Showing papers by "Mansaf Alam published in 2023"
17 May 2023
TL;DR: In this article , a biological brain optimized neuromorphic Convolution Neural Network (biCNN-HAR) was developed for human activity recognition (HAR), and its performance was compared with baseline CNN models and state-of-the-art models.
Abstract: Human activity recognition (HAR) is a rapidly growing field with numerous practical applications, such as healthcare, assistive living, and security. The majority of HAR applications are ideally suited for edge deployment. However, edge devices have limited memory and energy, making it challenging to deploy HAR tasks on them. To address this issue, a biological brain optimized neuromorphic Convolution Neural Network (biCNN-HAR) for HAR is developed. The performance of biCNN-HAR is evaluated on mHealth dataset, and its results are compared with baseline CNN models and state-of-the-art models. The findings demonstrate that biCNNHAR outperforms other models while utilizing fewer computational resources.
TL;DR: In this article , the authors present a feature analysis of the NoSQL solutions and then generate a data set of the investigated solutions for further analysis in order to better understand and select the technologies.
Abstract: With the explosion of social media, the Web, Internet of Things, and the proliferation of smart devices, large amounts of data are being generated each day. However, traditional data management technologies are increasingly inadequate to cope with this growth in data. NoSQL has become increasingly popular as this technology can provide consistent, scalable and available solutions for the ever-growing heterogeneous data. Recent years have seen growing applications shifting from traditional data management systems to NoSQL solutions. However, there is limited in-depth literature reporting on NoSQL storage technologies for big graph and their applications in various fields. This chapter fills this gap by conducting a comprehensive study of 80 state-of-the-art NoSQL technologies. In this chapter, we first present a feature analysis of the NoSQL solutions and then generate a data set of the investigated solutions for further analysis in order to better understand and select the technologies. We perform a clustering analysis to segment the NoSQL solutions, compare the classified solutions based on their storage data models and Brewer's CAP theorem, and examine big graph applications in six specific domains. To help users select appropriate NoSQL solutions, we have developed a decision tree model and a web-based user interface to facilitate this process. In addition, the significance, challenges, applications and categories of storage technologies are discussed as well.
TL;DR: In this paper , the authors proposed a novel BO-HyTS approach that combines seasonal autoregressive integrated moving average (SARIMA) and long short-term memory (LSTM) and fine-tuned it by using Bayesian optimization to predict air pollution levels.
Abstract: Air pollution is a significant environmental issue affecting public health and ecosystems worldwide, resulting from various sources such as industrial activities, vehicle emissions, and fossil fuel burning. Air pollution contributes to climate change and can cause several health problems, such as respiratory illnesses, cardiovascular disease, and cancer. A potential solution to this problem has been proposed by using different artificial intelligence (AI) and time-series models. These models are implemented in the cloud environment to forecast the Air Quality Index (AQI) utilizing Internet of things (IoT) devices. The recent influx of IoT-enabled time-series air pollution data poses challenges for traditional models. Various approaches have been explored to forecast AQI in the cloud environment using IoT devices. The primary objective of this study is to assess the efficacy of an IoT-Cloud-based model for forecasting the AQI under different meteorological conditions. To achieve this, we proposed a novel BO-HyTS approach that combines seasonal autoregressive integrated moving average (SARIMA) and long short-term memory (LSTM) and fine-tuned it by using Bayesian optimization to predict air pollution levels. The proposed BO-HyTS model can capture both linear and nonlinear characteristics of the time-series data, thus augmenting the accuracy of the forecasting process. Additionally, several AQI forecasting models, including classical time-series, machine learning, and deep learning, are employed to forecast air quality from time-series data. Five statistical evaluation metrics are incorporated to evaluate the effectiveness of models. While comparing the various algorithms among themselves becomes difficult, a non-parametric statistical significance test (Friedman test) is applied to assess the performance of the different machine learning, time-series, and deep learning models. The findings reveal that the proposed BO-HyTS model produced significantly better results than their competitor's, providing the most accurate and efficient forecasting model, with an MSE of 632.200, RMSE of 25.14, Med AE of 19.11, Max Error of 51.52, and MAE of 20.49. The results of this study provide insights into the future patterns of AQI in various Indian states and set a standard for these states as governments develop their healthcare policies accordingly. The proposed BO-HyTS model has the potential to inform policy decisions and enable governments and organizations to protect better and manage the environment beforehand.