Auto Cluster Research Articles

Significance of AI-assisted techniques for epiphyte plant monitoring and identification from drone images

Monitoring forest canopies is vital for ecological studies, particularly for assessing epiphytes in rain forest ecosystems. Traditional methods for studying epiphytes, such as climbing trees and building observation structures, are labor, cost intensive and risky. Unmanned Aerial Vehicles (UAVs) have emerged as a valuable tool in this domain, offering botanists a safer and more cost-effective means to collect data. This study leverages AI-assisted techniques to enhance the identification and mapping of epiphytes using UAV imagery. The primary objective of this research is to evaluate the effectiveness of AI-assisted methods compared to traditional approaches in segmenting/identifying epiphytes from UAV images collected in a reserve forest in Costa Rica. Specifically, the study investigates whether Deep Learning (DL) models can accurately identify epiphytes during complex backgrounds, even with a limited dataset of varying image quality. Systematically, this study compares three traditional image segmentation methods Auto Cluster, Watershed, and Level Set with two DL-based segmentation networks: the UNet and the Vision Transformer-based TransUNet. Results obtained from this study indicate that traditional methods struggle with the complexity of vegetation backgrounds and variability in target characteristics. Epiphyte identification results were quantitatively evaluated using the Jaccard score. Among traditional methods, Watershed scored 0.10, Auto Cluster 0.13, and Level Set failed to identify the target. In contrast, AI-assisted models performed better, with UNet scoring 0.60 and TransUNet 0.65. These results highlight the potential of DL approaches to improve the accuracy and efficiency of epiphyte identification and mapping, advancing ecological research and conservation.

Etiologies underlying subtypes of long-standing type 2 diabetes.

Attempts to subtype, type 2 diabetes (T2D) have mostly focused on newly diagnosed European patients. In this study, our aim was to subtype T2D in a non-white Emirati ethnic population with long-standing disease, using unsupervised soft clustering, based on etiological determinants. The Auto Cluster model in the IBM SPSS Modeler was used to cluster data from 348 Emirati patients with long-standing T2D. Five predictor variables (fasting blood glucose (FBG), fasting serum insulin (FSI), body mass index (BMI), hemoglobin A1c (HbA1c) and age at diagnosis) were used to determine the appropriate number of clusters and their clinical characteristics. Multinomial logistic regression was used to validate clustering results. Five clusters were identified; the first four matched Ahlqvist et al subgroups: severe insulin-resistant diabetes (SIRD), severe insulin-deficient diabetes (SIDD), mild age-related diabetes (MARD), mild obesity-related diabetes (MOD), and a fifth new subtype of mild early onset diabetes (MEOD). The Modeler algorithm allows for soft assignments, in which a data point can be assigned to multiple clusters with different probabilities. There were 151 patients (43%) with membership in cluster peaks with no overlap. The remaining 197 patients (57%) showed extensive overlap between clusters at the base of distributions. Despite the complex picture of long-standing T2D with comorbidities and complications, our study demonstrates the feasibility of identifying subtypes and their underlying causes. While clustering provides valuable insights into the architecture of T2D subtypes, its application to individual patient management would remain limited due to overlapping characteristics. Therefore, integrating simplified, personalized metabolic profiles with clustering holds greater promise for guiding clinical decisions than subtyping alone.

An energy‐efficient auto clustering framework for enlarging quality of service in Internet of Things‐enabled wireless sensor networks using fuzzy logic system

SummaryThe advancement of the Internet of Things (IoT) technologies will play a vital role in the evolution of the smart city, smart healthcare, and smart grid applications. Wireless sensor network (WSN) is one of the futuristic technologies utilized for sensing and data exchange processes in IoT‐enabled applications. However, the hotspot problem, control packet overhead, and inefficient clustering are the most significant challenges to attaining an energy‐efficient IoT‐enabled WSN (IWSN) model. Most of the existing clustering schemes lagged to mitigate these aforesaid constraints since it consumes extra energy for data computation and forwarding tasks under any environmental conditions. In this article, a novel energy‐efficient auto clustering (EEAC) framework has been proposed to develop an effective IWSN model with enhanced quality of service. The EEAC framework comprises three phases such as zone formation, node classification, and auto clustering phases. The objective of the first phase is to significantly form the different zones by alleviating the hotspot problem. Subsequently, the fuzzy logic algorithm is employed in the second phase to classify the nodes as master, sub‐master, and member nodes. Finally, the third phase of the proposed framework will accomplish the auto clustering mechanism based on hop information received from the reported packet. The performance results evident that the proposed EEAC framework obtains a lesser energy consumption of 0.01 J during a dense network and the network lifetime is prolonged up to 52% when compared with existing state‐of‐the‐art clustering models.

Impact of Government Policy Measures on Small and Medium Enterprises of Automotive Component Industry Working in Pune Auto Cluster

The government policy has a huge nexus with the development of the industrial sector and with the development of any specific industry. The automotive component industry is not an exception to this. This paper reviews the impact of policy measures adopted by the government pertaining to the automotive component industry in India on the small and medium enterprises of Pune Auto Cluster. The sample of 170 small and medium enterprises was considered to know their opinion about the government policy through a structured questionnaire based on the Likert scale. The technique of factor analysis is used as a construct validity tool and to reduce the number of variables into a few factors to understand the impact of government policy on small and medium enterprises in a better manner. The impact of government policy is remarkable on small and medium enterprises. Medium enterprises are affected more than the small enterprises in the case of regulatory policy measures. However, both small and medium enterprises perceived the operational policy measures equally. Small-scale industries have more impact of the difficulty in receiving benefits of any government schemes like duty drawbacks. On the other hand, medium enterprises perceived Goods and Services Tax and the tax policy as the most troublesome policy measures.

The Pattern Recognition of Small-Scale Privately-Owned Forest in Ciamis Regency, West Java, Indonesia

Small-scale Privately-owned Forest (SSPF) has various patterns identification, based on the stand structure and species composition. The recognition and classification of the SSPF cropping patterns are required for further planning and policy development. Therefore, this study aims to classify the cropping pattern of SSPF in Ciamis Regency, West Java Province, Indonesia. The data were collected by observing the stand structure and species composition of 150 plots of land, encompassing three Sub-districts representing the central, northern, and southern regions of Ciamis Regency. The four categorical variables include tree species composition, age, spatial distribution, and intercropping pattern. While the two continuous variables were stand density and basal area. The patterns obtained were classified based on a Two-Step Cluster algorithm with log-likelihood distance measure, and auto clustering using Schwarz's Bayesian Information Criterion, validated by silhouette index. In addition, a multicollinearity test was conducted to reduce redundancy in using variable sets. The results showed that, the improvement of the cluster quality based on the silhouette index value, was achievable by excluding the tree spatial distribution variable, which exhibits multicollinearity. The cropping patterns were classified into three categories, namely tree crops, mixed-tree lots, and agrisilviculture for group-1, group-2, and group-3, respectively. Group-1 consisted of stands with one or two commercial tree species, and in several cases, were intercropped. Group-2 contained uneven-aged mixed-tree stands without any crops. While Group-3 consisted of an intercropping system of uneven-aged mixed-tree stands and crops. The results suggest further analysis, in order to relate the cropping patterns with the socio-economic characteristics of the landowners, as well as the strategies for the development of a sustainable SSPF.

Assessing advantage cluster: the case of Pithampur auto industry

Learning outcomes The learning outcomes of this paper will help students in understanding the dynamics of the formation of industry clusters and the benefits associated with industry clusters. The case will give stimulus towards the cluster competition. Case overview/synopsis The case describes the dilemma of a potential investor of a tyre company that wants to diversify its product line and is searching for a new strategic location. The investor is thoughtful about the Pithampur auto industry cluster for its upcoming investment. The case demonstrates how Pithampur has transformed into an “industry cluster” and the benefits it provides to firms in it. However, Pithampur is not the only auto industry cluster in India, clusters like Chakan-Pune is in competition with Pithampur for attracting investments. This is a cause of worry for the cluster’s stakeholders. The case projects amalgamation of concerns of the stakeholders of the clusters and those of potential investors in evaluating and benchmarking it with other clusters for a competitive future. Complexity academic level Suitable for both undergraduate and post-graduate students (MBA students). Supplementary materials Teaching notes are available for educators only. Please contact your library to gain login details or email support@emeraldinsight.com to request teaching notes. Subject code CSS: 11: Strategy.

Auto clustering of the variety of pulse signals based on their symbolic description

In a number of applied studies of geophysics, medicine, cosmophysics, atomic physics and other fields of knowledge, useful information is often hidden in the character of the behavior of a stream of frequency modulated pulses, which are represented by a large variety of forms, significantly different from each other up to several orders value of magnitude amplitude and durations. Noise is often present in the signal. Under these conditions, the problem arises of identifying both individual pulses and groups of pulses to assess the connection between their dynamic characteristics and the state of system. To solve the problem by a method is proposed that includes signal cleaning from interference, the operation of extracting and converting pulses into a code representing a sequence of invariant amplitude and time transformations of similar pulses combined by a single graphic pattern called “symbol”. All symbols extracted from the signal make up the alphabet. A procedure for narrowing the dimension of the alphabet is shown, which allows you to automatically divide it into clusters according to the degree of coincidence of the code. The results of the practical application of the developed method for the selection of base classes of the geoacoustic emission (GAS) signals related to the objective data of the state of the signal-generating medium are presented. The study used data from the archives of observations IKIR FEB RAS.

Evaluation of industry cluster competitiveness: a quantitative approach

PurposeThe purpose of this paper is to provide a quantitative approach to measure industry clusters competitiveness.Design/methodology/approachAn attempt has been made to construct a composite indicator backed up by a conceptually grounded framework, by means of Analytical Hierarchical Process technique. Four industry clusters from auto sector in India are chosen for manifestation of the methodology.FindingsThe proposed methodology sufficiently emphasises on the order of significance of the factors/indicators that make a cluster competitive. The study demonstrates the comparative competitiveness performance of four select industry clusters from India.Research limitations/implicationsThe methodology only focusses on auto clusters from India, application of the model/methodology needs to be extended to other set of industries that follows tier structure, or belong to other developing nations to corroborate the findings.Practical implicationsThe proposed approach is a useful tool to provide guidance to policy-makers and in monitoring industry clusters progress.Originality/valueThe paper offers an empirical approach for measuring competitiveness of industry clusters. So far there has been only a minuscule research on cluster competitiveness using empirical methods specifically in case of developing countries like India. Because of the heterogeneity of actors in industry clusters and absence of cluster relevant databases, its performance has been mostly captured via means of case studies. This study is one of its kind that renders comparison of competitiveness across industry clusters by combining secondary data with the perception of cluster actors.

Lung nodule growth measurement and prediction using auto cluster seed K-means morphological segmentation and shape variance analysis

Lung nodule growth measurement and prediction using auto cluster seed K-means morphological segmentation and shape variance analysis

Lung nodule growth measurement and prediction using auto cluster seed K-means morphological segmentation and shape variance analysis

A quantitative model is developed in this work to predict the lung nodules which have the potential to grow in future. An Auto Cluster Seed K-means Morphological segmentation (ACSKMM) algorithm was implemented in this work to segment all the possible lung nodule candidates. An average of around 600 nodule candidates of size >3mm were segmented from each CT scan series of 34 patients. Finally, in total 34 real nodules were remained after eliminating the vessels, non-nodules and calcifications using centroid shift and 3D shape variance analysis. The rate of nodule growth (RNG) was computed on real nodules in terms of 3D-volume change. Out of the 34 real nodules, 3 nodules had RNG value>1, confirming their malignant nature. The nodule growth predictive measure was modelled through compactness, mass deficit, mass excess and isotropic factor.

Competitiveness of Industrial Clusters: A Comparative Study of Pithampur and Indore Clusters, India

Industry clusters have proved critical for a region’s economic prosperity and a nation’s overall competitiveness. This study aims to evaluate and compare competitiveness performance of two select industry clusters from India viz. Pithampur Auto Cluster and Indore Pharma Cluster. For this purpose, the study has developed a comprehensive framework and a simplified methodology that incorporate both quantitative as well as qualitative data on various aspects of cluster competitiveness. It can be used as a foundation for future works related to assessing competitiveness of the clusters.

Thriving innovation amidst manufacturing decline: the Detroit auto cluster and the resilience of local knowledge production

Analyzing the comprehensive 35-year patent data set associated with the Detroit auto cluster we confirm that innovation in clusters can increase in spite of a long-term decline in manufacturing activity. The “stickiness” of local knowledge is sustained by: (i) increasing technological specialization at the local level and (ii) growing connectedness to global centers of excellence. The very forces that bring about the decline in manufacturing in a cluster sustain their position as a global center of innovative excellence.

Lean Manufacturing Auto Cluster at Chennai

Due the presence of lot of automotive Industry, Chennai is known as Detroit of India, that producing over 40 % of the Indian vehicle and components. Lean manufacturing concepts have been widely recognized as an important tool in improving the competitiveness of industries. This is a continuous process involving everyone, starting from management to the shop floor. Automotive Component Industries (ACIs) in Ambattur Industrial Estate, Chennai has formed special purpose vehicle (SPV) society namely Ambattur Industrial Estate Manufacturers Association (AIEMA) Technology Centre (ATC) lean manufacturing cluster (ATC-LMC) during July 2010 under lean manufacturing competitiveness scheme, that comes under National Manufacturing Competitiveness Programme of Government of India. The Tripartite Agreement is taken place between National Productivity Council, consultants and cluster (ATC-LMC). The objective is to conduct diagnostic study, study on training and application of various lean manufacturing techniques and auditing in ten ACIs. The methodology adopted is collection of primary data/details from ten ACIs. In the first phase, diagnostic study is done and the areas for improvement in each of the cluster member companies are identified. In the second phase, training programs and implementation is done on 5S and other areas. In the third phase auditing is done and found that the lean manufacturing techniques implementation in ATC-LMC is sustainable and successful in every cluster companies, which will not only enhance competitiveness but also decrease cost, time and increase productivity. The technical efficiency of LMC companies also increases significantly.

Technical Efficiency of Automotive Industry Cluster in Chennai

Chennai is also called as Detroit of India due to its automotive industry presence producing over 40 % of the India’s vehicle and components. During 2001–2002, diagnostic study was conducted on the Automotive Component Industries (ACI) in Ambattur Industrial Estate, Chennai and in SWOT analysis it was found that it had faced problems on infrastructure, technology, procurement, production and marketing. In the year 2004–2005 under the cluster development approach (CDA), they formed Chennai auto cluster, under public private partnership concept, received grant from Government of India, Government of Tamil Nadu, Ambattur Municipality, bank loans and stake holders. This results development in infrastructure, technology, procurement, production and marketing interrelationships among ACI. The objective is to determine the correlation coefficient, regression equation, technical efficiency, peer weights, slack variables and return to scale of cluster before and after the CDA. The methodology adopted is collection of primary data from ACI and analyzing using data envelopment analysis (DEA) of input oriented Banker–Charnes–Cooper model. There is significant increase in correlation coefficient and the regression analysis reveals that for one percent increase in employment and net worth, the gross output increases significantly after the CDA. The DEA solver gives the technical efficiency of ACI by taking shift, employment, net worth as input data and quality, gross output and export ratio as output data. From the technical score and ranking of ACI, it is found that there is significant increase in technical efficiency of ACI when compared to CDA. The slack variables obtained clearly reveals the excess employment and net worth and no shortage of gross output. To conclude there is increase in technical efficiency of not only Chennai auto cluster in general but also Chennai auto components industries in particular.

Study on Jilin Automobile Industrial Cluster Based on a Perspective of Regional Innovation

In order to improve the competitive advantage of auto industry in Jilin, this paper, based on the view of factors of influencing auto industrial cluster, studies the regional conditions and advantages by comparing the analysis，and sets up a networking model of present development base and forming mechanism and then puts forward the necessity of auto industry clustering in Jilin. Finally, some suggestions are provided, which can be the directions for auto industry in Jilin.

Image Retrieval System Based on Adaptive Color Histogram and Texture Features

This paper proposes three image features for use in image retrieval. The first image feature is based on color distribution and is called an adaptive color histogram (ACH). The second and third image features, called adaptive motifs co-occurrence matrix (AMCOM) and gradient histogram for adaptive motifs (GHAM), are based on color and texture features, respectively. ACH uses three steps, including cluster drop, auto cluster merge and auto cluster split to improve the K-mean algorithm. AMCOM is commonly used and is a generally conventional AMCOM. GHAM estimates the average gradient of pixels in a motif of pattern blocks and creates a histogram of the average gradient corresponding to motifs of pattern blocks. We integrate ACH, AMCOM and GHAM to form an AMCGH system to facilitate a more accurate and efficient image retrieval system. To present the performance of the proposed system, four different image databases, including gray texture images, two types of color texture images and color natural images, are tested and analyzed.

The analysis of auto industrial clusters competitiveness in China in the context of economic globalisation

The paper mainly discusses the impacts of economic and market globalisation on the international competitiveness of China auto industrial clusters through three relative aspects: opening market, FDI effects and global management strategy. With the process of the integration with the whole global value chain, the new value point can be innovated and obtained; the implementation of the FDI strategy will facilitate the technological overflow, improve the geographical outlay of the auto industry clusters, form the international clusters network system so that the innovative capability of the auto industry clusters can be improved greatly; the implementation of the global management will overcome the inherent rigidity of the auto industrial clusters, push the alteration of the life circles of the clusters, reintegrate the value chain of the auto industry production; the global market strategy can extend the market for the product of the clusters and broaden the purchasing channels of the needed raw materials. The research indicates that the reasonable use of the alteration of the industry elements and the vicissitude of the economical geography may promote the development of China auto industry clusters greatly and improve the production efficiency obviously in a not long time.

Environmentally responsive supply chains

PurposeThe arrival of global manufacturers has brought about new challenges such as environmental concerns and sustainability of supply chains. The purpose of this paper is to identify implementation level, major drivers, various practices and performance of environmentally and socially‐conscious supply chain management (SCM) in the context of the automobile industry in India.Design/methodology/approachThe literature is reviewed to understand various challenges/barriers to the adoption of green supply chain management (GSCM) practices; statistical analysis of various drivers, practices and performance of environmentally and socially conscious supply chain is carried out in the case of an automobile cluster in central India. Personal interviews are conducted and a structured questionnaire is used for data collection from 30 organizations including original equipment manufacturers, first‐ and second‐tier suppliers.FindingsEnvironmentally and socially responsive supply chains are in the early adoption stages in India. Companies studied in the auto cluster are not adequately addressing these measures in supply chain design and operations; though awareness and inclination to adopt has been on the rise – actual implementation lacks a holistic approach.Originality/valueInvestigation of GSCM along with social concerns is rarely done in the Indian context. This paper will offer valuable insights for managers in understanding the consequences of non‐compliance, especially with the Indian automobile industry recently becoming global.

Rover and out? Globalisation, the West Midlands auto cluster, and the end of MG Rover

This paper sets the scene for this Policy Studies special issue on plant closures by outlining the form of the auto cluster in the West Midlands, the nature of structural changes unfolding in the industry, and the decline and eventual collapse of MG Rover (MGR). Structural changes highlighted include: greater pressure on firms to recover costs when technological change has been intensifying, driving up the costs of new model development; increased international sourcing of modular components; and a shift of final assembly operations towards lower cost locations. All of these make maintaining mature clusters such as the West Midlands more challenging for firms and policy makers. The paper then looks at ‘what went wrong’ at MGR. Given long-run problems at the firm and its inability to recover costs, BMW's sale of the firm in 2000 left MGR virtually dead on its feet, and by 2002/2003 it was clear to many that the firm was running out of time. Whilst recognising that the firm's demise was ultimately a long-term failure of management, the paper also looks at other contributing factors, including government policy mistakes over the years, such as the misguided ‘national champions’ approach in the 1950s and 1960s, a failure to integrate activities under nationalisation in the 1970s, a mistaken privatisation to British Aerospace in the 1980s, and a downside of competition policy in ‘allowing’ the sale to a largely inappropriate owner in BMW in the 1990s. The considerable volatility of sterling in recent years hastened the firm's eventual demise.

A tale of two regions: comparative versus competitive approaches to economic restructuring

In April 2004 Mitsubishi announced the closure of its Lonsdale plant in South Australia. Almost a year later, MG Rover went into administration, resulting in the immediate closure of its Longbridge plant just outside Birmingham, England. Both closures were expected to have a considerable impact on their regional economies through the loss of employment and associated economic activity. However, governments in Australia and England responded in significantly different ways: in England the focus was on competitive advantage through the modernisation of the auto cluster and the diversification of the regional economy into new, high-technology industries. In Australia, the national and state governments introduced policy responses based on the pursuit of comparative advantage. This paper compares and contrasts the two sets of government responses and examines the capacity of each to deliver long-term benefits to their affected communities.