experiments are used to provide clues as to how the monsoon might be changing due to the effects of global warming. Interestingly, this study has found that the large-scale wind shear monsoon indices have been decreasing at a rate of 0.1-0.3% per year (based on NCEP/CAR reanalysis 1958-98) in quantitative agreement with recent results from doubled CO2 simulations made using several state-of-the-art climate models. Nevertheless, despite the weakening of the monsoon circulation, all-India rainfall shows no clear trend in either the model results or in the observation reanalysis from 1958-98. Multiple regression is used to separate out the "dynamical" contribution from the observed all-India rainfall index, and a clear increasing trend then emerges in the "non-dynamical" residual. A simple dimensionless Multivariate Monsoon Index (MMI) is proposed that could be of use in monitoring global warming changes in the monsoon.

On measures to prevent theft of cell phones

Despite the fact that in recent years a number of committed crimes in Russia has decreased in general due to the taken measures, crimes against property are still prevalent within the overall structures of crime and considered a major problem. Theft of cell phones has a special place in this structure. It is worth noting that although the cell phones have acquired many additional functions, in recent years they are no longer the luxury goods and are in the category of everyday things that are now necessary (and available) for almost all classes of citizens. An analysis of the market for cell phone sales in Russia shows that over the last years the number of cell phones has increased significantly, while in large Russian cities their number equaled the number of residents (which means 100 phones per 100 inhabitants). The author, on the basis of statistics, points out a clear trend of continued growth in sales of smartphones, as well as an expansion of the market for expensive devices. Based on data on crime situation generally the article further shows that theft make up more than half of all crimes committed. This number, of course, includes theft of cell phones, but due to the lack of data on this specific type of theft, it is difficult to determine where they stand in the overall picture. The author provides a classification of this type of crime according to the place and the ways these crimes are committed, illustrating them with the materials of particular criminal cases, and gives practical recommendations to mobile phone users that will reduce the risk of smartphone theft. Having studied the domestic and foreign (UK, USA) experience in the field of combating such crimes, the author examines a number of measures aimed at preventing cell phone theft. The author believes that the solution to these problems in particular may be the adoption of a law on the state database of mobile phones, as has already been done in some foreign countries.