Search

Author presents a study of transverse momentum dependent(TMD) factorization formalism to investigate three dimensional spin structure of a proton. In this study we focus on evolution of collinear partons (quarks and gluons) distribution functions (PDFs) and Fragmentaion functions (FFs) to their evolved TMD versions. We present a review of quantum chromodynamics (QCD) factorization formalism which represents a formulation to calculate the cross section for QCD hard process like Drell-Yan (DY). In this study we present a framework of TMD factorization which allows PDFs and FFs to depend on intrinsic transverse momentum in addition to usaul momentum fractions. This study leads to understand a nautural and advanced step in the investigation of nucleon structure in an exapansion of our current picture by imaging the proton in both momentum and impact parameter space. [ABSTRACT FROM AUTHOR]

COVID-19 disease is caused by a contagious family of corona virus. The dynamics of infectious novel virus SARS-Cov-2 is studied in this paper. We have studied a 7 class Susceptible-Exposed-Vaccinated-Asymptomatic Infected-Symptomatic Infected-Hospitalized-Recovered (SEVI1I2HR) model. Local stability for the equilibrium pointsis established with the help of Routh Hurwitz criterion. Proof of Global stability of the endemic equilibrium is done with Dulac's function. Numerical simulation carried out for the model suggests that minimizing the contact rate, hospitalization of the infected and vaccinations for all are the only ways to control the pandemic COVID-19. Sensitivity analysis of the considered parameters in the Basic Reproduction Number (R0) was performed to understand the most affected and sensitive parameters of the model. It was observed that R0 is directly proportional to the contact rate while inversely proportional to vaccination rate. [ABSTRACT FROM AUTHOR]

Every day, a large number of people disappear for a variety of reasons, such as advanced age, mental illness, emotional disorders, Alzheimer's disease, etc. The process to find the missing individual faints because the majority of them go unfound. We propose a solution for the same. A record of each newly filed case is kept in the application's database. Anytime someone like this is encountered, they take a photograph of them and appearance up their data with inside the database. If no matches are found, they can upload the data to the database (optionally: if known), save the current location while uploading, and alert higher authorities to the problem. The other scenario is that if a match for the missing individual is discovered, the database's information will be accessed, and police or the family will be notified. [ABSTRACT FROM AUTHOR]

This study examines the critical role of ocean thermal еnеrgy convеrsion (OTEC) in alleviating frеshwatеr scarcity and increasing еnеrgy dеmand in India. OTEC is еmеrging as a disruptivе force with diverse applications such as powеr gеnеration, frеshwatеr production, hydrogеn production, and off-grid aquaculturе еnеrgy. As freshwater supplies decrease and renewable energy targets become more ambitious, OTEC is poised to play a significant role The study underlines the potential contributions of the Indian Ocean Deep Mission and OTEC in India's energy landscape. It underscores the benefits of OTEC, identifying the important research gaps and highlighting supportive regulatory frameworks, stakeholder perspectives, technological improvements, and complex socioeconomic and political issues. The realization of OTEC's full potential in India is еssеntial to address thе shortage of skillеd manpowеr and conduct comprehensive environmental considerations. [ABSTRACT FROM AUTHOR]

The sentiment classification is a real time process of automatically detecting the reviews in text and classifiedthose emotions such as negative, positive, or neutral. Most of the research focuses on sentiment analysis based on neural network methods for extracting the text from the reviews. The sentiment analysis is similar to the classification, where the extracted features are fed to the classifier as an input to predict an output. In this study, the hybrid method of two deep learning models are long short term memory (LSTM) and Convolution neural network (CNN) applied in the classification of sentiment reviews. The big data of sentiment analysis based on the topics of sensitive information. The hybrid method of Multi-head Attention (MHAT) with Bidirectional Long-Short Term Memory (BiLSTM) based on Chinese text social media for sentiment analysis. The Gated recurrent unit (GRU) has the limitations such as less convergence rate, decreases the learning efficiency and under fitting problem. The SVM has the limitation of large dataset is not suitable, more complexity and noise and the RNN model has the exploding vanishing gradient issues. [ABSTRACT FROM AUTHOR]

Performance appraisal systems (PAS) have been identified as one of the most difficult tasks in human resource management, with a negative impact on employee-employer relationships. It not only inspires employees but also increases an organization's production. Performance assessment is regarded as a critical tool and is used in virtually all types of organizations, with a few exceptions. Performance assessment systems have integrated new values and desirable behaviors in an attempt to influence the actions and attitudes of employees in businesses. Organizations have been more eager in recent years to improve the performance of their personnel. The chapter's aim is to discover the performance assessment method used in businesses and its impact on employee competencies and efficiency. It focuses on the issues and repercussions that companies confront, as well as the best practices implemented for effective implementation. Using data from 150 workers and regression research, we will evaluate and investigate the relationship between employee happiness and maximizing company performance with or without the level of supervising employee as a moderating variable. We discovered that quality connection supervisor employee plays an important function and can improve job happiness. This research also makes recommendations for strengthening the connection between the supervisor and the employee, as well as the efficacy of performance assessment in a company. Finally, this paper study will make recommendations on how to enhance supervisor-employee relationships in order to boost the degree of work satisfaction among employees in a government organization. [ABSTRACT FROM AUTHOR]

Twitter is an American social networking and blogging site where users can communicate through messages known as "Tweets. The number of characters is restricted to 280 for all languages except Korean, Chinese and Japanese. Users on social media platforms tend to easily believe the contents of posts related to any random events and some of these events happen to be fake. Twitter spammers may fulfill their malicious objectives, such as spam sending, distributing malware, hosting botnet command and control (C&C) networks, and launching other illicit activities in the underground. Hence, we have proposed a system that will not only help in finding the type of spammers but also eliminate identical tweets. So we have implemented multi-classifier algorithms such as naive Bayes, K-Nearest neighbor, Decision tree and Random forest on a dataset obtained from Twitter and their performance is compared, also the most accurate algorithm is found out. The results of the experiment have been very positive. [ABSTRACT FROM AUTHOR]

Genome editing is a novel technique to precisely manipulate genomic nucleotide in various organisms. The type II CRISPR/Cas9 system which is a part of the adaptive immune system of S. Pyogenes bacteria have governed this generation of genome engineering as it is straightforward to program and use. In a CRISPR/Cas system, the short gRNA sequence (20bp) controls the quality (accuracy and precision) of DNA cleavage. Even though various machine learning classifier algorithms are already being developed to evaluate the efficiency of gRNA and to predict off-targets but, there exist a discrepancy between predictions and experimentally observed results. A comprehensive analysis is required to identify a reliable CRISPR/Cas prediction algorithm. In this study, we aim to filter efficient classifier for evaluating CRISPR gRNA efficiency by exploring various classification algorithms on experimentally verified datasets of CRISPR. Also, we did a comparative study of their performances using machine learning software, WEKA. By using a 10-fold cross validation on the CRISPR dataset with 5310 instances and 9 attributes, we assessed the performance of 10 different machine learning algorithms by comparing their execution speed, completion time, precision, accurately and misclassified incidents, kappa statistics (K), mean absolute error, root mean square error, and true values of the confusion matrix. Our analysis suggests that tree-based classification algorithms have better potential to predict the efficiency of sgRNA in case of CRISPR genome editing system. In this research, we elaborate on the application of artificial intelligence to categorize and assess the features of gRNA to predict its efficacy and precision. [ABSTRACT FROM AUTHOR]

Vehicular Ad Hoc Networks (VANETs) are a subset of Mobile Ad Hoc Networks (MANETs) that are formed by vehicles installed with wireless devices. In VANET, communication occurs between Vehicle 2 Vehicle mode and Vehicle to road side unit, resulting in a good communication system. Routing is critical in getting the necessary data to the nodes or vehicles. In this paper, we examine the performance of reactive routing protocols like AODV and DSR, as well as proactive routing protocols like OLSR and DSDV, in an urban city traffic scenario using SUMO, and network performance using NS3 to find an appropriate protocol by using network parameters like packet delivery ratio, throughput, and delay. Based on the simulations, we discovered that AODV outperforms the others [3]. The results upon simulation. Location of real-world has also been simulated in addition. [ABSTRACT FROM AUTHOR]

Given the importance of visual vetting inspections in risk analysis the current article examines the role of mindfulness in enhancing the quality of these inspections by mitigating implicit bias in human inspectors and machine learning technology. Accordingly, the relationship between mindfulness and human bias is reviewed furthermore, association between mindfulness, human cognition and machine learning is explored. Based on premises of neuroscience, technology and cognitive psychology hypothetical model is proposed. The conceptual findings established that mindfulness may have the potential to provide a feasible solution for reducing bias in both humans and machines. Such unbiased objective inspections will have a tremendous impact on management and control of safety in organizations involving high risk factors such as shipping, aviation and healthcare. [ABSTRACT FROM AUTHOR]

Hexagonal Boron Nitride is readily machinable with high dielectric breakdown strength, thermal stability, and expansion, chemical inertness, and unique piezoelectric and pyroelectric capabilities. Thus, it possesses a wide scope for application in robotic sensors, actuators, and energy-related devices. A contact electrification-assisted piezoelectric nanogenerator (BCPENG) made of boron nitride nanotubes (BNNT) combined with carbon nanotubes (CNTs) was created to produce strong electrical outputs. The triboelectric nanogenerator principle is used to test this manufacturing which promises the viability of employing it successfully as kinematic sensors. Thus, new research is proposed to use it in the fabrication of robotic sensors and robot flex motion. Despite all the advantageous features, practical applications remain challenging. Various obstacles like structural variation, durability, recovery, and cost hinder future research and applications. Also, its physio-chemical properties are yet to be explored for prospects in robotics (robotic arm designing). In addition to the development of synthetic techniques, logical tools to properly resolve the defective structure are still required to comprehend the connections between structure and property. Quantitative Structure-Activity/Property Relationship (QSAR/QSPR) is an effective analytical method to explore the physio-chemical properties of any molecular structure. Topological Indices are an important tool in QSAR/QSPR studies. Topological Indices (TI's) are simple numerical descriptors that give a numerical value for the relation between the atom arrangement in any chemical structure with its intrinsic physical properties. In this paper, we can calculate the Discrete Adriatic indices of boron triangular sheet BTS that predict the heat capacity, octanol-water partition coefficient, TSA(Total Surface Area) and the standard enthalpy of vaporization to any length and breadth. The results further facilitate the detection of effective/defective structures and enhance durability at a low cost for robotic arm designing. [ABSTRACT FROM AUTHOR]

Diabetes is one of the lifelong chronic metabolic diseases which is prevalent globally. There is a continuous rise in the number of people suffering from this disease with time. It is characterized by hyperglycemia, which leads to severe damage to the body's system, such as blood vessels and nerves. Diabetes occurs due to the dysfunction of pancreatic β-cell which leads to the reduction in the production of insulin or body cells unable to use insulin produce efficiently. As per the data shared International diabetes federation (IDF), there are around 415 million affected by this disease worldwide. There are a number of hit targets available that can be focused on treating diabetes. There are many drugs available and still under development for the treatment of type 2 diabetes. Inhibition of gluconeogenesis, lipolysis, fatty acid oxidation and glucokinase activator is emerging targets for type 2 diabetes treatment. Diabetes management can be supplemented with drug intervention for obesity. The antidiabetic drug sale is the second-largest in the world, trailing only that of cancer. The future of managing diabetes will be guided by research on various novel targets and the development of various therapeutic leads, such as GLP-1 agonists, DPP-IV inhibitors, and SGLT2 inhibitors that have recently completed their different phases of clinical trials. Among these therapeutic targets associated with type 2 diabetes, this review focused on some common therapeutic targets for developing novel drug candidates of the newer generation with better safety and efficacy. [ABSTRACT FROM AUTHOR]

Cancer is a disease that leads to cellular changes, resulting in the uncontrolled growth and division of cells. Cancer cells extend to former parts of the body through the lymphatic systems and blood. Cancer is a second major burden of death globally. Every year, tens of millions of people are identified with cancer worldwide, and more than half of the patients ultimately die from it. Indole-based various compounds show diverse medicinal properties including anticancer. This indole scaffold plays a vital role in the progression of anticancer drugs as a core nucleus. Enzyme binding pockets inside the body have more affinity to interact and bind with indole rings. This indole scaffold is of good choice when designing molecules that will coordinate with target sites and interrupt the biological pathways linked with cancer progression. There is about 65% of the nitrogen-containing heterocyclic anti-cancer drugs allowed market approval by the FDA between 2010 and 2015 that form the basis for new anti-cancer agents in drug discovery and development. A large amount of work is going on, as well researchers are focusing on the N-heterocyclic indole skeleton in drug development for cancer treatment. The advantages of indole nucleus containing drugs in the medicinal field include easy preparation, low toxicity, less adverse effects, high bioavailability, lower drug resistance, and good biocompatibility. [ABSTRACT FROM AUTHOR]

The most common form of cancer among women is metastatic breast cancer. One of the world's three most common cancers, it is the second leading cause of death in the United States, following lung cancer. A plethora of drugs are available for breast cancer treatment. One of the promising new candidates for this type of tumor is Kisquali (Ribociclib), a selective cyclin-dependent kinase (CDK) 4 and 6 inhibitor. Ribociclib was recently developed by Novartis and approved by the USFDA under the trade name of "Kisquali" for the treatment of advanced receptor hormone positive (HR+), an inhibitor of human epidermal growth factor 2-negative cancer (HER2-). It functions by phosphorylation inhibition and can decrease the count of CDK4/6. In addition, Ribociclib also shows different interactions since the metabolism of the drug can be changed by enzyme inducers and inhibitors. Ribociclib was tested for multiple solid tumors and lymphomas in Phase I and II trials and further underwent Phase III studies in breast cancer. Results from Phase I and II trials on positive estrogen receptor (ER1) breast cancer indicate promising efficacy with controlled toxic effects, primarily neutropenia. All the successful approaches of this promising candidate are underlined in this study. [ABSTRACT FROM AUTHOR]

The green synthesis of silver nanoparticles is emerging as a potent approach to harvest the potential of silver and plant extracts in improving health. It is simple, cost-effective, non-toxic and eco-friendly than earlier physico-chemical approaches. Juvenile wheatgrass extract has been well proven for its anti-cancerous and anti-oxidant potential. In this study juvenile wheatgrass extract mediated synthesis of silver nanoparticles was approached. The characterization of nanoparticles was performed by Ultra violet-visible (UV-VIS) spectroscopy and transmission electron microscope (TEM). Antioxidant activity of nanoparticles was checked by the 2,2-diphenyl-1-picryl-hydrazyl-hydrate (DPPH) scavenging activity, bacterial activity was evaluated using agar well diffusion methods. Chorioallantoic membrane assay (CAM) assay was done on chicken eggs to elucidate its anti-cancer activity. Blood vessels were quantified using a software for image analysis and density of microvessel was also elucidated. The Ultra violet-visible (UV-VIS) spectroscopic absorbance peak at 380 nm confirmed the formation of silver nanoparticles while TEM confirmed the spherically shaped silver nanoparticles had an average size of 16.5 nm. Further, to explore the biological activities of these green synthesized nanoparticles, in vitro studies were carried out. The nanoparticles synthesized using wheatgrass extract showed significant free radical DPPH scavenging activity of 52.9±0.49 % inhibition. Antibacterial activity was seen against Gram-negative bacteria Escherischia coli (E. coli). The zone of inhibition of 1.8±0.029 cm was seen against bacterial culture. In addition, wheatgrass nanoparticles were also demonstrated to possess anti-angiogenic potential by CAM assay as the number of blood vessels significantly decreased. Results show the potency of wheatgrass as an antioxidant, anti-angiogenic and anti-bacterial compound. [ABSTRACT FROM AUTHOR]

Rice leaf infections have been reported all over the world, especially in China. They have a significant impact on rice productivity and quality. The majority of current control mechanisms rely on artificial means. Due to their lack of knowledge, farmers find it extremely difficult to detect these diseases. Recent breakthroughs in Deep Learning have revealed that the Image Recognition approach based on CNN models can be particularly effective in these scenarios. The CNN classification approach is used for both 2D and 3D pictures. CNN has several built-in algorithms and functions. Brown Spot, Leaf Blast, Hispa, and Healthy are the four disease categories in the dataset. [ABSTRACT FROM AUTHOR]

It was discovered that Coronavirus disease of 2019 (COVID-19) caused the death of a multitude of lifes and caused health problems and weakness. The WHO has declared this a pandemic. Hundreds of thousands of people are infected every day with this virus. In order to aid in automating the scanning process, researchers are using medical images such as X-rays and computed tomography (CT) scans, and also AI-based systems, to assist in the diagnosis of COVID-19 due to the complexity and expense of conventional reverse transcription polymerase chain reaction (RT-PCR) methods. Here, we reviewed a number of those emerging AI-based models with the ability to recognize COVID-19 based on X-rays or CT scans of lungs. As of June 20, 2021, we examined research papers and collected information about available resources. In order to discover future research directions towards self-learning diagnosis of COVID diseases, also explored different datasets and analyzed experimental results of various algorithms. Researchers at the novice and beginner levels can use this survey to begin their work on COVID classification. [ABSTRACT FROM AUTHOR]

Computer Vision and Natural Language Processing methods have been employed in Artificial Intelligence to describe the content of a picture. It is useful in assisting the visually impaired, as well as in self-driving automobiles and other applications. It is not simpleto describe an image, in order to do so, we must use appropriate phrase structure. However, by utilizing deep learning techniques, the process becamesimple and straightforward. CNN (pre-trained Xception model) and LSTM were the algorithms we employed. Convolutional neural networks are deep learning algorithms thatextract features from an input image. The extracted features are sent to the next layer,which is then fed to LSTM. In LSTM, we use a sequence processor to get sentences in order, and then we construct the final caption of the input image through LSTM. It is a type of deep convolutional neural network with depth-wise separable convolutions. We used Flickr_8k dataset.We used Google Colab for training and testing the model. An image will be given as input, the caption will be generated describing the image and the caption is read out(converted to audio) when selected by the user. [ABSTRACT FROM AUTHOR]

The study analyses the determinants of net inward FDI for four Asian countries, China, Japan, India, and Korea by considering the generic FDI theory models like Flying Geese Model and Eclectic theory. It considers GDP growth rate, Inflation (proxy for economic stability), Nominal exchange rate and Real interest rate (proxy for cost of capital) as the independent variables. The paper finds the existence of a long run cointegration between FDI inflow, GDP growth rate, Inflation and exchange rate using ARDL model with significant Error Correction Terms for all four countries. However, the analysis finds out that no specific set of common variables help to determine FDI for all the countries. The study concludes that a country specific FDI model may be better fit than a generic FDI theory-based model. [ABSTRACT FROM AUTHOR]

This article is a part of research study, where the effective hybrid Convolution Neural Network (CNN) algorithm was proposed to identify the forest fire more accurately. The proposed framework involves the use of multifare differentiation technique, Spatial transformation coordinates and fuzzy entropy. Pre-processing of the acquired input is considered in this architecture to avoid the presence of noise which misinterprets the data. The dynamic attributes of the input video are extracted accurately using multi frame differentiation technique and spatial transformation coordinate based extraction was done to avoid the false estimation. Fuzzy entropy methodology is used to accurately classify the degree of the fire from earlier, medium to the severe stages. The obtained results are compared against the existence dataset to evaluate the performance efficiency. The proposed methodology exhibits high accuracy about 96.38%. [ABSTRACT FROM AUTHOR]

We study an SEIRS epidemiological model for the infectious disease Tuberculosis using differential equations. The entry of an infectious individual into a susceptible population leads to the spread of infection. There are chances of getting infected even after recovery, which has been taken into consideration. When the infection will establish itself or diminish is researched and validated by stability of equilibrium. The factor which gives the conclusion of equilibrium is the Basic Reproduction Number 퓡0. If 퓡0 < 1 then infection dies out and if 퓡0 > 1, the infection would establish itself. [ABSTRACT FROM AUTHOR]

We have seen a lot of train fire crashes in recent years causing several people injured and even death. Not only fire accidents but also there are accidents on the railway tracks, these are caused during crossing the track or suddenly appearing in front of the train. Train temperature and obstacle detection system is used to detect temperature in train and is given to GSM module if there is raise in temperature. This paper uses an IR sensor to detect the obstacle in front of the train which will alert the driver to slow down the train. Every time when train accident takes place a large number of people suffer who were travelling in that train. The idea will help to prevent or to stop the fire before it spreads and also message sent to authorities will help to give the injured immediate care. [ABSTRACT FROM AUTHOR]

Nanocomposites have gained enormous attention in recent times due to their synergetic effects and excellent properties. Sensing properties improve after addition of graphene oxide to zinc oxide. Large surface area, high electric conductivity and good thermal stability make graphene oxide suitable material for composite based device fabrication. The prepared composite material ZnO/rGO is characterized by various techniques like XRD, UV-visible, RAMAN and FTIR. Crystallite size of graphene oxide doped zinc oxide was found to be 24.85nm. UV-visible confirms that band gap of the composite materialis reduced to 3.11eV from 3.37eV.An increasein yield amount of the product is found without harmful effects and less destruction of surface structure by using ecofriendly reducing agent ascorbic acid. Composite materials have large number of applications in sensing, optoelectronic devices and medical field.ZnO/rGO composite material is used for piezoelectric devices for pressure sensors and nanogenerators. [ABSTRACT FROM AUTHOR]

This paper draws the comparison between two different geometry designed PCFs and compares the optical parameters like confinement loss, dispersion, birefringence, non linearity and effective area. The two structures are 3rings Hexagonal PCF and Circular PCF. Comsol Multiphysics 5.6 software is used to model them and the physics used for the simulation is the electromagnetic waves frequency domain. The propagation constant and propagating mode are computed using mode analysis. The study of the parametric sweep has been used to find the wavelength mode. Air is used as the material for holes and silica glass of refractive index 1.46 is used for cladding. For both the structures, the diameter of air holes and lattice pitch is kept the same and the same wavelength 1.55µm is used for simulating various properties. From the simulation results, it is found that hexagonal PCF provides -1.08e−5 dB/km and circular PCF provides -2.18e−12 dB/km confinement loss. Hexagonal PCF provides 6.0720e−12 m2 effective area while circular PCF offers a low effective area of 9.149e−12 m2 because of the air holes present. The birefringence was investigated for hexagonal and circular PCF and was found to be 0.015 and 0.016 respectively. Nonlinearity in the case of hexagonal PCF has a value of 9.36368e−12 W−1km−1 and that for circular PCF has 6.1919e−11 W−1km−1. [ABSTRACT FROM AUTHOR]

In recent year Automobile industries increase developing automation in vehicles. Especially in related with vehicle braking systems and sensing systems. This work relate with Autonomous Emergency Braking Systems which stops down the vehicle if any sudden obstacle is detected and speed above 60km/hr. This braking system employs Ultrasonic and IR sharp sensors to monitor the vehicles in front and when it detects the sudden obstacle it first gives Audio and Optical warnings to the driver to take corrective action for avoid the collision and if the driver does not respond to it then emergency braking is automatically applied by using linear electric actuators to avoid the collision or at least to mitigate its effect. Most of the Road accidents are caused by drivers who apply inadequately, delayed or no brakes at all in order to overcome this effect an Autonomous Emergency Braking system can be used in future vehicles. [ABSTRACT FROM AUTHOR]

In this paper, a multi-port non-isolated SEPIC converter is analysed for integrating with the renewable energy source and also losses and efficiency are calculated. The proposed converter utilizes a single stage power conversion, thereby providing higher energy efficiency. The proposed structure comprises of a combination of Pulsating Voltage Cells (PVC) and Pulsating Voltage Source Cell (PVSC) on the input side and a Pulsating Voltage Load Cell (PVLC) on the output side. The two topologies involved are Multi Input Single Output (MISO) and Multi Input Multiple Output (MIMO) which are bidirectional. The efficiency of the proposed multi-port converter has been calculated by determining the switching stress of the power electronic switches used. The proposed multi-port SEPIC converter considers the entire system to be a single-stage converter, and promises higher energy efficiency. [ABSTRACT FROM AUTHOR]

The idea of neutrosophic θ-Compact along with neutrosophic θ-Almost Compact spaces are developed in neutrosophic topological spaces. We investigate their behavior besides giving characterizations of these spaces. [ABSTRACT FROM AUTHOR]

In this paper, we present some fixed point results for self-mappings satisfying an implicit relation in partial b-metric spaces which are generalization of several previously fixed point theorems in the literature. As an application, we obtained solution of non-linear integral equation. [ABSTRACT FROM AUTHOR]

Power generation from renewable energy sources is key to a clean energy future and solar energy is world's fastest growing energy sector. Solar energy is renewable, CO2-free and with low operational cost. There are several advantages of using solar energy; however, it does have a few drawbacks such as hefty initial cost, high-priced storage, weather dependency, sizable space requirement, etc. As such, it is critical to predict solar radiation (SR) in an accurate and efficient way to install solar plants in optimal locations. Factors like global horizontal irradiance (GHI), temperature, humidity, cloud cover, wind speed, etc. make SR highly intermittent and variable. Accurate forecasting of SR is vital to finalize installed capacity of the proposed power plant but is extremely challenging due to unpredictability of sunlight. Even the world's best organizations such as the International Energy Agency (IEA) finds it difficult to accurately predict SR. In this work, we analyze global and diffuse SR data gathered from India Meteorological Department (IMD) Pune. This data is first analyzed for features, dominant features are identified, and several machine learning algorithms are employed. Random forest method provides the best results on this data based on several quantitative measures. [ABSTRACT FROM AUTHOR]