Department of Agricultural Engineering

Permanent URI for this collectionhttp://197.255.125.131:4000/handle/123456789/23123

Browse

Search Results

Now showing 1 - 10 of 27
  • Thumbnail Image
    Item
    Lung Cancer Classification and Prediction Using Machine Learning and Image Processing
    (BioMed Research International, 2022) Nageswaran, S.; Arunkumar, G.; Bish, A.K.; Mewada, S.; Kumar, J.N.V.R.S.; Jawarneh, M.; Asenso, E.
    Lung cancer is a potentially lethal illness. Cancer detection continues to be a challenge for medical professionals. The true cause of cancer and its complete treatment have still not been discovered. Cancer that is caught early enough can be treated. Image processing methods such as noise reduction, feature extraction, identification of damaged regions, and maybe a comparison with data on the medical history of lung cancer are used to locate portions of the lung that have been impacted by cancer. This research shows an accurate classification and prediction of lung cancer using technology that is enabled by machine learning and image processing. To begin, photos need to be gathered. In the experimental investigation, 83 CT scans from 70 distinct patients were utilized as the dataset. The geometric mean filter is used during picture preprocessing. As a consequence, image quality is enhanced. The K-means technique is then used to segment the images. The part of the image may be found using this segmentation. Then, classification methods using machine learning are used. For the classification, ANN, KNN, and RF are some of the machine learning techniques that were used. It is found that the ANN model is producing more accurate results for predicting lung cancer.
  • Thumbnail Image
    Item
    Research on Network Security Situational Awareness Based on Crawler Algorithm
    (Hindawi Limited, 2022-07) Wu, X.; Wei, D.; Vasgi, B.; Oleiwi, A.K.; Bangare, S.L.; Asenso, E.
    Network security situation awareness is a critical basis for security solutions because it displays the target system's security state by assessing actual or possible cyber-attacks in the target system. Aiming at the security and stability of global information flow, this paper studies the perception and measurement of the overall situation of network security. Through the Scrappy web crawler framework, data were collected from several Zhiming network security event websites, and based on the vulnerability database of China Computer Network Intrusion Prevention Center, the network security event database was designed and established, which enriched the data of situational awareness research. This study investigates the analysis and processing of network security events, a crucial parameter in the stage of security insight and perception, and builds and implements a text-based network security event analysis tool. By designing a network security event analysis tool based on text processing, the data cleaning of network security time text information is completed, and a set of network security event processing solutions with high applicability and comprehensiveness are formed. Statistical experimental results show that the network security event database built based on the crawler algorithm contains 43,848 pieces of data, which increases the capacity by 12.79% and 29.33% compared with the traditional algorithm, and reduces the reading time by 63.5% and 87.2%.
  • Item
    Implementing Machine Learning for Smart Farming to Forecast Farmers’ Interest in Hiring Equipment
    (Hindawi, 2022) Rakhra, M.; Sanober, S.; Quadri, N.N.; Verma, N.; Ray, S.; Asenso, E.
    Farmers’ physical labor and debt are reduced as a result of agricultural automation, which emphasizes efficient and effective use of various machines in farming operations with the purpose of reducing physical labor and debt. It is a revolutionary idea in agriculture to create custom hiring centers, which are intended to make it easier for like-minded farmers to embrace technology/ machinery for enhanced resource management practices. The study in question examines the significance of tool renting and sharing in the workplace. Rental and sharing equipment are two approaches that might be used to enable farmers to borrow equipment at a cheaper cost than they would otherwise have to pay for it. The following is a manual pilot study of 562 farmers in India to address the numerous challenges farmers face when looking for tools and equipment, as well as to determine their strong interest in the process of renting and sharing equipment. The study was conducted to address the numerous challenges farmers face when looking for tools and equipment and to determine their strong interest in the process of renting and sharing equipment. Farmers are divided into three groups according to the results of this poll: small, moderate, and large. Training and testing splits were used on the same data set in order to get a better understanding of the target variables. The data set for the survey was standardized in order to remove ambiguity. In this research, three different machine learning models were utilized: nearest neighbors, logistic regression, and decision trees. K-nearest neighbors was the most often used model, followed by logistic regression and decision trees. In order to get the best possible result, a comparison of the aforementioned algorithm models was carried out, which revealed that the decision tree is the better model among the others in this regard. Because the decision tree model is completely reliant on a large number of input factors, such as the kind of crop, the time/month of harvest, and the type of equipment necessary for the crops, it has the potential to have a social and economic impact on farmers and their livelihoods.
  • Thumbnail Image
    Item
    Hybrid Feature-Based Disease Detection in Plant Leaf Using Convolutional Neural Network, Bayesian Optimized SVM, and Random Forest Classifier
    (Hindawi, 2022) Singh, A.K.; Sreenivasu, S.V.N.; Mahalaxmi, U.S.B. K.; Sharma, H.; Patil, D.D.; Asenso, E.
    Plant diseases are unfavourable factors that cause a significant decrease in the quality and quantity of crops. Experienced biologists or farmers often observe plants with the naked eye for disease, but this method is often imprecise and can take a long time. In this study, we use artificial intelligence and computer vision techniques to achieve the goal of designing and developing an intelligent classification mechanism for leaf diseases. This paper follows two methodologies and their simulation outcomes are compared for performance evaluation. In the first part, data augmentation is performed on the PlantVillage data set images (for apple, corn, potato, tomato, and rice plants), and their deep features are extracted using convolutional neural network (CNN). These features are classified by a Bayesian optimized support vector machine classifier and the results attained in terms of precision, sensitivity, f-score, and accuracy. The above-said methodologies will enable farmers all over the world to take early action to prevent their crops from becoming irreversibly damaged, thereby saving the world and themselves from a potential economic crisis. The second part of the methodology starts with the preprocessing of data set images, and their texture and color features are extracted by histogram of oriented gradient (HoG), GLCM, and color moments. Here, the three types of features, that is, color, texture, and deep features, are combined to form hybrid features. The binary particle swarm optimization is applied for the selection of these hybrid features followed by the classification with random forest classifier to get the simulation results. Binary particle swarm optimization plays a crucial role in hybrid feature selection; the purpose of this Algorithm is to obtain the suitable output with the least features. The comparative analysis of both techniques is presented with the use of the above-mentioned evaluation parameters.
  • Thumbnail Image
    Item
    Design and Evaluation of a Hybrid Technique for Detecting Sunflower Leaf Disease Using Deep Learning Approach
    (Wiley, 2022) Malik, A.; Vaidya, G.; Jagota, V.; Eswaran, S.; Sirohi, A.; Batra, I.; Rakhra, M.; Asenso, E.
    Agriculture and plants, which are a component of a nation’s internal economy, play an important role in boosting the economy of that country. It becomes critical to preserve plants from infection at an early stage in order to be able to treat them. Previously, recognition and classification were carried out by hand, but this was a time-consuming operation. Nowadays, deep learning algorithms are frequently employed for recognition and classification tasks. As a result, this manuscript investigates the diseases of sunflower leaves, specifically Alternaria leaf blight, Phoma blight, downy mildew, and Verticillium wilt, and proposes a hybrid model for the recognition and classification of sunflower diseases using deep learning techniques. VGG-16 and MobileNet are two transfer learning models that are used for classification purposes, and the stacking ensemble learning approach is used to merge them or create a hybrid model from the two models. &is work makes use of a data set that was built by the author with the assistance of Google Images and comprises 329 images of sunflowers divided into five categories. On the basis of accuracy, a comparison is made between several existing deep learning models and the proposed model using the same data set as the original comparison.
  • Thumbnail Image
    Item
    Impact of active night population and leakage exponent on leakage estimation in developing countries
    (IWA, 2022) Amoatey, P.K.; Obiri-Yeboah, A.A.; Akosah-Kusi, M.
    Methods for network leakage estimation include water balance, component analysis and minimum night flow (MNF) methods, the latter of which involves subtracting the customer night use (QCNU) from night leakage and multiplying by the hour day factor (HDF). QCNU and HDF respectively depend on Active Night Population (ANP) and leakage exponent (N1). In most developing countries, these parameters are assumed in the MNF method, thus introducing errors which makes setting realistic leakage reduction targets and key performance indicators (KPI) problematic. In this study, QCNU and HDF were evaluated by determining the relative error associated with ANP and N1 to establish localized rates for accurately estimating leakage in water networks. Between 7 and 11% relative error was associated with every 1% higher or lower ANP while up to 4% relative error was observed for every N1 step considered. A linear relationship exists between the relative error associated with both N1 and ANP although that of ANP is twice as high as N1: This has technical implications for setting water loss reduction targets and investing in the water infrastructure. It is recommended that water utilities must establish localized ANP and N1 values for accurate leakage estimation in water networks.
  • Thumbnail Image
    Item
    Intrusion Detection Using Machine Learning for Risk Mitigation in IoT-Enabled Smart Irrigation in Smart Farming
    (Hindawi, 2022) Raghuvanshi, A.; Singh, U.K.; Sajja, G.S.; Pallathadka, H.; Asenso, E.; Kamal, M.; Singh, A.; Phasinam, K.
    The majority of countries rely largely on agriculture for employment. Irrigation accounts for a sizable amount of water use. Crop irrigation is an important step in crop yield prediction. Field harvesting is very reliant on human supervision and experience. It is critical to safeguard the field’s water supply. The shortage of fresh water is a major challenge for the world, and the situation will deteriorate further in the next years. As a result of the aforementioned challenges, smart irrigation and precision farming are the only viable solutions. Only with the emergence of the Internet of Things and machine learning have smart irrigation and precision agriculture become economically viable. Increased efficiency, expense optimization, energy maximization, forecasting, and general public convenience are all benefits of the Internet of Things (IoT). As systems and data processing become more diversified, security issues arise. Security and privacy concerns are impeding the growth of the Internet of Things. This article establishes a framework for detecting and classifying intrusions into IoT networks used in agriculture. Security and privacy are major concerns not only in agriculture-related IoT networks but in all applications of the Internet of Things as well. In this framework, the NSL KDD data set is used as an input data set. In the preprocessing of the NSL-KDD data set, first all symbolic features are converted to numeric features. Feature extraction is performed using principal component analysis. Then, machine learning algorithms such as support vector machine, linear regression, and random forest are used to classify preprocessed data set. Performance comparisons of machine learning algorithms are evaluated on the basis of accuracy, precision, and recall parameters.
  • Thumbnail Image
    Item
    Optimal bed thickness and efective size for improving wastewater quality for irrigation
    (Springer, 2021) King‑Nyamador, G.; Amoatey, P.K.; Amoah, S.; Adu‑Ampong, B.
    With the increased use of wastewater for irrigation, there is the need to reduce the contaminant levels in wastewater. The slow sand fltration (SSF) is one such method that can be used to improve wastewater quality. However, the treatment quality depends among other factors on the depth of sand bed and the efective size. Acquiring sand of a particular efective size is becoming increasing difculty and, therefore, this study sought to investigate over a specifed area, the optimal depth and efective size that will be able to get rid of contaminants in wastewater. In separate experiments, three depths (30 cm, 40 cm and 50 cm) and two efective sizes (0.27 mm and 0.45 mm) were set up to investigate their efectiveness in removing Faecal coliform, E. coli and heavy metals (Pb, Cu and Fe) for wastewater from a peri-urban drain used for irrigating vegetables. Results showed that a minimum sand bed thickness of 40 cm and an efective size of up to 0.45 mm reduced the contami nants tested signifcantly, wastewater from the drain can be treated. It must be mentioned that the fner sand (0.27 mm) had a slightly better removal efciency. This implies that the extra cost of acquiring sand of relatively smaller efective size and a higher bed depth with the aim of improving wastewater quality can be saved. Further investigations are being carried out on the combined efects of the optimal sand bed depth and efective size.
  • Thumbnail Image
    Item
    Determining the Efficiency of the Government of Ghana’s Network of Grain Storage Facilities
    (West African Journal of Applied Ecology, 2018) Essien, E.; Addo, A.; Dzisi, K.A.
    Governments in developing countries design networks of grain storage facilities to help farmers store excess agricultural produce to prepare for climate induced crop failures. The efficiency of such networks has serious economic and food security implications on respective countries. Periodic review of the efficiency of such networks is necessary to identify lapses and opportunities for optimization. Past studies on efficiency of networks of facilities, which usually assume scenarios peculiar to the developed world used data that are usually unavailable or unreliable in developing countries. This work therefore developed an integrated approach that relies solely on readily available and reliable governmental and open source data to compute the short and long-term efficiencies of networks of grain storage facilities. This approach was used to analyze the efficiency of the government of Ghana’s network of forty-eight grain storage facilities. A transportation model was used to compute the total transportation cost within the existing network. A P-median model was then used to develop and compute the transportation cost of a theoretically optimal network. Outputs from a forecasting model were used with the transportation and P-median models to study the short and long-term efficiencies of the existing and optimal networks. The average short and long term efficiencies of the existing network were 66% and 26% respectively. The study also investigated the efficiencies of a rank network which is created by siting GSF’s in only high grain production districts. The short and long-term efficiencies of this network were 87% and 72% respectively. The study showed that Ghana’s GSFs were sub-optimally sited hence farmers would have to travel excessively longer distances than necessary to use it. This offers some explanation for its low patronage. Furthermore, the study shows that a rank network was not as efficient as the optimal network. This study therefore demonstrates the use of this integrated approach coupled with readily available data to analyze networks of grain storage facilities in developing countries.
  • Item
    Leakage estimation in developing country water networks based on water balance, minimum night flow and component analysis methods
    (Water Practice and Technology, 2018-03) Amoatey, P.K.; Minke, R.; Steinmetz, H.
    Estimating leakage in developing countries’ water networks is challenging as accurate records are needed. Three leakage estimation methods were compared to ascertain which was most suitable for such networks. The factors accounting for the differences in application of these methods to water networks were also ascertained. The water balance and component analysis methods were compared with the modified minimum night flow (MNF) method. The MNF method was modified to make it suitable for networks in developing countries. In the comparison, leakage was estimated at 10 and 18%, respectively, against 11% for the modified MNF. The latter is considered the most suitable for developing countries as all parameters are determined or estimated from field measurements. It was realized that burst flow rates and the infrastructure condition factor used in the water balance and component analysis methods affect the accuracy of leakage estimates. This has implications for further research, as well as policy and practice for developing countries’ water utilities.