BITS Faculty Publications
Permanent URI for this communityhttp://localhost:4000/handle/123456789/1867
Browse
80 results
Search Results
Item Deep q-learning framework based solar energy generation prediction(2022) Gupta, Karunesh KumarIn the recent years, the power system market has seen a huge shift towards the utilisation of Renewable energy sources (RES) as candidates of power generation since they proved to be a great alternative of conventional sources due to its low carbon footprints and less dependency over fossil fuels, thereby increasing the penetration of RES in microgrids. RES sources like Wind, Tidal, Hydro, Solar etc. are widely available today, among which Solar is the most popular source of energy due to its cheap running cost and easy installation. However, Solar faces complications such as intermittency which is a very big drawback to its applicability and reliability thus requiring additional strategies to increase its resiliency. A short term forecasting of solar generation might be a great solution to observe the intermittency and predict the future generation based on various factors. In this research work a Deep Q-learning framework was proposed to predict the Solar Generation and provide predictive results for special months and days like Spring equinox, Summer Solstice, Autumn Equinox and Winter Solstice. The Deep Q-learning (DQNN) framework is an amalgamation of Deep Learning networks and Q-learning technique that exploits the properties of Deep Learning networks and Q-learning technique to map the state-Q-value pair and perform the prediction process. The simulations of DQN network was performed in an open-source platform known as Keras and the prediction results were compared both in simulated and experimental datasets with other well known Deep learning networks such as CNN, LSTM, GRU and CNN-LSTM.Item A detailed comparative analysis of automatic neural metrics for machine translation: bleurt & bertscore(IEEE, 2025-04) Chamola, Vinay; Gupta, Karunesh KumarBleurt a recently introduced metric that employs Bert, a potent pre-trained language model to assess how well candidate translations compare to a reference translation in the context of machine translation outputs. While traditional metrics like Bleu rely on lexical similarities, Bleurt leverages Bert's semantic and syntactic capabilities to provide more robust evaluation through complex text representations. However, studies have shown that Bert, despite its impressive performance in natural language processing tasks can sometimes deviate from human judgment, particularly in specific syntactic and semantic scenarios. Through systematic experimental analysis at the word level, including categorization of errors such as lexical mismatches, untranslated terms, and structural inconsistencies, we investigate how Bleurt handles various translation challenges. Our study addresses three central questions: What are the strengths and weaknesses of Bleurt, how do they align with Bert's known limitations, and how does it compare with the similar automatic neural metric for machine translation, BERTScore? Using manually annotated datasets that emphasize different error types and linguistic phenomena, we find that Bleurt excels at identifying nuanced differences between sentences with high overlap, an area where BERTScore shows limitations. Our systematic experiments, provide insights for their effective application in machine translation evaluation.Item Qualitative and quantitative analysis of Indian honey samples and various adulterants using near infrared spectroscopy with water as a sensing probe (aquaphotomics) and chemometrics(Elsevier, 2025) Gupta, Karunesh KumarVarious honey samples and their adulterants from C3 plants (rice syrup) and C4 based plants (sugar syrup, corn syrup, and jaggery syrup) were analyzed using Near-Infrared Spectroscopy (NIRS) coupled with aquaphotomics and chemometric algorithms for qualitative and quantitative assessment. To validate the authenticity of the collected samples, stable carbon isotope ratio analysis (SCIRA) was performed. Spectral data for honey samples were acquired using NIRS (600–2600 nm, 1 nm resolution) and optimized using aquaphotomics by selecting wavelengths associated with water characteristics. Additionally, the aquaphotomics wavelength range was expanded by including spectral variables related to the O-H bend second overtone (1940 nm), O-H stretch/O-H bend combination (1960 nm), and O-H bend/C-O stretch combination band (2100 nm). The performance of these optimized variables was evaluated using qualitative (PCA, k-means, LDA, SVM) and quantitative (PCR, SVR, PLS) analyses, achieving a maximum classification accuracy of 100 % and a regression coefficient (R²) of 0.999. This study provides a rapid, non-destructive, and highly accurate method for honey authentication, offering significant applications in food quality control and combating fraudulent honey adulteration. The proposed approach can be effectively implemented in the honey industry and regulatory bodies to ensure product authenticity, protect consumer health, and maintain market integrity.Item Real-time water quality monitoring for distribution networks in IoT environment(Inder Science, 2022) Gupta, Raj Kumar; Gupta, Karunesh KumarWater quality has always been a significant concern worldwide as a large portion of accessible water is either contaminated or polluted, which can spread serious diseases like dysentery, diarrhoea and cholera. Before consumption, the water quality should be tested to reduce the risk of infection. In real-time applications, the traditional approach for water quality monitoring is not appropriate, as on-site water sample collection is often a cost-intensive and time-consuming process. This paper introduces a real-time assessment of water quality parameters in distribution systems employing Raspberry Pi and Arduino development boards. The parameters were chosen based on the different categories identified by the Central Pollution and Control Board, Government of India. An Arduino development board was used at the sensing node for water quality sensor interfacing, data acquisition, and transmission to the wireless sensor network via Zigbee. Raspberry Pi was used at the server to collect data and upload data on the cloud platform. The 'Thingspeak' cloud platform was used for IoT implementation. The results were validated with the reference instrument.Item Smart Water Quality Monitoring System for Distribution Networks(SSRN, 2019-06) Gupta, Raj Kumar; Gupta, Karunesh KumarDrinking water quality monitoring is essential these days as the available water is polluted and can cause several diseases like cholera, diarrhea, dysentery, etc. This paper presents a low-cost wireless water quality monitoring system based on Arduino and Zigbee Module. Water quality parameters for monitoring is decided by the Central Pollution and Control Board, New Delhi, India. The water quality sensors are interfaced with the Arduino board through signal conditioning circuit. Acquired data is sent to the server over the wireless network through the Zigbee module. At the server, Raspberry Pi is used for data receiving and results have been shown on the graphical display.Item Assessment of Water Quality Parameters in Real-Time Environment(Springer, 2020-10) Gupta, Raj Kumar; Gupta, Karunesh KumarAssessment of drinking water quality has been an important issue nowadays as the water available is severely polluted and can be the cause of diseases like cholera, diarrhea, dysentery, etc. The traditional methods for water quality monitoring require a high-labor-cost and tine consumption as these methods include a sample collection followed by lab-based chemical testing. In addition, the chemicals used in the testing are toxic and of high-cost. So, there is a need for real-time monitoring and chemical-free testing of water quality parameters. This paper presents a real-time water quality monitoring system based on the Raspberry Pi 3 development board and a Python framework. The water quality parameters utilized for water quality monitoring are temperature, pH, oxidation reduction potential, electrical conductivity, and dissolved oxygen and E. coli. The water quality sensors were interfaced with the designed embedded platform. Finally, the acquired parameters were compared with the benchmark equipment for validation.Item Towards the Green Analytics: Design and Development of Sustainable Drinking Water Quality Monitoring System for Shekhawati Region in Rajasthan(Springer, 2021-05) Gupta, Raj Kumar; Gupta, Karunesh KumarIn rural areas, there is limited monitoring of drinking water quality. Reliable water quality monitoring stations are expensive and require high costs for maintenance and calibration process. In this paper, the development of a sustainable water quality monitoring system is proposed. The green analytics principles were considered for developing the proposed system to reduce the measurement’s time consumption and labor cost. Five water quality parameters [pH, oxidation reduction potential (ORP), dissolved oxygen (DO), electrical conductivity (EC), and temperature] have been measured using the developed system. The overall drinking water quality is measured by the proposed partial least squares regression (PLSR) model. The developed system’s performance is determined by mean average percentage error (MAPE), root-mean-square error (RMSE), and R2. The traceability of water quality sensors is defined with required uncertainty in water quality parameters. The measured uncertainty is 0.002, 0.892, 0.015, 0.029, and 0.017 for pH, EC, DO, ORP, and temperature, respectively. The relation between estimated and predicted water quality parameters (R2 > 0.93) shows that the developed system can be a suitable replacement for traditional water quality monitoring techniques.Item A Review of Partial Least Squares Modeling (PLSM) for Water Quality Analysis(Springer, 2020-10) Gupta, Raj Kumar; Gupta, Karunesh KumarRegression is a powerful tool in statistical modeling suited for qualitative and quantitative analysis and widely used in forecasting and prediction. The partial least squares modeling (PLSM) is one of the regression tools used in statistical analysis. There are many fields in which PLSM has been used; water is one of them, which is an area of interest for many researchers and scientists for more than two decades. Since water has multiple parameters to analyze, there is a problem of dimensionality and collinearity. The problem of multidimensionality, as well as collinearity, can be solved by PLSM. PLS regression can be suitable for analysis as it is the most prominent multivariate regression tool. This paper describes the use of PLS regression modeling for water quality analysis of different kinds of water samples (groundwater, wastewater, river water, and coastal water). Various methods employing PLSM for water quality analysis has been discussed in detail.Item Raspberry Pi-based smart sensing platform for drinking-water quality monitoring system: a Python framework approach(Copernicus Publication, 2019) Gupta, Raj Kumar; Gupta, Karunesh KumarThis paper proposes the development of a Raspberry Pi-based hardware platform for drinking-water quality monitoring. The selection of water quality parameters was made based on guidelines of the Central Pollution and Control Board (CPCB), New Delhi, India. A graphical user interface (GUI) was developed for providing an interactive human machine interface to the end user for ease of operation. The Python programming language was used for GUI development, data acquisition, and data analysis. Fuzzy computing techniques were employed for decision-making to categorize the water quality in different classes like “bad”, “poor”, “satisfactory”, “good”, and “excellent”. The system has been tested for various water samples from eight different locations, and the water quality was observed as being good, satisfactory, and poor for the measured water samples. Finally, the obtained results were compared with the benchmark for authentication.Item Selective fluoride ion sensing in aqueous medium using ultrathin film of functionalized single-walled carbon nanotubes(IOP, 2023-12) Gupta, Raj Kumar; Gupta, Karunesh Kumar; Manjuladevi, V.The presence of fluoride ion (F-) in potable water above its permissible limit (1–4 ppm) poses serious health hazards. Hence, detection of fluoride in potable water is essential. The π-electron rich single-walled carbon nanotubes can interact with F- to form semi-covalent C-F bond which can act as a basis for F- sensing in aqueous medium. Here, a single layer of octadecylamine functionalized single-walled carbon nanotubes (ODA-SWCNTs) was transferred onto solid substrates by the Langmuir–Schaefer (LS) method and employed for sensing of F- in aqueous medium by recording piezo and electrochemical responses, simultaneously using an electrochemical quartz crystal microbalance. The lowest detectable concentration and range of detectable concentration of fluoride ion were found to be 0.5 ppm and 0.5–145 ppm, respectively. The analysis of the LS film of ODA-SWCNTs before and after interaction with fluoride ion by Raman spectroscopy and grazing angle x-ray diffraction measurement reveals perturbation of π-electrons of the SWCNTs due to semi-covalent binding of the fluoride with the carbon atom of the nanotubes. The sensor showed a good selectivity towards the F- in the presence of some heavy metal ions. Testing of the sensor towards F- in tap water obtained from some local region showed a good accuracy.