In agriculture science, accurate information of moisture content (MC) in fruits and vegetables in an automated fashion can be vital for astute quality and grading evaluation. This demands for a viable, feasible and cost-effective technique for the defect recognition using timely detection of MC in fruits and vegetables to maintain a healthy sensory characteristic of fruits. Here we propose a non-invasive machine learning (ML) driven technique to monitor variations of MC in fruits using the terahertz (THz) waves with Swissto12 material characterization kit (MCK) in the frequency range of 0.75 THz to 1.1 THz. In this regard, multi-domain features are extracted from time-, frequency-, and time-frequency domains, and applied three ML algorithms such as support vector machine (SVM), k-nearest neighbour (KNN) and Decision Tree (D-Tree) for the precise assessment of MC in both apple and mango slices. The results illustrated that the performance of SVM exceeded other classifiers results using 10-fold validation and leave-one-observation-out-cross-validation techniques. Moreover, all three classifiers exhibited 100% accuracy for day 1 and 4 with 80% MC value (freshness) and 2% MC value (staleness) of both fruits' slices, respectively. Similarly, for day 2 and 3, an accuracy of 95% was achieved with intermediate MC values in both fruits' slices. This study will pave a new direction for the real-time quality evaluation of fruits in a non-invasive manner by incorporating ML with THz sensing at a cellular level. It also has a strong potential to optimize economic benefits by the timely detection of fruits quality in an automated fashion.

Medical healthcare is one of the fascinating applications using Internet of Things (IoTs). The pervasive smart environment in IoTs has the potential to monitor various human activities by deploying smart devices. In our pilot study, we look at narcolepsy, a disorder in which individuals lose the ability to regulate their sleep-wake cycle. An imbalance in the brain chemical called orexin makes the sleep pattern irregular. This sleep disorder in patients suffering from narcolepsy results in them experience irrepressible sleep episodes while performing daily routine activities. This study presents a novel method for detecting sleep attacks or sleepiness due to immune system attacks and affecting daily activities measured using the S-band sensing technique. The S-Band sensing technique is channel sensing based on frequency spectrum sensing using the orthogonal frequency division multiplexing transmission at a 2 to 4 GHz frequency range leveraging amplitude and calibrated phase information of different frequencies obtained using wireless devices such as card, and omni-directional antenna. Each human behavior induces a unique channel information (CI) signature contained in amplitude and phase information. By linearly transforming raw phase measurements into calibrated phase information, we ascertain phase coherence. Classification and validation of various human activities such as walking, sitting on a chair, push-ups, and narcolepsy sleep episodes are done using support vector machine, K-nearest neighbor, and random forest algorithms. The measurement and evaluation were carried out several times with classification values of accuracy, precision, recall, specificity, Kappa, and F-measure of more than 90% that were achieved when delineating sleep attacks.

The Rapid Eye Movement (REM) Sleep Behavior Disorder (RBD) is a parasomnia that involves involuntary, unwanted and random movements of a dreaming patient. Typically, these dreams contain violent activities. There is a high likelihood of the patient being injured or hurt his bed-partner as a result of these enactments. Continuous monitoring of sleeping RBD patients can prevent these harmful events through timely intervention. This work presents a novel method for continuous observation of RBD patients exploiting fine-grained amplitude and phase information of the wireless channel response. The variations in the wireless channel response as a result of different patient movements are assessed and used to identify RBD episodes. The data obtained is classified using support vector machine and delivers accuracy level of more than 90%.To the best of authors’ knowledge, it is a first attempt at using radio frequency signals to sense RBD in real-time.

With the aging society approaching, the daily safety of the elderly has attracted more and more people’s attention, especially the elderly who live alone without anyone to take care of them. How to judge whether there is danger from the daily behavior of those who live alone and providing timely assistance is a research topic of health protection in the field of smart home care. Modern radar sensing technology and intelligent perception technology adopted in the domain of health care have started to gain significant interest, which can replace wearable sensors or cameras without feeling uncomfortable or having privacy issues. In this paper, some preliminary results were presented to develop an indoor monitoring system for human activity recognition using micro-Doppler features of radar signals. The experimental campaign involved five different with some similar activities of 10 subjects to be collected using a Doppler radar. A total of several texture features and numerical features are extracted from the spectrogram and time-frequency domain of measurements and applied three machine learning (ML) algorithms such as Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Decision Tree (D-Tree) for the precise classification of all five different motions. The results illustrated that the SVM classifier using the Radial Basis Function (RBF) kernel reaches the best results for all three feature sets, and the classification of mixed features can reach 93.2%, as well as 88.4% and 92.4% for numerical and texture features. The performance of SVM is 1.6% better than KNN and 3.2% better than D-Tree.

As an important biological signal, electrocardiogram (ECG) signals provide a valuable basis for the clinical diagnosis and treatment of several diseases. However, its reference significance is based on the effective acquisition and correct recognition of ECG signals. In fact, this mV-level weak signal can be easily affected by various interferences caused by the power of magnetic field, patient respiratory motion or contraction, and so on from the sampling terminal to the receiving and display end. The overlapping interference affects the quality of ECG waveform, leading to the false detection and recognition of wave groups, and thus causing misdiagnosis or faulty treatment. Therefore, the elimination of the interference of the ECG signal and the subsequent wave group identification technology has been a hot research topic, and their study has important significance. Based on the above, this paper introduces two improved adaptive algorithms based on the classical least mean square (LMS) algorithm by introducing symbolic functions and block-processing concepts.