Explore the vast range of titles available.

Billions of dollars are being spent nationally and globally on providing computing access to digitally disadvantaged groups and cultures with an expectation that computers and the Internet can lead to higher socio-economic mobility. This ethnographic study of social computing in the Central Himalayas, India, investigates alternative social practices with new technologies and media amongst a population that is for the most part undocumented. In doing so, this book offers fresh and critical perspectives in areas of contemporary debate: informal learning with computers, cyberleisure, gender access and empowerment, digital intermediaries, and glocalization of information and media.

The COVID-19 pandemic continues to have major impact to health and medical infrastructure, economy, and agriculture. Prominent computational and mathematical models have been unreliable due to the complexity of the spread of infections. Moreover, lack of data collection and reporting makes modelling attempts difficult and unreliable. Hence, we need to re-look at the situation with reliable data sources and innovative forecasting models. Deep learning models such as recurrent neural networks are well suited for modelling spatiotemporal sequences. In this paper, we apply recurrent neural networks such as long short term memory (LSTM), bidirectional LSTM, and encoder-decoder LSTM models for multi-step (short-term) COVID-19 infection forecasting. We select Indian states with COVID-19 hotpots and capture the first (2020) and second (2021) wave of infections and provide two months ahead forecast. Our model predicts that the likelihood of another wave of infections in October and November 2021 is low; however, the authorities need to be vigilant given emerging variants of the virus. The accuracy of the predictions motivate the application of the method in other countries and regions. Nevertheless, the challenges in modelling remain due to the reliability of data and difficulties in capturing factors such as population density, logistics, and social aspects such as culture and lifestyle.

Cyberbullying and hate speeches are common issues in online etiquette. To tackle this highly concerned problem, we propose a text classification model based on convolutional neural networks for the de facto verbal aggression dataset built in our previous work and observe significant improvement, thanks to the proposed 2D TF-IDF features instead of pre-trained methods. Experiments are conducted to demonstrate that the proposed system outperforms our previous methods and other existing methods. A case study of word vectors is carried out to address the difficulty in using pre-trained word vectors for our short-text classification task, demonstrating the necessities of introducing 2D TF-IDF features. Furthermore, we also conduct visual analysis on the convolutional and pooling layers of the convolutional neural networks trained.

Artificial neural networks (ANNs) are one of the most promising tools in the quest to develop general artificial intelligence. Their design was inspired by how neurons in natural brains connect and process, the only other substrate to harbor intelligence. Compared to biological brains that are sparsely connected and that form sparsely distributed representations, ANNs instead process information by connecting all nodes of one layer to all nodes of the next. In addition, modern ANNs are trained with backpropagation, while their natural counterparts have been optimized by natural evolution over eons. We study whether the training method influences how information propagates through the brain by measuring the transfer entropy, that is, the information that is transferred from one group of neurons to another. We find that while the distribution of connection weights in optimized networks is largely unaffected by the training method, neuroevolution leads to networks in which information transfer is significantly more focused on small groups of neurons (compared to those trained by backpropagation) while also being more robust to perturbations of the weights. We conclude that the specific attributes of a training method (local vs. global) can significantly affect how information is processed and relayed through the brain, even when the overall performance is similar.

Water is a prime necessity for the survival and sustenance of all living beings. Over the past few years, the water quality of rivers is adversely affected due to harmful wastes and pollutants. This ever-increasing water pollution is a big matter of concern as it deteriorating the water quality, making it unfit for any type of use. Recently, water quality modelling using machine learning techniques has generated a lot of interest and can be very beneficial in ecological and water resources management. However, they suffer many times from high computational complexity and high prediction error. The good performance of a deep neural network like long short-term memory network (LSTM) has been exploited for the time-series data. In this paper, a deep learning–based Bi-LSTM model (DLBL-WQA) is introduced to forecast the water quality factors of Yamuna River, India. The existing schemes do not perform missing value imputation and focus only on the learning process without including a loss function pertaining to training error. The proposed model shows a novel scheme which includes missing value imputation in the first phase, the second phase generates the feature maps from the given input data, the third phase includes a Bi-LSTM architecture to improve the learning process, and finally, an optimized loss function is applied to reduce the training error. Thus, the proposed model improves forecasting accuracy. Data comprising monthly samples of different water quality factors were collected for 6 years (2013–2019) at several locations in the Delhi region. Experimental results reveal that predicted values of the model and the actual values were in a close agreement and could reveal a future trend. The performance of our model was compared with various state of the art techniques like SVR, random forest, artificial neural network, LSTM, and CNN-LSTM. To check the accuracy, metrics like root mean square errors (RMSE), the mean absolute error (MAE), mean square error (MSE), and mean absolute percentage error (MAPE) have been used. Experimental analysis is carried out by measuring the COD and BOD levels. COD analysis reveals the MSE, RMSE, MAE, and MAPE values as 0.015, 0.117, 0.115, and 20.32, respectively, for the Palla region. Similarly, BOD analysis indicates the MSE, RMSE, MAE, and MAPE values as 0.107, 0.108, 0.124, and 18.22, respectively. A comparative analysis reveals that the proposed model outperforms all other models in terms of the best forecasting accuracy and lowest error rates.

It has been shown that deep learning models can under certain circumstances outperform traditional statistical methods at forecasting. Furthermore, various techniques have been developed for quantifying the forecast uncertainty (prediction intervals). In this paper, we utilize prediction intervals constructed with the aid of artificial neural networks to detect anomalies in the multivariate setting. Challenges with existing deep learning-based anomaly detection approaches include ( i ) large sets of parameters that may be computationally intensive to tune, ( ii ) returning too many false positives rendering the techniques impractical for use, and ( iii ) requiring labeled datasets for training which are often not prevalent in real life. Our approach overcomes these challenges. We benchmark our approach against the oft-preferred well-established statistical models. We focus on three deep learning architectures, namely cascaded neural networks, reservoir computing, and long short-term memory recurrent neural networks. Our finding is deep learning outperforms (or at the very least is competitive to) the latter.

Recent results of studies have indicated that neural network quantization effects on inference accuracy vary among layers. Therefore, partial quantization and mixed precision quantization have been studied for neural network accelerators with multi-precision designs. However, these quantization methods typically require network training, which entails a high computational cost because of the exponentially increasing search space with respect to the number of layers N . However, an insufficient search leads to a significant degradation of inference accuracy. For partial quantization, this paper presents a greedy search algorithm that can derive practical combinations of quantization layers without re-training; notably, the proposed method exhibits particularly low computational complexity O ( N 2 ) . The proposed greedy search algorithm achieved 4.2 × model size compression with only 0.03% accuracy degradation in ResNet50 and 2.5 × compression with +0.015% accuracy gain in Xception. The computational cost of the greedy search algorithm was only 2.6 hours for a single V100 GPU in the case of MobileNetV2 quantization for ImageNet classification. Furthermore, we accelerated the proposed algorithm to computational complexity O ( N ) and achieved 4.15 × model size compression with only 0.072% accuracy degradation in ResNet50.

Banana cultivation is one of the main agricultural elements in India, while the common problem of cultivation is that the crop has been influenced by several diseases, while the pest indications have been needed for discovering the infections initially for avoiding the financial loss to the farmers. This problem will affect the entire banana productivity and directly affects the economy of the country. A hybrid convolution neural network (CNN) enabled banana disease detection, and the classification is proposed to overcome these issues guide the farmers through enabling fertilizers that have to be utilized for avoiding the disease in the initial stages, and the proposed technique shows 99% of accuracy that is compared with the related deep learning techniques.

Purpose – The advent of mobile telephony devices with strong internet capabilities has laid the foundation for mobile commerce (m-commerce) services. The purpose of this paper is to empirically examine predictors of m-commerce adoption using a modification of the widely used technology acceptance model and the unified theory of acceptance and use of technology model. Design/methodology/approach – The data were collected from 213 respondents by means of an online survey. The data were analyzed through multi analytic approach by employing structural equation modeling (SEM) and neural network modeling. Findings – The SEM results showed that variety of services, social influence, perceived usefulness, cost and perceived trust have significant influence on consumer’s intention to adopt m-commerce. The only exception was perceived ease of use which observed statistically insignificant influence on adoption of m-commerce. Furthermore, the results obtained from SEM were employed as input to the neural network model and results showed that perceived usefulness, perceived trust and variety of services as most important predictors in adoption of m-commerce. Practical implications – The findings of this study give an insight of key determinants that are important to develop suitable strategic framework to enhance the use of m-commerce adoption. In addition, it also provides an opportunity to academicians and researchers to use the framework of this study for further research. Originality/value – The study is among a very few studies which analyzed m-commerce adoption by applying a linear and non-linear approach. The study offers a multi-analytical model to understand and predict m-commerce adoption in the developing nation like India.