Automatic Speaker Recognition (ASR) and related issues are continuously evolving as inseparable elements of Human Computer Interaction (HCI). With assimilation of emerging concepts like big data and ...Internet of Things (IoT) as extended elements of HCI, ASR techniques are found to be passing through a paradigm shift. Oflate, learning based techniques have started to receive greater attention from research communities related to ASR owing to the fact that former possess natural ability to mimic biological behavior and that way aids ASR modeling and processing. The current learning based ASR techniques are found to be evolving further with incorporation of big data, IoT like concepts. Here, in this paper, we report certain approaches based on machine learning (ML) used for extraction of relevant samples from big data space and apply them for ASR using certain soft computing techniques for Assamese speech with dialectal variations. A class of ML techniques comprising of the basic Artificial Neural Network (ANN) in feedforward (FF) and Deep Neural Network (DNN) forms using raw speech, extracted features and frequency domain forms are considered. The Multi Layer Perceptron (MLP) is configured with inputs in several forms to learn class information obtained using clustering and manual labeling. DNNs are also used to extract specific sentence types. Initially, from a large storage, relevant samples are selected and assimilated. Next, a few conventional methods are used for feature extraction of a few selected types. The features comprise of both spectral and prosodic types. These are applied to Recurrent Neural Network (RNN) and Fully Focused Time Delay Neural Network (FFTDNN) structures to evaluate their performance in recognizing mood, dialect, speaker and gender variations in dialectal Assamese speech. The system is tested under several background noise conditions by considering the recognition rates (obtained using confusion matrices and manually) and computation time. It is found that the proposed ML based sentence extraction techniques and the composite feature set used with RNN as classifier outperform all other approaches. By using ANN in FF form as feature extractor, the performance of the system is evaluated and a comparison is made. Experimental results show that the application of big data samples has enhanced the learning of the ASR system. Further, the ANN based sample and feature extraction techniques are found to be efficient enough to enable application of ML techniques in big data aspects as part of ASR systems.
Electronic warfare (EW) is one of the most important characteristics of modern battles. EW can affect a military force's use of the electromagnetic spectrum to detect targets or to provide ...information. Recent developments in artificial intelligence (AI) suggest that this emerging technology will have a deterministic and potentially transformative influence on military power. AI driven algorithms can be very effective in diverse domain of EW like processing of radar signals for efficient recognition and classification of emitters, detection of jammer and its characteristics and for developing efficient anti-jamming algorithms. AI techniques can also enable an EW system to operate autonomously. This paper provides a description of various branches of EW, the role of AI in EW systems and different AI techniques that have been deployed in EW systems.
Contrary to popular belief, agriculture is becoming more data-driven with artificial intelligence and Internet-of-Things (IoT) playing crucial roles. In this paper, the integrated processing executed ...by various sensors combined as an IoT pack and driving an intelligent agriculture management system designed for rainfall prediction and fruit health monitoring have been included. The proposed system based on an AI aided model makes use of a Convolutional Neural Network (CNN) with long short-term memory (LSTM) layer for rainfall prediction and a CNN with SoftMax layer along with a few deep learning pre-trained models for fruit health monitoring. Another model that works as a combined rainfall predictor and fruit health recognizer is designed using a CNN + LSTM and a multi-head self-attention mechanism which proves to be effective. The entire system is cloud resident and available for use through an application.
This paper presents a novel design of a single-layer, horizontally polarized, dual-band, omni- and multi-directional hybrid dielectric resonator antenna (DRA) feeding through a 50 Ω coaxial ...connector. The proposed antenna consists of an FR4 substrate, a regular ground plane and a cross-shaped patch. The connector is placed at the middle point of the square ground plane. Above the microstrip patch, four similar solid dielectric resonator elements are placed diagonally. These DRA structures generate the TE111, hybrid HEM22δ modes and put up an ideal magnetic dipole and an electric quadrupole far-field radiation pattern. To verify the idea, an optimized antenna model is fabricated and tested. A reasonable agreement between the measured and simulated results is obtained. The measured impedance bandwidths of the TE111 and HEM22δ modes are 4.26 % (2.9–3.2 GHz) and 4.34 % (4.4–4.6 GHz), respectively. The proposed antenna has a stable omnidirectional radiation pattern at the first resonance frequency and a directional radiation pattern at the second resonance frequency and provides volume reduction.
The Internet of Things (IoT) and artificial intelligence (AI) based methods for monitoring, control, and decision support are combined to design of a smart agriculture assistance system. The proposed ...system has a sensor pack that provides continuous data capture of temperature records, air and soil moisture and a camera for obtaining near-infrared (NIR) images of the plant leaves for use with an AI decision support system. We identify twelve types of vegetation for the study, out of which five disease classes of the tomato leaves are categorized using a Convolutional Neural Network (CNN). The work also includes experiments conducted with multiple clustering-based segmentation methods and some features namely Gray level co-occurrence matrix (GLCM), Local binary pattern (LBP), Local Binary Gray Level Co-occurrence Matrix (LBGLCM), Gray Level Run Length Matrix (GLRLM), and Segmentation-based Fractal Texture Analysis (SFTA). Out of several AI tools, CNN proves to be effective in providing automated decision support for classifying the plant leaf disease types through a cloud server that can be accessed using an app. Extensive on-field trials show that the system (VGG16 CNN, GLCM and a fuzzy based clustering) is effective in hot and humid conditions and proves to be reliable in identifying disease classes of certain vegetable types, certain usable vegetation cover of farmland and regulation of watering mechanism of crops.
Content extraction from satellite images continues to evolve with the application of learning aided approaches. Recently, with the addition of deep learning (DL) based methods, content extraction ...from satellite images has become more reliable and efficient, yet challenges continue to exist as these methods require a large number of training and annotated images to enable effective learning by these networks. For high-resolution satellite images, limited training data is a familiar problem. Therefore, amongst the DL-based methods, semi-supervised adversarial approaches represent an emerging area of application in content extraction from satellite images. Semi-supervised adversarial methods adopt a combination of unsupervised training and labeled data to process applied inputs to generate reliable classification. In this paper, a semi-supervised adversarial learning method, which includes architectural expansion and several other additions, is reported that is used for content extraction from satellite images. The objective of the work is to design a modified structure of a semi-adversarial network working in concert with a classifier layer to extract the region of interests (ROIs) of the satellite image with limited training and annotated data. The proposed method has been tested with four different input feeding mechanisms which enhance the quality of processed data by generating a higher correlation. Two learning-based networks constitute the core of the semi-supervised adversarial learning method reported in this work. The first is a segmentation network that combines unlabeled data and supervised learning for processing. Next is a discriminator block which is a variant of the popular Convolutional Neural Network (CNN) trained sufficiently to improve the segmentation accuracy. For all the experiments performed, both labeled and unlabeled cases are considered. Adversarial and semi-supervised losses are the cost functions to train the system with images of the DeepGlobe Land Cover Classification Challenge dataset. The outputs of the segmentation network which are the semantic labels of the satellite images are used as inputs to the classifier to extract the ROIs of the satellite image. A comparison of the performance of the classifiers used is also included for ascertaining the most suitable one for the specific combination for the discriminator-segmentation blocks. Experimental data reveal that the proposed work is reliable compared to earlier reported approaches.
•Signals which overlaps in both time and frequency domain, are very difficult to separate out without distortion.•In multimedia content making, sound plays a vital role.•Deep Neural Networks ...(DNN)have been used to handle the full separation of overlapping sources.•DNNs for audio signal separation depends on factors such as the quality, size of the training data, architecture of the network, and the specific task at hand.
Separating the signals from the mixture when the signals share same frequency and time domain pattern is always a matter of concern. In natural environment, sound events often appear simultaneously, increasing the complexity. Movie making and audio-visual content creation is an industry which covers a huge share of our economy. With the advancement of technology, it becomes important to give audience more realistic experience. But sometimes due to certain environmental conditions, recording devices capture sound signals which overlap with the character voice of the script or required ambience sound either in frequency domain or time domain or in both. To fix the problem, sound engineers mostly dub the sound in the studio and try to collect the ambience sound later on. Further mixing is done during post processing of sound. Although different software tools are available in market, but here aesthetic value and originality of the sound has been compromised. Because, it is very hard to get the exact voice parameters and same ambience in studio environment. This paper gives an overview of different approaches to deal with the overlapping sound by focussing the recently reported literature and highlights the key attributes which are catalysing the evolving scenario.
The ubiquitous nature of inventory and its reliance on a reliable decision support system (DSS) is crucial for ensuring continuous availability of goods. The DSS needs to be designed in a manner that ...enables it to highlight its present status. Further, the DSS should be able to provide indications about subtle and large-scale variations that are likely to occur in the supply chain within the context of the decision-making framework and inventory management. However, while dealing with the parameters of the system, it is observed that its operations and mechanisms are surrounded by uncertain, imprecise, and vague environments. Fuzzy-based approaches are best suited for such situations; however, these require assistance from learning systems like artificial neural network (ANN) to facilitate automated decision support. When ANN and fuzzy are combined, the fuzzy neural system and the neuro-fuzzy system (NFS) are formulated. The model of the DSS reported here is based on a framework commonly known as adaptive neuro-fuzzy inference system (ANFIS), which is a version of NFS. The configured model has the advantages of both the ANN and fuzzy systems, and has been tested for the design of a DSS for use as part of inventory control. In this work, we report the design of an ANFIS-based DSS configured to work as DSS for inventory management. The system accepts demand as input and generates procurement, ordering, and holding cost to control production and supply. The system deals with a certain profitability rating required to quantify the changes in the input and is combined with the day-to-day inventory records and demand-available cycle. The effectiveness of the system has been checked in terms of number and types of membership used, accuracy generated, and computational efficiency accounted by the computation cycles required.
Automatic sign language recognition (SLR) is a current area of research as this is meant to serve as a substitute for sign language interpreters. In this paper, we present the design of a continuous ...SLR system that can extract out the meaningful signs and consequently recognize them. Here, we have used height of the hand trajectory as a salient feature for separating out the meaningful signs from the movement epenthesis patterns. Further, we have incorporated a unique set of spatial and temporal features for efficient recognition of the signs encapsulated within the continuous sequence. The implementation of an efficient hand segmentation and hand tracking technique makes our system robust to complex background as well as background with multiple signers. Experiments have established that our proposed system can identify signs from a continuous sign stream with a 92.8% spotting rate.
This paper describes the design of an operative prototype based on Internet of Things (IoT) concepts for real time monitoring of various environmental conditions using certain commonly available and ...low cost sensors. The various environmental conditions such as temperature, humidity, air pollution, sun light intensity and rain are continuously monitored, processed and controlled by an Arduino Uno microcontroller board with the help of several sensors. Captured data are broadcasted through internet with an ESP8266 Wi-Fi module. The projected system delivers sensors data to an API called ThingSpeak over an HTTP protocol and allows storing of data. The proposed system works well and it shows reliability. The prototype has been used to monitor and analyse real time data using graphical information of the environment.