Requirement analysis is critical step before the starting of software development. There are two kinds of software requirement in software development: (1) functional requirement and (2) non-functional requirement. Visibility of Functional Requirement (FR) is very much clear in software development, but Non-Functional Requirement (NFR) is hidden in nature so much less research has been done in the area of NFR. Even though it is hidden requirement it still plays a very important role in software development because it specifies quality and constraints of the system. To automate the process of requirement classification in software development, Machine Learning (ML) techniques are used. This paper presents the exhaustive experimental analysis of traditional ML techniques used for classification of NFR. In this experimental analysis Multinomial Naive Bayes (MNB), Logistic Regression (LR), Support Vector Machine with Stochastic Gradient Descent (SVM-SGD) and K-Nearest Neighbours (KNN) algorithms are analysed in terms of accuracy, recall, precision, and F1-Score to classify the NFR. As the data set to perform this experimental analysis, the PROMISE repository is used. In this work results show that SVM-SGD outperforms all the ML techniques by giving the F1-Score 00.92, Recall 00.92, Precision 00.93 and Accuracy 00.92.

Accounting potential zones for recharging groundwater is a prerequisite before the implementation of the springshed conservation program. Many studies have suggested that the resurgence of the springs in the Himalayan region is waning due to anthropogenic and Climate Change impacts. Typical physical methods of recharge zone explorations are manpower fiscal-intensive and find limited applicability in areas with steep slopes and undulating topography. The deliberated study is an attempt towards the identification of potential recharge zones using topographical and meteorological indices via two MCDM methods, namely, AHP and Fuzzy AHP for the Saryu watershed of Kumaun Himalaya, Uttarakhand. Twelve thematic layers following the assignment of suitable weights were overlayed for the development of the groundwater recharge potentiality map. The findings indicated that following AHP 6

In software development processes, finding the requirement before developing the software is essential. There are two kinds of the requirements in software development: functional requirement and Non-Functional Requirement (NFR). For functional requirement a lot of research work has been done but for NFR very limited research has been done. NFR is critical for software development because it specifies quality and constraints of the system. A critical aspect of analysing NFRs is domain knowledge, expertise and significant human effort, since NFRs are written in natural language. To automate the software requirement classification many ML-based techniques are being developed. In this paper, the proposed CNN model obtained the accuracy, recall, precision, and F1-score of 0.984, 0.99, 0.984, 0.984 and 0.989, 0.99, 0.988, 0.999, performance respectively for BOWs and TF-IDF feature selection techniques. The proposed performance varies with respect to the number of requirement classes, but proposed CNN techniques performed better than the existing machine learning techniques.

With the increasing space between need and supply of natural resources, ‘sustainability’ became the talk of the hour. The escalating population worldwide has called for a judicial approach towards the usage of all kinds of non-renewable and natural resources. In the race of the crisis of natural resources, water has marked a striking position over the decades. The deficit for this elixir could be blamed on both natural and anthropogenic causes. For the latter, choosing the unsustainable path for a long time has made the crisis scenario worst than ever. The available amount of water would have been sufficient had it been well-governed, regulated, supervised and used in a prudential manner. India also has its fair share of water scarcity, especially in the Indian Himalayan Region, along with many other countries of the world. The alarm of deteriorating water was neglected for the longest time in IHR. Both the eastern and western Himalayan states have their own story to tell about the crisis. Even after having common reasons aiding the scarcity, there is end number of region-specific factors as well. Certainly, those factors must be studied and taken into consideration. Rapid urbanization in this fragile ecosystem has added to the aspects of water scarcity. It is very necessary to have a unique and specific solution for all the states. Despite the contribution mountains make towards feeding and sourcing a large number of perennial rivers, the health of the mountainous ecosystem still remains inconspicuous. The rate at which water scarcity is increasing might lead to a situation where the term ‘water’ becomes an endangered concept of the future generation. So, working towards making a sustainable environment is a pressing priority. This review paper has shed light on many factors of water scarcity across the states of the Indian Himalayan Region, along with a comparative study on issues of both the eastern and western belt of IHR.

Springs and streams are essential sources of fresh water for the Himalayan population. To global and regional extents, these resources are being severely affected by climate change as well as anthropogenic activities. However, the effects of seismicity also have considerable influence on springs but are negligibly studied in that aspect. Crustal deformation, shaking, and movement of the earth's surface due to an earthquake, can modify the stream flow and water level in wells through consolidation of surficial deposits and development of new fractures. The present study addresses the effect of an earthquake on water springs in a seismically active zone. On 18 September 2011, the Sikkim Himalaya experienced a strong earthquake of magnitude (Mw) 6.9. To assess the impact of this earthquake on hydrology, we studied the springs located in the South Sikkim district, India. Our research indicates that few springs dried up following the Mw 6.9 earthquake in 2011 while some springs discharged at a higher rate than before. The springs which were dried up due to climate change were excluded in this study. Furthermore, our study suggests that in tectonically active mountain ranges, like Himalaya, an earthquake not only causes surficial deformations but also influences the hydrological framework at a regional scale. Therefore, the seismic nature of the terrain should also be considered for spring rejuvenation policies.

The elicitation of non-functional and functional needs is one of the most critical jobs of a requirement engineer. This scenario involves the imposition of limits on non-functional needs, whereas functional requirements call for the operation of a system in order to carry out functionality. Over the last few years, agile software development approaches have gained widespread acceptance in the software industry as a problem-solving paradigm. Non-functional requirements (NFRs) are frequently cited as a point of contention in non-functional requirements (NFR) approaches. As well as functional requirements like speed and efficiency, security is desired, amongst a host of other things. Aspects like usability, security, and privacy must all be taken into account. Functional needs must be treated as though they were first-class under the current industry standard of practice. Functional requirements are distinguished from non-functional requirements by the fact that only implemented requirements can be evaluated. To give an example, this method attracts the attention of the system's end users to a critical defect in its architecture. Projects of this type frequently fail because to dissatisfaction among the target audience. If you'd like a great demonstration, consider the London Ambulance System. When dealing with non-compliance to the necessary degree of detail, it is feasible to raise the likelihood of software success this is the first study of its kind in its sector to bring attention to the most critical NFR issues. The problems that arise during the elicitation stage of requirement engineering in agile base models. It also outlines the techniques and strategies that are being considered. Proposed in the literature as a means of dealing with these problems.

The discharge pattern of springs in the Himalayan region is highly variable due to diverse lithology, complex hydro-geological formations and dynamic tectonic activities. Therefore, delineation of groundwater recharge potential zones is extremely essential for sustainability of groundwater resources in Himalayan region. Apart from delineating potential zone, it becomes more important to evaluate the identified recharge zones for their validity. The current study therefore, was aimed to delineate recharge potential zones that suggested the suitable sites where potential of recharging groundwater is more. Second objective of the study included evaluation of identified recharge sites/zone through implementation of groundwater recharge structures followed by monitoring discharge in Upper Kosi watershed in Uttarakhand, Kumaun Himalaya, India. Standard technique was established in order to detect potential recharge sites through allocating weightage as well as score to various controlling through multi-criteria decision-making approach in GIS domain. The results indicated that only 19.6% area in the Upper Kosi basin lied in good to excellent recharge potential. However, 31.7% and 15.2% area lied in fair and moderate recharge potential which was also considered as suitable for execution of artificial recharge structures. Moreover, a slow recession in discharge was observed from the treated micro-watershed as compared to the untreated one. This validates the legitimacy of the recharge zone(s) identified using the contended approach.

The inspection of insulator faults is an important task to prevent catastrophic failures in the operation of an electric substation. Manual inspection of overhead power line insulators can be very dangerous owning to the presence of high voltage in power sub-stations. Hence, in this paper, we present an infrared thermal (IRT) camera based non-invasive computer vision system for automatic monitoring and visual inspection of overhead on line power insulators. In the proposed work, initially, an optimal threshold method is applied to segment the region of interest (ROI) in IRT images. Subsequently, various geometrical, morphological, intensity and statistical features are computed from the segmented ROI, which are eventually utilized as an input to Gaussian kernel support vector machine to classify the different type of faults in insulator images. Computer vision based automatic inspection of insulators can play an important role from environment as well as human safety point of view. Timely inspection of insulators can ensure the environmental safety through prevention of fire that may be caused due to the insulator failures leading to the sudden breakdown of high-power lines. The proposed system achieved the true positive rate (TPR), and false negative rate (FNR) of 97.3%, and 2.66%, respectively. Whereas, the system obtained the Positive Predictive Value (PPV) and False Discovery Rates (FDR) of about 97% and 3%, respectively with the accuracy of 0.97 on the receiver operating characteristics (ROC) curve. The performance of the proposed method is compared with other existing state of the art methods and found that our method outperformed over them. Hence, we recommend proposed system to detect the severity of faults in IRT images long before any catastrophic failures take place at power sub-stations. (C) 2021 Published by Elsevier B.V.

The main aim of this study was to setup and evaluate the applicability of physically based soil and water assessment tool (SWAT) model with ArcGIS version 9.3 in assessing the runoff and sediment load from Mojo watershed having a total area of 2017.21 km(2) situated in central Oromia Regional state, Ethiopia. In this study for stream flow simulation parameters involving surface runoff (CN2.mgt) and ground water (ALPHA_BNK.rte) are found the most sensitive parameter and the parameters representing channel process (SPCON.bsn, SPEXP.bsn &ADJ_PKP.bsn), geomorphology (SLSUBBSN.hru) and surface runoff (CN2.mgt, & HRU_SLP.hru), were found more sensitive for sediment load simulation. There are a good agreement between the observed and simulated discharge, which was verified using both graphical technique and quantitative statistics. The value of R-2 = 0.75, NSE = 0.76, RSR = 0.49 and PBIAS = 10.9 obtained during calibration and R-2 value 0.71, NSE value 0.70, RSR value 0.59 and PBIAS 9.5 obtained during validation as well as the uniformly scatter points along the 1:1 line during calibration and validation justify that the model is good in simulating runoff from Mojo watershed. For sediment load the computed statistical indicators R-2 = 0.77, NSE = 0.76, RSR = 0.49 and PBIAS = 48.70 were obtained during calibration and during validation the computed statistical indicators were found 0.67 for R-2, 0.65 for NSE, 0.59 for RSR and 50.5 for PBIAS. From the calibration and validation result, it can be concluded that the calibrated parameter values of SWAT model can be used for hydrologic simulation of the un-gauged watershed that is having the similar agro-climatic condition.

A convenient and acceptable technique to develop mathematical models is through conceptual formulation and statistical development while integrating the effects of various variables on these physical processes. Overemphasizing on these techniques could result in an increase in complexity of model which in turn influence the performance of the model. In this study, one conjunction model combining wavelet-neuro-fuzzy for runoff forecast is proposed and compared with simple neuro-fuzzy inference system. The inflow series to the conjunction model has been decomposed by wavelet transform. The performance of the conjunction model under the changed inflow parameters has been compared with the simple model. The results show that both the model performed well, however, increase in complexity of a model does not necessarily increase the performance of the model.

Khulgad watershed is the constituent of the Kosi river basin and is located to the west of the Almora town in the Hawalbagh Development Block of Almora district in the Uttarakhand.The watershed is bounded within 79°32'20.71"to 79°37'11.19"E longitude and 29°34'30.20"to 29°38'48.03"Nlatitude, covering an area of 32.57km 2 and having cool temperature climate with an annual average temperature of 20°C.To achieve the Morphometric analysis, toposheet No. 63 C/ 2 Survey of India (SOI) in 1:50000 scales are procured and the boundary line is extracted by joining the ridge points.This will serve as area of interest for preparing base map and thematic maps.The drainage map is prepared with the help of geographical information system tool and morphometric parameters such as linear, aerial and relief aspects of the watershed have been determined.These dimensionless and dimensional parametric values are interpreted to understand the watershed characteristics.From the drainage map of the study area dendritic drainage pattern is identified.Strahler (1964) stream ordering method is used for stream ordering of the watershed.The mean bifurcation ratio of the watershed is 3.49.

Prediction of direct runoff using geomorphologic instantaneous unit hydrograph (GIUH) for a fourth-order hilly subwatershed of the Ramganga River Catchment in Uttarakhand (India) is presented. Based on kinematic-wave theory, the GIUHs were derived using two approaches: (1) geomorphologic parameters (GIUH-I) and (2) stream-order-law ratios (GIUH-II). The travel times for the overland-flow and the stream-flow in Horton-Strahler stream-ordering system of the watershed were determined analytically and probabilistically. The statistical analysis showed better overall correlation between predicted and observed direct runoff hydrographs for GIUH-II approach as compared to GIUH-I; however GIUH-I gave marginally better prediction of peak rate and volume of runoff. The time to peak was consistently underpredicted by half hour for all the storm events. The results in general indicate reasonably good applicability of these approaches to estimate direct runoff from ungauged hilly watersheds for better water management planning in the region.

The main aim of the present study was to develop a autoregressive model for annual streamflow of Godavari river. Autoregressive models of order 1,2.3.4 and 5 were tried. AR (I) model was found suitable based on Box- Pierce Portmonteau test and Akaike Information Criterion test. The mean and skewness of generated series were found close to historical values. The mean forecast error. mean relative error and integral square error indicates a high degree of model fitness to the observed data series.

Discrete Linear sediment models were developed using sediment mobilized and direct sediment flow graphs of Chaukhutia watershed of the Ramganga reservoir catchment, India, and applied for sediment flow routing. The parameters of the models were estimated by Lagrangian method. The sediment graphs computed by these models compared with remarkable accuracy to the measured sediment graphs. The average values of integral square error, coefficient of efficiency and ratio of mean error to the mean observed output for four parameter sediment discharge model are 5.991 %, 97.183% and 0.0022 respectively. For three parameter sediment discharge model, the average value of relative error in estimated peak is 6.976%.

A geomorphologic instantaneous unit hydrograph (OIUH) model, based on kinematic-wave and stream order ratios, has been developed to predict the direct runoff hydrograph from a hilly sub-watershed of Ramganga river catchment in Uttaranchal (India). The travel times for overland and stream flows in a stream-ordering system of the watershed have been determined analytically and probabilistically to derive the OIUH, without using the past record of rainfall and runoff data. The performance evaluation of the developed model indicates that the predicted and observed direct runoff hydrographs for the storm, events occurring in the watershed are in good correlation. Since the development of this model utilizes only the geomorphological parameters of the watershed, this model is very well applicable to any ungauged hilly watershed.

Linear discrete input-output models were developed for estimating sediment discharge hydrographs from the Chaukhutia watershed comprising an area of 452.25 km2 of the Ramganga reservoir catchment. The causative factors such as sediment mobilized, direct runoff and excess rainfall water was used as input to the models and sediment discharge as the output. The parameters of these models were estimated from rainfall hyetographs, direct runoff hydrographs and direct sediment flow graphs by Lagrangian's method. The generation and prediction performance of these models were assessed based on pattern recognition technique and using the criteria of accuracy. The computed sediment graphs were in closer agreement with measured sediment flow graphs. The average values of coefficient of efficiency and relative error in estimated peak for sediment mobilized-sediment discharge model were more than 96.0% and less than 7.6 %, respectively whereas for direct runoff-sediment discharge model the values were more than 79.0% and less than 18.8%, respectively. For rainfall excess-sediment discharge model these values were more than 57.0% and less than 29.0, respectively.