Search

The paper attempts to analyze fish production and the direction of trade. Data for the analysis was taken from a period of 10 years (2011- 2021) from the Ministry of Commerce & Industry and FAO. To examine the type and extent of increase in the fish area, production, and productivity throughout the course of the year for several countries, including China, Vietnam, the United States, Norway, and India, descriptive statistics and the sustainability index were utilized. Markov chain analysis employing linear programming was then applied to determine transition probabilities in fish trade. The fish export markets were the USA, China, Japan, Thailand, Taiwan, Kuwait, Hong Kong, and others. The fish export markets were categorized as stable markets (China, USA, Taiwan, Thailand, and Hong Kong) and unstable markets (Japan and Kuwait) based on the magnitude of transition probabilities. Though the country has a good potential for export of fish. India must therefore give rising output more consideration, supported by measures that encourage exports. In addition, initiatives must be made to develop a new market and broaden the trade area to include other significant, global markets.

The goal of phishing assaults is to trick users into giving up personal information by making them believe they need to act quickly on critical information. The creation of efficient solutions, such as phishing attack detection systems backed by AI, is essential for the safety of users. This research suggests a two-stage hybrid strategy that uses both URL and content analysis to identify phishing assaults. In the first step of the suggested method, URL analysis is used to determine the legitimacy of suspected phishing assaults. If the site is still live, the second check uses content analysis to determine how serious the attack is. Both analysis' findings are taken into account in the decision-making procedure. As can be seen from the experiments, the hybrid system obtains an astounding 99.06% accuracy rate. This research adds to the existing body of knowledge by providing a massive dataset of over 14 million data samples that includes both legal and phishing URLs. Furthermore, when content analysis is required for phishing URL detection, the two-stage hybrid technique significantly outperforms URL analysis alone by 70.23 %. The proposed method provides better defense against phishing attempts and is practical enough for widespread use.

Agriculture is the backbone of Indian Economy. Proper forecast of food crops and cash crops are necessary for the government in policy making decisions. The present paper aims to forecast Wheat and Sugarcane yield using Random Forest Regression. For the development of Random Forest models, Yield has been taken as dependent variable and variables like Gross Cropped Area, Maximum Temperature, Minimum Temperature, Rainfall, Nitrogen, Phosphorous Oxide, Potassium Oxide, Minimum Support Price and Area under Irrigation are taken as independent variables for both Wheat and Sugarcane crop. Values of R2 for Wheat and Sugarcane is 0.995 and 0.981 which indicates that the model is a good fit and other performance measures are calculated and results are satisfactory.

The study aimed to compare ARIMA and Holt's models for predicting coconut metrics in Kerala. The coconut data series was collected from the period 1957 to 2019. Of this, 80% of the data (from 1957 to 2007) is treated as training data, and the rest (20% from 2008 to 2019) is treated as testing data. Ideal models were selected based on lower AIC and BIC values. Their accuracy was evaluated through error estimation on testing data, revealing Holt's exponential, linear, and ARIMA (0,1,0) models as the bestfit choices for predicting coconut area, production, and productivity respectively. After using the testing data, we tried for the forecasting for 2020-2024 using these models, and the DM test confirmed their significant forecasting accuracy. This comprehensive analysis provides valuable insights into effective prediction models for coconut-related metrics, offering a foundation for informed decision-making and future projections.

Delhi's Yamuna River serves as a notable illustration of an ecologically compromised system that has undergone a transition into a conduit for sewage due to pervasive pollution and escalating anthropogenic influences. Delhi, being the primary contributor to pollution, is responsible for over 70% of the total pollutant load in the Yamuna. The city's drainage systems discharge a substantial Biological Oxygen Demand load into the river daily, resulting in severe pollution. This research utilizes pre-existing data to examine diverse factors, evaluating the quality of water at distinct observation locations along the Yamuna. The utilization of correlation analysis aids in recognizing connections among elements influencing the pollution of river water. The outcomes of the correlation analysis disclose a notable link between COD-BOD factors, whereas the connections among alternative factors like BOD-DO, BOD-pH, COD-DO, COD-pH, and DOpH range from moderate to negligible. The majority of observed parameters exceed hazardous levels deemed acceptable for river water utilization. The evaluation of Sewage Treatment Plants highlights the imperative to augment capacity in terms of treatment, storage, reactivation of closed plants, and efficient operation to meet the growing demand for fresh water. Additionally, there is a pressing need to generate demand for wastewater in diverse urban sectors.

Through the use of smart sensors to monitor and regulate plant conditions, smart home gardening management systems can maximize resource utilisation and minimize human intervention. This study offers a new system that remotely controls the water supply to ensure optimal plant growth without the need for personal presence. The system uses the Blynk IoT platform to monitor soil moisture and water levels. A Raspberry Pi is used in conjunction with several sensors, such as a soil moisture sensor and a DHT11 sensor for temperature and humidity readings. The technology activates a motor to provide water to the plants automatically when the soil moisture level falls below a certain threshold. Users can remotely monitor and manage the system from their cell phones thanks to integration with the Blynk platform. The suggested method is an affordable and effective way to garden in your home, and it’s simply customizable to fit the requirements of different users.

The present study aims to develop yield forecast models for the Sugarcane crop of the Coimbatore district in Tamilnadu using two different techniques namely Variables and Months in Discriminant function analysis. For this, the Sugarcane yield data for 57 years along with the monthly data on seven weather variables have been taken. For applying discriminant analysis, the yield data of sugarcane has been divided into two categories namely two groups and three groups. The discriminant scores from the two and three-group discriminant functions were employed as independent variables in the development of yield forecast models. The yield forecast models for both strategies were created utilizing scores and trend values as independent variables. The first 52 years of yield data (1960-2012) were used to create the model, and the last five years of data (2012-2016) were used for validation. The comparison has been made between two and three groups for both techniques. The results indicate the technique using the variable-wise method gives better results based on goodness of fit. Among the two categories in the variable-wise method, three groups performed better.

This study offers a detailed comparative analysis of maize crop cultivation in the kharif and rabi seasons within the agricultural landscape of Gonda District. 50 respondents were carefully selected from various villages in the block, with proportional representation for Marginal, Small, and Medium-sized farmers. The research delves into the economics of maize cultivation, emphasizing factors such as the cost of cultivation, input expenses, income generation, and input-output ratios. In the kharif season, it was distinguished that the cost of cultivation of maize with the farm's size. Marginal farms spent an average of ₹ 48125.93 per hectare, small farms incurred ₹ 51002.89, and large farms invested ₹ 54295.17. Similarly, during the rabi season, the cost of cultivation increased with farm size, with marginal farms investing an average of ₹ 52397.57, small farms spending ₹ 55444.93, and large farms allocating ₹ 58604.68 per hectare. Crucially, the study found that input-output ratios remained consistent across farm sizes in both seasons, reflecting uniform agricultural practices. The findings underscore the importance of efficient management, the adoption of advanced agricultural techniques, the use of high-quality seeds, and the timely application of irrigation and plant protection practices in enhancing net income, particularly on marginal farms.

Sugarcane is the primary agricultural industry that sustains and promotes economic growth in India. In 2018, the majority of India's sugarcane production, specifically 79.9%, was allocated for the manufacturing of white sugar. A smaller portion, 11.29%, was used to produce jaggery, while 8.80% was utilized as seed and feed components. A total of 840.16 million metric tonnes of cane sugar was shipped in the year 2019. The primary objective of this research is to determine the most suitable forecasting model for predicting the monthly export price of sugarcane in India. The input consists of a time series with 240 monthly observations of the export price of sugarcane in India, spanning from January 1993 to December 2013. The SARIMA approach was employed to predict the monthly export price of sugarcane and it is concluded that the SARIMA (0, 1, 1), (0, 0, 0)12 model is the best-fitted one by the expert modeler method. As a result, the fitted model appears to be adequate. The RMSE and MAPE statistics are used to analyze the precision of the model.

To model and forecast complex time series data, machine learning has become a major field. This machine learning study examined Moscow rainfall data's future performance. The dataset is split into 65% training and 35% test sets to build and validate the model. We compared these deep learning models using the Root Mean Square Error (RMSE) statistic. The LSTM model outperforms the BILSTM and GRU models in this data series. These three models forecast similarly. This information could aid the creation of a complete Moscow weather forecast book. This material would benefit policymakers and scholars. We also believe this study can be used to apply machine learning to complex time series data, transcending statistical approaches.

Weather has a profound influence on crop growth, development and yield. The present study deals with the use of weather parameters for sugarcane yield forecasting. Machine learning techniques like K- Nearest Neighbors (KNN) and Random Forest model have been used for sugarcane yield forecasting. Weather parameters namely maximum temperature and minimum temperature, rainfall, relative humidity in the morning and evening, sunshine hours, evaporation along with sugarcane yield have been used as inputs variables. The performance metrics like R2, Mean Square Error (MSE), Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE) have been used to select the best model for predicting the yield of the crop. Among the models, Random Forest algorithm is selected as the best fit based on the high R2 and minimum error values. The results indicate that among the weather variables, rainfall and relative humidity in the evening have significant influence on sugarcane yield.

Online shopping can be done from our convenient places like home, office, etc., and the product will be delivered to the respective places. There are many factors influencing online shopping. The purpose of this study is to develop a statistical model that is used to determine the factors that influence online shopping. In this study, using factor analysis five main factors have been obtained from 15 variables that influence online shopping. These five factors have significant effects on satisfaction of customers and accounted up to 56% of total variation. Using the factor scores as independent variables, multiple regression model has been developed for predicting customers satisfaction in online shopping. Customer satisfaction has been used as dependent variable in the regression model. The five main factors that contribute online shopping are: preference of consumers towards online shopping, the risk involved in purchasing products through online, time effectiveness in online shopping, difficulties faced during online shopping and getting products from trustworthy websites.

Sugarcane is the largest crop in the world in terms of production. We use sugarcane and its byproducts more and more frequently in our daily lives, which elevates it to the status of a unique crop. As a result, the assessment of sugarcane production is critical since it has a direct impact on a wide range of lives. The yield of sugarcane is predicted using ARIMA and ANN models in this study. The models are based on sugarcane yield data collected over a period of 56 years (1951-2017). Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) have been used to analyze and compare the performance of different models to obtain the best-fit model. The results show that the RMSE and MAPE values of the ANN model are lower than those of the ARIMA model and that the ANN model matches best to this data set.

We use the Tikhonov method as a regularization technique for solving the integral equation of the first kind with noisy and noise-free data. Following that, we go over how to choose the Tikhonov regularization parameter by implementing the Intelligent Piratical Swarm Optimization (IPOS) technique. The effectiveness of combining these two approaches IPOS and Tikhonov is demonstrated to be highly practicable.

The usage of cloud-based farther administration frameworks presents a heap of challenges that affect their proficiency and security. This paper investigates these challenges, centering on vague security controls over diverse benefit models, the chance of information breaches and unauthorized get to, and the inescapable risk of cyberattacks. It too looks at the complexities related with joining cloud administrations with existing bequest frameworks, tending to compatibility issues, the need for framework reconfiguration, and the noteworthy costs and time ventures required for fruitful integration. Besides, the paper dives into seller lock-in concerns, highlighting the restrictions and conditions that cloud buyers confront when tied to particular suppliers. In expansion, the ponder examines taken a toll administration obstacle, counting unforeseen costs related to information exchange, capacity, and extra administrations, emphasizing the require for vigorous taken a toll optimization procedures and precise budgeting hones. By recognizing these challenges and proposing potential arrangements, this paper points to supply a comprehensive diagram of the basic issues within the arrangement and administration of cloud-based farther frameworks, advertising profitable experiences for organizations looking for to use cloud advances successfully. [ABSTRACT FROM AUTHOR]

Residential aged care facilities (RACFs) have high prevalence of malnutrition and the condition increases the health risks of elderly patients. This research aims to determine the feasibility of utilizing zero-shot prompt engineering at the generative AI models with and without the practitioners' use of RAG to automatically summarize and extract key relevant malnutrition information from the EHRs of Iraqi RACFs. The research employed the model, the Llama 2 13B model with zero-shot prompting on a dataset of structured and unstructured EHRs from 40 Iraqi RACFs. Two tasks were performed: producing summary health status assessments of the clients' nutritional needs and identifying factors indicative of the client's risk of malnutrition. Two-hundred samples were used as a gold standard data to determine the efficiency of the proposed model. These outcomes confirmed that none of the learning process is needed with a 93% accuracy in terms of summarizing and extracting nutritional information. 25% for summarization. The integration of RAG enhanced the summarization accuracy of the program to 99. 25%. On the extraction of risk factors, the model equated to 90 % accuracy while RAG strived but did not add value to increasing the proficiency of the model. The model generally performed good when information was present in clear terms but had weakness related to hallucination when the information was vague. This study demonstrates that although zero-shot learning in summarizing and extracting key elements of EHR will have high potential in the field of AI, the limitation of generalization of this method should be taken into consideration in the application to generative models for malnutrition management in Iraqi RACFs. Based on the presented results, it can be concluded that the discussed approaches, including the use of RAG, could help increase the efficiency of handling large amounts of clinical data that is critical for the identification of the malnutrition problem and its mitigation in the context of aged care setting within Iraq. [ABSTRACT FROM AUTHOR]

This research is concerned with the critical domain of cybersecurity in edge computing environments, which aims to strengthen defenses against increasing cyber threats that target interconnected Internet of Things (IoT) devices. The widespread adoption of edge computing introduces vulnerabilities that necessitate a strong framework for detecting cyberattacks. This study utilizes Long Short-Term Memory (LSTM) networks to present a comprehensive approach based on stacked LSTM layers for detecting and mitigating cyber threats in the dynamic landscape of edge networks. Using the NSL-KDD dataset and rigorous experimentation, this model demonstrates its ability to detect subtle anomalies in network traffic, which can be used to accurately classify malicious activities while minimizing false alarms. The findings highlight the potential of LSTM-based approaches to enhance security at the edge, providing promising avenues for strengthening IoT ecosystems' integrity and resilience against emerging cyber threats. [ABSTRACT FROM AUTHOR]

Convolutional Neural Networks (CNNs) are the most popular neural network model for the image classification problem, which has seen a surge in interest in recent years thanks to its potential to improve medical picture classification. CNN employs a number of building pieces, including convolution layers, pooling layers, and fully connected layers, to determine features in an adaptive manner via backpropagation. In this study, we aimed to create a CNN model that could identify and categorize brain cancers in T1-weighted contrast-enhanced MRI scans. There are two main phases to the proposed system. To identify images using CNN, first they must be preprocessed using a variety of image processing techniques. A total of 3064 photos of glioma, meningioma, and pituitary tumors are used in the investigation. Testing accuracy for our CNN model was 94.39%, precision was 93.33%, and recall was 93% on average. The suggested system outperformed numerous well-known current algorithms and demonstrated satisfactory accuracy on the dataset. We have performed several procedures on the data set to get it ready for usage, including standardizing the pixel sizes of the photos and dividing the dataset into 80% for train, 10% for test, and 10% for validation. The proposed classifier achieves a high level of accuracy of 95.3%. [ABSTRACT FROM AUTHOR]

The "climate in the weather" (CW) approach, which combines the scientific and everyday sense of climate, has been proposed. The CW is based on the in-depth idea of E. E. Fedorov to classify regional climates as an ensemble of daily weather states. We have transformed this idea into a nonparametric method of processing meteorological series, where each member of the series is mapped to quantiles of corresponding distributions, and then new time series are formed, where meteorological variables are replaced by their quantiles. Next, the members of the new quantized series are combined in weather states. In this work, by using quantiles combination of monthly temperature and precipitation, we construct four CW states - "cold and dry", "cold and rainy", "warm and rainy", "warm and dry". Then we demonstrate the possibility of the CW approach to analyze space-time climate similarity and climate change in the Mesopotamian River system. The application of 16 CW states is also discussed. The climate change dynamical assessment (CCDA) showed that the Euphrates (Tigris) tributaries values varied from 13 to 19% (13-25%) with a clear increase in Greater Zab, Lesser Zab, Adhaim, and Dyala basins. The analysis of CW-altered states demonstrated that climate change is occurred due to an increase in temperature, a decrease in precipitation, and mixed changes simultaneously. In each of the basins, there were a different number of such changes. The "climate in weather" approach developed can be used for processing multidimensional meteorological time series data and outlining the general conception of the regional climate. [ABSTRACT FROM AUTHOR]

The COVID-19 epidemic has in fact placed the whole community in a dire predicament that has led to numerous tragedies, including an economic downturn, political unrest, and job losses. Forecasting and identifying COVID-19 infection cases is crucial for the government at all levels because the pandemic grows exponentially and results in fatalities. Hence, by giving information about the spread of the epidemic, the government can move quickly at multiple levels to establish new policies and modalities in order to minimize the trajectory of the COVID-19 pandemic's effects on both public health and the economic sectors. Forecasting models for COVID-19 infection cases in the Ural region in Russia were developed using two deep Long Short-Term Memory (LSTM) learning-based approaches namely Encoder–Decoder LSTM and Attention LSTM algorithms. The models were evaluated based on five standard performance evaluation metrics which include Mean Square Error (MSE), Mean Absolute Error (MAE), Root MSE (RMSE), Relative RMSE (RRMSE), and coefficient of determination (R2). However, the Encoder–Decoder LSTM deep learning-based forecasting model achieved the best performance results (MSE=32794.09, MAE=168.56, RMSE=181.09, RRMSE=13.46, and R2=0.87) compared to the model developed with Attention LSTM models. [ABSTRACT FROM AUTHOR]