Attention is the mental awareness of human on a particular object or a piece of information. The level of attention indicates how intense the focus is on an object or an instance. In this study, several types of human attention level have been observed. After introducing image segmentation and detection technique for facial features, eyeball movement and gaze estimation were measured. Eye movement were assessed using the video data, and a total of 10197 data instances were manually labelled for the attention level. Then Artificial Neural Network (ANN) and Recurrent Neural Network-Long Short Term Memory (LSTM) based Deep learning (DL) architectures have been proposed for analysing the data. Next, the trained DL model has been implanted into a robotic system that is capable of detecting various features; ultimately leading to the calculation of visual attention for reading, browsing, and writing purposes. This system is capable of checking the attention level of the participants and also can detect if participants are present or not. Based on a certain level of visual focus of attention (VFOA), this system interacts with the person, generates awareness and establishes verbal or visual communication with that person. The proposed ML techniques have achieved almost 99.24% validation accuracy and 99.43% test accuracy. It is also shown in the comparative study that, since the dataset volumes are limited, ANN is more suitable for attention level calculation than RNN-LSTM. We hope that the implemented robotic structure manifests the real-world implication of the proposed method.

A Human-Robot Interaction System Calculating Visual Focus of Human’s Attention Level

Breast cancer (BC) is a type of tumor that develops in the breast cells and is one of the most common cancers in women. Women are also at risk from BC, the second most life-threatening disease after lung cancer. The early diagnosis and classification of BC are very important. Furthermore, manual detection is time-consuming, laborious work, and, possibility of pathologist errors, and incorrect classification. To address the above highlighted issues, this paper presents a hybrid deep learning (CNN-GRU) model for the automatic detection of BC-IDC (+,−) using whole slide images (WSIs) of the well-known PCam Kaggle dataset. In this research, the proposed model used different layers of architectures of CNNs and GRU to detect breast IDC (+,−) cancer. The validation tests for quantitative results were carried out using each performance measure (accuracy (Acc), precision (Prec), sensitivity (Sens), specificity (Spec), AUC and F1-Score. The proposed model shows the best performance measures (accuracy 86.21%, precision 85.50%, sensitivity 85.60%, specificity 84.71%, F1-score 88%, while AUC 0.89 which overcomes the pathologist’s error and miss classification problem. Additionally, the efficiency of the proposed hybrid model was tested and compared with CNN-BiLSTM, CNN-LSTM, and current machine learning and deep learning (ML/DL) models, which indicated that the proposed hybrid model is more robust than recent ML/DL approaches.

/pdf/intelligent-hybrid-deep-learning-model-for-breast-cancer-exxjgno6.pdf

Intelligent Hybrid Deep Learning Model for Breast Cancer Detection

Attention is a human’s concentration of awareness on a specific moment or information. The level of attention describes how deep the focus is on that specific moment or information. The level of attention generally depends on the environment and the mental condition of a human. This paper has offered various machine learning approaches for predicting the level of visual focus of human’s attention. Using data collected from survey reports (environmental data) and eyeball data (eyeball movement, reading time, and head turn) while reading an article, a dataset with each participant’s attention level was formed. Eight different classifiers were trained, namely: Logistic Regression, Support Vector Machine (SVM), Decision Tree, K-Nearest Neighbor (KNN), AdaBoost, Multilayer Perceptron (MLP), Extra Tree Classifier, and Voting Classifier for classifying the participant’s attention level into three classes: High, Average, and Low. The Logistic Regression achieved the highest accuracy of 96% beating others in predicting these classes. The aggregated weighted Voting Classifier attained an accuracy of 95%.

Predicting Level of Visual Focus of Human’s Attention Using Machine Learning Approaches

In the present era, the applications of computer vision is increasing day by day. Computer vision is related to the automatic recognition, exploration and extraction of the necessary information from a particular image or a group of image sets. This paper addresses the method to detect the desired object from an image. Usually, a template of the desired object is used in detection through a matching technique named Template Matching. But it works well when the template image is cropped from the original one, which is not always invariant due to various transformations in the test images. To cope with this difficulty and to develop a generalized approach, we investigate in detail another technique which is known as HOG (Histogram of Oriented Gradient) approach. In HOG, the image is divided into overlapping blocks of template size and then compare each block’s normalized HOG with the normalized HOG of the template to find the best match of the object. We perform experiments with a large number of images and have found satisfactory performance.

/pdf/object-detection-using-template-and-hog-feature-matching-3m6mbdkpza.pdf

Object Detection using Template and HOG Feature Matching

Smart cities can be complemented by fusing various components and incorporating recent emerging technologies. IoT communications are crucial to smart city operations, which are designed to support the concept of a “Smart City” by utilising the most cutting-edge communication technologies to enhance city administration and resident services. Smart cities have been outfitted with numerous IoT-based gadgets; the Internet of Things is a modular method to integrate various sensors with all ICT technologies. This paper provides an overview of smart cities’ concepts, characteristics, and applications. We thoroughly investigate smart city applications, challenges, and possibilities with solutions in recent technological trends and perspectives, such as machine learning and blockchain. We discuss cloud and fog IoT ecosystems in the in capacity of IoT devices, architectures, and machine learning approaches. In addition we integrate security and privacy aspects, including blockchain applications, towards more trustworthy and resilient smart cities. We also highlight the concepts, characteristics, and applications of smart cities and provide a conceptual model of the smart city mega-events framework. Finally, we outline the impact of recent emerging technologies’ implications on challenges, applications, and solutions for futuristic smart cities.

/pdf/a-review-of-emerging-technologies-for-iot-based-smart-cities-2pc2ivdp.pdf

A Review of Emerging Technologies for IoT-Based Smart Cities

LungNet: A hybrid deep-CNN model for lung cancer diagnosis using CT and wearable sensor-based medical IoT data

Cryptography and Steganography are two prominent techniques to obtain secure communication over the shared media like the Internet. Steganography is slightly ahead of cryptography because of its stealthy characteristics. In this paper, a new method has been proposed which combines cryptography and steganography to ensure even more secure communication. The Advanced Encryption Standard (AES) in spatial domain of the carrier/cover image and Least Significant Bit (LSB) replacement in the transformed domain of the same image has been used after performing a Discrete Cosine Transform (DCT) on the pixels. An additional layer of security has been introduced by applying XOR operation on the AES encrypted message with the pixel values of the carrier image. The Peak Signal to Noise Ratio (PSNR) of the proposed algorithm is better than most of the similar algorithms. With better PSNR, the proposed method depicts a three layer of security of the information and error free decryption.

/pdf/a-secure-image-steganography-using-advanced-encryption-39ukutfor6.pdf

A Secure Image Steganography Using Advanced Encryption Standard and Discrete Cosine Transform

Attention is the behavioral and cognitive process of selectively concentrating on a discrete aspect of information. It is the taking possession by the mind in clear and colorful form of one out of what seem several simultaneous objects or trains of thought. The purpose of this work is to establish a human–robot interaction system to detect the visual focus of attention (VFOA) based on human attention (in case of both reading and browsing purposes). The system detects the person’s current task (attention) and estimates the level by detecting the head and estimating eye region specially detected iris center within eye area (gaze pattern calculation). The system also determines the interest or willingness of the target person to interact with it based upon a certain level of VFOA. Then, depending on the level of interest of the target person, the system/robot generates awareness and establishes a communication channel with her/him.

How Can a Robot Calculate the Level of Visual Focus of Human’s Attention

Data have ascended a place among capital, labor and land in production. The emerging data-driven economy has facilitated the scope of growth of data-entry industry – an industry equipped with modern computing and communication infrastructure enriched with specialized software interface allowing data-entry professionals to look into the source, collect and store target data. These data are used in business intelligence and analytics for value creation. By nature, data-entry is a tedious and repetitive task. It not only hampers creativity of the operators but also leave a possibility of wrong entry. In this paper, an innovative algorithm has been proposed which can automate the date entry industry with above 97% accuracy, more than 15 times faster than existing speed with no additional cost apart from the cost of existing infrastructure. The proposed algorithm has been tested and compared with several data-entry focused companies which demonstrate that it outperforms current manual data-entry approach and it has the potential to revolutionize the data-entry industry.

Innovative Automation Algorithm in Micro-multinational Data-Entry Industry

Security has always been a significant concern since the dawn of human civilization. That is why we build houses to keep ourselves and our belongings safe. And we do not hesitate to spend a lot on front-door locks and install CCTV cameras to monitor security threats. This paper presents an innovative automatic Front Door Security (FDS) algorithm that uses Human Activity Recognition (HAR) to detect four different security threats at the front door from a real-time video feed with 73.18% accuracy. The activities are recognized using an innovative combination of GoogleNet-BiLSTM hybrid network. This network receives the video feed from the CCTV camera and classifies the activities. The proposed algorithm uses this classification to alert any attempts to break the door by kicking, punching, or hitting. Furthermore, the proposed FDS algorithm is effective in detecting gun violence at the front door, which further strengthens security. This Human Activity Recognition (HAR)-based novel FDS algorithm demonstrates the potential of ensuring better safety with 71.49% precision, 68.2% recall, and an F1-score of 0.65.

Nuruzzaman Faruqui

Papers

LungNet: A hybrid deep-CNN model for lung cancer diagnosis using CT and wearable sensor-based medical IoT data

A Secure Image Steganography Using Advanced Encryption Standard and Discrete Cosine Transform

How Can a Robot Calculate the Level of Visual Focus of Human’s Attention

Innovative Automation Algorithm in Micro-multinational Data-Entry Industry

A Novel Front Door Security (FDS) Algorithm Using GoogleNet-BiLSTM Hybridization