Artificial Intelligence and Deep Learning in Sensors and Applications.

To effectively solve the increasingly complex problems experienced by human beings, the latest development trend is to apply a large number of different types of sensors to collect data in order to establish effective solutions based on deep learning and artificial intelligence [...].

Improving Patient Safety in the X-ray Inspection Process with EfficientNet-Based Medical Assistance System.

Patient safety is a paramount concern in the medical field, and advancements in deep learning and Artificial Intelligence (AI) have opened up new possibilities for improving healthcare practices. While AI has shown promise in assisting doctors with early symptom detection from medical images, there is a critical need to prioritize patient safety by enhancing existing processes. To enhance patient safety, this study focuses on improving the medical operation process during X-ray examinations. In this study, we utilize EfficientNet for classifying the 49 categories of pre-X-ray images. To enhance the accuracy even further, we introduce two novel Neural Network architectures. The classification results are then compared with the doctor's order to ensure consistency and minimize discrepancies. To evaluate the effectiveness of the proposed models, a comprehensive dataset comprising 49 different categories and over 12,000 training and testing sheets was collected from Taichung Veterans General Hospital. The research demonstrates a significant improvement in accuracy, surpassing a 4% enhancement compared to previous studies.

An open automation system for predatory journal detection.

The growing number of online open-access journals promotes academic exchanges, but the prevalence of predatory journals is undermining the scholarly reporting process. Data collection, feature extraction, and model prediction are common steps in tools designed to distinguish between legitimate and predatory academic journals and publisher websites. The authors include them in their proposed academic journal predatory checking (AJPC) system based on machine learning methods. The AJPC data collection process extracts 833 blacklists and 1213 whitelists information from websites to be used for identifying words and phrases that might indicate the presence of predatory journals. Feature extraction is used to identify words and terms that help detect predatory websites, and the system's prediction stage uses eight classification algorithms to distinguish between potentially predatory and legitimate journals. We found that enhancing the classification efficiency of the bag of words model and TF-IDF algorithm with diff scores (a measure of differences in specific word frequencies between journals) can assist in identifying predatory journal feature words. Results from performance tests suggest that our system works as well as or better than those currently being used to identify suspect publishers and publications. The open system only provides reference results rather than absolute opinions and accepts user inquiries and feedback to update the system and optimize performance.

Using Deep Learning with Thermal Imaging for Human Detection in Heavy Smoke Scenarios.

In this study, we propose using a thermal imaging camera (TIC) with a deep learning model as an intelligent human detection approach during emergency evacuations in a low-visibility smoky fire scenarios. We use low-wavelength infrared (LWIR) images taken by a TIC qualified with the National Fire Protection Association (NFPA) 1801 standards as input to the YOLOv4 model for real-time object detection. The model trained with a single Nvidia GeForce 2070 can achieve >95% precision for the location of people in a low-visibility smoky scenario with 30.1 frames per second (FPS). This real-time result can be reported to control centers as useful information to help provide timely rescue and provide protection to firefighters before entering dangerous smoky fire situations.

Hash-Chain Fog/Edge: A Mode-Based Hash-Chain for Secured Mutual Authentication Protocol Using Zero-Knowledge Proofs in Fog/Edge.

Authentication is essential for the prevention of various types of attacks in fog/edge computing. Therefore, a novel mode-based hash chain for secure mutual authentication is necessary to address the Internet of Things (IoT) devices' vulnerability, as there have been several years of growing concerns regarding their security. Therefore, a novel model is designed that is stronger and effective against any kind of unauthorized attack, as IoT devices' vulnerability is on the rise due to the mass production of IoT devices (embedded processors, camera, sensors, etc.), which ignore the basic security requirements (passwords, secure communication), making them vulnerable and easily accessible. Furthermore, crackable passwords indicate that the security measures taken are insufficient. As per the recent studies, several applications regarding its requirements are the IoT distributed denial of service attack (IDDOS), micro-cloud, secure university, Secure Industry 4.0, secure government, secure country, etc. The problem statement is formulated as the "design and implementation of dynamically interconnecting fog servers and edge devices using the mode-based hash chain for secure mutual authentication protocol", which is stated to be an NP-complete problem. The hash-chain fog/edge implementation using timestamps, mode-based hash chaining, the zero-knowledge proof property, a distributed database/blockchain, and cryptography techniques can be utilized to establish the connection of smart devices in large numbers securely. The hash-chain fog/edge uses blockchain for identity management only, which is used to store the public keys in distributed ledger form, and all these keys are immutable. In addition, it has no overhead and is highly secure as it performs fewer calculations and requires minimum infrastructure. Therefore, we designed the hash-chain fog/edge (HCFE) protocol, which provides a novel mutual authentication scheme for effective session key agreement (using ZKP properties) with secure protocol communications. The experiment outcomes proved that the hash-chain fog/edge is more efficient at interconnecting various devices and competed favorably in the benchmark comparison.

Efficiently Classifying Lung Sounds through Depthwise Separable CNN Models with Fused STFT and MFCC Features.

Lung sounds remain vital in clinical diagnosis as they reveal associations with pulmonary pathologies. With COVID-19 spreading across the world, it has become more pressing for medical professionals to better leverage artificial intelligence for faster and more accurate lung auscultation. This research aims to propose a feature engineering process that extracts the dedicated features for the depthwise separable convolution neural network (DS-CNN) to classify lung sounds accurately and efficiently. We extracted a total of three features for the shrunk DS-CNN model: the short-time Fourier-transformed (STFT) feature, the Mel-frequency cepstrum coefficient (MFCC) feature, and the fused features of these two. We observed that while DS-CNN models trained on either the STFT or the MFCC feature achieved an accuracy of 82.27% and 73.02%, respectively, fusing both features led to a higher accuracy of 85.74%. In addition, our method achieved 16 times higher inference speed on an edge device and only 0.45% less accuracy than RespireNet. This finding indicates that the fusion of the STFT and MFCC features and DS-CNN would be a model design for lightweight edge devices to achieve accurate AI-aided detection of lung diseases.

STAM-CCF: Suspicious Tracking Across Multiple Camera Based on Correlation Filters.

There is strong demand for real-time suspicious tracking across multiple cameras in intelligent video surveillance for public areas, such as universities, airports and factories. Most criminal events show that the nature of suspicious behavior are carried out by un-known people who try to hide themselves as much as possible. Previous learning-based studies collected a large volume data set to train a learning model to detect humans across multiple cameras but failed to recognize newcomers. There are also several feature-based studies aimed to identify humans within-camera tracking. It would be very difficult for those methods to get necessary feature information in multi-camera scenarios and scenes. It is the purpose of this study to design and implement a suspicious tracking mechanism across multiple cameras based on correlation filters, called suspicious tracking across multiple cameras based on correlation filters (STAM-CCF). By leveraging the geographical information of cameras and YOLO object detection framework, STAM-CCF adjusts human identification and prevents errors caused by information loss in case of object occlusion and overlapping for within-camera tracking cases. STAM-CCF also introduces a camera correlation model and a two-stage gait recognition strategy to deal with problems of re-identification across multiple cameras. Experimental results show that the proposed method performs well with highly acceptable accuracy. The evidences also show that the proposed STAM-CCF method can continuously recognize suspicious behavior within-camera tracking and re-identify it successfully across multiple cameras.

A Wi-Fi Union Mechanism for Internet Advertising Reciprocal Platform in Microenterprises.

With the evolution of the Internet and smartphone devices, Internet advertising has become one of the most important methods for delivering promotional marketing messages to customers. However, the efficiency of Internet advertising for microenterprise is not very high, since Wi-Fi advertising-which is limited by a small router coverage area-is mainly used. Moreover, because of the lack of money, microenterprises have been using low-cost methods to promote their products. Thus, enhancing the effectiveness of Wi-Fi advertising, and solving the problem of cost and the range of the views are now an essential investigation in this study. In this paper, we propose a reciprocal model with Wi-Fi union mechanism for Internet advertising based on fog computing architecture to enhance the efficiency of advertisement, reduce the cost, and increase the range of the views for microenterprise by using the Internet. In particular, the system was built in advertisers', publishers', and consumers' sides. In our system, we use contribution point (CP) as an exchange value among the participants. Advertisers and publishers can get CP by helping the others in the system to promote their advertisements, increasing their CP by one unit. Similarly, advertisers and publishers can use their CP to ask for assistance from the others, decreasing their CP by one unit. The result shows that the system in a Wi-Fi union is easy to use, and advertisements can be seen by all customers who are using free Wi-Fi from the stores of the union. This method can solve the problem of cost and fixed consumer groups.

Eye Tracking Based Control System for Natural Human-Computer Interaction.

Eye movement can be regarded as a pivotal real-time input medium for human-computer communication, which is especially important for people with physical disability. In order to improve the reliability, mobility, and usability of eye tracking technique in user-computer dialogue, a novel eye control system with integrating both mouse and keyboard functions is proposed in this paper. The proposed system focuses on providing a simple and convenient interactive mode by only using user's eye. The usage flow of the proposed system is designed to perfectly follow human natural habits. Additionally, a magnifier module is proposed to allow the accurate operation. In the experiment, two interactive tasks with different difficulty (searching article and browsing multimedia web) were done to compare the proposed eye control tool with an existing system. The Technology Acceptance Model (TAM) measures are used to evaluate the perceived effectiveness of our system. It is demonstrated that the proposed system is very effective with regard to usability and interface design.

CUDT: a CUDA based decision tree algorithm.

Decision tree is one of the famous classification methods in data mining. Many researches have been proposed, which were focusing on improving the performance of decision tree. However, those algorithms are developed and run on traditional distributed systems. Obviously the latency could not be improved while processing huge data generated by ubiquitous sensing node in the era without new technology help. In order to improve data processing latency in huge data mining, in this paper, we design and implement a new parallelized decision tree algorithm on a CUDA (compute unified device architecture), which is a GPGPU solution provided by NVIDIA. In the proposed system, CPU is responsible for flow control while the GPU is responsible for computation. We have conducted many experiments to evaluate system performance of CUDT and made a comparison with traditional CPU version. The results show that CUDT is 5 ∼ 55 times faster than Weka-j48 and is 18 times speedup than SPRINT for large data set.

A vision-based driver nighttime assistance and surveillance system based on intelligent image sensing techniques and a heterogamous dual-core embedded system architecture.

This study proposes a vision-based intelligent nighttime driver assistance and surveillance system (VIDASS system) implemented by a set of embedded software components and modules, and integrates these modules to accomplish a component-based system framework on an embedded heterogamous dual-core platform. Therefore, this study develops and implements computer vision and sensing techniques of nighttime vehicle detection, collision warning determination, and traffic event recording. The proposed system processes the road-scene frames in front of the host car captured from CCD sensors mounted on the host vehicle. These vision-based sensing and processing technologies are integrated and implemented on an ARM-DSP heterogamous dual-core embedded platform. Peripheral devices, including image grabbing devices, communication modules, and other in-vehicle control devices, are also integrated to form an in-vehicle-embedded vision-based nighttime driver assistance and surveillance system.

Vision-based finger detection, tracking, and event identification techniques for multi-touch sensing and display systems.

This study presents efficient vision-based finger detection, tracking, and event identification techniques and a low-cost hardware framework for multi-touch sensing and display applications. The proposed approach uses a fast bright-blob segmentation process based on automatic multilevel histogram thresholding to extract the pixels of touch blobs obtained from scattered infrared lights captured by a video camera. The advantage of this automatic multilevel thresholding approach is its robustness and adaptability when dealing with various ambient lighting conditions and spurious infrared noises. To extract the connected components of these touch blobs, a connected-component analysis procedure is applied to the bright pixels acquired by the previous stage. After extracting the touch blobs from each of the captured image frames, a blob tracking and event recognition process analyzes the spatial and temporal information of these touch blobs from consecutive frames to determine the possible touch events and actions performed by users. This process also refines the detection results and corrects for errors and occlusions caused by noise and errors during the blob extraction process. The proposed blob tracking and touch event recognition process includes two phases. First, the phase of blob tracking associates the motion correspondence of blobs in succeeding frames by analyzing their spatial and temporal features. The touch event recognition process can identify meaningful touch events based on the motion information of touch blobs, such as finger moving, rotating, pressing, hovering, and clicking actions. Experimental results demonstrate that the proposed vision-based finger detection, tracking, and event identification system is feasible and effective for multi-touch sensing applications in various operational environments and conditions.