International Research Journal of Multidisciplinary Technovation

AI and Neural Network-Based Approach for Paddy Disease Identification and Classification

2024-03-10T07:27:18+00:00

The purpose of this work is to use the artificial intelligence features of the ResNet50 architecture to provide a novel method of paddy disease identification. Farmers face numerous problems in raising paddy as its yield is affected by various factors like changing biodiversity, environment, weather pests, and disease. Traditional methods combined with smart farming, innovation, tools, and technology are needed for the mass production of food Here we develop a model using a convolutional neural network, ResNet50 that identifies disease in paddy leaf. The proposed model paddy disease identification model will give more precise results. The paddy disease identification model may be transformed into TensorFlow Lite (TFLite), which can be used for Android phones and drone applications, among other things. The Paddy model in this article obtained a training accuracy of almost 99% and a test accuracy of 92.83% when it was trained on 13,876 well-defined datasets. The loss function of 0.0014 at 100 epochs demonstrated that the model was effectively trained using ResNet50.

Conglomerate Crop Recommendation by using Multi-label Learning via Ensemble Supervised Clustering Techniques

2024-03-12T05:41:23+00:00

Existing crop recommender related to either binary classification or multiclass classification. This paper presents conglomerate crop recommendations which consist of a number of different and distinct crops that are grouped together. In this work we focus on transferring knowledge from single label output prediction to multiple label predicted output for a given input data instances. We proposed ESCT algorithm i.e. Ensemble Supervised Clustering Techniques in our research work. ESCT provides a combined approach of conventional clustering and enhanced supervised clustering methodology to optimize the conglomerate recommendation. We are focusing on K-mean clustering for conventional approach and ICCC i.e. Inter cluster correlation coefficient to achieve enhancement in supervised clustering. In conventional K-mean clustering there is a big challenge on how to optimize the k-value of clustering which directly affects the convergence of the clusters. To resolve this problem, we mainly apply function approximation on K-Value which provides us with better clustering and fast convergence. Existing methods for inter-clustering do not adequately address one of the key challenges i.e. exploiting correlations between labels and that is achieved by ICCC algorithm. This model provides learning and prediction of unknown observation by using Back propagation MLL algorithm which provides improved performance.

Mitigating Frame Cracks in Off-Highway Vehicle: A Combined Approach of Finite Element Analysis and IoT-based Chassis Health Monitoring System

2024-02-13T05:22:46+00:00

A Heavy-duty cargo truck manufactured by the Chinese company SHACMAN X3000 is designed and analyzed in this paper. Here, this paper developed a Chassis Health Monitoring System (CHMS). The objective of the system is improving the safety measures by combining computational techniques using FEA on static structural and Modal analysis followed by experimental work by implementation of IoT for monitoring and validation purposes. In this paper, for analysis purpose, we selected four critical points based on the survey and underwent the analysis by computational tool. The CHMS consists of a Force sensor, a Flux sensor, and RGB with Arduino, which is to collect and analyze to monitor the frame. The analyzed results give the optimal value in the frame near the critical areas, which results the crack. The CHMS, it a pre-alert system and safe guard the chassis.

BCSDNCC: A Secure Blockchain SDN framework for IoT and Cloud Computing

2024-01-09T13:35:10+00:00

Rapid progress can be observed in the field of computer network technologies. Blockchain technology(BCT) presents a potentially viable alternative for effectively mitigating performance and security issues encountered in distributed systems. Recent studies have focused on exploring a number of exciting new technologies, including BlockChain (BC), Software-Defined Networking (SDN), and the Internet of Things (IoT). Various technologies offer data integrity and secrecy. One such technology that has been utilized for a number of years is cloud computing (CC). Cloud architecture facilitates the flow of confidential information, enabling customers to access remote resources. CC is also accompanied with notable security dangers, concerns, and challenges. In order to tackle these difficulties, we suggest integrating BC and SDN into a CC framework designed for the IoT. The fundamental flexibility and centralized capabilities of SDN facilitate network management, facilitate network abstraction, simplify network evolution, and possess the capacity to effectively handle the IoT network. The utilization of BCT is widely acknowledged as a means to ensure robust security inside distributed SDN (DSDN) and IoT networks, hence enhancing the efficacy of the detection and mitigation procedures.

An Intelligent Computer Aided Diagnosis System for Classification of Ovarian Masses using Machine Learning Approach

2023-12-13T16:01:25+00:00

Ovarian cancer, a difficult and often asymptomatic malignancy, remains a substantial global health concern in women. An ovary is a female reproductive organ, which lies on each side of the uterus and used to store eggs. Computer-aided diagnosis (CAD) is an approach that involves using computer algorithms and machine learning techniques to assist medical professionals in diagnosing ovarian malignancies, benign tumors or Poly-cystic ovaries (PCOS). The need for models that can effectively predict benign ovarian tumors and ovarian cancer has led to the use of machine learning techniques. Our research objective is to propose a machine learning-based system for accurate and early ovarian mass detection utilizing novel annotated ovarian masses. We have used an actual patient database whose input features were extracted from 187 transvaginal ultrasound images from database. The input image is preprocessed using the Block Matching 3D filter. The process involves employing binary and watershed segmentation techniques, followed by the integration of Gabor, Gray-Level Co-Occurrence Matrix (GLCM), Tamura, and edge feature extraction methods. K-Nearest Neighbors (KNN) and Random Forest (RF) are two classifiers used for classification. Based on our results, we are able to demonstrate that binary segmentation with RF classifiers is more accurate (above 86%) than KNN classifiers (under 84%).

Enhanced Classification of Imbalanced Medical Datasets using Hybrid Data-Level, Cost-Sensitive and Ensemble Methods

2024-01-30T08:32:35+00:00

Addressing the class imbalance in classification problems is particularly challenging, especially in the context of medical datasets where misclassifying minority class samples can have significant repercussions. This study is dedicated to mitigating class imbalance in medical datasets by employing a hybrid approach that combines data-level, cost-sensitive, and ensemble methods. Through an assessment of the performance, measured by AUC-ROC values, Sensitivity, F1-Score, and G-Mean of 20 data-level and four cost-sensitive models on seventeen medical datasets - 12 small and five large, a hybridized model, SMOTE-RF-CS-LR has been devised. This model integrates the Synthetic Minority Oversampling Technique (SMOTE), the ensemble classifier Random Forest (RF), and the Cost-Sensitive Logistic Regression (CS-LR). Upon testing the hybridized model on diverse imbalanced ratios, it demonstrated remarkable performance, achieving outstanding performance values on the majority of the datasets. Further examination of the model's training duration and time complexity revealed its efficiency, taking less than a second to train on each small dataset. Consequently, the proposed hybridized model not only proves to be time-efficient but also exhibits robust capabilities in handling class imbalance, yielding outstanding classification results in the context of medical datasets.

A Novel Approach for Surveillance Compression using Neural Network Technique

2024-03-15T00:35:09+00:00

The integration of closed-circuit television (CCTV) monitoring is crucial in the field of video processing, which provides an efficient method for comprehensive surveillance. However, a key challenge associated with this practice is its substantial demand for storage space. Typically, surveillance footage is stored in hard disk drives, and due to limited storage spaces, it is deleted after some time. To address this issue, an innovative method for compressing CCTV video, named object detection-based surveillance compression (ODSC), is introduced. Our ODSC model is divided into two steps: -i) depending upon the objects in the video, determine the significant and non-significant frames of surveillance video using the neural network approach YOLOv5s & YOLOv7-tiny and Yolov8s ii) construct the video of significant frames. Following a comprehensive analysis of the experimental outcomes, it is noted that YOLOv8s stands out with a remarkable detection accuracy of 99.7% on the COCO dataset. Our ODSC approach is reducing the storage space greatly and achieving an average compression ratio of up to 96.31% using YOLOv8s, which surpasses the existing state-of-the-art methods.

Green Synthesis of Selenium Nanoparticles: Characterization and Therapeutic Applications in Microbial and Cancer Treatments

2024-03-15T01:54:31+00:00

Selenium is one of these micronutrients that are essential for animals, plants and microorganisms to remain functional. This review is about the green synthesis of selenium nanoparticles and its application in microbial and cancer therapies. Our hypothesis was that Se NPs produced using plant extracts might offer the biocompatibility and environmental friendliness advantages, and hence be a new prospect for medical applications. To test our hypothesis, we conducted a comprehensive analysis of recent literature, exploring various green synthesis conditions and processes for Se NPs. Various characterisation techniques such as spectroscopy, microscopy and physicochemistry were discussed in order to provide insight into the formation and function of green-synthesised Se NPs. Our findings show that Se NPs produced by green chemistry methods have good properties such as uniform size, shape and stability as detailed examples from recent studies reveal. Furthermore, we discussed the therapeutic and theranostic applications of Se NPs produced in this manner: their potential in antimicrobial and anticancer treatments. Through illustrations of cases where Se NPs inhibit microbial growth and cause apoptosis in cancer cells, the practical significance of our findings was underscored. In summary, our review affirms that using green-mediated synthesis Se NPs improves their biocompatibility and therapeutic efficacy, thus opening up new realms for their application in medical research.