Search

This article explores the trends in computer science research in India from 2019 to 2022 based on research coming out of leading Indian technology institutes, including Chennai Mathematical Institute, Indian Institute of Science and Indian Institute of Technology Delhi. Topics include research on automata theory, formal verification, computational complexity research, and Algorithms research.

Purpose: The purpose of this paper is to develop a hybrid algorithm, which is a blend of auto-regressive integral moving average (ARIMA) and multilayer perceptron (MLP) for addressing the non-linearity of the load time series. Design/methodology/approach: Short-term load forecasting is a complex process as the nature of the load-time series data is highly nonlinear. So, only ARIMA-based load forecasting will not provide accurate results. Hence, ARIMA is combined with MLP, a deep learning approach that models the resultant data from ARIMA and processes them further for Modelling the non-linearity. Findings: The proposed hybrid approach detects the residuals of the ARIMA, a linear statistical technique and models these residuals with MLP neural network. As the non-linearity of the load time series is approximated in this error modeling process, the proposed approach produces accurate forecasting results of the hourly loads. Originality/value: The effectiveness of the proposed approach is tested in the laboratory with the real load data of a metropolitan city from South India. The performance of the proposed hybrid approach is compared with the conventional methods based on the metrics such as mean absolute percentage error and root mean square error. The comparative results show that the proposed prediction strategy outperforms the other hybrid methods in terms of accuracy. [ABSTRACT FROM AUTHOR]

A recent study conducted at the Central University of Haryana in India has proposed a privacy-preserving collaborative model for the classification of brain tumors using magnetic resonance imaging (MRI) images. The study utilized deep learning and transfer learning algorithms to analyze an open-source dataset of MRI images, which included four types of tumors and no tumor. The researchers found that federated deep learning models, involving multiple clients, outperformed conventional pretrained models in terms of accuracy. The proposed framework offers a solution for early diagnosis of brain tumors while ensuring data privacy for edge devices with limited resources. [Extracted from the article]

Researchers from Deenbandhu Chhotu Ram University of Science and Technology in India have published a new study on information technology management. The study focuses on the development of a brain-computer interface using a genetic algorithm with modified genome and phenotype structures. The researchers propose a novel scheme that combines genetic algorithms, support vector machines, and wavelet packet transform for motor imagery classification and optimal channel selection. The scheme outperforms existing methods in terms of classification accuracy and number of channels. This research contributes to the advancement of human-machine interface technology. [Extracted from the article]

A new report from researchers at the Department of Management in Dehradun, India, discusses the use of computer-aided detection (CAD) in classifying brain diseases, with a focus on Alzheimer's Disease (AD) and brain tumors. The study highlights the importance of expertise in interpreting MRI, PET, and CT scans for accurate diagnosis. The researchers propose pre-processing methods that improve the classification performance of MRI images and reduce training time for learning algorithms. The study concludes that their proposed algorithms outperformed existing methods in terms of accuracy and sensitivity. For more information, the full article can be accessed through the provided link. [Extracted from the article]

A new report from researchers at the Ramrao Adik Institute of Technology in Maharashtra, India, explores the integration of machine learning and traditional image processing in dentistry. The study reviews the literature on deep learning and dental radiograph analysis, focusing on applications such as automatic teeth identification and numbering, caries and anomaly detection, disease detection, and dental treatment prediction. The researchers provide an overview of machine learning algorithms in these areas and discuss the available dental radiograph dataset for experiments. The study concludes by highlighting new research opportunities and initiatives in this field, offering a comprehensive overview of the growing area of machine learning in dentistry. [Extracted from the article]

A recent study conducted in Tamil Nadu, India, has focused on autism spectrum disorders (ASD) and their impact on behavior and communication abilities. The study highlights the increasing number of people being diagnosed with ASD and the high medical expenses associated with it. To address these challenges, the researchers propose a novel deep recurrent neural network algorithm for the detection of autism levels. The algorithm utilizes an artificial algae algorithm for feature extraction and an intelligent water droplet algorithm for obtaining optimal weights and biases. The experimental results show promising classification accuracy, sensitivity, and cost reduction. For more information, readers can refer to the research article published in the International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems. [Extracted from the article]

A study conducted by researchers at VIT-AP University in Andhra Pradesh, India, has developed a deep learning algorithm called RU-Net2+ for accurate brain tumor segmentation and survival rate prediction. The algorithm was applied to a dataset of brain tumor images and achieved impressive results, surpassing current benchmarks in classification accuracy, tumor segmentation precision, and survival rate prediction. The framework shows promise for automating brain tumor diagnosis and enhancing patient care, providing valuable insights for medical professionals making treatment decisions. The study was published in IEEE Access. [Extracted from the article]

The article discusses the automated translation of Indian languages. The 2001 census in India states that there are 122 languages spoken in India with 22 designated as official by the Indian government. Sampark, a multipart machine translation architecture, is being constructed by 11 different institutions under the leadership of the Language Technologies Research Center at the International Institute of Information Technology in Hyderabad. Sampark utilizes dictionary-based algorithms and traditional rules alongside statistical machine learning to translate and it could be available to the public on the Internet in January 2010.