Information is mounting exponentially, and the world is moving to hunt knowledge with the help of Big Data. The labelled data is used for automated learning and data analysis which is termed as Machine Learning. Linear Regression is a statistical method for predictive analysis. Gradient Descent is the process which uses cost function on gradients for minimizing the complexity in computing mean square error. This work presents an insight into the different types of Gradient descent algorithms namely, Batch Gradient Descent, Stochastic Gradient Descent and Mini-Batch Gradient Descent, which are implemented on a Linear regression dataset, and hence determine the computational complexity and other factors like learning rate, batch size and number of iterations which affect the efficiency of the algorithm.

Unit Commitment (UC) is an important problem in power system operations. It is traditionally scoped for 24 hours with one-hour time intervals. To improve system flexibility by accommodating the increasing net-load variability, sub-hourly UC has been suggested. Such a problem is larger and more complicated than hourly UC because of the increased number of periods and reduced unit ramping capabilities per period. The computational burden is further exacerbated for systems with large numbers of virtual transactions leading to dense transmission constraints matrices. Consequently, the state-of-the-art and practice method, branch-and-cut (B&C), suffers from poor performance. In this paper, our recent Surrogate Absolute-Value Lagrangian Relaxation (SAVLR) is enhanced by embedding ordinal-optimization concepts for a drastic reduction in subproblem solving time. Rather than formally solving subproblems by using B&C, subproblem solutions that satisfy SAVLR’s convergence condition are obtained by modifying solutions from previous iterations or solving crude subproblems. All virtual transactions are included in each subproblem to reduce major changes in solutions across iterations. A parallel version is also developed to further reduce the computation time. Testing on MISO’s large cases demonstrates that our ordinal-optimization embedded approach obtains near-optimal solutions efficiently, is robust, and provides a new way on solving other MILP problems.

Reports on a reimplementation of the ENIAC programming demonstrated at its unveiling on Feb 15, 1946. The reconstructed demonstration is shown in the YouTube video: https://youtu.be/SGBT2Danh-g

This paper addresses the issue of reliability in Industrial Internet of Things (IIoT) in case of missing sensors measurements due to network or hardware problems. We propose to support the fault detection and classification modules, which are the two critical components of a monitoring system for IIoT, with a generative model. The latter is responsible of imputing missing sensor measurements so that the monitoring system performance is robust to missing data. In particular, we adopt Generative Adversarial Networks (GANs) to generate missing sensor measurements and we propose to fine-tune the training of the GAN based on the impact that the generated data have on the fault detection and classification modules. We conduct a thorough evaluation of the proposed approach using the extended Tennessee Eastman Process dataset. Results show that the GAN-imputed data mitigate the impact on the fault detection and classification even in the case of persistently missing measurements from sensors that are critical for the correct functioning of the monitoring system.

The use of face masks is an important way to fight the COVID-19 pandemic. In this paper, we envision the Smart Mask, an IoT supported platform and ecosystem aiming to prevent and control the spreading of COVID-19 and other respiratory viruses. The integration of sensing, materials, AI, wireless, IoT, and software will help gathering of health data and health-related event detection in real time from the user as well as from their environment. In larger scale, with the help of AI-based analysis for health data it is possible to predict and decrease medical costs with accurate diagnoses and treatment plans, where comparison of personal data to large-scale public data enables drawing up a personal health trajectory, for example. Key research problems for smart respiratory protective equipment are identified in addition to future research directions.

This paper presents a convex recovery method for block-sparse signals whose block partitions are unknown a priori. We first introduce a nonconvex penalty function, where the block partition is adapted for the signal of interest by minimizing the mixed l2/l1 norm over all possible block partitions. Then, by exploiting a variational representation of the l2 norm, we derive the proposed penalty function as a suitable convex relaxation of the nonconvex one. For a block-sparse recovery model designed with the proposed penalty, we develop an iterative algorithm which is guaranteed to converge to a globally optimal solution. Numerical experiments demonstrate the effectiveness of the proposed method.

The formulation and implementation of the Love’s condition constraint for the source reconstruction method (SRM) in near-field antenna measurements is analyzed in the context of inverse problems. To this end, the SRM is first analyzed to identify the non-unique or non-radiating current sources which may be present. Next, the advantages and disadvantages of general regularization techniques, which may address the non-radiating currents, are presented which serve to motivate the use of the Love’s condition constraint. The main methods of formulating the constraint are then presented, one of which is a novel technique developed for this paper. Following this, the formulation methods are analyzed in order to predict the similarities and differences of the methods in the context of addressing the non-radiating currents of the SRM. This analysis is reinforced by simulated antenna measurements. In particular, the novel formulation method is demonstrated to provide greater reconstruction accuracy (in the examples considered), at the cost of computational complexity.

Recent advancement of research in biometrics, computer vision, and natural language processing has discovered opportunities for person retrieval from surveillance videos using textual query. The prime objective of a surveillance system is to locate a person using a description, e.g., a short woman with a pink t-shirt and white skirt carrying a black purse. She has brown hair. Such a description contains attributes like gender, height, type of clothing, colour of clothing, hair colour, and accessories. Such attributes are formally known as soft biometrics. They help bridge the semantic gap between a human description and a machine as a textual query contains the person’s soft biometric attributes. It is also not feasible to manually search through huge volumes of surveillance footage to retrieve a specific person. Hence, automatic person retrieval using vision and language-based algorithms is becoming popular. In comparison to other state-of-the-art reviews, the contribution of the paper is as follows: 1. Recommends most discriminative soft biometrics for specific challenging conditions. 2. Integrates benchmark datasets and retrieval methods for objective performance evaluation. 3. A complete snapshot of techniques based on features, classifiers, number of soft biometric attributes, type of the deep neural networks, and performance measures. 4. The comprehensive coverage of person retrieval from handcrafted features based methods to end-to-end approaches based on natural language description.

Energy efficient galvanic coupling (GC) technology is used in this work to send electromyography (EMG) data through intra-body communication links. Real EMG data are first acquired and recorded with needle electrodes inserted in the muscle of a person’s forearm. Then, the data are transferred via GC communication employing a GC sound card-based testbed. The experiments are conducted by transferring EMG data in both ex-vivo and in-vivo tissue with different electrodes placements. Almost error free performance is achieved with a robust and reliable communication, a valuable result in medical applications.

Classification of 3D objects – the selection of a category in which each object belongs – is of great interest in the field of machine learning. Numerous researchers use deep neural networks to address this problem, altering the network architecture and representation of the 3D shape used as an input. To investigate the effectiveness of their approaches, we conduct an extensive survey of existing methods and identify common ideas by which we categorize them into a taxonomy. Second, we evaluate 11 selected classification networks on three 3D object datasets, extending the evaluation to a larger dataset on which most of the selected approaches have not been tested yet. For this, we provide a framework for converting shapes from common 3D mesh formats into formats native to each network, and for training and evaluating different classification approaches on this data. Despite being generally unable to reach the accuracies reported in the original papers, we can compare the relative performance of the approaches as well as their performance when changing datasets as the only variable to provide valuable insights into performance on different kinds of data. We make our code available to simplify running training experiments with multiple neural networks with different prerequisites. The final version was published: https://doi.org/10.1109/TPAMI.2021.3102676

The paper describes an online deep learning algorithm for the adaptive modulation and coding in 5G Massive MIMO. The algorithm is based on a fully connected neural network, which is initially trained on the output of the traditional algorithm and then is incrementally retrained by the service feedback of its output. We show the advantage of our solution over the state-of-the-art Q-Learning approach. We provide system-level simulation results to support this conclusion in various scenarios with different channel characteristics and different user speeds. Compared with traditional OLLA our algorithm shows 10% to 20% improvement of user throughput in full buffer case.

In our previous study, a concept of electromagnetic kurtosis for time-reversal source reconstruction was presented. From a two-step process, the electromagnetic kurtosis can first identify the excitation time instants then localize the sources locations with time-reversal technique. In this paper, we extend the concept of the electromagnetic kurtosis from two different perspectives. The proposed space kurtosis and time kurtosis in the electromagnetic time-reversal process can directly reconstruct excitation time instants and spatial locations of sources respectively. The newly proposed time kurtosis takes the advantages of time-domain computational electromagnetics methods. Its algorithm with the threshold technique simplifies the procedures of multiple sources localization. Numerical experiments are conducted to verify the effectiveness of the presented algorithm.

Fretting is a common problem for modular orthopaedic implants which may lead to mechanical failure of the implant or inflammatory tissue responses due excessive release of wear debris. Compressive residual stresses at the contacting surfaces may alleviate the problem. Here we investigate the potential of a surface enhancement method known as low plasticity burnishing (LPB) to increase the fretting resistance of bone-anchored implants for skeletal attachment of limb prostheses. Rotation bending fatigue tests performed on LPB treated and untreated test specimens demonstrate that the LPB treatment leads to statistically significantly increased resistance to fretting fatigue (LPB treated test specimens withstood on average 108 780 load cycles as compared with 37 845 load cycles for untreated test specimens, p = 0.004). LPB treated test specimens exhibited less wear at the modular interface as compared with untreated test specimens. This surface treatment may lead to reduced risk of fretting induced component failure with the consequence of a reduced need for implant revisions.

An analysis of many IoT deployments showed that most of them can address the Sustainable Development Goals (SDG) and the UN’s 2030 agenda. Interestingly, most of these projects concentrate on five SDGs: Industry, innovation, and infrastructure, Smart cities and communities, Affordable and clean energy, Good health and wellbeing, and Responsible production and consumption. Examples include a remote water-monitoring solution that ensures clean water in regions with an indigenous population, and smart lighting initiatives

Electrocardiogram (ECG) is the graphical portrayal of heart usefulness. The ECG signals holds its significance in the discovery of heart irregularities. These ECG signals are frequently tainted by antiques from various sources. It is basic to diminish these curios and improve the exactness just as dependability to show signs of improvement results identified with heart usefulness. The most commonly disturbed artifact in ECG signals is Motion Artifacts (MA). In this paper, we have proposed a new concept on how machine learning algorithms can be used for de-noising the ECG signals. Towards the goal, a unique combination of Recurrent Neural Network (RNN) and Deep Neural Network (DNN) is used to efficiently remove MA. The proposed algorithm is validated using ECG records obtained from the MIT-BIH Arrhythmia Database. To eliminate MA using the proposed method, we have used Adam optimization algorithm to train and fit the contaminated ECG data in RNN and DNN models. Performance evaluation results in terms of SNR and RRMSE show that the proposed algorithm outperforms other existing MA removal methods without significantly distorting the morphologies of ECG signals.

Left ventricular assist devices (LVADs) are mechanical pumps, which can be used to support heart failure (HF) patients as bridge to transplant and destination therapy. To automatically adjust the LVAD speed, a physiological control system needs to be designed to respond to variations of patient hemodynamics across a variety of clinical scenarios. These control systems require pressure feedback signals from the cardiovascular system. However, there are no suitable long-term implantable sensors available. In this study, a novel real-time deep convolutional neural network (CNN) for estimation of preload based on the LVAD flow was proposed. A new sensorless adaptive physiological control system for an LVAD pump was developed using the full dynamic form of model free adaptive control (FFDL-MFAC) and the proposed preload estimator to maintain the patient conditions in safe physiological ranges. The CNN model for preload estimation was trained and evaluated through 10-fold cross validation on 100 different patient conditions and the proposed sensorless control system was assessed on a new testing set of 30 different patient conditions across six different patient scenarios. The proposed preload estimator was extremely accurate with a correlation coefficient of 0.97, root mean squared error of 0.84 mmHg, reproducibility coefficient of 1.56 mmHg, coefficient of variation of 14.44 %, and bias of 0.29 mmHg for the testing dataset. The results also indicate that the proposed sensorless physiological controller works similarly to the preload-based physiological control system for LVAD using measured preload to prevent ventricular suction and pulmonary congestion. This study shows that the LVADs can respond appropriately to changing patient states and physiological demands without the need for additional pressure or flow measurements.

The Internet of Bodies (IoB) is an imminent extension of the vast Internet of things (IoT) domain, where wearable, ingestible, injectable, and implantable smart objects form a network in, on, and around the human body. Even though on-body IoB communications are required to occur within very close proximity of the human body, on-body wireless radio frequency (RF) IoB devices unnecessarily extend the coverage range beyond the human body due to their radiative nature. This eventually reduces energy efficiency, causes co-existence and interference issues, and exposes sensitive personal data to security threats. Alternatively, capacitive body channel communications (BCC) exhibit much less signal leakage by confining signal transmission to the human body and experience substantially less propagation loss than RF systems as body tissues has better conductivity than surrounding air. Furthermore, the BCC band (10-100 MHz) decouples the transceiver size from the carrier wavelength, eliminating the need for complex and power-hungry radio front-ends. Therefore, capacitive BCC is a key enabler to reach the ultimate design goals of ultra-low-power, high throughput, and small form-factor IoB devices. Albeit these attractive features, the communication and networking aspects of the capacitive BCC are not thoroughly explored yet. This paper is the first to model orthogonal and non-orthogonal body channel access schemes with or without cooperation among the IoB nodes. In order to address the quality of service (QoS) demand scenarios of different IoB applications, we present and formulate max-min rate, max-sum rate, and QoS sufficient operational regimes, then provide solution methodologies for optimal power and phase time allocations. Extensive numerical results are analyzed to compare the performance of orthogonal and non-orthogonal schemes with and without cooperation for various design parameters under prescribed QoS regimes.

Diabetic Retinopathy (DR) is an intricacy of dia- betes that affects the eyes. In this paper, we have proposed a hybrid pre-processing and feature extraction technique named as Microaneurysm Retinal vein Haemorrhage Exudate (MRHE) extraction using Feature Enhancement and Edge Detection (FEED) which can extract all the features in a single step and with very less complexity. To classify the presence of DR, we have used an efficient Deep Convolutional Neural Network (D-CNN), model. The D-CNN model is trained with four salient features namely retinal veins, MA’s, exudates, and haemorrhages which were extracted from the raw images using image-processing techniques. After training and testing the D-CNN model, we were able to classify the presence of DR based on the features extracted from the testing data. To implement this proposed method, we have used a dataset from the STructured Analysis of the Retina (STARE) Database, which comprises of retinal images taken under various imaging conditions using fundus photography. To demonstrate the legitimacy of the proposed method, we have compared our method with the existing DR detection and classification methods such as SVM, ANN,etc.. Performance evaluation results in terms of Accuracy and Recall show that the proposed algorithm outperforms other existing DR classification methods.