Pneumonia causes the death of around 700,000 children every year and affects 7% of the global population. Chest X-rays are primarily used for the diagnosis of this disease. However, even for a trained radiologist, it is a challenging task to examine chest X-rays. There is a need to improve the diagnosis accuracy. In this work, an efficient model for the detection of pneumonia trained on digital chest X-ray images is proposed, which could aid the radiologists in their decision making process. A novel approach based on a weighted classifier is introduced, which combines the weighted predictions from the state-of-the-art deep learning models such as ResNet18, Xception, InceptionV3, DenseNet121, and MobileNetV3 in an optimal way. This approach is a supervised learning approach in which the network predicts the result based on the quality of the dataset used. Transfer learning is used to fine-tune the deep learning models to obtain higher training and validation accuracy. Partial data augmentation techniques are employed to increase the training dataset in a balanced way. The proposed weighted classifier is able to outperform all the individual models. Finally, the model is evaluated, not only in terms of test accuracy, but also in the AUC score. The final proposed weighted classifier model is able to achieve a test accuracy of 98.43% and an AUC score of 99.76 on the unseen data from the Guangzhou Women and Children’s Medical Center pneumonia dataset. Hence, the proposed model can be used for a quick diagnosis of pneumonia and can aid the radiologists in the diagnosis process.

In the present digital world, digital images and videos are the main carrier of information. However, these sources of information can be easily tampered by using readily available software thus making authenticity and integrity of the digital images an important issue of concern. And in most of the cases copy-move image forgery is used to tamper the digital images. Therefore, as a solution to the aforementioned problem we are going to propose a unique method for copy-move forgery detection which can sustained various pre-processing attacks using a combination of Dyadic Wavelet Transform (DyWT) and Scale Invariant Feature Transform (SIFT). In this process first DyWT is applied on a given image to decompose it into four parts LL, LH, HL, and HH. Since LL part contains most of the information, we intended to apply SIFT on LL part only to extract the key features and find a descriptor vector of these key features and then find similarities between various descriptors vector to conclude that there has been some copy-move tampering done to the given image. And by using DyWT with SIFT we are able to extract more numbers of key points that are matched and thus able to detect copy-move forgery more efficiently.

In recent years there has been remarkable progress in one computer vision application area: object detection. One of the most challenging and fundamental problems in object detection is locating a specific object from the multiple objects present in a scene. Earlier traditional detection methods were used for detecting the objects with the introduction of convolutional neural networks. From 2012 onward, deep learning-based techniques were used for feature extraction, and that led to remarkable breakthroughs in this area. This paper shows a detailed survey on recent advancements and achievements in object detection using various deep learning techniques. Several topics have been included, such as Viola–Jones (VJ), histogram of oriented gradient (HOG), one-shot and two-shot detectors, benchmark datasets, evaluation metrics, speed-up techniques, and current state-of-art object detectors. Detailed discussions on some important applications in object detection areas, including pedestrian detection, crowd detection, and real-time object detection on Gpu-based embedded systems have been presented. At last, we conclude by identifying promising future directions.

Facial micro expressions are brief, spontaneous, and crucial emotions deep inside the mind, reflecting the actual thoughts for that moment. Humans can cover their emotions on a large scale, but their actual intentions and emotions can be extracted at a micro-level. Micro expressions are organic when compared with macro expressions, posing a challenge to both humans, as well as machines, to identify. In recent years, detection of facial expressions are widely used in commercial complexes, hotels, restaurants, psychology, security, offices, and education institutes. The aim and motivation of this paper are to provide an end-to-end architecture that accurately detects the actual expressions at the micro-scale features. However, the main research is to provide an analysis of the specific parts that are crucial for detecting the micro expressions from a face. Many states of the art approaches have been trained on the micro facial expressions and compared with our proposed Lossless Attention Residual Network (LARNet) approach. However, the main research on this is to provide analysis on the specific parts that are crucial for detecting the micro expressions from a face. Many CNN-based approaches extracts the features at local level which digs much deeper into the face pixels. However, the spatial and temporal information extracted from the face is encoded in LARNet for a feature fusion extraction on specific crucial locations, such as nose, cheeks, mouth, and eyes regions. LARNet outperforms the state-of-the-art methods with a slight margin by accurately detecting facial micro expressions in real-time. Lastly, the proposed LARNet becomes accurate and better by training with more annotated data.

No abstract

The Internet of Things (IoT) is transforming all applications into real-time monitoring systems. Due to the advancement in sensor technology and communication protocols, the implementation of the IoT is occurring rapidly. In agriculture, the IoT is encouraging implementation of real-time monitoring of crop fields from any remote location. However, there are several agricultural challenges regarding low power use and long-range transmission for effective implementation of the IoT. These challenges are overcome by integrating a long-range (LoRa) communication modem with customized, low-power hardware for transmitting agricultural field data to a cloud server. In this study, we implemented a custom-based sensor node, gateway, and handheld device for real-time transmission of agricultural data to a cloud server. Moreover, we calibrated certain LoRa field parameters, such as link budget, spreading factor, and receiver sensitivity, to extract the correlation of these parameters on a custom-built LoRa testbed in MATLAB. An energy harvesting mechanism is also presented in this article for analyzing the lifetime of the sensor node. Furthermore, this article addresses the significance and distinct kinds of localization algorithms. Based on the MATLAB simulation, we conclude that hybrid range-based localization algorithms are more reliable and scalable for deployment in the agricultural field. Finally, a real-time experiment was conducted to analyze the performance of custom sensor nodes, gateway, and handheld devices.

No abstract

In recent years, with the advancements in the Deep Learning realm, it has been easy to create and generate synthetically the face swaps from GANs and other tools, which are very realistic, leaving few traces which are unclassifiable by human eyes. These are known as 'DeepFakes' and most of them are anchored in video formats. Such realistic fake videos and images are used to create a ruckus and affect the quality of public discourse on sensitive issues; defaming one's profile, political distress, blackmailing and many more fake cyber terrorisms are envisioned. This work proposes a microscopic-typo comparison of video frames. This temporal-detection pipeline compares very minute visual traces on the faces of real and fake frames using Convolutional Neural Network (CNN) and stores the abnormal features for training. A total of 512 facial landmarks were extracted and compared. Parameters such as eye-blinking lip-synch; eyebrows movement, and position, are few main deciding factors that classify into real or counterfeit visual data. The Recurrent Neural Network (RNN) pipeline learns based on these features-fed inputs and then evaluates the visual data. The model was trained with the network of videos consisting of their real and fake, collected from multiple websites. The proposed algorithm and designed network set a new benchmark for detecting the visual counterfeits and show how this system can achieve competitive results on any fake generated video or image. INDEX TERMS DeepFakes, Generative Adversarial Network (GANs), Facial landmarks, Convolutional Neural Networks (CNN), Recurrent Neural Network (RNN), Visual Counterfeits.