IoT platforms assessment methodology for COVID-19 vaccine logistics and transportation: a multi-methods decision making model
Overview3:58CCAI
paperi.ai
0:00 / 0:00
Yasir Khalif Ali, Habib Ullah Khan
A vaccine can be perfectly made and still fail before reaching a patient. Its safety may depend on an invisible journey: keeping it cold, watched, and accounted for every step of the way.
The supply chain management (SCM) of COVID-19 vaccine is the most daunting task for logistics and supply managers due to temperature sensitivity and complex logistics process. Therefore, several technologies have been applied but the complexity of COVID-19 vaccine makes the Internet of Things (IoT) a strong use case due to its multiple features support like excursion notification, data sharing, connectivity management, secure shipping, real-time tracking and monitoring etc. All these features can only feasible through choosing and deploying the right IoT platform. However, selection of right IoT platform is also a major concern due to lack of experience and technical knowledge of supply chain managers and diversified landscape of IoT platforms. Therefore, we introduce a decision making model for evaluation and decision making of IoT platforms that fits for logistics and transportation (L&T) process of COVID-19 vaccine. This study initially identifies the major challenges addressed during the SCM of COVID-19 vaccine and then provides reasonable solution by presenting the assessment model for selection of rational IoT platform. The proposed model applies hybrid Multi Criteria Decision Making (MCDM) approach for evaluation. It also adopts Estimation-Talk-Estimation (ETE) approach for response collection during the survey. As, this is first kind of model so the proposed model is validated and tested by conducting a survey with experts. The results of the proposed decision making model are also verified by Simple Additive Weighting (SAW) technique which indicates higher results accuracy and reliability of the proposed model. Similarly, the proposed model yields the best possible results and it can be judged by the precision, accuracy and recall values i.e. 93%, 93% and 94% respectively. The survey-based testing also suggests that this model can be adopted in practical scenarios to deal with complexities which may arise during the decision making of IoT platform for COVID-19 SCM process.
Transcript
A vaccine can be perfectly made and still fail before reaching a patient. Its safety may depend on an invisible journey: keeping it cold, watched, and accounted for every step of the way. During the COVID-19 pandemic, the main challenge was to keep the integrity of the vaccine.
COVID-19 vaccines are temperature sensitive and require careful monitoring during shipping. The vaccine’s integrity depends on maintaining a cold chain, because COVID-19 vaccines are temperature sensitive and require careful monitoring during shipping.
That cold-chain process must extend from manufacturing to the administration site, and maintaining it correctly is essential for achieving vaccine efficacy. Storage itself is challenging: most vaccines need two to eight degrees, while some coronavirus vaccines require temperatures as low as minus seventy degrees Celsius.
That is why connected devices matter: they can support alerts when conditions change, share data, manage connections, secure shipments, and track and monitor them in real time. But those capabilities only work if the right digital platform is chosen, and supply managers may lack the experience or technical knowledge to make that choice.
IoT platforms offer multiple features, but using those features effectively requires choosing and deploying the right platform for the task. Because platform selection is a concern, the useful choice is the one that fits logistics and transportation for COVID-19 vaccine delivery.
The framework focuses on evaluating, ranking, and selecting a connected technology platform for the logistics and transportation of COVID-19 vaccines. It combines two decision-making approaches to assess the platforms. After the experts’ responses were collected, the result was a table matching the platforms with the features they offered.
That table became the decision matrix used in the next step. The criteria were then given different weights, and the platforms were evaluated and prioritized. For choosing an internet-of-things platform, the priorities are not equal: the ability to grow as demand increases receives the strongest emphasis, while the remaining features receive noticeably smaller weights.
That makes future growth the central concern in the later platform ranking. Using the study’s criteria, Microsoft Azure was judged the best choice among the selected connected platforms. The study compared all selected IoT platforms, and that comparison supported identifying Microsoft Azure as the best choice under the proposed criteria.
A second approach produced the same leading platform: Microsoft Azure had the highest ranking score among the selected platforms. The researchers therefore concluded that the numerical results were accurate and consistent, and that the decision model was validated. The results give supply managers a clearer understanding of which platform features matter and how important they are relative to one another.
The framework is intended to cover the different dimensions of connected platforms, so managers do not have to choose features without guidance. The selected platform can manage connected sensors and provide location information, allowing cargo, vehicles, or other assets to be monitored across wide distances and difficult environments.
It also provides fleet management, including information about vehicles, drivers, and routes. The proposed method produces promising results and covers the features used in the decision, but limitations may still affect how practical and stable it is.
The study offers a structured way to choose the digital platform that best supports vaccine transport. In its comparison, Microsoft Azure ranked highest and was also supported by a separate check.
A derivative work by Paperi · AI-generated script, voice and captions
· pages and figures unaltered
Made with Paperi.
Drop in a research PDF — get a narrated video walkthrough like this one,
with highlights that follow the narration. Free to start.
Samuel Sokota, Eugene Vinitsky, Hengyuan Hu, Zhiyuan Fan, J. Zico Kolter, Gabriele Farina
For years, computers could master games where everything was visible, but hidden information stopped them cold. Then one system beat Stratego’s most decorated human player by a margin never seen at the highest level.Stratego has enormous hidden information, and years of expensive AI research still could not beat its best humans. This paper introduces an approach that wins decisively, and does so with only a few thousand dollars of training.
Imagine living with a threat that feels frightening, yet still seems unlikely to happen to you. Among Chinese university students, fear of cyber fraud was common, while expecting to be defrauded was not.Here’s the paper’s central tension: only ten percent of students thought cyber fraud was likely to happen to them, but about half said they felt afraid of it. Fear and perceived risk are not the same thing.
Finding a new medicine can demand enormous effort and resources. This paper explores whether a machine that reads molecular strings can create promising new drug structures instead of searching only through existing ones.What if designing a drug molecule could look less like searching a massive catalog and more like generating a new sentence? This paper explores how AI models use SMILES strings to create and optimize candidate molecules.