Journal of Advanced Applied Scientific Research (JOAASR)
Not a member yet
259 research outputs found
Sort by
Detection and Removal of Assymmetrical Skin Lesions Using DU-Net for Patch Extraction
Get PDFThis study presents DSeg-net, a novel method for accurately identifying and removingpigmented skin lesions from dermoscopic images, crucial for timely diagnosis and managementof melanoma. DSeg-net combines deep convolutional neural networks, particularly YOLOv5, forpatch detection, asymmetrical patch contouring for edge preservation, and clustering techniquesfor patch extraction. Additionally, it employs De Trop Noise Exclusion with in-painting toeliminate hair from challenging dataset images. The method involves rigorous annotation of skinimages with lesions of varying sizes and shapes using rectangle bounding, followed by fine-tuning YOLOv5 hyperparameters for high-confidence multiple lesion detection. Despitecomplex textures and unclear boundaries, DSeg-net consistently detects and labels patches,accurately segmenting areas of skin pathology. Evaluation on various datasets demonstrates thatthe proposed segmentation techniques achieve an overall average accuracy of approximately92% to 94%
Transfer Learning Using Teachable Machine For Classification Of Glassware In Chemistry Lab
Get PDFImage classification is an important use case of deep learning algorithms. Convolution Nural networks, CNNs, have evolved to an extent where pretrained models can be used to train new models. The technique used for this type of model building activity is called as Transfer lerning. We have developed an image classification model using transfer lerning to classify lab glassware used in Chemistry lab. This model can be used for training purpose for the students in high schools who are not much aware about the practical implementation of laboratory experiments. We have used subset of Labpics dataset developed by Eppel et.al. We have used teachable machine as a platform to build this model with very limited computational resource. With transfer learning mechanism used by teachable machine platform we were able to achieve ~83% accurate image classification mode
Deep learning models for stock prediction on diverse datasets
Get PDFMarket forecasting has attracted the interest of investors all over the world. The investors are looking for an accurate and reliable forecasting model that can fully embrace the extremely volatile and nonlinear market behavior. It is now possible to design effective stock price prediction algorithms due to the abundance of data, the quick advancement of AI and machine learning techniques, and the machine's increased computational capability. Deep learning algorithms are particularly successful in modelling market volatility. To forecast the closing prices of three stocks: Apple (AAPL), Google (GOOG), and Amazon (AMZN), Convolutional Neural Network (CNN) and Long-Short Term Memory (LSTM) are implemented and compared. The stock data was obtained from yahoo finance for one year, three years and five years. The Root Mean Square Error (RMSE) metric and loss are employed for evaluating the model’s performance
Self-Governing Feedback Network (SGFN) Based Super Resolution for bean leaf disease detection
Get PDFCrop loss caused by diseases that result from a range of insects, bacteria, viruses, and fungi has been a severe concern for generations that demands global attention. As a result, diagnosing crop diseases as soon as feasible can dramatically reduce production loss and enhance monetary value. The Self-governing Feedback Network (SGFN) model is suggested in this paper for producing Super Resolution images from low-resolution bean leaf images and recognizing disease. On the bean leaf dataset, the proposed SGFN model is tested for super-resolution factors 2, 4, and 6. PSNRs of 31.27, 35.653, and 37.721 are achieved for super-resolution factors 2, 4, and 6, respectively, with classification accuracies of 99.54, 98.73, and 97.64
Role of bio-fertilizers towards sustainable agricultural development: A review
Get PDFAs bioinoculants, numerous eco-friendly microorganisms with a wide range of products are regularly utilised to improve the soil's potential and provide the host plant with the nutrients it requires. The inorganic chemical-based fertilisers employed in the soil management practises are a serious threat to both human health and the environment. Biofertilizers are alternatives that are used in sustainable agriculture to increase soil fertility and crop productivity. The use of beneficial microorganisms as bio-fertilizers has become crucial in the agricultural sector due to its potential impact on food safety and sustainable crop production. The numerous bacteria used in bioinoculant formulations, the carrier materials used, and the applications of biofertilizers are the main subjects of this paper. In especially in appropriate farming, bio-fertilizers are essential for maintaining soil fertility over the long term and crop production sustainability
Design and Fabrication of Earth Auger with trolley
Get PDFThe purpose of this project is to design and fabricate an earth auger to overcome limitations on the existing earth augers. The earth auger is designed by introducing the trolley system. The project will be successful in providing the earth auger which is operator friendly and can be transported from one place to another by the single operator. The simplified mechanisms are implemented in the project including the winches and pulley systems for the feed and movement of the drill bit. The clamping systems are introducing to increase the stability and to decrease the vibrations which keeps the operator to be in a distance during the operations for the purpose of safety. Therefore, this project is made to reduce the fault and to improve the safety measures as well as the usability
Designing of voice-controlled drone using BT-voice control for Arduino
Get PDFThe hand-free drone project aims to create a drone that can be controlled through voice commands, eliminating the need for remote control or gestures. The system uses voice recognition technology to process the commands and act accordingly, using code to control the motors and achieve the desired outcome. This technology can be used in various applications, including military, surveillance, photography, gaming, and more
Dimensions Identified for Physical Ergonomic Analysis in Manufacturing Industries: A Review
Get PDFProductivity is a crucial factor in the manufacturing sector. However, exposure to poor ergonomic conditions can have a significant negative impact on productivity. Work-related injuries are a major issue in the active population of the manufacturing industry. This study examines the various ergonomic issues that could impact labour and result in illnesses, accidents, and musculoskeletal diseases, which reduce productivity. The aim is to reduce or eliminate work-related injuries and accidents altogether to boost productivity. This review pinpoints the variables crucial for physical ergonomic analysis in the manufacturing sector, such as job activities, the workplace, machine safety, work environment, and work organization. The inference is that identifying and addressing ergonomic issues is essential for improving productivity in the manufacturing industry. The study recommends creating surveys based on these aspects for workplace analysis in manufacturing industries
Edible Biopolymers from Marine Algae used as an Alternate Packaging material: A Review on their characteristics and properties
Get PDFFood packaging is estimated to account for two-thirds of all plastic waste. As a result, it is crucial to discover alternative packaging materials that are both environmentally friendly and safe for human health. Marine algae are becoming more well-known and in demand as cutting-edge resources for producing biopolymers like proteins and polysaccharides. Because of their biocompatibility, biodegradability, and lack of toxicity, biopolymers have been suggested as potential sources for food packaging materials. Numerous research has thoroughly examined the extraction, separation, and use of marine biopolymers in the creation of sustainable packaging. Marine algae are also rich in protein and mineral content, they also have anticancer, anti-obesity, and hypolipidemic properties due to the presence of polyunsaturated conjugated fatty acids. The edible films enhance the shelf life of food by controlling moisture without changing the elements of food. The marine algae are collected either in the intertidal or subtidal areas and they will be dried for further process. The edible films are environmentally friendly. The edible film made from marine algae is a mixture of protein, polysaccharides, lipids, and resins. The factors which affect the properties of the edible film are the source of raw material, surface charge, hydrophobicity, polymer chain length, plasticizer type, proportion, and synthesis method. There are numerous research has been conducted to develop edible film using various matrix constituents. This review provides an overview of Marine algae, its process, and edible films, its characteristics, and factors affecting the film
Evaluating Sentiment Classification to Specify Polarity by Lexicon-Based and Machine Learning Approaches for COVID-19 Twitter Data Sets
Get PDFAs part of data science, sentiment analysis (SA) applied to social media data is a trending research topic. Identifying positive, negative, or neutral opinions or feelings in the text is the attention of sentiment analysis. In the past few years, Social media platforms have become increasingly popular. In this research, natural language processing (NLP) will be employed to extract useful data and information from unstructured text. .The two methods for sentiment analysis covered in this research are the machine-learning method and the lexicon-based method. The paper examines several lexicon approaches to demonstrate the sentiments from Twitter. To increase classification accuracy, it is necessary to use a reliable method with the highest performance. In this study, classifiers such as Support Vector Machine (SVM) and Naive Bayes (NB) were used together with techniques such as TF-IDF (Term Frequency-Inverse Document Frequency) and BOW (Bag of Words). Each algorithm produces a unique outcome. In order to measure the accuracy of classification, metrics such as Precision, Recall, and F-score are considered. This research shows Support Vector Machine (SVM) with TF-IDF is better than other classifiers with an accuracy of 88%