Search

Brain tumours are malignant tissues in which cells replicate rapidly and indefinitely, and tumours grow out of control. Deep learning has the potential to overcome challenges associated with brain tumour diagnosis and intervention. It is well known that segmentation methods can be used to remove abnormal tumour areas in the brain. It is one of the advanced technology classification and detection tools. Can effectively achieve early diagnosis of the disease or brain tumours through reliable and advanced neural network classification algorithms. Previous algorithm has some drawbacks, an automatic and reliable method for segmentation is needed. However, the large spatial and structural heterogeneity between brain tumors makes automated segmentation a challenging problem. Image tumors have irregular shapes and are spatially located in any part of the brain, making their segmentation is inaccurate for clinical purposes a challenging task. In this work, propose a method Recursive SigmoidNeural Network based on Multi-scale Neural Segmentation (RSN2-MSNS) for image proper segmentation. Initially collets the image dataset from standard repository for brain tumour classification. Next, pre-processing method that targets only a small part of an image rather than the entire image. This approach reduces computational time and overcomes the over complication. Second stage, segmenting the images based on the Enhanced Deep Clustering U-net (EDCU-net) for estimating the boundary points in the brain tumour images. This method can successfully colour histogram values are evaluating segment complex images that contain both textured and non-textured regions. Third stage, Feature extraction for extracts the features from segmenting images using Convolution Deep Feature Spectral Similarity (CDFS2) scaled the values from images extracting the relevant weights based on its threshold limits. Then selecting the features from extracting stage, this selection is based on the relational weights. And finally classified the features based on the Recursive Sigmoid Neural Network based on Multi-scale Neural Segmentation (RSN2-MSNS) for evaluating the proposed brain tumour classification model consists of 1500 trainable images and the proposed method achieves 97.0% accuracy. The sensitivity, specificity, detection accuracy and F1 measures were 96.4%, 952%, and 95.9%, respectively.

1. Smart Street Light: Electrical Energy consumption of a nation is an indicator of the economic and social growth of the country. With the increasing demand for non-conventional energy resources, the conservation of energy is an important domain in current research .Energy Conservation can be the best solution for the rising energy demand .Utilizing electricity efficiently and reducing its wastage as much as possible is an important criterion considering the depleting natural reserves of fossil fuel traditionally used its generation. This paved way for developing appliance based automation for energy conservation. The PIR sensor provides an alternative method to save power consumption by detecting human movement. 2. Smart Motor: Technology has been developing throughout the world as system moved from manual to auto. Appliances are Inductive, resistive and capacitive in nature. Inductive type are mostly motors. Three-phase Induction motor is one of the most common types of electrical machines with vast amount of applications in the entire power system all over the world due to its various advantages such as low starting power, lower maintenance cost etc. For the sake of economy and their longer life, it is very much necessary to provide them with feasible conditions to perform optimal operation with best possible smart protection techniques. Control elements used here are vibration as well temperature sensation with GSM based remote data acquisition technique for automatic operations as well as a manual control using a selector switch for automatic as well as manual operation and a molded case circuit breaker for protection purpose.

Aims and objectives: Diabetes Mellitus predisposes patients to invasive fungal infections. Aim of this study is to find out the incidence and outcome of Mucormycosis in diabetic patients with COVID-19. Materials and Methodology: A Retrospective study of 150 patients with COVID-19 who were admitted in VMKVMCH COVID-19 Ward, Salem from May 2021 to July 2021 was included in the study. Results: Among 150 hospitalized patients with COVID 19 infection, 32 patients had CAM with an incidence of 3.36%. In patients with CAM, 87.5% had Diabetes Mellitus as the most common co-morbidity. The majority of the patients had poor glycemic control with a mean HbA1c of 9.06%. Out of the total study population, 93% had prior exposure to high dose corticosteroids. During the study period, 12.5% patients of CAM did not survive. Conclusion: Mucormycosis is an angioinvasive fungal infection with high mortality. The disease has surged in COVID 19 pandemic due to uncontrolled diabetes and improper corticosteroid use.

Background- The current outbreak of viral pneumonia, caused by novel coronavirus SARS-CoV-2, is the focus of worldwide attention.Based on their mechanism of action and their demonstrated utility in chronic inflammatory conditions and early feasibility studies in COVID-19, there is a strong case for TNF inhibitor use in COVID-19. Objectives-To find out the Outcome of covid 19 patients treated with and without monoclonal antibody – Adalimumab, along with conventional antiviral therapy. Methods-A Retrospective case comparative study of 100 patients with COVID19 who were admitted in VMKVMCH COVID19 Ward, Salem from May 2021 to July 2021 was included in this study. Purposive sampling technique was used. Demographic details of the patients and outcomes were noted.SPSS (Version 22.0) was used. Results- Males were mostly affected (65%) as compared to females (35%), mean age was 49 years. Number of days in hospital stay was 8 days. Mortality was around 4%.RTPCR was the investigation of choice for the diagnosis of COVID done in 93% of patients and it was statistically significant (p

To assess the use of intraoperative IV ketorolac (Toradol) on the peri-operative total morphine milligram equivalent (MME) requirements of patients undergoing ureteroscopy for nephrolithiasis.Patients undergoing ambulatory ureteroscopy for nephrolithiasis were randomized to receive ketorolac at time of anesthesia induction. Patients and surgeons were blinded to treatment. Intraoperative, postoperative and combined MME were calculated. Multivariable regression was used to identify independent predictors of MME requirement. Complications were recorded.A total of 94 patients were analyzed following randomization. There were 46 patients in the treatment arm and 48 patients in the control arm. There were no statistically significant differences in gender, age, BMI, operative length or baseline pain medication use between groups (P.05). Patients in the treatment arm required lower intraoperative MME when compared to the control arm (17.1 vs 24, P.01). There were no statistically significant differences in the postoperative MME requirements between groups. The combined peri-operative MME was lower in the treatment arm compared to the control arm (22.2 vs 30.4, P.02). Ketorolac use was an independent predictor of lower MME use on multivariable analysis (beta coefficient -5.1, P.01). There was no statistically significant difference with regards to complication numbers between the treatment arms.Ketorolac during ureteroscopy is associated with a 37% reduction in narcotic requirement and is an independent predictor of decreased peri-operative narcotic needs. These findings show that intra-operative use of ketorolac effectively reduces narcotic requirements and should be considered independently or as part of a multimodal pain control protocol, unless otherwise contraindicated.

The NDLI Club is an initiative in the Indian Digital Education platform aimed at revolutionizing the educational landscape. Its primary objective is to engage learners and promote the effective use of the National Digital Library of India's resources through competitions, training sessions, and workshops. However, the reach of the NDLI Club remains limited, with only 2500+ registered clubs in colleges, indicating the need for expansion and awareness. To address this, a study was conducted to identify challenges faced by colleges in establishing NDLI Clubs. Using Kurt Lewin's action research model, teachers were made aware of the NDLI Club and encouraged to initiate clubs in their colleges. Interviews with key members revealed three main challenges: registration, event creation, and report submission. Only five out of 17 colleges fulfilled all registration requirements. Recommendations were proposed to overcome challenges and increase registrations, including organizing awareness programs, providing vernacular-based technical support, and implementing a user-friendly event creation and report submission system. Further research can explore successful implementations, best practices, and the impact of NDLI Clubs on student learning outcomes and teacher professional development.

The classification of plant diseases is essential for the timely detection and prevention of outbreaks, which can lead to significant crop loss and reduced food security. In recent years, machine learning techniques, such as SVM algorithm, have been used to classify plant diseases based on their symptoms and features extracted from images of diseased plants. This study aims to provide an overview of the SVM algorithm's application in plant disease classification and its potential for future development. The SVM algorithm has been shown to be effective in classifying various plant diseases, including black spot and anthranose. Furthermore, the integration of machine learning models with remote sensing and precision agriculture technologies has the potential to improve disease detection and prevention. Future directions for plant disease classification using machine learning techniques include the development of deep learning models, multimodal classification, and transfer learning. In conclusion, the use of machine learning techniques, including SVM algorithm, provides a valuable tool for the early detection and prevention of plant diseases, ultimately benefiting farmers, consumers, and the environment.