Search

The success factor of sentimental analysis lies in identifying the most occurring and relevant opinions among users relating to the particular topic. In this paper, we develop a framework to analyze users' sentiments on Twitter on natural disasters using the data pre-processing techniques and a hybrid of machine learning, statistical modeling, and lexicon-based approach. We choose TF-IDF and K-means for sentiment classification among affinitive and hierarchical clustering. Latent Dirichlet Allocation, a pipeline of Doc2Vec and K-means used to capture themes, then perform multi-level polarity indices classification and its time series analysis. In our study, we draw insights from 243,746 tweets for Kerala's 2018 natural disasters in India. The key findings of the study are the classification of sentiments based on similarity and polarity indices and identifying themes among the topics discussed on Twitter. We observe different sets of emotions and influencers, among others. Through this case example of Kerala floods, it shows how the government and other organizations could track the positive/negative sentiments concerning time and location; gain a better understanding of the topic of discussion trending among the public, and collaborate with crucial Twitter users/influencers to spread and figure out the gaps in the implementation of schemes in terms of design and execution. This research's uniqueness is the streamlined and efficient combination of algorithms and techniques embedded in the framework used in achieving the above output, which can be integrated into a platform with GUI for further automation. [ABSTRACT FROM AUTHOR]

Managed Aquifer Recharge (MAR) has emerged as a multi-facet, sustainable and effective technique to replenish dwindling groundwater resources. Suitable site selection is an important step in the design phase of MAR process. Conventional methods of site suitability studies using GIS and Multi Criteria Decision Analysis (MCDA) does not address the aquifer's response to MAR, while limited modelling-based studies have considered the effect of surface hydraulic factors. In this paper, a fresh approach is presented, that utilises decision model, K-mean clustering technique and numerical model to identify optimal sites for MAR interventions. The methodology was applied in a semi-arid region of Lower Betwa River Basin (LBRB), India. Four different parameter combinations were employed that incorporated the impact of surface and subsurface parameters. Multiple model runs were executed using MODFLOW–NWT to assess the groundwater head response to the infiltrated volume of water. The results indicated that under the least head change category (< 0.7 m), the north and south–east regions of the LBRB were the most appropriate sites. The coalition of geomorphology and drainage density along with aquifer properties such as hydraulic conductivity, specific yield and aquifer thickness were found to be the best suited combination for site selection in LBRB, with maximum spatial coverage (16%) under it. It was observed that the choice of parameter combinations affected the range of groundwater head variations and depended upon the site-specific criteria of accepted head change ranges for determining the best suitable parameter combinations for MAR site selection. [ABSTRACT FROM AUTHOR]

Purpose: The purpose of this paper is to determine compatibility groups of different fruits and vegetables that can be stored and transported together based upon their requirements for temperature, relative humidity, odour and ethylene production. Pre-cooling which is necessary to prepare the commodity for subsequent shipping and safe storage is also discussed. Design/methodology/approach: The methodology used in this journal is an attempt to form clusters/groups of storing together 43 identified fruits and vegetables based on four important parameters, namely, temperature, relative humidity, odour and ethylene production. An agglomerative hierarchical clustering algorithm is used to build a cluster hierarchy that is commonly displayed as a tree diagram called dendrogram. The same is further analyzed using K-means clustering to find clusters of comparable spatial extent. The results obtained from the analytics are compared with the available data of grouping fruits and vegetables. Findings: This study investigates the usefulness and efficacy of the proposed clustering approach for storage and transportation of different fruits and vegetables that will eventually save huge investment made in terms of developing infrastructure components and energy consumption. This will enable the investors to adopt it for using the space more effectively and also reducing food wastage. Research limitations/implications: Due to limited research and development (R&D) data pertaining to storage parameters of different fruits and vegetables on the basis of temperature, relative humidity, ethylene production/sensitivity, odour and pre-cooling, information from different available sources have been utilized. India needs to develop its own crop specific R&D data, since the conditions for soil, water and environment vary when compared to other countries. Due to the limited availability of the research data, various multi-criteria approaches used in other areas have been applied to this paper. Future studies might be interested in considering other relevant variables depending upon R&D and data availability. Practical implications: With the increase in population, the demand for food is also increasing. To meet such growing demand and provide quality and nutritional food, it is important to have a clear methodology in terms of compatibility grouping for utilizing the available storage space for multi-commodity produce and during transportation. The methodology used shall enable the practitioners to understand the importance of temperature, humidity, odour and ethylene sensitivity for storage and transportation of perishables. Social implications: This approach shall be useful for decision making by farmers, Farmer Producer Organization, cold-storage owners, practicing managers, policy makers and researchers in the areas of cold-chain management and will provide an opportunity to use the available space in the cold storage for storing different fruits and vegetables, thereby facilitating optimum use of infrastructure and resources. This will enable the investors to utilize the space more effectively and also reduce food wastage. It shall also facilitate organizations to manage their logistic activities to gain competitive advantage. Originality/value: The proposed model would help decision makers to resolve the issues related to the selection of storing different perishable commodities together. From the secondary research, not much research papers have been found where such a multi-criteria clustering approach has been applied for the storage of fruits and vegetables incorporating four important parameters relevant for storage and transportation. [ABSTRACT FROM AUTHOR]

Purpose: India has the second highest percentage of mobile wallet adoption driven by availability of affordable smartphones and Internet. Despite a general interest, studies on its adoption have been scarce. This research assumes that user segments exist, each with their own level of maturity, and addresses the question "Are there segments which can be profiled?" Thus, the objectives of the study are to propose a model that explains the attitude of user segments towards its adoption; identify probable user segments and profile them; examine the importance and performance of constructs which influence attitude within each cluster and recommend ways to improve performance. Design/methodology/approach: This paper employs the constructs from two popular theories on technology adoption, i.e. technology acceptance model (TAM) and Unified Theory of Acceptance and Use of Technology (UTAUT). A synthesis of review of literature on these models, besides two focus group discussions (FGDs), was used to design a pilot instrument. A nationwide survey was conducted, and 744 responses were obtained. Convenience sampling was used to select the respondents. The average scores of various constructs were computed and subjected to hierarchical clustering. Further, k-means clustering was carried out. The demographic profiling of each cluster was done through cross-tabulation and differences related to attitude and intention between clusters were tracked by one-way Analysis of Variance (ANOVA). To determine the relative importance and performance of constructs within each cluster, Importance-Performance Map Analysis (IPMA) using Smart Partial Least Squares (PLS) was carried out. Findings: The hierarchical clustering resulted in three clusters. The result of k-means clustering was used to label the clusters as Technology Enthusiasts (TE), Technology Sceptics (TS) and Technology Pragmatists (TP). The obtained clusters were found to differ in terms of perception, attitude, intention, behavior, marital status, education, occupation and income levels. With respect to each cluster, it was seen that the top three important constructs are Perceived Usefulness (PU), Security (SEC) and Lifestyle Compatibility (LC) as indicated by the IPMA. The findings indicate that mobile wallet providers should focus on all six constructs, with special focus on PU, SEC and LC. The findings of this study will help mobile wallet providers in customizing their offerings to enhance adoption attitude in all three clusters. Research limitations/implications: This study examines the perception of students and working professional towards mobile wallet adoption and uses this data for segmentation. However, there could be underlying differences between these two groups, as the motive behind adopting a technology may be different. Thus, treating them as homogenous user segments could be a limitation. Therefore, exploring segments and profiles for each type of user may be an area for future research. Mobile wallet providers should also give utmost importance to perceived usefulness, security and lifestyle compatibility while designing their services. This will not only enhance user trust and compatibility with mobile wallet but also improve the outcomes associated with its usage. Practical implications: This study will help mobile wallet providers understand the user segments and customize their service offerings. Originality/value: This study provides a comparison of the respondent profiles of three obtained segments of mobile wallet users. While prior studies have identified segments associated with adoption of technologies like ATM banking, SMS banking, online banking, Internet banking, mobile banking etc., not much has been reported on mobile wallet adoption. To the best of the authors' knowledge, this is a novel study in India, aimed at identifying user clusters among adopters of mobile wallets and developing cluster profiles based on demographic, attitude and intention. [ABSTRACT FROM AUTHOR]

Purpose The purpose of this paper is to identify a classification scheme which represents the variation in business and supply chain performance of supply chains in Indian manufacturing industry. Classification is done by presenting an empirical taxonomy of clusters representing supply chains in Indian manufacturing industry based on variation in supply chain excellence index (SCEI) and business performance index (BPI).Design/methodology/approach The clustering of supply chains in Indian manufacturing industry is done by considering BPI and SCEI as clustering variables, which were found by using survey responses and results of a prior empirical study which was carried out in Indian manufacturing industry. The cluster analysis is performed by using Ward’s agglomerative hierarchical clustering followed by using K-means clustering algorithm to establish final set of clusters.Findings It was found that supply chains in Indian manufacturing industries can be clustered in four major clusters which are named as strategic, celebrity, capable and undeveloped cluster. The characteristics of these clusters reveal some major characteristics of supply chains in Indian manufacturing industry.Originality/value The research work presented in this paper takes a novel way to introduce the clusters of supply chains in Indian manufacturing industry. The researchers who are seeking patterns in large data sets of manufacturing companies of Indian industry will be benefitted by using the proposed clusters. While practitioners who are seeking to move their supply chain one step ahead will also reap the benefits of the paper by seeking the characteristics of particular cluster. [ABSTRACT FROM AUTHOR]

Background: The concept of tuberculosis diagnosis plays a significant role in the current world since, in accordance with the Global Tuberculosis (TB) Report in 2019, more than one million cases are reported per year in India. Various tests are available even then the chest X-ray is the most significant one, devoid of which the diagnosis will be incomplete. By the usage of computationally designed algorithms, various clinical, as well as diagnostic functions, were built in ancient poster anterior chest radiographs. The Digital image (X-ray) may be an essential medium for examining and annotating patient's demographics coverage in the screening of TB via chest radiography. Results: Even though several medicines are available to cure TB, diagnosis with accuracy is a major challenge. So, we have introduced a fastened technique with the merged combination of Adaptive Boosting (AdaBoost) and learning vector quantization (LVQ) for determining TB in an easier way with the input chest X-ray image of a person with the aid of computer-aided diagnosis with greatest accuracy, precision, recall and F1 values. This finest technique got an accuracy of 94.73% when compared to the prior conventional methods used such as SVM and Convolutional Neural Network. Conclusions: Tuberculosis detection can be done in a meaningful way with the aid of MATLAB simulation using Computer Aided Diagnosis. The algorithms Adaboost and LVQ works best with the datasets for around 400 chest X-ray images for detecting the normal and abnormal images conditions for the detection of the disease for a patient suspected to have TB, in a fraction of seconds. [ABSTRACT FROM AUTHOR]

Purpose: Due to the economic benefits and environmental awareness, most of the battery manufacturing industries in India are interested to redesign their existing supply chain network or to incorporate the effective closed loop supply chain network (CLSCN). The purpose of this paper is to develop CLSCN model with eco-friendly distribution network and also enhance recycling to utilize recycled lead for new battery production. The existing CLSCN model of a battery manufacturing industry considered for case study is customized for attaining economic benefit and environmental safety. Hence, single objective, multi-echelon, multi-period and multi-product CLSCN model with centralized depots (CD) is developed in this work to maximize the profit and reduce the emission of CO2 in transportation. Design/methodology/approach: The proposed CD has the facility to store new batteries (NB), scrap batteries (SB) and lead ingot. The objective of the proposed research work is to identify potential location of CD using K-means clustering algorithm, to allocate facilities with CD using multi-facility allocation (MFA) algorithm and to minimize overall travel distance by allowing bidirectional flow of materials and products between facilities. The proposed eco-friendly CLSCN-CD model is solved using GAMS 23.5 for optimal solutions. Findings: The performance of the proposed model is validated by comparing with existing model. The evaluation reveals that the proposed model is better than the existing model. The sensitivity analysis is demonstrated with different rate of return of SB, different proportion of recycled lead and different type of vehicles, which will help the management to take appropriate decision in the context of cost savings. Originality/value: This research work has proposed single objective, multi echelon, multi period and multi product CLSCN-CD model in the battery manufacturing industry to maximize the profit and reduce the CO2 emission in transportation, by enhancing the bidirectional flow of materials/products between facilities of entire model. [ABSTRACT FROM AUTHOR]

India is a highly populated agricultural country which has land area of 60.3% for agriculture purpose. The production of rice plant is decreased up to 20–30% because of various diseases. The most frequent diseases occurred in paddy leaves are leaf blast, leaf blight, false smut, brown spot and leaf streak. This paper mainly considers a method to detect the leaf diseases automatically using image processing techniques. To determine these diseases, the proposed methodology involves image Acquisition, image pre-processing, segmentation and classification of paddy leaf disease. In this proposed system, the features are extracted using hybrid method of discrete wavelet transform, scale invariant feature transform and gray scale co-occurrence matrix approach. Finally, the extracted features are given to various classifiers such as K nearest neighborhood neural network, back propagation neural network, Naïve Bayesian and multiclass SVM to categorize disease and non-disease plants. Many classification techniques are examined to classify the leaf disease. In experimental result, the proposed work is implemented in MATLAB software and performance of this work is measured in terms of accuracy. It is observed that multi class SVM provides the better accuracy of 98.63% when compared to other classifiers. [ABSTRACT FROM AUTHOR]

Diabetes is the common chronic disease and a major health challenge in all population. Gestational Diabetes Mellitus (GDM) is a type of diabetes developed in women at the time of pregnancy. Our study is about predicting GDM by considering various risk factors using ensemble classification techniques. In this paper different ensemble learning models are used for prediction of GDM. A new ensemble model is proposed where ensemble stacking is done for the results of k-means clustering. Where clustering is done by excluding the class attribute of the data set. The data samples used for testing the model is collected from the local hospitals of Mysuru, Karnataka state, India. The performance of the classifiers have been measured and compared in terms of accuracy. [ABSTRACT FROM AUTHOR]

Pavement Management Systems (PMS) can benefit the highway agencies in several ways both at network and project levels, especially in selecting cost-effective alternatives. Whether it is new construction, maintenance, or rehabilitation, PMS helps the authorities attain the best possible utilisation of available resources and public money. This investigative paper proposes a network level PMS for the roads of Tiruchirappalli city, India. Data pertaining to inventory, traffic, maintenance history, and serviceability of the study roads are gathered at regular intervals for a period of 7 years. The pavement sections are grouped into homogeneous clusters by k-means clustering, and Multiple Linear Regression Models are developed for the clusters to predict pavement performance. Based on the pavement condition, different maintenance treatments are identified through expert opinion surveys. An optimisation programme UPMMS-GAMS is developed using Generic Algebraic Modelling System (GAMS) software, to consolidate the city's PMS. Pavement condition, age, maintenance options, and maintenance cost are given as model inputs. Minimum performance levels and the maximum number of maintenance activities are constraints that must be guaranteed. The optimisation programme defines the maintenance and rehabilitation strategies to be employed each year to maintain the pavement sections above a minimum desired level. [ABSTRACT FROM AUTHOR]

The main purpose of this study is to explore cross-format shopping motives among grocery consumers and to categorise cross-format shopping typologies based on identified motives. The paper also aims to identify common consumer subgroups amongst the customer base of different retail formats and differences among shopper segments in relation to format choice and repeat patronage (loyalty). In this method, exploratory qualitative (semi-structured personal interviews) and quantitative research (mall intercept survey) approaches were used. Primary data were collected from 1040 grocery consumers by self-administering a structured questionnaire. Multivariate techniques including exploratory factor analysis, k-means cluster analysis, multiple discriminant analysis, multivariate analysis of variance, and X2 tests were applied to test the formulated propositions. This paper identifies nine cross-format shopping motivations: value for money, value for time, price-conscious, local shopping, shopping enjoyment, social shopping, variety seeking, entertainment, and brand-conscious motives. Based on these central dimensions, this paper finds five cross-format shopper segments: economic shopper, convenience shopper, price-promotional shopper, hedonic shopper, and social shopper. The study also indicates that there are significant differences amongst shopper typologies in relation to retail format choice and repatronage. This study provides specific knowledge of the cross-shopping motives to the grocery retailers that consumers consider important when making format choices. The study also helps retailers develop various retailing strategies to increase store format loyalty. Despite the importance of understanding grocery consumers' cross-shopping, little research has been conducted to investigate the growing incidence of cross-format shopping. Given the absence of published academic literature in relation to cross-format shopping behaviour in the context of emerging retail markets, the empirical evidence may serve as a departure point for future studies in this area of concern. The research is relevant to grocery retailers in terms of format development. [ABSTRACT FROM AUTHOR]

Pavements, being a significant component of urban infrastructure, their maintenance and rehabilitation to the desired serviceability level is a challenging problem faced by engineers. The development of a reliable pavement deterioration model is essential to devise proper maintenance policies. This exploratory paper presents the development of network-level pavement performance prediction models for the selected arterial and sub-arterial roads of Tiruchirappalli city, India. Road inventory, traffic volume, maintenance history, pavement condition, and roughness data of the study area are collected periodically for seven years. The Pavement Condition Index (PCI) is determined from the data collected through visual evaluation of the type, severity, and amount of pavement distress. Roughometer is deployed to obtain the International Roughness Index. The parameters which influence pavement deterioration vary widely for different roads within the same network. The pavement sections are assembled into three homogeneous clusters using k-means clustering, which is a nonhierarchical clustering algorithm, so that they can be modeled with better acceptability. Pavement performance prediction models are generated for different clusters using multiple linear regression analysis, and comparison is made with that developed for non-clustered data. The error in prediction is found to be less for clustered models. While the pavement sections in cluster 2, when left unmaintained, deteriorates from a PCI value of 100 to 77 in 5 years, those belonging to cluster 3 are found to deteriorate from 100 to 13. The variation in the deterioration process and the significance of clustering pavement sections for efficient pavement maintenance management is established. [ABSTRACT FROM AUTHOR]

Early rainfall prediction is very important to ensure the economic balance of any agriculture-dominated country, such as India. Deep learning has recently received considerable attention for predicting rainfall using historical data. However, rainfall depends on multiple factors like ElNino, rising sea levels, warming of the Atlantic Ocean, etc. The changing climate has also significantly increased rainfall variability. The current deep-learning approaches are either based on a limited set of predictors or do not utilize the time-series properties for the recurrence of similar climate conditions every 12 months. Besides, they perform poorly in predicting accurate rainfall estimates for the diverse areas of India due to limited data availability across various regions. Therefore, this paper presents a groundbreaking solution to address the challenge of limited data by introducing RfGan (Rainfall GAN), a novel variant of generative adversarial networks. RfGan aims to fulfill the crucial need for abundant data to ensure the effectiveness of model training. Moreover, a novel rainfall prediction method, RfGanNet, has been introduced that leverages the strengths of the proposed RfGan for data augmentation, long-short-term memory, and convolutional neural networks for rainfall prediction. The performance of RfGanNet has been validated for India and its clustered regions in terms of nine parameters: precision, recall, specificity, Matthews correlation coefficient, accuracy, F1-score, mean absolute error, mean square error and computation time. The experimental results of RfGan are compared against original and synthetic datasets generated from state-of-the-art methods, namely tabular gan (TGAN), Wasserstein gan (WGAN), and conditional tabular gan (CTGAN). The experimental results indicate that the proposed RfNet model, when trained using RfGan-generated data, surpassed all the other considered methods by achieving 97.22 % accuracy. Moreover, RfNet has been compared with other related deep Learning approaches to validate its efficacy. Additionally, an ablation study investigating various LSTM–CNN combinations has been conducted. The findings of the study indicate that oceanic and climate-related predictors have a noteworthy influence on Indian rainfall. Moreover, the study highlights the suitability of combining Bidirectional LSTM, CNN, and multiple predictors for accurate rainfall prediction. • Novel variant of generative adversarial network- RfGan is proposed. • Different combinations of LSTM and CNN for rainfall prediction are tested. • Novel classifier — RfNet is tested on different augmented datasets. • K-means clustered regions of India have been identified. [ABSTRACT FROM AUTHOR]

Mobility as a Service (MaaS) has emerged as a transformative concept in urban transportation, integrating multiple modes of transportation through digital platforms to provide seamless travel experiences. By utilizing smartphone applications, MaaS simplifies trip planning, real-time information access, and consolidated payment systems, offering convenience to users. However, MaaS research has primarily focused on developed countries with well-established transport systems, making it crucial to explore its potential and challenges in developing cities of the global south, such as Noida in India. In this study, Noida, a satellite town of NCT Delhi, was chosen as only case study to gather data on user behaviour and preferences regarding appbased mobility services. A comprehensive survey collected information on socio-economic factors, personal vehicle ownership, commuting patterns, public transport usage, and attitudes towards digital ecosystems and app-based mobility services. Principal Component Analysis and K-means Clustering techniques were applied to identify distinct user types and categories, providing insights into user preferences and expectations. The analysis of the collected data revealed user clusters and their respective characteristics. The sustainability aspects of on-demand mobility services were evaluated, comparing user perceptions with private vehicle usage. The study also examined the impact of app-based mobility services on public transport and identified barriers and constraints specific to different user clusters, contributing to a better understanding of the feasibility of implementing MaaS. The findings will provide valuable insights for policymakers and transportation authorities, enabling the development of strategies and interventions to enhance urban mobility and foster MaaS adoption. By addressing the specific needs and preferences of users, MaaS can play a significant role in improving the efficiency and sustainability of transportation in complex urban environment cities like Noida in India. [ABSTRACT FROM AUTHOR]

Massive boost in data traffic demand and inconsistent user's behavior have necessitated modern cellular networks to evolve toward heterogeneous architectural framework consisting of macro and small cells to accommodate ever‐increasing user's density. Literature survey reveals that the deployment of additional small cells can encounter the booming coverage, capacity, and QoS constraints by maintaining the overall operational cost of the network. In this paper, at first, a suitable model based on nonhomogeneous Poisson point process (NHPPP) is designed for heterogeneous wireless network (HetNet) consisting of two‐tiers eNodeBs (Macro and Small Cell), where each of the tiers is differentiated in terms of transmitting power, eNodeB density, and supported data rate. Subsequently, analytical expressions are derived for coverage probability (CP) and average rate (AR) to assess the performance of the HetNet. The contribution of the paper further lies in integrating the K‐means clustering algorithm with NHPPP to find the optimal locations of the small cell eNodeBs for extended coverage and rate improvement. The proposed model is investigated under differently dense scenarios like urban and suburban areas in India. It establishes the requisite of an optimal number of small cells along with the traditional infrastructure to maximize the performance in terms of CP and AR. Finally, the proposed integrated model is compared with the traditional homogeneous Poisson point process (HPPP) and NHPPP for coverage and rate analysis. It is observed that the K‐means clustering algorithm in integration with NHPPP overshadows both HPPP and NHPPP in terms of coverage and rate under both urban and suburban deployment scenarios. [ABSTRACT FROM AUTHOR]

The rapidly evolving high-throughput sequencing (HTS) technologies generate voluminous genomic and metagenomic sequences, which can help classify the microbial communities with high accuracy in many ecosystems. Conventionally, the rule-based binning techniques are used to classify the contigs or scaffolds based on either sequence composition or sequence similarity. However, the accurate classification of the microbial communities remains a major challenge due to massive data volumes at hand as well as a requirement of efficient binning methods and classification algorithms. Therefore, we attempted here to implement iterative K-Means clustering for the initial binning of metagenomics sequences and applied various machine learning algorithms (MLAs) to classify the newly identified unknown microbes. The cluster annotation was achieved through the BLAST program of NCBI, which resulted in the grouping of assembled scaffolds into five classes, i.e., bacteria, archaea, eukaryota, viruses and others. The annotated cluster sequences were used to train machine learning algorithms (MLAs) to develop prediction models to classify unknown metagenomic sequences. In this study, we used metagenomic datasets of samples collected from the Ganga (Kanpur and Farakka) and the Yamuna (Delhi) rivers in India for clustering and training the MLA models. Further, the performance of MLAs was evaluated by 10-fold cross validation. The results revealed that the developed model based on the Random Forest had a superior performance compared to the other considered learning algorithms. The proposed method can be used for annotating the metagenomic scaffolds/contigs being complementary to existing methods of metagenomic data analysis. An offline predictor source code with the best prediction model is available at (https://github.com/Nalinikanta7/metagenomics). [ABSTRACT FROM AUTHOR]

This study investigates disparities in healthcare services in the districts of Uttar Pradesh, the most populous and one of the poorest states of India in the health sector. To measure the disparities in healthcare services, a composite index has been computed using Principal Component Analysis in three domains namely, health availability, health amenities and health affordability and 12 representative indicators. On the basis of the results, districts have been clubbed into five categories, such as high, high-medium, medium, medium–low and low according to their composite scores. The study also uses k-means cluster analysis to find out the set of districts which are similar within the group, but they are different between the groups. Key results indicate that the districts of the western region are more developed in comparison to the districts of the eastern region in terms of three indices such as availability, amenities, affordability of healthcare services and overall composite health index. Also, k-means cluster analysis shows that there are many districts which are identical in many respects; however, they are located in different regions of the state. This study may be helpful to understand the poor availability and affordability of healthcare services in the districts of Uttar Pradesh, which should be improved to meet the objectives of the basic-needs approach and the millennium development goals. [ABSTRACT FROM AUTHOR]

In India, which has numerous officially recognized scripts, there is a primary need for categorizing the documents on the basis of the scripts used therein. Identification of script used in a document is essential for its effective handling both manually and digitally. Identification of script in a document image is an important research problem in the pattern recognition field, which, at times, suffers from the issue of growing dimensionality of the feature vector and requires an efficient feature selection technique. Keeping this fact in mind, in this paper, we propose a clustering‐based filter feature selection framework in order to extract an optimal and effective feature subset from the original feature vector. The present feature selection methodology is evaluated on a script classification problem involving handwritten documents in 12 major Indic scripts. Experiments are done at word‐level, text‐line‐level, and block‐level. Experiments demonstrate that a reasonable increment in classification accuracy has been realized using comparatively lesser number of features. The proposed framework for feature selection is computationally inexpensive and can be applied to other pattern recognition problems as well. [ABSTRACT FROM AUTHOR]

Agriculture in India accounts for 18% of greenhouse gas (GHG) emissions and uses significant land and water. Various socioeconomic factors and food subsidies influence diets in India. Indian food systems face the challenge of sustainably nourishing the 1.3 billion population. However, existing studies focus on a few food system components, and holistic analysis is still missing. We identify Indian food systems covering six food system components: food consumption, production, processing, policy, environmental footprints, and socioeconomic factors from the latest Indian household consumer expenditure survey. We identify 10 Indian food systems using k-means cluster analysis on 15 food system indicators belonging to the six components. Based on the major source of calorie intake, we classify the ten food systems into production-based (3), subsidy-based (3), and market-based (4) food systems. Home-produced and subsidized food contribute up to 2000 kcal/consumer unit (CU)/day and 1651 kcal/CU/day, respectively, in these food systems. The calorie intake of 2158 to 3530 kcal/CU/day in the food systems reveals issues of malnutrition in India. Environmental footprints are commensurate with calorie intake in the food systems. Embodied GHG, land footprint, and water footprint estimates range from 1.30 to 2.19 kg CO2eq/CU/day, 3.89 to 6.04 m2/CU/day, and 2.02 to 3.16 m3/CU/day, respectively. Our study provides a holistic understanding of Indian food systems for targeted nutritional interventions on household malnutrition in India while also protecting planetary health. [ABSTRACT FROM AUTHOR]

The present study focuses on examining the potential of accepted gaps to assess traffic safety at unsignalized T-intersections by estimating the likelihood of a crash. Four unsignalized T-intersections with varying geometry from four different cities in India were selected. Postencroachment time (PET), a surrogate safety measure, was included in the present study to validate the results obtained through the accepted gap. The critical gap was devised as a potential parameter to evaluate traffic safety based on accepted gaps. Various probability distributions were checked for defining accepted gap and PET datasets. Generalized extreme value (GEV) was found to be the best-fitted distribution defining both: accepted gap and PET datasets. Thereafter, GEV distribution was used to estimate the likelihood of crash using accepted gap and PET datasets. The statistical check showed no significant difference in the crash probability obtained using the accepted gap and PET. Thus, the study was further extended, and risk characterization was performed using accepted gap data. The risk is characterized into different levels using the K-means clustering technique. The results attained were validated with 3 years' crash data obtained from Surat police authorities. The developed risk thresholds provided a close approximation with the crash data. Thus, it can be concluded that accepted gaps can be considered as a potential surrogate safety measure for analyzing the risk and severity of crossing conflicts at unsignalized intersections. [ABSTRACT FROM AUTHOR]

Proper regionalisation (identification of homogeneous regions) is key to reliable regional flood frequency analysis. Several methods have been proposed in the literature for regionalisation, including the method of residuals, L-moment method, and fuzzy c-means clustering algorithm. The present study explores the suitability of the theory of complex networks for regionalisation of watersheds, with an aim to perform regional flood frequency analysis. The west-flowing rivers of Kerala in India are considered for this study. Two complex networks-based methods, namely degree centrality and clustering coefficient, are applied for regionalisation, and daily streamflow data are analysed. To identify possible links between streamflow gauging stations, different correlation threshold values (i.e. linear correlations in streamflow between stations) are used. Two approaches are adopted in the use of correlation threshold values: the first (Method I) with threshold as mean, median, and mode of correlation values; and the second (Method II) with arbitrary threshold values. The regionalisation results suggest that Method II yields better results, both with degree centrality and clustering coefficient. Based on Method II, the use of degree centrality results in seven regions (five homogeneous and two heterogeneous) and clustering coefficient results in eight regions (seven homogeneous and one heterogeneous). Comparison of predicted and observed flood quantiles indicates that the degree centrality-based regionalisation yields R2 values in the range 0.94–0.86 for return periods 2, 5, 20, 50, and 100 years, whereas the clustering coefficient-based regionalisation yields R2 values in the range 0.98–0.91. The results from this present study suggest that complex network theory is a suitable alternative for identifying homogeneous regions for regional flood frequency analysis. [ABSTRACT FROM AUTHOR]

The changes in weather have beneficial and harmful effects on crop yields. There will be a loss of yield because of the diseases in crops. With the growing population, the fundamental want of food is growing. That is why agriculture gains a prominent position all around the world. It eventually ends up by a massive defeat for the farmers and the financial boom of India. The article's primary goalis to bring together farmers and cutting-edge technologies to minimise diseases in plant leaves. To enforce the idea, 'Tomato' is selected in which leaf sicknesses are expected and identified by the Artificial Intelligence algorithms, CNN (Convolution Neural Network) with pc technological know-how. Tomato is a mere consumable vegetable in India. In this investigation, seven types of tomato leaf disorders were sensed, including one wholesome elegance. The farmers are able to check the symptoms with the shapes of images of the tomato leaves with those expecting diseases. Its comparison of various classification and filters/methods with different techniques, such as K-Means classifier, SVM (Support Vector), RBF(Radial Basis Function) Kernel, Optimised MLP(Multilayer perceptron), NN classifier, BPNN (back-propagation neural network) and CNN Classifier. The classification accuracy of the existing method after experiment is RBF − 89%, k-means – 85.3%, SVM – 88.8%, Optimised MLP – 91.4%, NN – 97, BPNN – 85.5%, CNN – 94.4%. The proposed architecture can achieve the desired accuracy of 99.4%. [ABSTRACT FROM AUTHOR]

Pedestrian crossing activity at unmarked crosswalks on urban roads in developing countries like India is a common phenomenon. Pedestrians used to cross the road at their place of interest to access residential and commercial land use. Such crossing operations cause a twofold effect: first the pedestrian put themselves at high risk of collision with the moving traffic, and they also affect the normal traffic operations, which causes excessive delay to vehicular traffic. Available pedestrian crossing warrants (PCWs) based on PV2 (where P is the volume of crossing pedestrians per hour and Vis per-hourly traffic volume) focus on the safe movement of pedestrians, but traffic operation is least considered in such warrants. The present study deals with the development of pedestrian crossing facility warrants based on pedestrian safe movement along with vehicular delay, which includes traffic efficiency as well. The traffic data collected from four different locations through the videographic survey were used for evaluating the delay for the individual vehicle due to pedestrian crossing activity. The delay thus evaluated was further validated using the probe vehicle data collected during the same observation period. The vehicle was fitted with the GPS-based performance box instrument that provides the vehicle trajectory at any instance. A significant number of sample data were collected with the probe vehicle and delay was determined using trajectory data. The finding of the delay obtained from the field data was validated incorporating a simulation-based analysis to resemble the interaction of pedestrian flow dynamics with vehicular flows. The crossing behavior of pedestrians was simulated using microscopic simulation software VISSIM. The microsimulation model was first calibrated and validated for field traffic conditions. The total delay was assessed for the traffic stream, and it was found to follow a second-degree polynomial relationship with PV2 values. The clustering analysis was carried out using K-means clustering to define a threshold value for pedestrian crossing facilities. These warrants were also identified based on PV2 utilizing the relationship between total delay and PV2 values. The results of the present study will be useful for practicing engineers for designing pedestrian crossing facilities considering pedestrian safety and vehicular operation as well. [ABSTRACT FROM AUTHOR]

Drought patterns are better understood by analysing the joint dependence among long‐term drought characteristics: severity, duration, and frequency. Changes in these drought characteristics are also likely due to potential climate change, for instance, increased drought severity and duration, increased frequency of drought events, and increased spatial extent of drought impacts. In this study, we performed a regional‐scale analysis of potential changes in meteorological drought characteristics in a tropical region in India under a warming future climate scenario. The meteorological drought characteristics were computed using the Standardized Precipitation Index. The Coordinated Regional Downscaling Experiment South Asia Regional Climate Model future precipitation simulation under the RCP 4.5 scenario was bias‐corrected and utilized for future drought frequency analysis. Regionalization of meteorological drought characteristics was performed using the simple k‐means clustering technique to identify the homogeneous regions for baseline and future periods. Bivariate copula was utilized to model the dependence among the drought characteristics in order to develop the S‐D‐F curves. The changes in regionalization and regional S‐D‐F curves under future potential climate change were then investigated. The results of the study suggest an increase in drought severity by 2–3% for long‐term droughts (duration more than 5 months) in the future as indicated by upward shift and changes in the slope of the regional S‐D‐F curves. There is a projected increase in the occurrence of long‐term droughts in the future when compared to short‐term (duration of 1 to 3 months) droughts. We also observed a considerable spatial shift of drought hotspots, the severe drought‐prone regions lie in the eastern part of the study region in the future. Future projections of regional S‐D‐F curves and Spatio‐temporal drought characteristics obtained from the proposed framework may be utilized for devising drought mitigation strategies. [ABSTRACT FROM AUTHOR]

Topography evolves under the coupled effect of exogenic and endogenic governing factors, and their scale‐(in)variant dynamics. This results in a self‐affine topography across a finite range, with a characteristic fractal dimension. Fractal analysis has been used to classify geological terrains having distinct litho‐tectonic settings. However, process‐based understanding of the fractal behaviour of a natural landscape is still limited. The current study aims to substantiate and expand upon the present knowledge of topographic response to the complex actions of the governing factors using fractal characteristics. We examined the association between the litho‐tectonic, climatic settings and the fractal characteristics of the topography in the tectonically active Northwest Himalaya. Our analysis was carried out in three separate sectors having diverse litho‐tectonic settings. We used the roughness–length method to calculate the fractal parameters (fractal dimension, D; ordinate intercept, q). The Higher and the Lesser Himalaya were found to be characterized by low D and high q, while the tectonically active Sub Himalaya was found to have moderate D and low q. The southernmost foreland alluvial plains were characterized by high D and low q. Clusters of the fractal parameters were found to be consistent in spatial pattern across the three sectors. Our results showed that the geological–geomorphological settings and the associated processes (e.g. uplift, erosion and diffusion) can be well inferred using the fractal characteristics of the topography. Further, our results implied first‐order control of lithology in sustaining and shaping the topographic geometry (both its amplitude and texture) in the tectonically active Northwest Himalaya. The spatial distribution of the fractal parameters also suggested the secondary control of tectonic uplift and, to a much lesser extent, mean annual rainfall on the topographic geometry. These results collectively point to the role of complex actions of the governing factors in the landscape evolution process. © 2020 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Rural tourism in India is increasingly becoming competitive. Customers expect better services and unique experiences. It is therefore essential for the service providers to better understand the expectations of the visitors and carefully match their offers. Segmentation and targeting of the market are accepted principles of business and there has been a lot of research on the basis of segmentation. The primary objective of this article is to identify the profile of the different clusters (popularly known as segments) of motivations of tourists traveling within rural India. The intention is to decipher the causative clusters, which influences the tourists to visit the rural areas. These variables are used to identify the various rural domestic tourist market segments. A self-administered instrument was used to collect the data. Four factors have been identified through exploratory factor analysis: socialization, escape, rural experience, and self-indulgence. After identifying factors, K-means clustering was used to segment the market. The researchers have identified two relevant segments of domestic rural tourists. These are family retreaters and rural escapists. The study advances the understanding of the Indian domestic rural tourism market. It will help policymakers and practitioners to design products and marketing programs matching the expectations of these targeted markets. [ABSTRACT FROM AUTHOR]

This study utilizes cluster analysis to produce sets of weather patterns for the Indian subcontinent. These patterns have been developed with future applications in mind; specifically relating to the occurrence of high‐impact weather and meteorologically induced hazards such as landslides. The weather patterns are also suited for use within probabilistic medium‐ to long‐range weather pattern forecasting tools driven by ensemble prediction systems. A total of 192 sets of weather patterns have been generated by varying the parameter which is clustered, the spatial domain and the number of weather patterns. Non‐hierarchical k‐means clustering was applied to daily 1200 UTC ERA‐Interim reanalysis data between 1979 and 2016 using pressure at mean sea level (PMSL) and u‐ and v‐component winds at 10‐m, 925‐hPa and 850‐hPa. The resultant weather pattern sets (clusters) were analysed for their ability to represent the main climatic precipitation patterns over India using the explained variation score. Weather patterns generated using 850‐hPa winds are among the most representative, with 30 patterns being enough to represent variability within different phases of the Indian climate. For example, several weather pattern variants are evident within the active monsoon, break monsoon and retreating monsoon. There are also several variants of weather patterns susceptible to western disturbances. These weather pattern variants are useful when it comes to identifying periods most susceptible to high‐impact weather within a large‐scale regime, such as identifying the most flood prone periods within the active monsoon. They hence have potentially many forecasting applications. [ABSTRACT FROM AUTHOR]

The promulgation of the first National Telecom Policy of India in the year 1994 resulted in the geographical segregation of the country into 22 administrative units referred to as Telecom Circles (TCs). The creation of TCs was to enable targeted policy formulation and smooth implementation of the policy objectives of the government. The TCs were further clustered into four different categories, namely Metro, category A, category B, and category C, each category signaling to the telecom service providers the unique market characteristics and the Teledensity potential of the region. We attempt to reexamine today the rationale behind this unique policy experiment using an unsupervised k-means clustering technique. We identify Human Development Index, Gross Domestic Product, and Teledensity indicators to be the suitable parameters for clustering the TCs now. Interestingly, this time too, the clustering analysis suggests four categories only to be suitable for India's case. Subsequently, a fresh TC allocation exercise, based on clustering, recommends only a few re-assignments of TCs to different categories. Thus, the results largely validate the currently existing framework of TC categorization in the country without finding the need for any major overhaul. [ABSTRACT FROM AUTHOR]

Empirical test of asset-pricing models are typically performed on portfolios based on firm-characteristics such as size and book-to-market ratios etc. However, because of their strong factor structure, the characteristic sorted portfolios do not provide a sufficient test for asset pricing models. In recent, the appropriateness to use characteristics sorted portfolios has been debated. Literature suggests various alternative test portfolios sorted by other attributes to improve the empirical tests. To address this issue, we construct three sets of test portfolios sorted by firm beta, volatility, and clustering method to test various asset pricing models. We examine whether portfolios sorted by the above methods can improve the explanatory power of various alternative asset pricing models. Our test results suggest that for unconditional models, the statistical significance and estimated risk premiums depend on the choice of tests portfolios. The conditional model has more power to explain the variation of average returns than the unconditional model. [ABSTRACT FROM AUTHOR]

Data mining offers strong techniques for different sectors involving education. In the education field the research is developing rapidly increasing due to huge number of student's information which can be used to invent valuable pattern pertaining learning behavior of students. The institutions of education can utilize educational data mining to examine the performance of students which can support the institution in recognizing the student's performance. In data mining classification is a familiar technique that has been implemented widely to find the performance of students. In this study a new prediction algorithm for evaluating student's performance in academia has been developed based on both classification and clustering techniques and been ested on a real time basis with student dataset of various academic disciplines of higher educational institutions in Kerala, India. The result proves that the hybrid algorithm combining clustering and classification approaches yields results that are far superior in terms of achieving accuracy in prediction of academic performance of the students. [ABSTRACT FROM AUTHOR]

Pedestrian crossing warrants are guidelines used around the world for safe pedestrian crossing movements. Pedestrian volume (P) and vehicular volume (V) are the most widely used parameters in crossing warrants. PV2-based pedestrian crossing warrants are used in India, Iran, and UK. These warrants were first reported in UK in 1987 and adopted in India in 1988. The registered vehicles in India have increased 10 times since then. Moreover, the pedestrian crossing warrants recommended in India by IRC 103:2012 do not identify the type of crossing facility to be installed in case, the warrant criteria is satisfied. To re-examine the existing warrants, the maximum hourly pedestrian and vehicular flows estimated from the data are used as the upper bounds for developing the PV2 matrices. K-means clustering was used to obtain the new PV2 threshold values. The proposed warrant charts can be used to identify the type of crossing facility that is suitable for a location based on the observed peak hour pedestrian and vehicular volume. [ABSTRACT FROM AUTHOR]

In this study, a support vector machine (SVM)-based ensemble model was developed for reliability forecasting. The hyperparameters of the SVM were selected by applying a genetic algorithm. Input variables of the SVM model were selected by maximizing the mean entropy value. The diverse members of the ensemble model were obtained by a k-means clustering algorithm, and one ensemble member was selected from each cluster by choosing the closest from the cluster center. The optimum cluster number was selected using the Davies-Bouldin index. The developed model was validated by a benchmark turbocharger data set. A comparative study reveals that the proposed method performs better than existing methods on benchmark data sets. A case study was conducted investigating a dumper operated at a coal mine in India. Time-to-failure historical data for the dumper were collected, and cumulative time to failure was calculated for reliability forecasting. Study results demonstrate that the developed model performs well with high accuracy (R² = 0.97) in the prediction of dumper failure, and a comparison with other methods demonstrates the superiority of the proposed ensemble SVM model. [ABSTRACT FROM AUTHOR]

In recent years, Brain tumor detection and segmentation has created an interest on research areas. The process of identifying and segmenting brain tumor is a very tedious and time consuming task, since human physique has anatomical structure naturally. Magnetic Resonance Image (MRI) scan analysis is a powerful tool that makes effective detection of the abnormal tissues from the brain. Among different techniques, Magnetic Resonance Image (MRI) is a liable one which contains several modalities in scanning the images captured from interior structure of human brain. A novel hybrid energy-efficient method is proposed for automatic tumor detection and segmentation. The proposed system follows K-means clustering, integrated with Fuzzy C-Means (KMFCM) and active contour by level set for tumor segmentation. An effective segmentation, edge detection and intensity enhancement can detect brain tumor easily. For that, active contour with level set method has been utilized. The performance of the proposed approach has been evaluated in terms of white pixels, black pixels, tumor detected area, and the processing time. This technique can deal with a higher number of segmentation problem and minimum execution time by ensuring segmentation quality. Additionally, tumor area length in vertical and horizontal positions is determined to measure sensitivity, specificity, accuracy, and similarity index values. Further, tumor volume is computed. Knowledge of the information of tumor is helpful for the physicians for effective diagnosing in tumor for treatments. The entire experimentation was implemented in MATLAB environment and simulation results were compared with existing approaches. [ABSTRACT FROM AUTHOR]