One of the main requirements of tumor extraction is the annotation and segmentation of tumor boundaries correctly. For this purpose, we present a threefold deep learning architecture. First, classifiers are implemented with a deep convolutional neural network (CNN) and second a region-based convolutional neural network (R-CNN) is performed on the classified images to localize the tumor regions of interest. As the third and final stage, the concentrated tumor boundary is contoured for the segmentation process by using the Chan–Vese segmentation algorithm. As the typical edge detection algorithms based on gradients of pixel intensity tend to fail in the medical image segmentation process, an active contour algorithm defined with the level set function is proposed. Specifically, the Chan–Vese algorithm was applied to detect the tumor boundaries for the segmentation process. To evaluate the performance of the overall system, Dice Score, Rand Index (RI), Variation of Information (VOI), Global Consistency Error (GCE), Boundary Displacement Error (BDE), Mean Absolute Error (MAE), and Peak Signal to Noise Ratio (PSNR) were calculated by comparing the segmented boundary area which is the final output of the proposed, against the demarcations of the subject specialists which is the gold standard. Overall performance of the proposed architecture for both glioma and meningioma segmentation is with an average Dice Score of 0.92 (also, with RI of 0.9936, VOI of 0.0301, GCE of 0.004, BDE of 2.099, PSNR of 77.076, and MAE of 52.946), pointing to the high reliability of the proposed architecture.

The rapid expansion of the Internet of Things (IoT) and Machine Learning (ML) has significantly increased the demand for Location-Based Services (LBS) in today’s world. Among these services, indoor positioning and navigation have emerged as crucial components, driving the growth of indoor localization systems. However, using GPS in indoor environments is impractical, leading to a surge in interest in Received Signal Strength Indicator (RSSI) and machine learning-based algorithms for in-building localization and navigation in recent years. This paper aims to provide a comprehensive review of the technologies, applications, and future research directions of ML-based indoor localization for smart cities. Additionally, it examines the potential of ML algorithms in improving localization accuracy and performance in indoor environments.

In this study the problem of fully automated brain tumor classification and segmentation, in Magnetic resonance imaging (MRI) containing both Glioma and Meningioma types of brain tumors are considered. This paper proposes a Convolutional Neural Network (CNN), for classification problem and Faster Region based Convolutional Neural Network (Faster R-CNN) for segmentation problem with reduced number of computations with a higher accuracy level. This research has used 218 images as training set and the systems shows an accuracy of 100% in Meningioma and 87.5% in Glioma classifications and an average confidence level of 94.6% in segmentation of Meningioma tumors. The segmented tumor regions are validated through ground truth analysis and manual analysis by a Neurologist.

Tuberculosis (TB) is a contagious bacterial airborne disease, and is one of the top 10 causes of death worldwide. According to the World Health Organisation, around 1.8 billion people are infected with TB and 1.6 million deaths were reported in 2018. More importantly, 95% of cases and deaths were from developing countries. Yet, TB is a completely curable disease through early diagnosis. To achieve this goal one of the key requirements is efficient utilisation of existing diagnostic technologies, among which chest X-ray is the first line of diagnostic tool used for screening for active TB. The presented deep learning pipeline consists of three different modern deep learning architectures, to generate, segment, and classify lung X-rays. Apart from this, image preprocessing, image augmentation, genetic algorithm based hyper parameter tuning, and model ensembling were used to improve the diagnostic process. We were able to achieve classification accuracy of 97.1% (Youden’s index-0.941, sensitivity of 97.9%, specificity of 96.2%) which is a considerable improvement compared to the existing work in the literature. In our work, we present a highly accurate, automated TB screening system using chest X-rays, which would be helpful especially for low income countries with low access to qualified medical professionals.

Molecular communication (MC) has recently emerged as a novel paradigm for nano-scale communication utilizing molecules as information carriers. In diffusion-based molecular communication, the system performance is constrained by the inter-symbol-interference caused by the crossover of information carrying molecules in consecutive bits. To cope with this, we propose the Reed-Solomon (RS) codes as an error recovery tool, to improve the transmission reliability in diffusion-based MC systems. To quantify the performance improvement due to RS codes, we derive the analytical expression for the approximate bit error probability (BEP) of the diffusion-based MC system with the full absorption receiver. We further develop the particle-based simulation framework to simulate the proposed system with RS code to verify the accuracy of our derived analytical results. Our results show that, as the number of molecules per bit increases, the BEP of the system with RS codes exhibits a substantial improvement than that of non-coded systems. Furthermore, the BEP of the proposed system with RS codes can be greatly improved by increasing the minimum distance of the codeword.

In recent years, communicating information using molecules via diffusion has attracted significant interest in bio-medical applications. To date, most of the studies have concentrated on point-to-point molecular communication (MC), whereas in a realistic environment, multiple MC transmitters are likely to transmit molecular messages simultaneously sharing the same propagation medium, resulting in significant performance variation of the MC system. In this type of large-scale MC system, the collective signal strength at the desired receiver can be impaired by the interference caused by other MC transmitters, which may degrade the system reliability and efficiency. This paper presents the first tractable analytical framework for the collective signal strength at a partially absorbing receiver due to the desired transmitter under the impact of a swarm of interfering transmitters in a 3D large-scale MC system using stochastic geometry. To combat the multi-user interference and the intersymbol interference (ISI) in the multi-user environment, we propose Reed-Solomon (RS) error correction coding, due to its high effectiveness in combating burst and random errors, as well as the two types of information molecule modulating scheme, where the transmitted bits are encoded using two types of information molecules at consecutive bit intervals. We derive analytical expressions for the bit error probability (BEP) of the large-scale MC system with the proposed two schemes to show their effectiveness. The results obtained using Monte Carlo simulations, match exactly with the analytical results, justifying the accuracy of the derivations. Results reveal that both schemes improve the BEP by a factor of 3-4 compared with that of a conventional MC system without using any ISI mitigation techniques. Due to the implementation simplicity, the two-type molecule encoding scheme is better than the RS error correction coding scheme, as the RS error correction coding scheme involves additional encoding and decoding process at both the transmitter and receiver nodes. Furthermore, the proposed analytical framework can be generalized to the analysis of other types of receiver designs and performance characterization in multi-user large-scale MC systems. Also, the two types of information molecule modulating scheme can be extended to M-type of information molecule modulating scheme without loss of generality.