Air Quality Prediction Using the Fractional Gradient-Based Recurrent Neural Network.

In this study, the air quality index (AQI) of Indian cities of different tiers is predicted by using the vanilla recurrent neural network (RNN). AQI is used to measure the air quality of any region which is calculated on the basis of the concentration of ground-level ozone, particle pollution, carbon monoxide, and sulphur dioxide in air. Thus, the present air quality of an area is dependent on current weather conditions, vehicle traffic in that area, or anything that increases air pollution. Also, the current air quality is dependent on the climate conditions and industrialization in that area. Thus, the AQI is history-dependent. To capture this dependency, the memory property of fractional derivatives is exploited in this algorithm and the fractional gradient descent algorithm involving Caputo's derivative has been used in the backpropagation algorithm for training of the RNN. Due to the availability of a large amount of data and high computation support, deep neural networks are capable of giving state-of-the-art results in the time series prediction. But, in this study, the basic vanilla RNN has been chosen to check the effectiveness of fractional derivatives. The AQI and gases affecting AQI prediction results for different cities show that the proposed algorithm leads to higher accuracy. It has been observed that the results of the vanilla RNN with fractional derivatives are comparable to long short-term memory (LSTM).

Smart Pacemaker: A Review.

Since the first pacemaker was implanted, nearly 60 years have passed. Since then, pacemaker technology has made major advancements that have increased both its safety and effectiveness in treating people with bradyarrhythmias. The repeated stimulation of cells in specialized "pacemaker" regions of the mammalian heart and the transmission of stimulus via the ventricles serve as evidence that the electrical function of the mammalian heart is necessary for a regular mechanical (pump) role. The development of action potentials in individual cardiac cells is linked to myocardial electrical activity and the heart's regular cooperative electrical functioning. A container or pulse initiator that houses the battery and electronics, as well as lines that connect to the myocardium to deliver a depolarizing pulse and detect intrinsic cardiac stimulation, are all parts of a pacemaker. Defibrillators could be used with artificial hearts that have electrical pacemakers integrated into them in order to treat arrhythmia, heart failure, and cardiac arrest. Modern pacemakers have units for supporting patients with other disorders like "heart failure," which happens when the heart does not pump as forcefully as it should. While many pacemakers are effective in treating different types of arrhythmias (irregular heartbeats), they also have units for treating them.

A novel methodology for perception-based portfolio management.

Selecting and investing in stock market with right proportions is one of the major challenges. Majority of the investors end up losing their invested equity capital due to uncertainty in the market. The present study provides a novel framework for novice investors to construct portfolio based on multicriteria decision making techniques under fuzzy environment. The scores obtained from these techniques were used to introduce two non-dimensional parameters for categorization of risky and non-risky assets. Three perceptions portfolios were constructed based on the proposed non-dimensional parameters along with fractional lion clustering algorithm. In order to demonstrate the proposed framework, an illustrative application is included in equity portfolio selection. The returns and risks of these perception based portfolios are compared to major Index funds for validating the efficiency and are found to overpower the Index funds with significant margins by maintaining the risk comparable to Index funds. Further, Markowitz based efficient frontier is plotted for better understanding of optimal returns and risk for perception based investment.