The Internet of Things is integrating information systems, places, users and billions of constrained devices into one global network. This network requires secure and private means of communications. The building blocks of the Internet of Things are devices manufactured by various producers and are designed to fulfil different needs. There would be no common hardware platform that could be applied in every scenario. In such a heterogeneous environment, there is a strong need for the optimization of interoperable security. We present optimized elliptic curve Cryptography algorithms that address the security issues in the heterogeneous IoT networks. We have combined cryptographic algorithms for the NXP/Jennic 5148- and MSP430-based IoT devices and used them to created novel key negotiation protocol.

In this paper, we propose AFSense-ECG, an intelligence-embedded single lead ECG sensor that is enabled with the ability of accurate detection of Atrial Fibrillation (AF) condition, which is the most common sustained cardiac arrhythmia and increased risk of stroke is higher with sub-clinical AF patients. AFSense-ECG acts like an early-warning sensor for AF condition detection. A processing unit (e.g., ESP32WROVERE microcontroller) integrated with off-the-shelf single lead ECG sensor like Alivecor or AD8232 embeds intelligence to the sensing system to augment for inferential sensing for empowering automated decision-making. AFSense-ECG captures the quasi-periodic nature of typical ECG signals with repetitive P-wave, QRS complex and T-wave patterns into its feature extraction and the representation learning process of model construction and learning rate optimization. Our empirical study validates the superiority of proposed ECG signal characteristics-based hyper-parameter tuned ECG classification model construction. AFSense-ECG demonstrates F1-measure of 86.13%, where the current state-of-the-art methods report F1-measures of 83.70%, 83.10%, 82.90%, 82.60%, 82.50%, 81.00% over publicly available single lead ECG datasets of Physionet 2017 Challenge. Further, the proposed learning model for the inferential sensing is lean (approximately 25 times simpler in terms of total number of trainable parameters with reduced model size than relevant state-of-the-art model, where the state-of-the-art method with 83.70% F1-measure consists of 10474607 trainable parameters, and our proposed model consists of 433675 trainable parameters) and more effective (better F1-measure than the state-of-the-art methods), which enables us to construct affordable intelligent sensing system.

Remote and automated healthcare management has shown the prospective to significantly impact the future of human prognosis rate. Internet of Things (IoT) enables the development and implementation ecosystem to cater the need of large number of relevant stakeholders. In this paper, we consider the cardiac health management system to demonstrate that data-driven techniques produce substantial performance merits in terms of clinical efficacy by employing robust machine learning methods with relevant and selected signal processing features. We consider phonocardiogram (PCG) or heart sound as the exemplary physiological signal. PCG carries substantial cardiac health signature to establish our claim of data-centric superior clinical utility. Our method demonstrates close to 85% accuracy on publicly available MIT-Physionet PCG datasets and outperform relevant state-of-the-art algorithm. Due to its simpler computational architecture of shallow classifier with just three features, the proposed analytics method is performed at edge gateway. However, it is to be noted that healthcare analytics deal with number of sensitive data and subsequent inferences, which need privacy protection. Additionally, the problem of healthcare data privacy prevention is addressed by de-risking of sensitive data management using differential privacy, such that controlled privacy protection on sensitive healthcare data can be enabled. When a user sets for privacy protection, appropriate privacy preservation is guaranteed for defense against privacy-breaching knowledge mining attacks. In this era of IoT and machine intelligence, this work is of practical importance, which enables on-demand automated screening of cardiac health under minimizing the privacy breaching risk.

The new generation of devices connected to Internet are moving towards billion of small and smart objects, so-called Smart Things. These Smart Things are destined to manage the security of our houses, watch our health, and optimize the energy consumption of our cities. They bring a new set of opportunities, but they also present high challenges regarding scalability, management, bootstrapping, identity verification and authentication. For that reason, this work is focused on addressing the security requirements for Smart Things providing an optimized family of primes for Elliptic Curve Cryptography(ECC), denominated Shifting Primes. ECC on Smart Things needs special optimizations for the cryptographic primitives that requires a precise study of the instruction set and the number of cycles for those instructions. The modular multiplication is the basic operation, critical for highly constrained microprocessors, in terms of which ECC is built. It is optimized and also analyzed the interaction between partial results in the chain of modular multiplications needed for ECC. This optimizations have been carried out over the MSP430, which is a widely extended microprocessor for Smart Things. MSP430 is featured by not offering hardware multiplier. For that reason, we have defined a special kind of prime numbers, the Shifting Primes. They are featured by offering a very fast multiplication algorithm for ECC through addition and shifting operations for the multiplications. It is presented the full faster multiplication algorithm for Shifting Primes. These results are presenting a lowest time and number of operations for the multiplication in ECC than the existing solutions. Finally, note that the presented primes can be applied also to other similar architectures with fast shifting operation on registers.

The typical problem like insufficient training instances in time series classification task demands novel deep neural network architecture to warrant consistent and accurate performance. Deep Residual Network (ResNet) learns through ℋ(x) = ℱ(x) + x, where ℱ(x) is a nonlinear function. We propose Blend-Res ² Net that blends two different representation spaces: ℋ ¹ (x) = ℱ(x) + Trans(x) and ℋ ² (x) = ℱ(Trans(x)) + x with the intention of learning over richer representation by capturing the temporal as well as the spectral signatures (Trans(∙) represents the transformation function). The sophistication of richer representation for better understanding of the complex structure of time series signals, may result in higher generalization loss. Hence, the deep network complexity is adapted by proposed novel restrained learning, which introduces dynamic estimation of the network depth. The efficacy of Blend-Res ² Net is demonstrated by a series of ablation experiments over publicly available benchmark time series archive- UCR. We further establish the superior performance of Blend-Res ² Net over baselines and state-of-the-art algorithms including 1-NN-DTW, HIVE-COTE, ResNet, InceptionTime, ROCKET, DMS-CNN, TS-Chief.