Sustainable Operations and Computers最新文献

The heavy reliance of the transportation and power generation sector on fossil fuels is seriously impacting the environment. Transitioning towards more sustainable transportation modes is necessary to reduce this dependency on fossil fuels. Even though shifting toward electric vehicles (EVs) can reduce harmful emissions, due to the lack of adequate charging infrastructures, underdeveloped power transmission systems, and increased cost of power generation, it is difficult for a developing country to adopt and rely heavily on EVs. However, developing countries like Bangladesh can adopt a different strategy to address this issue. Harmful emission reduction is also possible by transitioning from conventional internal combustion engine (ICE) vehicles to hybrid electric vehicles (HEVs). The drivers that can promote the expansion of HEV adoption have not been extensively studied to date, which inspired the proposed study. This study explores the drivers for the growth of HEV adoption in emerging economies. First, the study identifies seventeen drivers from the literature review and expert feedback. Then the identified drivers were assessed using the Bayesian Best-Worst method (BWM). The study findings indicate that no requirement for a charging station, incentivizing consumers through policy measures, and enhanced fuel efficiency are the top three drivers influencing the growth of HEV adoption in developing or emerging economies. This study can help the decision-makers and end users in developing counties to gradually shift towards a low-carbon emission-based economy and ensure a greener and more sustainable future.

In agriculture, one of the most challenging tasks is the early detection of plant diseases. It is essential to identify diseases early in order to boost agricultural productivity. This problem has been solved with machine learning and deep learning techniques using an automated method for detecting plant diseases on large crop farms which is beneficial because it reduces monitoring time. In this paper, we used the dataset "Plant Village" with 17 basic diseases, with a display of four bacterial diseases, two viral illnesses, two mould illnesses, and one mite-related disease. A total of 12 crop species are also shown with images of unaffected leaves. The machine learning approaches viz support vector machines (SVMs), gray-level co-occurrence matrices (GLCMs), and convolutional neural networks (CNNs) are used for the development of prediction models. With the development of backpropagation ANNs, artificial intelligence for classification has also evolved. A K-mean clustering operation is also used to detect disease based on the real-time leaf images collected.

Solar energy is the energy discharged by the sun in the form of radiation of light which is then utilized by human beings using a diversity of method such as photovoltaic cells. It is unlimited source of energy such as solar energy does not belongs to anybody and so it is at no cost. The quantity of solar energy acknowledged by the world was considered to be 3000–50,000 EJ, which is much superior to the total world energy utilization of 600 EJ. Maximum Power Point Tracking (MPPT) can be integrated in controlling charge and further used to take out highest extractable and obtainable output from photovoltaic cells depending on few circumstances. The particular input for Photovoltaic module is capable of generating highest possible output power is called MPP (Maximum power point) or highest voltage. Maximum power changes with Sun's energy parameter of required temperature of PV module. Along with dissimilar tracking technique with P-O methods etc. Furthermore, several components were used to compute input parameters which had their own uncertainty. This uncertainty was removed by using devices equipped with sensors comprising of industry 4.0 techniques. The values were delivered back by sensors enabling error free solar energy estimation. This delivers admirable outcome and hence are employed. This system can be developed for charge controller by employing a microcontroller-based circuit for DC-DC buck converter and introducing MPPT.

Given that the previous industrial revolution brought about significant and occasionally unanticipated changes in the “economy,” “the environment,” and “society,” industry 4.0’s sustainability effects deserve all of academia's attention. The study of the start-up operations 4.0 sustainability effects is in its infancy, and more research is needed to fully understand the sustainability implication of start-up operation 4.0 in terms of the influence of digitization on the economy, the environment, and society. Though research on sustainability in industry 4.0 has been performed, a study on the factors influencing start-up operations 4.0 to achieve sustainability has not received the necessary attention. To address this issue and gap, the current study models the factors influencing start-up operations 4.0 to achieve sustainability. Through review of literatures and experts’ opinion, ten factors have been identified. To identify how the factors interact, the “Modified-Total Interpretive Structural Modelling (M-TISM)” technique is employed, and the “MICMAC method” is used to “rank and categorize” the factors. The findings shows that the key importance should be given to the “management support for sustainability adoption,” “decentralized system,” “green design,” and “machine learning system.” The developed hierarchical link between variables provides a comprehensive understanding of how sustainability helps start-ups competitiveness and what elements are responsible for this impact. The management of the start-ups can utilize this framework to enhance start-up operations 4.0 since our study uses factors often studied separately but not combined. This study will help academics, and key stakeholders understand the aspects that lead to sustainability in start-up operations 4.0.

Additive Manufacturing (AM) has tremendous applications in this decade, which speeding up various design, engineering, and manufacturing processes. AM encompasses 3D Printing, 3D Scanning, and software support for designing, printing, and post-processing. It is helpful to the specific stages of the product development cycle by allowing manufacturers to produce better sustainable products than those previously limited by the limitations of traditional production techniques. This technological platform enables engineers and scientists to develop more robust and lighter functional geometries. It triggers an innovative surge in design. AM allows firms to produce complicated components that could not be produced through conventional technologies. 3D printers speed up tool cycles, improve measures and tests, and deliver customised solutions in every element of the development process. 3D printing lays the material in several layers until the product is manufactured per the requirements. This study provides a quick overview of AM, its substantial benefits, and the various types of AM that have been researched. Materials from the three polymers, ceramics, and metals classes have been utilised in all AM processes. This study also discussed the latest developments, featured AM-based process classes, and identified materials used in AM technologies. The authors have identified and discussed seventeen significant potentials of AM and finally discussed AM's potential for Sustainability. 3D printing offers incredible design flexibility, enabling us to build passageways that enhance performance, giving customers and operations great value. The benefits of AM for sustainability are evident in the manufacturing environment today. Readers should be able to access the knowledge structure of the subject through this study, which will assist them in recognising past research, the most active research clusters, and the strength of research relationships.

In e-commerce, Industry 4.0 is all about combining analytics, artificial intelligence, and machine learning to simplify procedures and enable product quality review. In addition, the importance of anticipating client behavior in the context of e-commerce is growing as individuals migrate from visiting physical businesses to shopping online. By providing a more personalized purchasing experience, it can increase consumer satisfaction and sales, leading to improved conversion rates and competitive advantage. Using data from e-commerce platforms such as Flipkart and Amazon, it is possible to build models for forecasting customer behavior. This study examines machine learning techniques for product quality prediction and gives an insight into the performance differences of machine learning-based models by doing descriptive data analysis and training each model separately on three datasets viz Mobile, Health Equipments, and Book Datasets. Support Vector Machine, Nave Bayes, k-Nearest Neighbors, Random Forest, and Random Tree were the machine learning methods utilized in this work. The results indicate that a Support Vector Machine Model provides the greatest fit for the prediction task, with the best performance, reasonable latency, comprehensibility, and resilience for the first two datasets, but Random Forest provides the highest performance for the Book dataset.

COVID-19 pandemic expedites the development of digital technologies to tackle the spread of the virus. Several digital interventions have been deployed to reduce the catastrophic impact of the pandemic and observe preventive measures. However, the adoption and utilization of these technologies by the affected populace has been a daunting task. Therefore, this study carried out exploratory investigation of the factors influencing the behavioural intention (BI) of people to accept COVID-19 digital tackling technologies (CDTT) using the UTAUT (Unified Theory of Acceptance and Use of Technology) framework. The study applied principal components analysis and multiple regression analysis for hypotheses testing. The study revealed that performance expectancy (PE), facilitating conditions (FC) and social influence (SI) are the best predictors of people's BI to accept CDTT. Also, organizational

influence and benefit (OIB) and government expectancy and benefits (GEB) influence the people's BI. However, variables such as age, gender and voluntariness to use CDTT have no significance to influence BI because the CDTT is still nascent and not easily accessible. The results show that the decision-makers and regulators should consider inciting variables such as PE, FC, SI, OIB and GEB, that motivate the acceptance and use of CDTT. Furthermore, the populace must be sensitized to the availability and use of CDTT in all communities. Also, the path diagram and hypothesis testing results for CDTT acceptance and use, will help government and private organizations in planning and responding to the digitalization of COVID-19 protective measures and hence revise the COVID-19 health protection regulation.

Breast cancer detection based on the deep learning approach has gained much interest among other conventional-based CAD systems as the conventional based CAD system's accuracy results seems to be inadequate. The convolution neural network, a deep learning approach, has emerged as the most promising technique for detecting cancer in mammograms. In this paper we delve into some of the CNN classifiers used to detect breast cancer by classifying mammogram images into benign, cancer, or normal class. Our study evaluated the performance of various CNN architectures such as AlexNet, VGG16, and ResNet50 by training some of them from scratch and some using transfer learning with pre-trained weights. The above model classifiers are trained and tested using mammogram images from the mini-DDSM dataset which is publicly available. The medical dataset contains limited samples of data due to low patient volume; this can lead to overfitting issue, so to overcome this limitation data augmentation process is applied. Rotation and zooming techniques are applied to increase the data volume. The validation strategy used here is 90:10 ratio. AlexNet showed an accuracy of 65 percent, whereas VGG16 and ResNet50 showed an accuracy of 65% and 61%, respectively when fine-tuned with pre-trained weights. VGG16 performed significantly worse when trained from scratch, whereas AlexNet outperformed others. VGG16 and ResNet50 performed well when transfer learning was applied.

In the modern era, computers using artificial intelligence (AI) and industry 4.0 have found acceptance since its application in renewable energy sectors thereby optimising the cost and efficiency of the equipment. Despite its importance, lack of comprehensive literature has been reported in the past highlighting its relationship with consumer behaviour (CB) in the market considering the modern women's in the sustainable energy field. Findings from 10 studies furnish that physiological, social, personal and economical aspects significantly impact women consumer behaviour when categorized on the perception for intention to buy, acceptance and need for recognition. The current review paper is the first distinguishable review highlighting the importance of stipulating the relationship between artificial intelligence and characteristics of consumer behaviour in the field of sustainable energies. The paper synthesises previous findings by developing a model with the aid of meta-analysis. The review and organization procedure were simultaneously verified. Eventually, outcomes of the review stipulated intention to buy area, which requires utmost importance in order to establish and maintain a healthy attitude of consumers towards women entrepreneurs and industry 4.0. In future, this review will establish a roadmap to researchers, thereby guiding to collect technology information and analyse the applications in sustainability and CB. This paper aims to enhance our expertise and simultaneously develop a feasible relationship between consumer behaviour and computer based renewable technologies by addressing different concerns related to implementation of robots at home and outlining the investigation programs for the future experiments.

Climate change has become a major global challenge. At present, few studies have reviewed the application practices and theoretical research of carbon neutrality. This paper summarizes the practical progress of carbon neutrality, the realization path of carbon neutrality, and the carbon neutrality research in typical fields, and concludes that the previous research has made some progress in the carbon neutrality goal domestic and overseas, the pathways to carbon neutrality, and the carbon neutrality issues in various fields. However, this paper also points out existing problems. Firstly, more studies should be carried out on the quantitative evaluation of carbon neutrality by adopting empircal datas and tools in various fields; Secondly, the correlation between paths and industries should be taken more attention; Additionally, how to measure carbon neutral capability, d potential and costis of great significance in subsequent studies.