Agriculture is the backbone of every country in the world. In India, most of the rural population still depends on agriculture. The agricultural sector provides major employment in rural areas. Furthermore, it contributes a significant amount to India’s gross domestic product (GDP). Therefore, protecting and enhancing the agricultural sector helps in the development of India’s economy. In this work, a real-time decision support system integrated with a camera sensor module was designed and developed for identification of plant disease. Furthermore, the performance of three machine learning algorithms, such as Extreme Learning Machine (ELM) and Support Vector Machine (SVM) with linear and polynomial kernels was analyzed. Results demonstrate that the performance of the extreme learning machine is better when compared to the adopted support vector machine classifier. It is also observed that the sensitivity of the support vector machine with a polynomial kernel is better when compared to the other classifiers. This work appears to be of high social relevance, because the developed real-time hardware is capable of detecting different plant diseases.
6 June 2021 in Iranian Journal of Science and Technology, Transactions of Electrical Engineering
Dementia has become a global public health issue. The current study is focused on diagnosing dementia with Electro Encephalography (EEG). The detection of the advancement of the disease is carried out by detecting the abnormal behavior in EEG measurements. Assessment and evaluation of EEG abnormalities is conducted for all the subjects in order to detect dementia. EEG feature analysis, namely dominant frequency, dominant frequency variability, and frequency prevalence, is done for abnormal and normal subjects and the results are compared. For dementia with Lewy bodies, in 85% of the epochs, the dominant frequency is present in the delta range whereas for normal subjects it lies in the alpha range. The dominant frequency variability in 75% of the epochs is above 4Hz for dementia with Lewy bodies, and in normal subjects at 72% of the epochs, the dominant frequency variability is less than 2Hz. It is observed that these features are sufficient to diagnose dementia with Lewy bodies. The classification of Lewy body dementia is done by using a feed-forward artificial neural network wich proved to have a 94.4% classification accuracy. The classification with the proposed feed-forward neural network has better accuracy, sensitivity, and specificity than the already known methods.
Detecting kidney disease at an early stage is crucial for timely intervention and improved patient outcomes. In recent years, machine learning classifiers have shown promise in enhancing the accuracy and efficiency of diagnosing kidney disease. This research paper delves into the comparative analysis of Support Vector Machine (SVM) classifier, Random Forest classifiers, and a Hybrid model combining SVM and Decision Tree for kidney disease detection. The introduction of each classifier, including SVM's classification mechanism, advantages, and preferred usage scenarios, as well as Random Forest's approach to combating overfitting through ensemble learning and parameter tuning considerations, sets the stage for a comprehensive evaluation. Additionally, exploring the benefits, challenges, and synergistic strengths of a Hybrid model in leveraging SVM's robustness and Decision Tree's interpretability is essential for understanding its potential in kidney disease detection. By investigating the common features utilized for kidney disease detection and assessing the accuracy and implications of early detection using machine learning models, this paper aims to contribute to the advancement of medical diagnostics. Furthermore, the study will evaluate and compare the performance of SVM, Random Forest, and Hybrid classifiers, examining the metrics employed for model effectiveness assessment and addressing any limitations or biases inherent in interpreting the results for kidney disease detection. Through this research, we aim to provide valuable insights into the application of machine learning classifiers in medical diagnostics, particularly in the context of kidney disease detection.
18 December 2013 in International Journal of Computer Applications
Colonoscopy is a crucial procedure for gastrointestinal diagnostics, providing direct visualization of the colon's internal structure. The quality of acquired colonoscopy images significantly impacts diagnostic accuracy and treatment planning. This study focuses on enhancing colonoscopy image quality through computational multi step image processing techniques aimed at enhancing colonoscopy image quality and interpretability. The methodology involves multi step strategy for evaluating various noise reduction filters including Gaussian, bilateral, and hybrid bilateral-Gaussian filters, along with Contrast Limited Adaptive Histogram Equalization (CLAHE) and Unsharp Masking techniques. Evaluation metrics such as Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) are used to quantify the efficacy of these techniques. The study employs the CVC Clinic DB dataset for experimentation, ensuring clinical relevance and diversity in the images analyzed. Results from ablation studies and quantitative analyses highlight the effectiveness of specific preprocessing techniques in preserving image details, enhancing contrast, and sharpening edges. In first step, the hybrid bilateral-Gaussian filter achieved as a suitable noise reduction filter, followed by CLAHE and edge enhancement using Unsharp masking. The PSNR and SSIM values from the first to third step shows increase of 2.88% (from 37.86 dB to 38.95 dB) and 1.56% (from 0.96 to 0.975) respectively. The study's findings contribute to advancing gastrointestinal diagnostics, aiding in more accurate diagnoses, treatment planning, and patient outcomes