Autonomous driving has become a prominent topic with the rise of intelligent urban vision in communities. Advancements in automated driving technology play a significant role in the intelligent transportation system. Autonomous vehicles (AVs) rely heavily on sensor technologies as they are responsible for navigating safely through their environment and avoiding obstacles. This paper aims to outline the vital role of sensor fusion in intelligent transportation systems. Sensor fusion is the process of combining data from multiple sensors to obtain more comprehensive measurements and greater cognitive abilities than a single sensor could achieve. By merging data from different sensors, it ensures that driving decisions are based on reliable data, with improved accuracy, reliability, and robustness in AVs. This paper provides a comprehensive review of AV capacity, impacts, planning, technological challenges, and omitted concerns. We used state-of-the-art evaluation tools to check the performance of different sensor fusion algorithms in AVs. This paper will help us to determine our position, direction, the impacts of AVs on society, the need for smart city mobility outcomes, and the way to solve the auto industry challenges in the future. The analysis of AV systems from the perspective of sensor fusion in this research is expected to be beneficial to current and future researchers.

Human–computer communication using hand gestures has always been difficult. More than half a century ago, people used differentways of interactionwith computers from the early mediums such as perforated game cards. Nowadays, if a richer lexicon of gestures is given, people can communicate more effectively with computers. Machine learning is now used to recognize and classify hand gestures in amore preciseway. In order to increase the communication between computers and humans, we proposed a technique, which uses a wearable low-cost device to generate the electrical impedance tomography (EIT) images to recover the inner impedance structure of a user’s wrist. This is done by measuring the transverse impedance between all the 16 pairs of electrodesofwrist band that lie on the skin of the user hand. The proposedtechnique is enough to integrate the technology into the prototypewrist band tomonitor and classify gestures in real time. We have conducted a study of 16 gestures with a focus on gross hand and pinch finger gestures. The results evaluation shows that the gross hand gestures achieved 90% accuracy inwrist position, while pinch gestures achieved 93% accuracy.

Digital droplet PCR (ddPCR) is a powerful amplification technique for absolute quantification of viral nucleic acids. Although commercial ddPCR devices are effective in the lab bench tests, they cannot meet current urgent requirements for on-site and rapid screening for patients. Here, we have developed a portable and fully integrated lab-on-a-disc (LOAD) device for quantitively screening infectious disease agents. Our designed LOAD device has integrated (i) microfluidics chips, (ii) a transparent circulating oil-based heat exchanger, and (iii) an on-disc transmitted-light fluorescent imaging system into one compact and portable box. Thus, droplet generation, PCR thermocycling, and analysis can be achieved in a single LOAD device. This feature is a significant attribute for the current clinical application of disease screening. For this custom-built ddPCR setup, we have first demonstrated the loading and ddPCR amplification ability by using influenza A virus-specific DNA fragments with different concentrations (diluted from the original concentration to 10⁷ times), followed by analyzing the droplets with an external fluorescence microscope as a standard calibration test. The measured DNA concentration is linearly related to the gradient–dilution factor, which validated the precise quantification for the samples. In addition to the calibration tests using DNA fragments, we also employed this ddPCR-LOAD device for clinical samples with different viruses. Infectious samples containing five different viruses, including influenza A virus (IAV), respiratory syncytial virus (RSV), varicella zoster virus (VZV), Zika virus (ZIKV), and adenovirus (ADV), were injected into the device, followed by analyzing the droplets with an external fluorescence microscope with the lowest detected concentration of 20.24 copies/µL. Finally, we demonstrated the proof-of-concept detection of clinical samples of IAV using the on-disc fluorescence imaging system in our fully integrated device, which proves the capability of this device in clinical sample detection. We anticipate that this integrated ddPCR-LOAD device will become a flexible tool for on-site disease detection.

Most existing saliency methods measure foreground saliency by using the contrast of a foreground region to its local context, or boundary priors and spatial compactness. These methods are not powerful enough to extract a precise salient region from noisy and cluttered backgrounds. To evaluate the contrast of salient and background regions effectively, we consider high-level features from both supervised and unsupervised methods. We propose an affinity-based robust background subtraction technique and maximum attention map using a pre-trained convolution neural network. This affinity-based technique uses pixel similarities to propagate the values of salient pixels among foreground and background regions and their union. The salient pixel value controls the foreground and background information by using multiple pixel affinities. The maximum attention map is derived from the convolution neural network using features of the Pooling and Relu layers. This method can detect salient regions from images that have noisy and cluttered backgrounds. Our experimental results demonstrate the effectiveness of the proposed approach on six different saliency data sets and benchmarks and show that it improves the quality of detection beyond current saliency detection methods.