Convolutional Neural Networks (CNNs) have begun to permeate all corners of electronic society (from voice recognition to scene generation) due to their high accuracy and machine efficiency per operation. At their core, CNN computations are made up of multi-dimensional dot products between weight and input vectors. This paper studies how weight repetition-when the same weight occurs multiple times in or across weight vectorscan be exploited to save energy and improve performance during CNN inference. This generalizes a popular line of work to improve efficiency from CNN weight sparsity, as reducing computation due to repeated zero weights is a special case of reducing computation due to repeated weights.To exploit weight repetition, this paper proposes a new CNN accelerator called the Unique Weight CNN Accelerator (UCNN). UCNN uses weight repetition to reuse CNN sub-computations (e.g., dot products) and to reduce CNN model size when stored in off-chip DRAM-both of which save energy. UCNN further improves performance by exploiting sparsity in weights. We evaluate UCNN with an accelerator-level cycle and energy model and with an RTL implementation of the UCNN processing element. On three contemporary CNNs, UCNN improves throughputnormalized energy consumption by 1.2× ∼ 4×, relative to a similarly provisioned baseline accelerator that uses Eyeriss-style sparsity optimizations. At the same time, the UCNN processing element adds only 17-24% area overhead relative to the same baseline.

PurposeThe purpose of this paper is to provide a review of the history, trends and needs of continuous improvement (CI) and Industry 4.0. Four strategies are reviewed, namely, Lean, Six Sigma, Kaizen and Sustainability.Design/methodology/approachDigitalization and CI practices contribute to a major transformation in industrial practices. There exists a need to amalgamate Industry 4.0 technologies with CI strategies to ensure significant benefits. A systematic literature review methodology has been followed to review CI strategy and Industry 4.0 papers (n = 92).FindingsVarious frameworks of Industry 4.0, their advantages and disadvantages were explored. A conceptual framework integrating CI strategies and Industry 4.0 is being presented in this paper.Practical implicationsThe benefits and practical application of the developed framework has been presented.Originality/valueThe article is an attempt to review CI strategies with Industry 4.0. A conceptual framework for the integration is also being presented.

PurposeThis study aims to conduct a comprehensive review and network-based analysis by exploring future research directions in the nexus of circular economy (CE) and sustainable business performance (SBP) in the context of digitalization.Design/methodology/approachA systematic literature review methodology was adopted to present the review in the field of CE and SBP in the era of digitalization. WOS and SCOPUS databases were considered in the study to identify and select the articles. The bibliometric study was carried out to analyze the significant contributions made by authors, various journal sources, countries and different universities in the field of CE and SBP in the era of digitalization. Further, network analysis is carried out to analyze the collaboration among authors from different countries.FindingsThe study revealed that digitalization could be a great help in developing sustainable circular products. Moreover, the customers' involvement is necessary for creating innovative sustainable circular products using digitalization. A move toward the product-service system was suggested to accelerate the transformation toward CE and digitalization.Originality/valueThe paper discusses digitalization and CE practices' adoption to enhance the SP of the firms. This work's unique contribution is the systematic literature analysis and bibliometric study to explore future research directions in the nexus of CE and SP in the context of digitalization. The present study has been one of the first efforts to examine the literature of CE and SBP integration from a digitalization perspective along with bibliometric analysis.

The automobile industry is one of the most rapidly growing sectors in our society. The increase in demand for vehicles drives the growth of the automobile sector worldwide. Fabrication of vehicles consumes an enormous amount of water, energy and resources, thereby increasing carbon emissions. Nonbiodegradable and manufacturing waste after the end of life usage results in a significant contribution to incineration, landfills, air acidification and water eutrophication. The adoption of circular economy (CE) initiatives can play a significant role in dealing with increasing waste and environmental pollution. The main goal of CE is to recycle and reuse materials to reduce waste and also to minimise environmental impacts. This article strongly supports the adoption of CE in the Indian automobile industry. For the successful adoption of CE in the Indian automobile sector, first, it is important to analyse roadblocks to the adoption. Twenty potential roadblocks towards the adoption of CE have been identified from a literature review and in consultation with experts in the field. To capture the vagueness of the data and to carry out a robust analysis, a Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method with Fuzzy theory is employed. The results reveal that roadblock ‘lacking ability to deliver high‐quality remanufactured products’ is ranked first among all considered roadblocks. This study will help the Indian automobile industry, decision makers, research practitioners and government officials develop effective strategies for adopting CE in Indian automobile companies. A sensitivity analysis has been conducted to validate the stability of results.

Society is facing many challenges, including, climate change, COVID, inequity and human population growth. Some researchers suggest that integration of Circular Economy (CE) and Industry 4.0 (I4.0) concepts and approaches can help us to make progress towards sustainable societies. Integrated implementation can help to improve the design of product-service systems focused on prevention and reduction of wastage of materials, energy, human health, and ecosystems. The CE practices enable consumers to return products after use and to reuse the products with more value. Will integrated adoption of CE and I4.0 practices help society to be more sustainable? What is known about the climate change benefits of integration of I4.0 and CEs to reduce energy and resource usage? The authors sought to answer these questions, via a systematic bibliometric literature review, and network analysis of literature on I4.0 and CE for logistics and supply chain applications. The review was performed by searching the SCOPUS database for literature about I4.0 and CE. A total of 165 articles were shortlisted for in-depth review. The literature review was complimented by bibliometric and network analyses. The review provided insights into the present and future trends in integration of I4.0 and related Artificial Intelligence (AI) tools in CE's. Based on the findings, a framework for integrating I4.0 and CE, was developed to guide CE decision-making that will help researchers and industrialists, integrate I4.0 tools within CEs to improve logistics, resource efficiency, safety, product quality and reduce fossil-carbon footprints.

The challenging situations and disruptions that occurred due to the outbreak of the COVID-19 pandemic have created a severe need for supply chain resiliency (SCR). There has been a growing interest among researchers to investigate the resiliency in supply chain operations to overcome risks and disruptions and to achieve successful project management. The supply chain of every business requires innovative projects to accomplish competitive advantage in the market. This study was conducted to identify the significance of artificial intelligence (AI) for creating a sustainable and resilient supply chain, and also to provide optimum solutions for supply chain risk mitigation. A systematic literature review has been conducted to examine the potential research contribution or directions in the field of AI and SCR. In total, 162 articles were shortlisted from the SCOPUS database in the chosen field of research. Structural Topic Modeling (STM), a big data-based approach, was employed to generate several thematic topics of AI in SCR based on the shortlisted articles, and all topics were discussed. Furthermore, the bibliometric analysis was conducted using R-package to investigate the research trends in the area of AI in SCR. Based on the conducted review of literature, a research framework was proposed for AI in SCR that will facilitate researchers and practitioners to improve technological development in supply chain firms. The purpose is to combat sudden risks and disruptions so that project management will perform well Post COVID-19. The study will be also helpful for future researchers and practitioners to identify research directions based on existing literature covered in this paper in the field of SCR. Future research directions are proposed for AI-enabled resilient supply chain management. This study will also provide several implications for supply chain managers to achieve the required resilience in their supply chains post COVID-19 by focusing on the elements of the proposed research framework.

The past several years have seen both an explosion in the use of Convolutional Neural Networks (CNNs) and the design of accelerators to make CNN inference practical. In the architecture community, the lion share of effort has targeted CNN inference for image recognition. The closely related problem of video recognition has received far less attention as an accelerator target. This is surprising, as video recognition is more computationally intensive than image recognition, and video traffic is predicted to be the majority of internet traffic in the coming years.This paper fills the gap between algorithmic and hardware advances for video recognition by providing a design space exploration and flexible architecture for accelerating 3D Convolutional Neural Networks (3D CNNs)-the core kernel in modern video understanding. When compared to (2D) CNNs used for image recognition, efficiently accelerating 3D CNNs poses a significant engineering challenge due to their large (and variable over time) memory footprint and higher dimensionality.To address these challenges, we design a novel accelerator, called Morph, that can adaptively support different spatial and temporal tiling strategies depending on the needs of each layer of each target 3D CNN. We codesign a software infrastructure alongside the Morph hardware to find good-fit parameters to control the hardware. Evaluated on state-of-the-art 3D CNNs, Morph achieves up to 3.4× (2.5× average) reduction in energy consumption and improves performance/watt by up to 5.1× (4× average) compared to a baseline 3D CNN accelerator, with an area overhead of 5%. Morph further achieves a 15.9× average energy reduction on 3D CNNs when compared to Eyeriss.

Globalisation and technological advancements have increased the pressure on small businesses to increase their productivity and to gain competitive advantages. That pressure has been placed on the resources available, resulting in increased environmental degradation as a result of the traditional linear model of make‐use‐dispose. Circular economy (CE) practices offer the opportunity for sustainable production based on the reuse‐remanufacture and recycling of resources for small and medium‐sized enterprises (SMEs) to increase their sustainability, resulting in enhanced performance levels in terms of business strategies and environmental perspectives. But in academic literature, the role of people‐driven factors (PDFs) in the adoption of CE practices in the supply chains (SCs) of SMEs is limited. Therefore, to fill this literature gap, this research looks at analysing PDFs for the implementation of CE in the SMEs in developing countries in two phases. PDFs are identified from an extensive literature review; a DEMATEL technique is then employed to understand the significant influence of each factor in the adoption of CE practices in SCs by dividing them into cause–effect groups. The findings show that PDFs such as training and knowledge sharing, employee participation, leadership and management plus strategic alignment are considered to be the most important significant factors in the adoption. The findings of this study will help industrial managers to understand the significance of the role of PDFs for enhancing business strategies; these findings can reduce the negative environmental impact in the adoption of CE practices in the SCs of SMEs.