A Modified Deep Learning Framework for Arrhythmia Disease Analysis in Medical Imaging Using Electrocardiogram Signal.

Arrhythmias are anomalies in the heartbeat rhythm that occur occasionally in people's lives. These arrhythmias can lead to potentially deadly consequences, putting your life in jeopardy. As a result, arrhythmia identification and classification are an important aspect of cardiac diagnostics. An electrocardiogram (ECG), a recording collecting the heart's pumping activity, is regarded the guideline for catching these abnormal episodes. Nevertheless, because the ECG contains so much data, extracting the crucial data from imagery evaluation becomes extremely difficult. As a result, it is vital to create an effective system for analyzing ECG's massive amount of data. The ECG image from ECG signal is processed by some image processing techniques. To optimize the identification and categorization process, this research presents a hybrid deep learning-based technique. This paper contributes in two ways. Automating noise reduction and extraction of features, 1D ECG data are first converted into 2D pictures. Then, based on experimental evidence, a hybrid model called CNNLSTM is presented, which combines CNN and LSTM models. We conducted a comprehensive research using the broadly used MIT_BIH arrhythmia dataset to assess the efficacy of the proposed CNN-LSTM technique. The results reveal that the proposed method has a 99.10 percent accuracy rate. Furthermore, the proposed model has an average sensitivity of 98.35 percent and a specificity of 98.38 percent. These outcomes are superior to those produced using other procedures, and they will significantly reduce the amount of involvement necessary by physicians.

A Comparison Between Measured Concentration of 3H in Kalpakkam Environment with Predicted Atmospheric Dispersion Model.

The field measurements of 3H in the form of HTO present in air moisture carried out around Madras Atomic Power Station were compared with predicted values using atmospheric dispersion modeling. Air 3H samples were collected from different sectors at the site boundary of the operating reactors for the period of 2 y and compared with Gaussian Plume model. The predictions were comparable with the measured value. The slight variation observed between the two methods is attributed to the uncertainty involved in the measurement of air 3H concentration and in the measurement of site-specific meteorological parameters. The radiation dose imparted to members of public due to the levels observed is well within station technical specification limit for 3H.

Efficiency as a function of MEQ-CWT for large area germanium detectors using LLNL phantom.

The lung counting system at Kalpakkam, India, used for the estimation of transuranics deposited in the lungs of occupational workers, consists of an array of three large area germanium detectors fixed in a single assembly. The efficiency calibration for low energy photons was carried out using ²4¹Am and ²³²Th lung sets of Lawrence Livermore National Laboratory phantom. The muscle equivalent chest wall thickness (MEQ-CWT) was derived for the three energies 59.5, 75.95 (average energy of ²³²Th) and 238.9 keV for the series of overlay plates made of different adipose mass ratios. Efficiency as a function of MEQ-CWT was calculated for individual detectors for the three energies. Variation of MEQ-CWT from 16 to 40 mm resulted in an efficiency variation of around 40 % for all the three energies. The array efficiency for different MEQ-CWT ranged from 1.4×10⁻³ to 3.2×10⁻³, 1.5×10⁻³ to 3.3×10⁻³ and 1.1×10⁻³ to 2.3×10⁻³ for 59.5, 75.95 and 238.9 keV, respectively. In the energy response, efficiency was observed to be maximum for 75.95 keV compared with 59.5 and 238.9 keV.

Evaluation of 25 y of environmental monitoring data around Madras Atomic Power Station (MAPS), Kalpakkam, India.

The Environmental Survey Laboratory at Kalpakkam, India carries out elaborate monitoring programme involving atmospheric, terrestrial and aquatic samples for radioactivity to evaluate the impact of operating two pressurised heavy water reactors. This paper presents the evaluation of 25 y (1983-2008) data. Statistical analysis of the environmental data for different radionuclides showed that the data best fits log-normal distribution. The data analysed showed that fission products such as (137)Cs, (90)Sr and (131)I were due to global fallout only. A ratio of 0.2 was obtained for (90)Sr to (137)Cs in air filter samples, only during Chernobyl accident period. The transfer factor of (137)Cs and (90)Sr for rice was computed to be 0.23 and 0.03 and vegetables 0.25 and 0.10, respectively. Activation products (3)H and (41)Ar are the only radionuclides that are related to MAPS operation. A strong correlation (r = 0.9) was observed between (3)H activity in air and (3)H discharged to the atmosphere. A similar correlation (r = 0.8) was observed in (3)H concentration in seawater and (3)H discharged in the liquid waste. The annual internal dose due to (3)H and annual external dose due to (41)Ar evaluated in the last 25 y show that the members of the public received less than 2 % of the dose limit (1 mSv y(-1)) set by ICRP 72.

A comparative study of body potassium content in males and females at Kalpakkam (India).

A group of 300 subjects of both sexes were measured for total body potassium content using a shadow shield whole-body counting system at Kalpakkam (India). The mean body potassium content for males was 1.7 +/- 0.5 g kg(-1) body weight and 1.5 +/- 0.5 g kg(-1) body weight for females. The body potassium content varies inversely with age as well as with the body weight for both the sexes. However, the total body potassium varies directly with body-build index for both males and females. The mean annual dose due to (40)K for males and females was found to be 149 +/- 44 and 132 +/- 41 uGy, respectively.