Advanced Imaging Applications for Interdisciplinary Engineering

Artificial Intelligence (AI) is responsible for the transformation of image processing through cutting-edge imaging algorithms. This chapter delves deeper into AI-based imaging algorithms, such as image classification and pattern recognition. It provides a detailed review of the utilization of machine learning and deep learning models in imaging algorithms. Further, the applications of these AI-driven algorithms are also explored, thus emphasizing the advantages of these models in the real world. Key challenges and opportunities in AI-driven imaging are discussed, offering insights into emerging research directions.

The pursuit of highly efficient photodetectors has garnered substantial interest recently, driven by their wide-ranging applications spanning environmental monitoring, communication systems, and imaging technologies. This chapter examines how combining few-layer graphene (FLG), zinc oxide (ZnO), and silicon (Si) in a dual heterojunction design can create a photodetector that captures light across a wide range, from ultraviolet (UV) to near-infrared wavelengths. Utilizing the exceptional properties of graphene, the wide-bandgap nature of ZnO, and the scalability of Si as a substrate, the dual-heterojunction is optimized for UV-to-NIR light absorption and efficient carrier transport. A comprehensive simulation and analysis of the photodetector's characteristic parameters, including biased and unbiased operation, is conducted using the Silvaco Atlas TCAD software. The results show enhanced performance, with a least dark current density (Jdark) of 2.7×10–15 A/cm2, superior photocurrent density (Jlight) of 0.26 µA/cm2, along with a remarkable Jlight/Jdark ratio of 9.77×107, a 3-dB cut-off frequency of 7.36 THz, and a rapid rise (fall) time of 0.47 (0.88) ns at –1.0 V. Under illumination conditions, the photodetector exhibits a peak external quantum efficiency of 69.3%, photocurrent responsivity of 0.26 A/W, detectivity of 8.12×1015 cmHz1/2/W, and noise equivalent power of 7.79×10–20 W at –1.0 V bias. This research advances photodetection capabilities by demonstrating that combining p+ - FLG, n-ZnO, and n-Si in a dual-heterojunction design enables effective light detection from UV-to-NIR wavelengths. The findings suggest this integrated approach could lead to improved sensors and imaging devices. Moreover, a comprehensive comparative analysis is performed, utilizing the power of different machine learning (ML) regression models to evaluate their predictive performance in modeling the photodetector's behavior. The main goal is to determine the effectiveness of each ML regression model in accurately forecasting the photodetector's characteristics. This will be achieved by evaluating model performance across varying test set sizes using a range of metrics such as mean squared errors, root mean squared errors, mean absolute errors, and R2 scores. The findings highlight the utility of machine learning algorithms in modeling and optimizing optoelectronic devices, offering valuable insights into their potential applications in advancing photodetector research and development endeavors.

Nanotechnology has significantly revolutionized numerous fields, including materials science, medicine, and diagnostics, with its ability to manipulate materials at the nanoscale. Central to these advancements is the development of cutting-edge imaging techniques that offer enhanced visualization and characterization of nanomaterials. This paper focuses on recent innovations in imaging technologies for nanomaterial analysis, examining both the evolution of conventional methods and the integration of novel approaches to meet the growing demands of high-resolution and high-sensitivity imaging. Additionally, by providing better resolution, targeting specificity, and signal enhancement, the use of nanoparticles as contrast chemicals in healthcare imaging modalities, such as magnetic resonance imaging, computed tomography, ultrasonography, PET, and SPECT, has improved illness detection and diagnosis.

Nanoparticles' ability to exploit passive and active targeting mechanisms, such as the enhanced permeability and retention (EPR) effect, and functionalization with ligands for receptor-specific targeting, has revolutionized imaging in oncology, cardiovascular diseases, and neurological disorders. This chapter further highlights the development of multimodal imaging platforms, where nanoparticles are designed to integrate multiple imaging modalities, such as MRI-fluorescence or PET-CT, providing a more holistic diagnostic capability. These multimodal platforms enable the simultaneous acquisition of anatomical and molecular data, improving diagnostic accuracy and allowing for real-time monitoring of therapeutic responses. The integration of machine learning algorithms for image analysis and interpretation is another area of exploration, with the potential to automate and enhance the accuracy of nanomaterial imaging. While nanoparticle-based imaging holds great promise, challenges remain in ensuring their biocompatibility, biodistribution, and long-term safety. This chapter emphasizes the need for continued research into the optimization of nanoparticle design, surface functionalization, and toxicity profiles to advance their clinical translation. By reviewing the current state of imaging technologies and their applications, this research outlines the critical role that advanced imaging techniques play in pushing the frontiers of nanotechnology, ultimately paving the way for significant breakthroughs in science, medicine, and engineering.

This research work is focused on detecting visual anomalies/abnormal events in video surveillance systems. In such situations, human attention may wander, and abnormal situations may be more challenging to note. So, to avoid such situations, an automated system is needed that can analyze such a huge amount of data and trigger alarms in abnormal events. Nowadays, the automation of surveillance systems is a major research area. This chapter presents a 3D local descriptor-based anomaly detection method for traffic surveillance videos, capable of extracting information about the appearance and motion of objects. Appearance information is extracted by 3D Histogram of Gradients (HOG), and motion information is extracted by 3D Histogram of Optical Flow Orientation (HOOF). Finally, these features are fed to a combined classifier for the detection of abnormality. Appearance information plays an important role when different types of objects are in the scene, like in traffic surveillance videos. This algorithm is tested on the YouTube video due to the unavailability of a publicly available standard traffic surveillance dataset.

Many applications rely on the correct analysis of low-quality photographs, yet effective interpretation is sometimes hampered by the inherent constraints of degraded image settings. We present a novel approach to estimating the energy content of low-quality images. We create a framework for measuring the dynamic features of these images by applying physical rules, particularly those governing motion. To preprocess the photos for precise energy estimation, we use image enhancement techniques and motion features. Following that, we calculate the energy of the objects' motions in the images using kinetic energy principles, considering characteristics, such as mass and velocity. Our proposed method accurately calculates energy levels from low-quality pictures, as demonstrated experimentally with synthetic and real-world datasets. This methodology has applications in environmental monitoring, robotics, and surveillance, all of which rely on insights into energy dynamics for analysis and decision-making. It also increases our understanding of the dynamics involved in such imaging.

Quantum imaging is an emerging field based on quantum mechanics and imaging technology, capable of unique capabilities in resolution, sensitivity, and information processing. An extensive review of the concepts, methods, and uses of quantum imaging is given in this chapter. The main ideas of quantum mechanics that are relevant to imaging, including superposition, entanglement, and quantum measurement, are introduced in this chapter. Following this, the various quantum imaging techniques, including quantum entanglement imaging, ghost imaging, and quantum lithography, illuminating their operational mechanisms and advantages over classical methods, are explored. The role of advanced photonic systems, single-photon detectors, and quantum dots in enhancing image quality are discussed. Additionally, the incorporation of quantum computing and machine learning with quantum imaging is examined, highlighting how these interdisciplinary approaches are pushing the boundaries of what can be visualized and analysed. Quantum imaging applications are varied, groundbreaking, and innovative, ranging from medical diagnostics and biological imaging to quantum communication and fundamental physics research. By harnessing the exclusive properties of quantum states, these applications achieve higher precision and new capabilities that classical imaging techniques cannot match. The challenges and future directions of quantum imaging, considering both the technical hurdles and the potential for groundbreaking discoveries, are discussed as well. In a nutshell, the chapter aims to offer the readers an in-depth insight into quantum imaging, its current state, and its future prospects by providing a holistic view of how quantum imaging is composed to revolutionize various scientific and technological fields.

Air Quality Index (AQI) forecasting is vital for environmental monitoring and public health management. Hence, in this chapter, a machine learning (ML) algorithm, i.e., Facebook Prophet Algorithm (a well-liked, flexible, and user-friendly time series forecasting tool), Auto Regressive Integrated Moving Average (ARIMA), and exponential smoothing are used in AQI forecasting. The ML model is created for Insights and future prediction for environmental policy formulation and decisionmaking by utilizing past AQI data. The procedure entails gathering past AQI data from online sources, handling missing values and outliers in the data through preprocessing/cleaning, and then training a Facebook Prophet model. Nonetheless, the model's performance is evaluated using common metrics like root mean square error (RMSE) and mean absolute error (MAE). The suggested method is effective in predicting AQI levels, as evidenced by the results. The ARIMA, Exponential Smoothing, and Facebook Prophet algorithms anticipate accuracy with their corresponding performance metrics falling in the range between 97 and 99. 

The systematic application of blockchain in the healthcare environment will likely change the conduct, retrieval, and dissemination of health records. Blockchain technology has attracted global attention as an innovation with the potential to disrupt several industries. In this research, the application of blockchain in healthcare is explored, and ‘Health Chain’ is positioned as an invention that addresses the challenges of existing healthcare systems. Health Chain leverage the Internet by incorporating innovative technology like blockchain for the secure storage of EHRs, management of patients’ consent, enhancement of marketing channels for drug distribution, use of IoT devices for tracking, and improvement of ease of use and efficiency. This study investigates the prospects of deploying this technology, highlighting the development of a recommended framework and directions for further research. It aims to assess the potential of utilizing blockchain in healthcare settings for more efficient information management, integration of multiple functions, and provision of services to patients in a more effective manner through the proposed framework.

Indian cities nowadays have very poor waste management. Rapid industrialization has caused the intensification of Municipal Solid Waste (MSW) at a very progressive rate. Alternative solutions are required because disposing of waste material in open landfills and using only incineration techniques increases environmental damage. The present study conducted the physico-chemical and spectroscopic characterization of municipal solid waste compost in Pathankot city of the Punjab region to analyze its appropriateness for various purposes. The compost was prepared collectively from the college hostel mess waste and from the dry leaves available in the proximity of the college campus. The compost pit was constructed with dimensions of 4*4 feet in the college campus area. The study revealed the examination of nutrient concentration and structural behaviour during the entire process of waste degradation. The study concluded that the region's waste is rich in organic materials and, hence, composting is an appropriate option for processing and minimizing waste.

Open dumpsites are one of the major causes of environmental degradation, and their impact on groundwater largely depends on leachate concentration. The environment can be severely polluted by leachate percolation if it is not properly managed. The present study examines the effect of leachate percolating into aquifers and soil in the vicinity of dumping sites in the study region of Pathankot, Punjab. The study primarily focuses on the evaluation of groundwater characterization, leachate characterization, and heavy metal analysis for quality assessment. In this context, the leachate pollution index is used to categorize the toxic potential of leachate so that immediate remedial actions can be implemented at dumping locations. Higher concentrations of leachate pollutants increase the likelihood of toxicity and, in turn, the pollution of groundwater and soil. From this perspective, groundwater pollution is an impending environmental issue that requires urgent consideration. In a nutshell, the current study endorses the construction of engineered landfills and effective leachate management to ensure the sustainability and conservation of groundwater aquifers and soil quality.