Generative Artificial Intelligence: A Systematic Review and Applications

In recent years, the study of artificial intelligence (AI) has undergone a paradigm shift. This has been propelled by the groundbreaking capabilities of generative models both in supervised and unsupervised learning scenarios. Generative AI has shown state-of-the-art performance in solving perplexing real-world conundrums in fields such as image translation, medical diagnostics, textual imagery fusion, natural language processing, and beyond. This paper documents the systematic review and analysis of recent advancements and techniques in Generative AI with a detailed discussion of their applications including application-specific models. Indeed, the major impact that generative AI has made to date, has been in language generation with the development of large language models, in the field of image translation and several other interdisciplinary applications of generative AI. Moreover, the primary contribution of this paper lies in its coherent synthesis of the latest advancements in these areas, seamlessly weaving together contemporary breakthroughs in the field. Particularly, how it shares an exploration of the future trajectory for generative AI. In conclusion, the paper ends with a discussion of Responsible AI principles, and the necessary ethical considerations for the sustainability and growth of these generative models.

Classification of White Blood Cells Using Machine and Deep Learning Models: A Systematic Review

Machine learning (ML) and deep learning (DL) models have been employed to significantly improve analyses of medical imagery, with these approaches used to enhance the accuracy of prediction and classification. Model predictions and classifications assist diagnoses of various cancers and tumors. This review presents an in-depth analysis of modern techniques applied within the domain of medical image analysis for white blood cell classification. The methodologies that use blood smear images, magnetic resonance imaging (MRI), X-rays, and similar medical imaging domains are identified and discussed, with a detailed analysis of ML/DL techniques applied to the classification of white blood cells (WBCs) representing the primary focus of the review. The data utilized in this research has been extracted from a collection of 136 primary papers that were published between the years 2006 and 2023. The most widely used techniques and best-performing white blood cell classification methods are identified. While the use of ML and DL for white blood cell classification has concurrently increased and improved in recent year, significant challenges remain - 1) Availability of appropriate datasets remain the primary challenge, and may be resolved using data augmentation techniques. 2) Medical training of researchers is recommended to improve current understanding of white blood cell structure and subsequent selection of appropriate classification models. 3) Advanced DL networks including Generative Adversarial Networks, R-CNN, Fast R-CNN, and faster R-CNN will likely be increasingly employed to supplement or replace current techniques.

Automatic Classification of Blood Cell Images Using Convolutional Neural Network

Human blood primarily comprises plasma, red blood cells, white blood cells, and platelets. It plays a vital role in transporting nutrients to different organs, where it stores essential health-related data about the human body. Blood cells are utilized to defend the body against diverse infections, including fungi, viruses, and bacteria. Hence, blood analysis can help physicians assess an individual's physiological condition. Blood cells have been sub-classified into eight groups: Neutrophils, eosinophils, basophils, lymphocytes, monocytes, immature granulocytes (promyelocytes, myelocytes, and metamyelocytes), erythroblasts, and platelets or thrombocytes on the basis of their nucleus, shape, and cytoplasm. Traditionally, pathologists and hematologists in laboratories have examined these blood cells using a microscope before manually classifying them. The manual approach is slower and more prone to human error. Therefore, it is essential to automate this process. In our paper, transfer learning with CNN pre-trained models. VGG16, VGG19, ResNet-50, ResNet-101, ResNet-152, InceptionV3, MobileNetV2, and DenseNet-20 applied to the PBC dataset's normal DIB. The overall accuracy achieved with these models lies between 91.375 and 94.72%. Hence, inspired by these pre-trained architectures, a model has been proposed to automatically classify the ten types of blood cells with increased accuracy. A novel CNN-based framework has been presented to improve accuracy. The proposed CNN model has been tested on the PBC dataset normal DIB. The outcomes of the experiments demonstrate that our CNN-based framework designed for blood cell classification attains an accuracy of 99.91% on the PBC dataset. Our proposed convolutional neural network model performs competitively when compared to earlier results reported in the literature.

Design and Evaluation of Reconfigurable Intelligent Surfaces in Real-World Environment

Reconfigurable intelligent surfaces (RISs) have promising coverage and data rate gains for wireless communication systems in 5G and beyond. Prior work has mainly focused on analyzing the performance of these surfaces using computer simulations or lab-level prototypes. To draw accurate insights about the actual performance of these systems, this paper develops an RIS proof-of-concept prototype and extensively evaluates its potential gains in the field and under realistic wireless communication settings. In particular, a 160-element reconfigurable surface, operating at a 5.8GHz band, is first designed, fabricated, and accurately measured in the anechoic chamber. This surface is then integrated into a wireless communication system and the beamforming gains, path-loss, and coverage improvements are evaluated in realistic outdoor communication scenarios. When both the transmitter and receiver employ directional antennas and with 5m and 10m distances between the transmitter-RIS and RIS-receiver, the developed RIS achieves $15$-$20$dB gain in the signal-to-noise ratio (SNR) in a range of $\pm60^\circ$ beamforming angles. In terms of coverage, and considering a far-field experiment with a blockage between a base station and a grid of mobile users and with an average distance of $35m$ between base station (BS) and the user (through the RIS), the RIS provides an average SNR improvement of $6$dB (max $8$dB) within an area $> 75$m$^2$. Thanks to the scalable RIS design, these SNR gains can be directly increased with larger RIS areas. For example, a 1,600-element RIS with the same design is expected to provide around $26$dB SNR gain for a similar deployment. These results, among others, draw useful insights into the design and performance of RIS systems and provide an important proof for their potential gains in real-world far-field wireless communication environments.

Investigation of lightweight acoustic curtains for mid-to-high frequency noise insulations

The continuous surge of environmental noise levels has become a vital challenge for humanity. Earlier studies have reported that prolonged exposure to loud noise may cause auditory and non-auditory disorders. Therefore, there is a growing demand for suitable noise barriers. Herein, we have investigated several commercially available curtain fabrics' acoustic performance, potentially used for sound insulation purposes. Thorough experimental investigations have been performed on PVC coated polyester fabrics' acoustical performances and 100 % pure PVC sheets. The PVC-coated polyester fabric exhibited better sound insulation properties, particularly in the mid-to-high frequency range (600-1600 Hz) with a transmission loss of about 11 to 22 dB, while insertion loss of > 10 dB has been achieved. Also, the acoustic performance of multi-layer curtains has been investigated. These multi-layer curtains have shown superior acoustic properties to that of single-layer acoustic curtains.

Self Training with Ensemble of Teacher Models

In order to train robust deep learning models, large amounts of labelled data is required. However, in the absence of such large repositories of labelled data, unlabeled data can be exploited for the same. Semi-Supervised learning aims to utilize such unlabeled data for training classification models. Recent progress of self-training based approaches have shown promise in this area, which leads to this study where we utilize an ensemble approach for the same. A by-product of any semi-supervised approach may be loss of calibration of the trained model especially in scenarios where unlabeled data may contain out-of-distribution samples, which leads to this investigation on how to adapt to such effects. Our proposed algorithm carefully avoids common pitfalls in utilizing unlabeled data and leads to a more accurate and calibrated supervised model compared to vanilla self-training based student-teacher algorithms. We perform several experiments on the popular STL-10 database followed by an extensive analysis of our approach and study its effects on model accuracy and calibration.