Two-Way Feature Extraction for Speech Emotion Recognition Using Deep Learning.

Recognizing human emotions by machines is a complex task. Deep learning models attempt to automate this process by rendering machines to exhibit learning capabilities. However, identifying human emotions from speech with good performance is still challenging. With the advent of deep learning algorithms, this problem has been addressed recently. However, most research work in the past focused on feature extraction as only one method for training. In this research, we have explored two different methods of extracting features to address effective speech emotion recognition. Initially, two-way feature extraction is proposed by utilizing super convergence to extract two sets of potential features from the speech data. For the first set of features, principal component analysis (PCA) is applied to obtain the first feature set. Thereafter, a deep neural network (DNN) with dense and dropout layers is implemented. In the second approach, mel-spectrogram images are extracted from audio files, and the 2D images are given as input to the pre-trained VGG-16 model. Extensive experiments and an in-depth comparative analysis over both the feature extraction methods with multiple algorithms and over two datasets are performed in this work. The RAVDESS dataset provided significantly better accuracy than using numeric features on a DNN.

ThoraciNet: thoracic abnormality detection and disease classification using fusion DCNNs.

Chest X-rays are arguably the de facto medical imaging technique for diagnosing thoracic abnormalities. Chest X-ray analysis is complex, especially in asymptomatic diseases, and relies heavily on the expertise of radiologists. This work proposes the use of deep learning models to automate the process of thoracic abnormality detection, classification, and segmentation. The advent of large-scale, annotated and public chest X-ray databases have enabled deep learning researchers to build state-of-the-art computer-aided diagnosis systems for such tasks. In this work, a two-stage pipeline is proposed for thoracic abnormality detection and disease classification using chest X-rays. Two fusion-based models are proposed for disease classification, using two asymmetric, deep convolutional neural networks. Results are evaluated over NIH database covering multiple patients' X-rays with metrics such as accuracy and AUC scores. The proposed architecture outperforms the existing ones, achieving AUC scores of 0.99 for CXR triaging and 0.79 for CXR disease classification. Furthermore, GradCAM visualization is performed to validate the results, rendering model predictions interpretable to experts and end-users.

3-D twelve-port multi-service diversity antenna for automotive communications.

This paper presents a twelve-port ultra-wideband multiple-input-multiple-output (MIMO)/diversity antenna integrated with GSM and Bluetooth bands. The twelve-port antenna is constructed by arranging four elements in the horizontal plane and eight elements in the vertical plane. The antenna element, which is created using a simple rectangular monopole, exhibits a frequency range of 3.1 to 12 GHz. The additional Bluetooth and GSM bands are achieved by introducing stubs into the ground plane. The size of the MIMO antenna is 100 × 100 mm2. The antenna offers polarization diversity, with vertical and horizontal polarization in each plane. The diversity antenna has a bandwidth of 1.7-1.9 GHz, 2.35-2.55 GHz, and 3-12 GHz, the radiation efficiency of 90%, and peak gain of 2.19 dBi. The proposed antenna offers an envelope correlation coefficient of < 0.12, apparent diversity gain of > 9.9 dB, effective diversity gain of > 8.9 dB, mean effective gain of < 1 dB, and channel capacity loss of < 0.35 bits/s/Hz. Also, the MIMO antenna is tested for housing effects in order to determine its suitability for automotive applications.

On the design and performance analysis of wristband MIMO/diversity antenna for smart wearable communication applications.

The design of a silicone rubber-based wristband wearable antenna exploiting pattern diversity is presented in this paper. The wristband diversity antenna consists of four identical antenna elements with an inter-element spacing of 0.68λ0, where λ0 is the lower cut-off wavelength. A modified trapezoidal-shaped radiator with a rectangular ground structure is used to achieve ultra-wide bandwidth. The proposed multiple-input-multiple-output (MIMO)/diversity antenna covers a frequency range of 2.75-12 GHz. The antenna element offers a radiation efficiency of 89.3% and a gain of 3.41 dBi. The size of the wristband diversity antenna is 1.1λ0 × 18.4λ0 × 0.18λ0. The diversity performance characteristics of the prototype antenna are examined, with the envelope correlation coefficient (ECC) < 0.18, apparent diversity gain (ADG) > 9.5, effective diversity gain (EDG) > 9.5, mean effective gain (MEG) < 1 dB, total active reflection coefficient (TARC) < - 10 dB, and channel capacity loss (CCL) < 0.1  bits/s/Hz over the entire operating band. The specific absorption rate (SAR) of the proposed wristband antenna is analyzed to determine its radiation exposure on the human body, and the results show that the values are less than 0.02 W/kg.

Detection of anomalous nitrogen dioxide (NO2) concentration in urban air of India using proximity and clustering methods.

Owing to accurate future air quality estimates, need for detecting the anomalously high increase in concentration of pollutants cannot be adjourned. Plentiful approaches were proposed in the past to substantially determine the abnormal conditions, but most of the statistical approaches were computationally expensive and ignored the false alarm ratios. Thus, a hybrid of proximity- and clustering-based anomaly detection approaches to identify anomalies in the air quality data is suggested in this work. The Gaussian distribution property of the real-world data set is utilized further to segregate out anomalies. The results depicted twofold advantages of our approach, by efficient extraction of anomalies and with increased accuracy by reducing the number of false alarms. Specifically, the presence of NO2 concentration in air is investigated in this work, considering its constant increase over decades as well as its inevitable health risks. Furthermore, spatiotemporal segments with anomalously high NO2 concentrations for 14 residential, industrial, and commercial areas of five cities in India are extracted. To validate the results, a comparative analysis with existing approaches of anomaly detection and with two benchmark data sets is performed. Results showed that our method outperformed the existing methods of anomaly detection, when evaluated over metrics such as sensitivity, miss rate, and false alarms. Further, a detailed analysis of extracted anomalies and a detailed discussion about the factors responsible for such anomalies are presented in this work. This study is helpful in educating government and people about spatiotemporal, geographical, and economic conditions responsible for anomalously high NO2 concentrations in air. Implications: Using our methodology, days with extremely high concentration of any pollutant in air, at any particular location, can be extracted. The reasons for such extremely high pollutant concentration on particular days of a year can be studied and preventive measures can be taken by the government. Thus, by identification of causes of anomalies, future similar events can be avoided. This would also help in people's decision making in case such events occur in the future.