Microwave Imaging (MWI) has emerged as a potential candidate for brain stroke detection due to its low cost, time efficiency and accurate nature when compared to other screening techniques. TinyML is a revolutionary technique for utilizing AI in portable and low-powered devices. The need for more compact and concise systems grows by the day in order to provide smart services, particularly in the medical arena. This paper tries to fulfil these requirements by presenting the first-ever portable MWI-based TinyML brain stroke detection system with high accuracy. The head-imaging dataset, utilized here for the training of models, provides open-source data generated by our prototype head imaging system consisting of a low-cost vector network analyzer, single-board computer, rotating motor setup, and a Vivaldi antenna. The Tiny ML model is a compressed-size model of our proposed Deep Learning (DL) framework that obtains an accuracy of 93% on testing data with an F1-score of 0.929 deployed on the single-board computer. The compressed model obtained by pruning or quantization is not only small in size but also retains the above 90% accuracy of the DL model. This work reassures the possibility of successful deployment of Tiny ML- based solutions in microwave imaging systems for medical diagnostic applications in low-resource settings.

Breast Microwave Imaging (BMI) has emerged as a competitive and potentially disruptive alternative to conventional breast cancer screening techniques owing to its desirable features and improved detection rate. In this paper, we apply various artificial intelligence, and deep learning approaches for automatic breast tumor detection, classification and localization in an open-source experimental BreastCare dataset obtained using our pre-clinical, portable and cost-effective BMI system. We compare the effectiveness of various cutting-edge machine-learning detection algorithms to assess the usefulness of the obtained data-set. Also, we present a deep learning framework that outperforms state-of-the-art microwave imaging methods and ML algorithms for tumor detection, localization, and characterization. The proposed framework gives promising results using our BMI system's measured reflection coefficients ($S_{11}$). This work shows the potential advantages of applying cutting-edge deep learning algorithms in practical BMI systems.

Summary The throughput of a TCP flow depends on the average size of Congestion Window (cwnd) of a congestion control mechanism being used during the communication. The size of cwnd depends upon the usage of available link bandwidth during communication. The response function is a measure of average throughput of a single TCP flow of congestion control mechanism as the level of random packet loss is varied. Nowadays, many organizations are deploying IoT based applications for the analytics of their Big Data. TCP CUBIC and TCP Compound are the default congestion control mechanisms in Linux and Microsoft Windows Operating Systems respectively. Whereas, TCP Reno which is also known as Standard TCP congestion control mechanism is act as a trademark congestion control mechanism. During communication among different IoT applications, TCP CUBIC flows use more available link bandwidth as compared to TCP Reno flows, thus, the average cwnd size of TCP CUBIC flows are greater than the TCP Reno flows. It implies that these both kinds of flows are not sharing available link fairly, which refers as low TCP friendliness of TCP CUBIC. It means that the throughput of TCP CUBIC flows is higher than the trademark congestion control mechanism, i.e., TCP Reno flows. As a result, friendliness behavior or fair share of available link bandwidth among TCP CUBIC flows and TCP Reno flows is decreased. In other words, TCP friendliness of TCP CUBIC flows is reduced. Now, it is important to decrease the average cwnd size of TCP CUBIC flows, such that available link bandwidth can be shared fairly among flows of TCP CUBIC and TCP Reno. The aim of this research is to enhance the TCP friendliness behavior of TCP CUBIC congestion control mechanism for IoT based applications using Big Data. In this paper, an Advance Response Function of TCP CUBIC (ARFC) is designed to share fairly available link bandwidth among flows of TCP CUBIC and TCP Reno. Results show that TCP friendliness behavior of TCP CUBIC is increased by using ARFC. Overall, 18.6% performance is increased by using ARFC.