Exploring inertial sensor-based balance biomarkers for early detection of mild cognitive impairment.

Dementia is characterized by a progressive loss of cognitive abilities, and diagnosing its early stages Mild Cognitive Impairment (MCI), is difficult since it is a transitory state that is different from total cognitive collapse. Recent clinical research studies have identified that balance impairments can be a significant indicator for predicting dementia in older adults. Accordingly, the current research focuses on finding innovative postural balance-based digital biomarkers by using wearable inertial sensors and pre-screening of MCI in home settings using machine learning techniques. For this research, sixty subjects (30 cognitively normal and 30 MCI) with waist-mounted inertial sensor performed balance tasks in four different standing postures: eyes-open, eyes-closed, right-leg-lift, and left-leg-lift. The significant balance biomarkers for MCI identification are discovered by our research, demonstrating specific characteristics in each of these four states. A robust feature selection approach is ensured by the multi-step methodology that combines the strengths of Filter techniques, Wrapper methods, and SHAP (Shapley Additive exPlanations) technique. The proposed balance biomarkers have the potential to detect MCI (with 75.8% accuracy), as evidenced by the results of machine learning algorithms for classification. This work adds to the growing body of literature targeted at enhancing understanding and proactive management of cognitive loss in older populations and lays the groundwork for future research efforts aimed at refining digital biomarkers, validating findings, and exploring longitudinal perspectives.

An effective modular approach for crowd counting in an image using convolutional neural networks.

Abrupt and continuous nature of scale variation in a crowded scene is a challenging task to enhance crowd counting accuracy in an image. Existing crowd counting techniques generally used multi-column or single-column dilated convolution to tackle scale variation due to perspective distortion. However, due to multi-column nature, they obtain identical features, whereas, the standard dilated convolution (SDC) with expanded receptive field size has sparse pixel sampling rate. Due to sparse nature of SDC, it is highly challenging to obtain relevant contextual information. Further, features at multiple scale are not extracted despite some inception-based model is not used (which is cost effective). To mitigate theses drawbacks in SDC, we therefore, propose a hierarchical dense dilated deep pyramid feature extraction through convolution neural network (CNN) for single image crowd counting (HDPF). It comprises of three modules: general feature extraction module (GFEM), deep pyramid feature extraction module (PFEM) and fusion module (FM). The GFEM is responsible to obtain task independent general features. Whereas, PFEM plays a vital role to obtain the relevant contextual information due to dense pixel sampling rate caused by densely connected dense stacked dilated convolutional modules (DSDCs). Further, due to dense connections among DSDCs, the final feature map acquires multi-scale information with expanded receptive field as compared to SDC. Due to dense pyramid nature, it is very effective to propagate the extracted feature from lower dilated convolutional layers (DCLs) to middle and higher DCLs, which result in better estimation accuracy. The FM is used to fuse the incoming features extracted by other modules. The proposed technique is tested through simulations on three well known datasets: Shanghaitech (Part-A), Shanghaitech (Part-B) and Venice. Results justify its relative effectiveness in terms of selected performance.

HADF-Crowd: A Hierarchical Attention-Based Dense Feature Extraction Network for Single-Image Crowd Counting.

Crowd counting is a challenging task due to large perspective, density, and scale variations. CNN-based crowd counting techniques have achieved significant performance in sparse to dense environments. However, crowd counting in high perspective-varying scenes (images) is getting harder due to different density levels occupied by the same number of pixels. In this way large variations for objects in the same spatial area make it difficult to count accurately. Further, existing CNN-based crowd counting methods are used to extract rich deep features; however, these features are used locally and disseminated while propagating through intermediate layers. This results in high counting errors, especially in dense and high perspective-variation scenes. Further, class-specific responses along channel dimensions are underestimated. To address these above mentioned issues, we therefore propose a CNN-based dense feature extraction network for accurate crowd counting. Our proposed model comprises three main modules: (1) backbone network, (2) dense feature extraction modules (DFEMs), and (3) channel attention module (CAM). The backbone network is used to obtain general features with strong transfer learning ability. The DFEM is composed of multiple sub-modules called dense stacked convolution modules (DSCMs), densely connected with each other. In this way features extracted from lower and middle-lower layers are propagated to higher layers through dense connections. In addition, combinations of task independent general features obtained by the former modules and task-specific features obtained by later ones are incorporated to obtain high counting accuracy in large perspective-varying scenes. Further, to exploit the class-specific response between background and foreground, CAM is incorporated at the end to obtain high-level features along channel dimensions for better counting accuracy. Moreover, we have evaluated the proposed method on three well known datasets: Shanghaitech (Part-A), Shanghaitech (Part-B), and Venice. The performance of the proposed technique justifies its relative effectiveness in terms of selected performance compared to state-of-the-art techniques.

Development of Scientific Fishery Biomass Estimator: System Design and Prototyping.

This paper presents a new compact single beam advanced echosounder system designed to estimate fish count in real time. The proposed device is a standalone system, which consists of a transducer, a processing unit, a keypad, and a display unit to show output. A fish counting algorithm was developed and implemented in the device. The device is capable of performing all the functions required for fish abundance estimation including target strength calculation, simultaneous echo integration, and echogram generation. During operation, the device analyzes ping data continuously and calculates various parameters in real time while simultaneously displaying the echogram and results on the screen. The device has been evaluated by technical verification in a lab and on-site experiments. The experimental results demonstrate that the proposed device is on par with a commercial echosounder and is capable of accurately estimating the fish abundance. The proposed device is beneficial for fish management.

Convolutional-Neural Network-Based Image Crowd Counting: Review, Categorization, Analysis, and Performance Evaluation.

Traditional handcrafted crowd-counting techniques in an image are currently transformed via machine-learning and artificial-intelligence techniques into intelligent crowd-counting techniques. This paradigm shift offers many advanced features in terms of adaptive monitoring and the control of dynamic crowd gatherings. Adaptive monitoring, identification/recognition, and the management of diverse crowd gatherings can improve many crowd-management-related tasks in terms of efficiency, capacity, reliability, and safety. Despite many challenges, such as occlusion, clutter, and irregular object distribution and nonuniform object scale, convolutional neural networks are a promising technology for intelligent image crowd counting and analysis. In this article, we review, categorize, analyze (limitations and distinctive features), and provide a detailed performance evaluation of the latest convolutional-neural-network-based crowd-counting techniques. We also highlight the potential applications of convolutional-neural-network-based crowd-counting techniques. Finally, we conclude this article by presenting our key observations, providing strong foundation for future research directions while designing convolutional-neural-network-based crowd-counting techniques. Further, the article discusses new advancements toward understanding crowd counting in smart cities using the Internet of Things (IoT).

Two-Wired Active Spring-Loaded Dry Electrodes for EEG Measurements.

Dry contact electrode-based EEG acquisition is one of the easiest ways to obtain neural information from the human brain, providing many advantages such as rapid installation, and enhanced wearability. However, high contact impedance due to insufficient electrical coupling at the electrode-scalp interface still remains a critical issue. In this paper, a two-wired active dry electrode system is proposed by combining finger-shaped spring-loaded probes and active buffer circuits. The shrinkable probes and bootstrap topology-based buffer circuitry provide reliable electrical coupling with an uneven and hairy scalp and effective input impedance conversion along with low input capacitance. Through analysis of the equivalent circuit model, the proposed electrode was carefully designed by employing off-the-shelf discrete components and a low-noise zero-drift amplifier. Several electrical evaluations such as noise spectral density measurements and input capacitance estimation were performed together with simple experiments for alpha rhythm detection. The experimental results showed that the proposed electrode is capable of clear detection for the alpha rhythm activation, with excellent electrical characteristics such as low-noise of 1.131 µVRMS and 32.3% reduction of input capacitance.

Deep Feature Learning for Sudden Cardiac Arrest Detection in Automated External Defibrillators.

Ventricular fibrillation and ventricular tachycardia (VF/VT), known as shockable (SH) rhythms, are the mainly cause of sudden cardiac arrests (SCA), which is cured efficiently by the automated external defibrillator (AED). The performance of the shock advice algorithm (SAA) applied in the AED has been improved by using machine learning technique and variously conventional features, recently. In this paper, we propose a novel algorithm with relatively high performance for the SCA detection on electrocardiogram (ECG) signal. The algorithm consists of a convolutional neural network as a feature extractor (CNNE) and a Boosting (BS) classifier. A grid search with nested 5-folds cross validation (CV) is used to select the CNNE trained with preprocessed ECG, SH, and NSH signals using the modified variational mode decomposition technique. The deep feature vector learned by this CNNE is extracted at the first fully connected layer and then fed into BS classifier to validate its performance using 5-folds CV procedure. The secondary learning of the BS classifier and the use of three input channels for the CNNE improve certainly the detection performance of the proposed SAA with the validated accuracy of 99.26%, sensitivity of 97.07%, and specificity of 99.44%.

Detection of Early Stage Alzheimer's Disease using EEG Relative Power with Deep Neural Network.

Electroencephalogram (EEG) signal based early diagnosis of Alzheimer's Disease (AD), especially a discrimination between healthy control (HC) and mild cognitive impairment (MCI) has received remarkable attentions to complement conventional diagnosing methods in clinical fields. A relative power (RP) metric which quantifies the abnormal EEG pattern 'slowing' has widely been used as a major feature to distinguish HC and MCI, however, the optimal spectral ranges of the RP are influenced by the given dataset. In this study, we proposed the deep neural network based classifier using the RP to fully exploit and recombine the features through its own learning structure. The DNN enhanced the diagnosis results compared to shallow neural network, and enabled to interpret the results as we used the wellknown RP features as the domain knowledge. We investigated and explored the potentials of DNN based detection of the earlystage AD.

Visual Evoked Potential Recordings in Mice Using a Dry Non-invasive Multi-channel Scalp EEG Sensor.

For scalp EEG research environments with laboratory mice, we designed a dry-type 16 channel EEG sensor which is non-invasive, deformable, and re-usable because of the plunger-spring-barrel structural facet and mechanical strengths resulting from metal materials. The whole process for acquiring the VEP responses in vivo from a mouse consists of four steps: (1) sensor assembly, (2) animal preparation, (3) VEP measurement, and (4) signal processing. This paper presents representative measurements of VEP responses from multiple mice with a submicro-voltage signal resolution and sub-hundred millisecond temporal resolution. Although the proposed method is safer and more convenient compared to other previously reported animal EEG acquiring methods, there are remaining issues including how to enhance the signal-to-noise ratio and how to apply this technique with freely moving animals. The proposed method utilizes easily available resources and shows a repetitive VEP response with a satisfactory signal quality. Therefore, this method could be utilized for longitudinal experimental studies and reliable translational research exploiting non-invasive paradigms.

Development and Experimental Validation of a Dry Non-Invasive Multi-Channel Mouse Scalp EEG Sensor through Visual Evoked Potential Recordings.

In this paper, we introduce a dry non-invasive multi-channel sensor for measuring brainwaves on the scalps of mice. The research on laboratory animals provide insights to various practical applications involving human beings and other animals such as working animals, pets, and livestock. An experimental framework targeting the laboratory animals has the potential to lead to successful translational research when it closely resembles the environment of real applications. To serve scalp electroencephalography (EEG) research environments for the laboratory mice, the dry non-invasive scalp EEG sensor with sixteen electrodes is proposed to measure brainwaves over the entire brain area without any surgical procedures. We validated the proposed sensor system with visual evoked potential (VEP) experiments elicited by flash stimulations. The VEP responses obtained from experiments are compared with the existing literature, and analyzed in temporal and spatial perspectives. We further interpret the experimental results using time-frequency distribution (TFD) and distance measurements. The developed sensor guarantees stable operations for in vivo experiments in a non-invasive manner without surgical procedures, therefore exhibiting a high potential to strengthen longitudinal experimental studies and reliable translational research exploiting non-invasive paradigms.

Performance Analysis of Amplify-and-Forward Systems with Single Relay Selection in Correlated Environments.

In this paper, we consider amplify-and-forward (AnF) cooperative systems under correlated fading environments. We first present a brief overview of existing works on the effect of channel correlations on the system performance. We then focus on our main contribution which is analyzing the outage probability of a multi-AnF-relay system with the best relay selection (BRS) scheme under a condition that two channels of each relay, source-relay and relay-destination channels, are correlated. Using lower and upper bounds on the end-to-end received signal-to-noise ratio (SNR) at the destination, we derive corresponding upper and lower bounds on the system outage probability. We prove that the system can achieve a diversity order (DO) equal to the number of relays. In addition, and importantly, we show that the considered correlation form has a constructive effect on the system performance. In other words, the larger the correlation coefficient, the better system performance. Our analytic results are corroborated by extensive Monte-Carlo simulations.

Localization with a mobile beacon in underwater acoustic sensor networks.

Localization is one of the most important issues associated with underwater acoustic sensor networks, especially when sensor nodes are randomly deployed. Given that it is difficult to deploy beacon nodes at predetermined locations, localization schemes with a mobile beacon on the sea surface or along the planned path are inherently convenient, accurate, and energy-efficient. In this paper, we propose a new range-free Localization with a Mobile Beacon (LoMoB). The mobile beacon periodically broadcasts a beacon message containing its location. Sensor nodes are individually localized by passively receiving the beacon messages without inter-node communications. For location estimation, a set of potential locations are obtained as candidates for a node's location and then the node's location is determined through the weighted mean of all the potential locations with the weights computed based on residuals.

Average BER analysis of SCM-based free-space optical systems by considering the effect of IM3 with OSSB signals under turbulence channels.

In this paper, we derive the average bit error rate (BER) of subcarrier multiplexing (SCM)-based free space optics (FSO) systems using a dual-drive Mach-Zehnder modulator (DD-MZM) for optical single-sideband (OSSB) signals under atmospheric turbulence channels. In particular, we consider the third-order intermodulation (IM3), a significant performance degradation factor, in the case of high input signal power systems. The derived average BER, as a function of the input signal power and the scintillation index, is employed to determine the optimum number of SCM users upon the designing FSO systems. For instance, when the user number doubles, the input signal power decreases by almost 2 dBm under the log-normal and exponential turbulence channels at a given average BER.

BER performance analysis of radio over free-space optical systems considering laser phase noise under Gamma-Gamma turbulence channels.

This paper analytically investigates a bit error rate (BER) performance of radio over free space optical (FSO) systems considering laser phase noise under Gamma-Gamma turbulence channels. An external modulation using a dual drive Mach-Zehnder modulator (DD-MZM) and a phase shifter is employed because a DD-MZM is robust against a laser chirp and provides high spectral efficiency. We derive a closed form average BER as a function of different turbulence strengths and laser diode (LD) linewidth, and investigate its analytical behavior under practical scenario. As a result, for a given average SNR with normalized perturbation, it is shown that the difference of average BER corresponding to two LDs (with linewidth of 624 MHz and 10 MHz) under weak turbulence is almost 3 times larger than that under strong turbulence.