The proper handling of waste is one of the biggest challenges of modern society. Municipal Solid Waste (MSW) requires categorization into a number of types, including bio, plastic, glass, metal, paper, etc. The most efficient techniques proposed by researchers so far include neural networks. In this paper, a detailed summarization was made of the existing deep learning techniques that have been proposed to classify waste. This paper proposes an architecture for the classification of litter into the categories specified in the benchmark approaches. The architecture used for classification was EfficientNet-B0. These are compound-scaling based models proposed by Google that are pretrained on ImageNet and have an accuracy of 74% to 84% in top-1 over ImageNet. This research proposes EfficientNet-B0 model tuning for images specific to particular demographic regions for efficient classification. This type of model tuning over transfer learning provides a customized model for classification, highly optimized for a particular region. It was shown that such a model had comparable accuracy to that of EfficientNet-B3, however, with a significantly smaller number of parameters required by the B3 model. Thus, the proposed technique achieved efficiency on the order of 4X in terms of FLOPS. Moreover, it resulted in improvised classifications as a result of fine-tuning over region-wise specific litter images.

Machine learning and deep learning are one of the most sought-after areas in computer science which are finding tremendous applications ranging from elementary education to genetic and space engineering. The applications of machine learning techniques for the development of smart cities have already been started; however, still in their infancy stage. A major challenge for Smart City developments is effective waste management by following proper planning and implementation for linking different regions such as residential buildings, hotels, industrial and commercial establishments, the transport sector, healthcare institutes, tourism spots, public places, and several others. Smart City experts perform an important role for evaluation and formulation of an efficient waste management scheme which can be easily integrated with the overall development plan for the complete city. In this work, we have offered an automated classification model for urban waste into multiple categories using Convolutional Neural Networks. We have represented the model which is being implemented using Fine Tuning of Pretrained Neural Network Model with new datasets for litter classification. With the help of this model, software, and hardware both can be developed using low-cost resources and can be deployed at a large scale as it is the issue associated with healthy living provisions across cities. The main significant aspects for the development of such models are to use pre-trained models and to utilize transfer learning for fine-tuning a pre-trained model for a specific task.

In today's fast-paced society, stress is a prevalent issue that can have detrimental effects on one's health. This study aims to investigate machine learning-based techniques for detecting stress in humans. Participants who were engaged in a variety of their daily routine tasks were taken for dataset taking their physiological signs, including breathing rate, skin conductance, and heart rate variability into consideration. Then, in order to detect stress, these signals were utilized to train different models of machine learning like support vector machines, random forest and logistic regression. The accuracy, precision, recall, and F1 score were a few of the metrics used to assess performance of these methods. According to the findings, the random forest model had the highest level of stress detection accuracy at 89%. The development of wearable technology and other applications that can aid people in managing their stress levels causes significant impact on state-of-the-art technological advancements in this area.

The recognition of handwritten numbers is a significant challenge in the field of computer vision, as it finds applications in various domains including banking, medical diagnostics, and handwriting recognition. In recent years, there has been a notable enhancement in our technological capabilities due to the progress made in internet accessibility and technology. Deep learning algorithms have emerged as valuable computational tools for addressing several challenges, including the task of digit recognition. The utilization of convolutional neural networks in the task of digit recognition is driven by their ability to acquire hierarchical representations from picture data. This scholarly article provides a comprehensive examination of the application of Convolutional Neural Networks (CNNs) in the field of machine learning for the purpose of digit recognition. This research examines the architectural components of Convolutional Neural Networks (CNNs), the training procedures employed, and the various methodologies employed for the purpose of digit recognition. The paper also provides an overview of the different datasets used for training and testing CNNs for digit recognition and a discussion of the results obtained from various studies.

With the increasing reliance on automatic software-based applications, it is critical to automate software defect classification and assure software dependability. This article proposes an expert-based automatic software flaw classification system. Defect report categorization is the process of categorizing defects into predefined groups. Many machine learning (ML) algorithms have recently been presented to categorize defect in various classes. This research proposes a classification model based on the Long Short Term Memory (LSTM) network and Convolution Neural Network (CNN) that uses these deep learning (DL) models to categorize defect reports by generating new word embedding from the defect reports. In terms of recall, accuracy and precision, the results are compared to pre-trained word embedding using Google's word2vec. According to the experimental results, LSTM beats the other models utilized in the study. On the redmine dataset, LSTM achieves a maximum accuracy of 70%.

Digit recognition using the Artificial Neural Network method is discussed in this study. Due to the enormous volumes of data and algorithms, the neural network can now be used to train the network and get the desired result. With the advancement in information and communication technology, internet access has increased as the use of technology increases the demand for digit recognition systems has gained popularity. This paper will discuss one of the techniques for digit recognition. We will train our model with the MNIST dataset & then test our model. Programming in Python is used to perform digit recognition. We have taken a dataset of 28,000-digit images, that will be used for training and 14,000-digit images for testing. The test performance accuracy of our multi-layer artificial neural network is 99.59 %.