Reasonable Classification Research Articles

Efficient quantum feature extraction for CNN-based learning

Hybrid quantum-classical algorithms provide a promising way to harness the power of current quantum devices. In this framework, parametrized quantum circuits (PQCs) which consist of layers of parametrized unitaries can be considered as a kind of quantum neural networks. Recent works have begun to explore the potential of PQCs as general function approximators. In this work, we propose a quantum-classical deep network structure to enhance model discriminability of convolutional neural networks (CNNs). In CNNs, the convolutional layer uses linear filters to scan the input data followed by a nonlinear operation. Instead, we build PQCs, which are more potent function approximators, with more complex structures to capture the features within the receptive field. The feature maps are obtained by sliding the PQCs over the input in a similar way as CNN. We also give a training algorithm for the proposed model. Through numerical simulation, the proposed hybrid models demonstrate reasonable classification performance on MNIST and Fashion-MNIST (4-classes). In addition, we compare the performance of models in different settings. The results demonstrate that the model with high-expressibility ansaetze achieves lower cost and higher accuracy, but exhibits a “saturation” phenomenon.

Comparative Evaluation of Rainfall Forecasts during the Summer of 2020 over Central East China

By using various skill scores and spatial characteristics of spatial verification methods and traditional techniques of the model evaluation tool, the gridded precipitation observation, known as Climate Prediction Center Morphing Technique, gauge observation and three datasets that were derived from local, Shanghai, and Grapes models, respectively, were conducted to assess the 3 lead day rainfall forecast with 0.5 day intervals during the summer of 2020 over Central East China. Results have shown that the local model generally outperforms the other two for the most skill scores but usually with relatively larger uncertainties than the Shanghai model, and it has the least displacement errors for moderate rainfall among the three datasets. However, the rainfall of the Grapes model has been heavily underestimated and is accompanied with a large displacement error. Both the local and Shanghai model can effectively forecast the large-scale convection and rainstorms but over forecast the local convection, while the local model likely over forecasts the local rainstorms. In addition, the Shanghai model slightly favors over forecasting on a broad scale range and a broad threshold range, and the local model slightly misses the rainfall exceeding 100 mm. Generally, for a broadly comparative evaluation on rainfall, the popular dichotomous methods should be recommended when considering reasonable classification of thresholds if the accuracy is highly demanding. In addition, most spatial methods are suggested to conduct with proper pre-handling of non-rainfall event cases. Especially, the verification metrics including spatial characteristic difference information should be recommended to emphasize rewarding the severe events forecast under a global warming background.

Accurate OCT-based diffuse adult-type glioma WHO grade 4 tissue classification using comprehensible texture feature analysis

Maximum safe resection of diffuse adult-type glioma WHO grade 4 (glioma °4) is a well-established procedure in order to prolong a patient’s lifetime. However, differentiation between glioma and healthy brain tissue remains a challenge in an intraoperative setting. As shown previously, the attenuation coefficient extracted from OCT images does not provide sufficient discrimination between healthy gray matter and tumor infiltrated tissue. On the other hand, the majority of published approaches based on structural information in OCT images uses sophisticated machine learning approaches as e.g. deep convolutional neural networks which bring the need for large data sets for reasonable modeling. In this work, we propose a method, which is based on comprehensible texture features and provides reasonable classification performance for healthy gray and white matter against glioma °4 samples, while requiring a relatively low number of samples for training. Our sample collective consists of 36 tissue samples from 27 different patients. Texture features based on the average contrast were optimized with respect to best discrimination of the tissue types of interest. Best discrimination could be obtained for the contrast of structure sizes of approximately 100μm. By using a linear discriminant analysis (LDA), we could achieve a sensitivity and specificity of 97.7% and 91.7%, respectively, when classifying white matter and samples with a mixture of white and gray matter against glioma °4 samples. For an extended data set, also including pure gray matter samples, we determined a sensitivity of 86.7% and a specificity of 86.3%.

Improving in-text citation reason extraction and classification using supervised machine learning techniques

In the last decade, automatic extraction and classification of in-text citations have received immense popularity and have become one of the most frequently used techniques to evaluate research. Due to the large volume of in-text citations in various digital libraries such as Web of Science, Scopus, Google Scholar, Microsoft Academic, etc., machine learning models and natural language processing techniques are being used to extract, classify, and analyze them. Typical automatic in-text classification techniques use sentiment-based classes (Positive, Negative, and Neutral). However, there are cognitive-based schemes as well that classify in-text citations based on the author’s perspective. In such schemes, extracting citation reasons with high recall is challenging. To address this challenge, we have used eight citations’ context and reason classes defined by CCRO (Citation’s Context and Reasons Ontology) to develop a machine learning model to achieve high recall without compromising on precision. We have worked on Association for Computational Linguistics Corpus with over 7000 in-text citations, randomly annotated by experts in CCRO classes. Afterwards, an array of machine-learning models is implemented on the annotated dataset: Support Vector Machine (SVM), Naïve Bayesian (NB), and Random Forest (RF). We have used various part-of-speech (Nouns, Verbs, Adverbs, and Adjectives) as novel features. Our results show that we have outperformed the three comparative models by achieving 91% accuracy.

Detection of Corneal Ulcer Using a Genetic Algorithm-Based Image Selection and Residual Neural Network.

Corneal ulcer is one of the most devastating eye diseases causing permanent damage. There exist limited soft techniques available for detecting this disease. In recent years, deep neural networks (DNN) have significantly solved numerous classification problems. However, many samples are needed to obtain reasonable classification performance using a DNN with a huge amount of layers and weights. Since collecting a data set with a large number of samples is usually a difficult and time-consuming process, very large-scale pre-trained DNNs, such as the AlexNet, the ResNet and the DenseNet, can be adapted to classify a dataset with a small number of samples, through the utility of transfer learning techniques. Although such pre-trained DNNs produce successful results in some cases, their classification performances can be low due to many parameters, weights and the emergence of redundancy features that repeat themselves in many layers in som cases. The proposed technique removes these unnecessary features by systematically selecting images in the layers using a genetic algorithm (GA). The proposed method has been tested on ResNet on a small-scale dataset which classifies corneal ulcers. According to the results, the proposed method significantly increased the classification performance compared to the classical approaches.

A hybrid machine learning model for landslide-oriented risk assessment of long-distance pipelines

Preparation of pipeline risk zoning is essential for pipeline construction and safe operation. Landslides are one of the main sources of risk to the safe operations of oil and gas pipelines in mountainous areas. This work aims to propose a quantitative assessment model of landslide-induced long-distance pipeline risk by analyzing historical landslide hazard data along oil and gas pipelines. Using the Changshou-Fuling-Wulong-Nanchuan (CN) gas pipeline dataset, two independent assessments were carried out: landslide susceptibility assessment and pipeline vulnerability assessment. Firstly, the study combined the recursive feature elimination and particle swarm optimization-AdaBoost method (RFE-PSO-AdaBoost) to develop a landslide susceptibility mapping model. The RFE method was used to select the conditioning factors, while PSO was used to tune the hyper-parameters. Secondly, considering the angular relationship between the pipelines and landslides, and the segmentation of the pipelines using the fuzzy clustering (FC), the CRITIC method (FC-CRITIC) was combined to develop a pipeline vulnerability assessment model. Accordingly, a pipeline risk map was obtained based on pipeline vulnerability and landslide susceptibility assessment. The study results show that almost 35.3% of the slope units were in extremely high susceptibility zones, 6.68% of the pipelines were in extremely high vulnerability areas, the southern and eastern pipelines segmented in the study area were located in high risk areas and coincided well with the distribution of landslides. The proposed hybrid machine learning model for landslide-oriented risk assessment of long-distance pipelines can provide a scientific and reasonable risk classification for new planning or in service pipelines to avoid landslide-oriented risk and ensure their safe operation in mountainous areas.

Comprehensive analysis of three female patients with different types of X/Y translocations and literature review

BackgroundX/Y translocations are highly heterogeneity in terms of clinical genetic effects, and most patients lack complete pedigree analysis for clinical and genetic characterization.ResultsThis study comprehensively analyzed the clinical and genetic characteristics of three new patients with X/Y translocations. Furthermore, cases with X/Y translocations reported in the literature and studies exploring the clinical genetic effects in patients with X/Y translocations were reviewed. All three female patients were carriers of X/Y translocations with different phenotypes. The karyotype for patient 1 was 46,X,der(X)t(X;Y)(p22.33;q12)mat, patient 2 was 46,X,der(X)t(X;Y)(q21.2;q11.2)dn, and patient 3 was 46,X,der(X)t(X;Y)(q28;q11.223)t(Y;Y)(q12;q11.223)mat. C-banding analysis of all three patients revealed a large heterochromatin region in the terminal region of the X chromosome. All patients underwent chromosomal microarray analysis, which revealed the precise copy number loss or gain. Data on 128 patients with X/Y translocations were retrieved from 81 studies; the phenotype of these patients was related to the breakpoint of the chromosome, size of the deleted region, and their sex. We reclassified the X/Y translocations into new types based on the breakpoints of the X and Y chromosomes.ConclusionX/Y translocations have substantial phenotypic diversity, and the genetic classification standards are not unified. With the development of molecular cytogenetics, it is necessary to combine multiple genetic methods to obtain an accurate and reasonable classification. Thus, clarifying their genetic causes and effects promptly will help in genetic counseling, prenatal diagnosis, preimplantation genetic testing, and improvement in clinical treatment strategies.

Lower limits of petrophysical parameters for effective reservoirs in ultradeep carbonate gas reservoirs: A case study from the Deng IV Member, Gaoshiti-Moxi Area, Sichuan Basin, SW China

Lower limits of petrophysical parameters (LLPP) of effective reservoirs are significant parameters for reserve evaluation and exploitation scheme formulation of hydrocarbon reservoirs. However, the existing LLPP determination method is not applicable to ultradeep carbonate reservoirs with diverse reservoir space and strong heterogeneity. Therefore, a systematic method for determining the LLPP of ultradeep carbonate gas reservoirs was developed in this study. First, the geological setting and reservoir characteristics were briefly introduced, and numerous cores were classified according to whether cavities and fractures were developed. Subsequently, the test data of petrophysical property, NMR, high-pressure mercury intrusion (HPMI), and fluid physical property were collected, and a series of LLPP values were obtained through static methods of cumulative frequency statistics, porosity–permeability relationship, irreducible water saturation, and minimum flowable pore throat radius (Rmin). The LLPP determined by static methods were then verified by dynamic methods of gas well testing, productivity model prediction, and productivity simulation experiment, and the LLPP of reservoirs that can form industrial gas flow were determined. Finally, the effect of reservoir heterogeneity on LLPP was revealed, the applicability of various LLPP determination methods were summarized, and the accuracy of the obtained LLPP was confirmed by well testing interpretations. The research results show that the reasonable classification of reservoir types is the prerequisite to accurately determine the LLPP of carbonate reservoirs. The lower limit of porosity is little affected by cavities, while the lower limit of permeability is greatly affected by fractures. Rmin of ultradeep carbonate reservoirs obtained by HPMI test and water film thickness calculation is approximately 60 nm. The significant heterogeneity of carbonate reservoirs requires that effective reservoirs should reach the lower limit of porosity and permeability simultaneously. LLPP determined through static methods and dynamic methods can be applied to evaluate geological and dynamic reserves, respectively. The LLPP of effective reservoirs that allow gas to accumulate, migrate, and form industrial gas production are 2.68% and 0.042 mD.

Automatic inference of hypoglycemia causes in type 1 diabetes: a feasibility study.

Hypoglycemia is the most common adverse consequence of treating diabetes, and is often due to suboptimal patient self-care. Behavioral interventions by health professionals and self-care education helps avoid recurrent hypoglycemic episodes by targeting problematic patient behaviors. This relies on time-consuming investigation of reasons behind the observed episodes, which involves manual interpretation of personal diabetes diaries and communication with patients. Therefore, there is a clear motivation to automate this process using a supervised machine learning paradigm. This manuscript presents a feasibility study of automatic identification of hypoglycemia causes. Reasons for 1885 hypoglycemia events were labeled by 54 participants with type 1 diabetes over a 21 months period. A broad range of possible predictors were extracted describing a hypoglycemic episode and the subject's general self-care from participants' routinely collected data on the Glucollector, their diabetes management platform. Thereafter, the possible hypoglycemia reasons were categorized for two major analysis sections - statistical analysis of relationships between the data features of self-care and hypoglycemia reasons, and classification analysis investigating the design of an automated system to determine the reason for hypoglycemia. Physical activity contributed to 45% of hypoglycemia reasons on the real world collected data. The statistical analysis provided a number of interpretable predictors of different hypoglycemia reasons based on self-care behaviors. The classification analysis showed the performance of a reasoning system in practical settings with different objectives under F1-score, recall and precision metrics. The data acquisition characterized the incidence distribution of the various hypoglycemia reasons. The analyses highlighted many interpretable predictors of the various hypoglycemia types. Also, the feasibility study presented a number of concerns valuable in the design of the decision support system for automatic hypoglycemia reason classification. Therefore, automating the identification of the causes of hypoglycemia may help objectively to target behavioral and therapeutic changes in patients' care.

Demand Grading of Emergency Medical Materials Based on Factor Analysis

Reasonable and scientific classification and urgency classification of emergency materials is the premise and basis of emergency management, which affects the effect and efficiency of emergency rescue. Emergency medical materials are related to people's life, health, and safety. In this paper, based on the early stage of COVID-19, the demand for emergency medical materials is combined to determine the demand grading evaluation indicator system, and factor analysis is used to reduce the dimensionality of data and to determine the weights of each indicator. Therefore, a comprehensive evaluation model is established and the demand for emergency medical materials is graded by clustering.

Assessing Completeness of OpenStreetMap Building Footprints Using MapSwipe

Natural hazards threaten millions of people all over the world. To address this risk, exposure and vulnerability models with high resolution data are essential. However, in many areas of the world, exposure models are rather coarse and are aggregated over large areas. Although OpenStreetMap (OSM) offers great potential to assess risk at a detailed building-by-building level, the completeness of OSM building footprints is still heterogeneous. We present an approach to close this gap by means of crowd-sourcing based on the mobile app MapSwipe, where volunteers swipe through satellite images of a region collecting user feedback on classification tasks. For our application, MapSwipe was extended by a completeness feature that allows to classify a tile as “no building”, “complete” or “incomplete”. To assess the quality of the produced data, the completeness feature was applied to four regions. The MapSwipe-based assessment was compared with an intrinsic approach to quantify completeness and with the prediction of an existing model. Our results show that the crowd-sourced approach yields a reasonable classification performance of the completeness of OSM building footprints. Results showed that the MapSwipe-based assessment produced consistent estimates for the case study regions while the other two approaches showed a higher variability. Our study also revealed that volunteers tend to classify nearly completely mapped tiles as “complete”, especially in areas with a high OSM building density. Another factor that influenced the classification performance was the level of alignment of the OSM layer with the satellite imagery.

Pollution threshold assessment and risk area delineation of heavy metals in soils through the finite mixture distribution model and Bayesian maximum entropy theory

Pollution threshold and high-risk area determination for heavy metals is important for effectively developing pollution control strategies. Based on heavy metal contents in 3627 dense samples, an integrated framework combining the finite mixture distribution model and Bayesian maximum entropy (BME) theory was proposed to assess pollution thresholds, contamination levels and risk areas in an uncertain environment for soil heavy metals. The results showed that the average heavy metal contents were in the order Zn > Cr > Pb > Cu > Ni > As > Cd > Hg, with strong/moderate variation, and the corresponding pollution thresholds were 158.39, 84.29, 47.84, 49.75, 28.95, 18.01, 0.49 and 0.16 mg/kg, respectively. The thresholds were consistently greater than the Zhejiang Province backgrounds but lower than the national risk screening values, except for Cd. Approximately 27.9% of the samples were classified as contaminated at various levels, and they were distributed in the northern, northwestern and eastern regions of the study area. Additionally, 3.73%, 5.34% and 8.22% of the total area were classified as at-risk areas under confidence levels of 95%, 90% and 75%, respectively, through BME theory. The findings provide a reasonable classification system and suggestions for heavy metal pollution management and control.

Detection of Covid 19 Using Deep Learning Approach

COVID-19 has been a major field for researchers to investigate it using deep learning techniques using Resnet, The prevalence rate of COVID-19 is rapidly raising everybody throughout the globe. Although no vaccines for this pandemic have been discovered yet, deep learning techniques proved themselves to be a powerful tool in the arsenal used by clinicians for the automatic diagnosis of COVID-19.A deep learning model is used to predict Covid-19 with high accuracy, The Reset introduces the concept of skip connection to facilitate the computation faster and results with less training error than other architectures, Reset combined batch normalization and individual residual units to solve the problem of vanishing gradients, degradation, low-quality image and provides a reasonable classification into infected of non-infected, with a average accuracy. Deep learning approach is used to provide more reliable diagnosis, specifically in resource limited areas and it also reduces the cost of diagnosis. In the proposed work, the image are passed through convolutional layer consists of residual units which is defined by Relu and Batch normalization. Finally, proceeded by fully connected layer to give the predicted output either covid-19 infected or uninfected images .This paper aims to overview the recently developed systems based on deep learning techniques using medicals imaging modalities like X- Ray.

New staging systems for left-sided colon cancer based on the number of retrieved and metastatic lymph nodes provide a more accurate prognosis.

Objectives: We aimed to explore reasonable lymph node classification strategies for left-sided colon cancer (LCC) patients. Methods: 48,425 LCC patients from 2010 to 2015 were identified in the US Surveillance, Epidemiology, and End Results database. We proposed an innovative revised nodal (rN) staging of the 8th American Joint Committee on Cancer (AJCC) Tumor/Node/Metastasis (TNM) classification based on the cut-off value of retrieved lymph nodes and survival analyses in patients with LCC. Log odds of positive lymph nodes (LODDS) stage is a numerical classification strategy obtained by a formula that incorporates the numbers of retrieved and positive lymph nodes. To develop the TrN or TLODDS classification, patients with similar survival rates were grouped by combining T and rN or LODDS stage. The TrN or TLODDS classification was further evaluated in a validation set of 12,436 LCC patients from 2016 to 2017 in the same database and a Chinese application set of 958 LCC patients. Results: We developed novel TrN and TLODDS classifications for LCC patients that incorporated 7 stages with reference to the AJCC staging system. In comparison to the 8th AJCC TNM and TrN classifications, TLODDS classification demonstrated significantly better discrimination (area under the receiver operating characteristic curve, 0.650 vs. 0.656 vs. 0.661, p < 0.001), better model-fitting (Akaike information criteria, 309,287 vs. 308,767 vs. 308,467), and superior net benefits. The predictive performance of the TrN and TLODDS classifications was further verified in the validation and application sets. Conclusion: Both the TrN and TLODDS classifications have better discriminatory ability, model-fitting, and net benefits than the existing TNM classification, and represent an alternative to the current TNM classification for LCC patients.

Development and Training Strategies of College Teachers Based on Data Mining Technology

With the increasing investment in education in China, higher education institutions have higher requirements for the introduction of teachers. This research mainly discusses the development and training strategies of college teachers based on data mining technology. Data mining technology is dedicated to data analysis and understanding, and the technology of revealing the information contained in the data. It is a frontier research topic in the field of information and database technology. Therefore, the system of monitoring and evaluation of college teaching quality based on data mining is designed for the management of educational affairs in colleges provided convenience. This paper selects an unsupervised classification method: a cluster analysis. This method can not only obtain reasonable classification results but also give consideration to the comprehensiveness of employee development and give reasonable development suggestions for each employee through classification results. For a series of introduced teacher’s information, personnel management module should provide the following functions: teacher information management, contract information management, resignation information management, and query teacher personnel information. The recruitment management module often collects the candidate information, registers and stores it, and then conducts a series of personnel screening for these candidates according to the recruitment criteria, and finally determines the possible candidates. Afterwards, a series of comprehensive evaluations are carried out on these selected candidates, and finally the candidates are selected for admission based on the comprehensive performance of the candidates. The K-means clustering algorithm in the cluster analysis method is adopted. This algorithm has the excellent characteristics of high computational efficiency and is suitable for the operation of large amount of data. Through the clustering algorithm, a reasonable assessment method is established, and it is effectively used in the human resources assessment management system. Among the introduced teachers, the number of teachers whose professional title is high, the highest degree is doctorate, and the number of teachers whose papers are published at SCI level accounts for 16%. The data tested by the data mining tool contains 1,400 rows of data. The minimum support is 5%, and the minimum confidence is 90%. This study is helpful for the rational planning of human resources and the promotion of comprehensive competitiveness of colleges and universities.

Motivating Integration Processes in Entrepreneurial Structures

The article analyzes key theories, reasons for building and functioning of integrated entrepreneurial structures. The authors regard the essence of mergers and acquisitions (M &amp; A) as economic phenomena dealing with capital concentration, which makes it possible to highlight their gradual complication with each stage of global economy development. They define the notion ‘integrated infrastructure of entrepreneurship’, which means a sum total of economic business units that reach mutual coordination in organizational-economic and financial-credit fields in order to resolve common problems and obtain synergy effect. The article studied two principle theories available in today’s economics substantiating benefits of company amalgamation through M &amp; A into integrated business structures: the theory of synergy or the theory of added economic value growth and the theory of pride. By researching detailed classifications of reasons for M &amp; A of companies, goals of integration agreements in view of their participants the classification of reasons was worked out by the following classification signs: reasons of current work efficiency, finance reasons and reasons for gaining competitive advantages. Specific features of home practice in the field of M &amp; A operations were identified and characterized, which include bankruptcy and raiding.

Progress on eco-technology classification in ecologically vulnerable regions of China

Ecological technology is the core of ecological environment governance and restoration in ecologically vulnerable regions. A reasonable classification method is the basis for induction and summary of ecological techno-logy, which is of great significance to classify and solve ecological environmental problems and evaluate the effects of ecological technology implementation. However, there is still no standard method for the classification of ecological technology. From the perspective of ecological technology classification, we summarized the concept of eco-technology and related classification methods, in view of current situation and deficiency of ecological technology related classification, we put forward a system suitable for defining and classifying ecological technology in ecologically vulnerable regions of China, and analyzed the practicality and application prospect. Our review would provide reference for the management and promotion of ecological technology classification.

Gait Patterns in Snow—a Possible Criterion to Differentiate Sika Deer and Japanese Serow Tracks

There is a compelling need to develop user-friendly and sensitive techniques to monitor sika deer (Cervus nippon) populations in snowy regions, where initial stages of deer invasion have been observed. In snow, we can easily detect footsteps of terrestrial mammals, which often serve as a useful index of population size. Here, we examined the possibility of identifying tracks with similar hoof prints left by two sympatric ungulates, sika deer and Japanese serow (Capricornis crispus), using gait patterns. We then recorded tracks of free-ranging deer and serows on the snow by following ∼200-km survey routes in the Tohoku region. We successfully recorded the gait patterns of 27 deer and 34 serows. Our key findings were as follows: 1) the step width of deer tracks (mean and SE, 20.3 ± 0.7 cm) was substantially narrower than that of serow tracks (26.9 ± 0.8 cm); 2) step width was less sensitive to body size and ground conditions for both species; and 3) the step width of 22.5 cm became an optimal threshold to maintain a reasonable classification accuracy (> 80%) for both species. Thus, the gait patterns serve as a possible criterion for identifying the tracks of these two ungulates.

Strategic Costs Analysis in Railway Operation Implementation

The basic concept of business development is focused on achieving high efficiency of projects due to a positive financial result, which implies optimization of costs with constant monitoring. The analysis of the railway transport monopolist company costs enhances their controlling influence on the entire process of road operation. Conducting a strategic cost analysis for the operation of railway company will ensure high-quality management of material, labor and financial resources of the company. Strategic operating cost analysis tools provide viable strategies for the long-term asset maintenance. The information basis for such an analysis is a reasonable classification of operating costs, which allows making strategic decisions within the framework of the estimated cost items’ existing nomenclature. Conducting a strategic analysis of the railways operating costs provides implementation of management functions in relation to costs for all elements of the management cycle. The developed model will make it possible to level the gap between the strategic goals and real costs indicators.

The Possibilities of Anti-Colonial Constitutionalism – Commentary on State of West Bengal v. Anwar Ali Sarkar and others AIR 1952 SC 75

The case of Anwar Ali Sarkar has been a founding precedent for equality jurisprudence in India and elsewhere. The case is most cited for the two-step reasonable classification test. Yet over the years, it has become increasingly clear that there are limitations to the test as a doctrinal framework to adjudicate equality. This article is a comment on Tarunabh Khaitan’s accompanying rewritten judgment on Anwar Ali Sarkar, which seeks to offer a more robust doctrine of equality grounded in the anti-colonial character of the Indian Constitution. In this piece, I locate the original judgment in its historical and socio-political context to understand the possibilities of building an anti-colonial jurisprudence of equality for and of the Indian Constitution, and to evaluate the differences between the original and rewritten judgments. I argue that the rewritten judgment offers a more robust defence of equality, in line with strands of anti-colonial ideas that shaped the framing of the Indian Constitution, as well as offering a restrained method for judicial interpretation that acknowledges historical context while centering the interpretation of law and rules.