Low-cost Implementation Research Articles

The cost of implementing the Systems Analysis and Improvement Approach for a cluster randomized trial integrating HIV testing into family planning services in Mombasa County, Kenya

BackgroundAlthough HIV testing in family planning (FP) clinics is a promising approach for engaging women in HIV treatment and prevention services, HIV testing rates are low in FP clinics in Kenya. In 2018, a cluster randomized trial was implemented in Mombasa, Kenya applying the Systems Analysis and Improvement Approach (SAIA) to integrate HIV testing into FP services (1K24HD088229-01). We estimated the incremental costs and explored cost drivers of the FP HIV SAIA implementation in Mombasa, Kenya.MethodsWe conducted a costing evaluation from the payer perspective for the FP HIV SAIA randomized control trial. We identified relevant activities for the intervention including start-up, training, research and FP HIV SAIA. We estimated activity time burden using a time-and motion study. We derived unit costs through staff interviews and programmatic budgets. We present cost estimates for two different scenarios: as-implemented including research and projected costs for a Ministry of Health-supported intervention. All costs are reported in 2018 USD.ResultsFor an annual program output of 36,086 HIV tests administered to new FP clients, we estimated the total annual program cost to be $91,994 with an average cost per new FP client served of $2.55. Personnel and HIV rapid testing kits comprised 55% and 21% of programmatic costs, respectively. Assuming no changes to program outputs and with efficiency gains under the MOH scenario, the estimated cost per new FP client served decreased to $1.30 with a programmatic cost reduction of 49%.ConclusionFP HIV SAIA is a low-cost and flexible implementation strategy for facilitating integrated delivery of HIV testing alongside FP services. Although cost implications of the FP HIV SAIA intervention must continue to be evaluated over time, these findings provide context-specific cost data useful for budget planning and decision-making regarding intervention delivery and expansion.Trial registrationThe trial was registeredon December 15, 2016, with clinicaltrials.gov (NCT02994355).

Design of Reconfigurable Intelligent Surface-Aided Cross-Media Communications

A novel reconfigurable intelligent surface (RIS)-aided hybrid reflection/transmitter design is proposed for achieving information exchange in cross-media communications. In pursuit of the balance between energy efficiency and low-cost implementations, the cloud-management transmission protocol is adopted in the integrated multi-media system. Specifically, the messages of devices using heterogeneous propagation media, are firstly transmitted to the medium-matched AP, with the aid of the RIS-based dual-hop transmission. After the operation of intermediate frequency conversion, the access point (AP) uploads the received signals to the cloud for further demodulating and decoding process. Based on time division multiple access (TDMA), the cloud is able to distinguish the downlink data transmitted to different devices and transforms them into the input of the RIS controller via the dedicated control channel. Thereby, the RIS can passively reflect the incident carrier back into the original receiver with the exchanged information during the preallocated slots, following the idea of an index modulation-based transmitter. Moreover, the iterative optimization algorithm is utilized for optimizing the RIS phase, transmit rate and time allocation jointly in the delay-constrained cross-media communication model. Our simulation results demonstrate that the proposed RIS-based scheme can improve the end-to-end throughput than that of the AP-based transmission, the equal time allocation, the random and the discrete phase adjustment benchmarks.

Electric poling-assisted additive manufacturing technique for piezoelectric active poly(vinylidene fluoride) films: Towards fully three-dimensional printed functional materials

The development of science and technology simplifies the fabrication of functional materials and devices. Polymeric piezoelectric materials have attracted interest for actuation, sensing, energy harvesting, and storage applications due to their capability to sustain larger strains than ceramic piezoelectric materials. In this work, a novel electric poling-assisted additive manufacturing (EPAM) technology that integrates a fused deposition modeling (FDM) three-dimensional (3D) printer with a corona electric poling setup is demonstrated to directly print piezoelectric active materials with improved piezoelectric characteristics. The developed EPAM technology overcomes two main shortcomings of the conventional manufacturing methods for poly(vinylidene fluoride) (PVdF) materials: (1) their shapes are constrained to planar or fiber-like geometries, and (2) the need for additional electric poling as a post-processing treatment. Compared with the contact poling method, the EPAM method eliminates the need to apply electrodes for poling. The EPAM process can accomplish stretching and poling simultaneously which are necessary conditions for the polarization. During the EPAM process, stretching the molten PVdF rod rearranges the amorphous strands in the film plane, and the applied electric field aligns dipoles towards the same direction. The EPAM process can print free-form PVdF structures and induce the formation of β -phase, which is primarily responsible for the piezoelectric response. The Fourier-transform infrared spectroscopy (FTIR) results indicate the β -phase content increased from 15.38% to 17.14% corresponding to unpoled printed and EPAM printed samples, respectively. PVdF force sensors were successfully printed, and the piezoelectric activity (pC/N) was calculated based on the piezoelectric output voltage. The piezoelectric activity has a positive correlation with the piezoelectric coefficient that is explained in detail in section 3.2. The results demonstrate that the average piezoelectric activity of EPAM printed PVdF films was 47.76 pC/N, or about five times higher than unpoled 3D printed films, at 9.0 pC/N. The piezoelectric activity of unpoled 3D printed PVdF films indicates that 3D printing in the absence of an electric field does not result in dipole alignment. The 3D printed samples show an anisotropic mechanical behavior, and the bonding surface strength is sensitive to the printing speed. The maximum Young’s modulus (534.63 MPa) occurred at 3 mm/s and 0° infill, and the highest ultimate tensile strength (UTS) (25.35 MPa) was achieved at 20 mm/s, and 90° infill. Both the Young’s modulus and UTS from the EPAM printed samples are lower than unpoled samples. A fully 3D printed device was demonstrated to identify the position and magnitude of forces and results were visualized via structure-embedded integrated Light emitting diodes (LEDs). Overall, with the advantage of mechanical structural design flexibility and ease of printing of piezoelectric materials, the developed EPAM technology opens a new avenue to simplify device design and fabrication methodologies along with low-cost implementations.

Double sliding window variance detection-based time-of-arrival estimation in ultra-wideband ranging systems

<span lang="EN-US">Ultra-wideband (UWB) ranging via time-of-arrival (TOA) estimation method has gained a lot of research interests because it can take full advantage of UWB capabilities. Energy detection (ED) based TOA estimation technique is widely used in the area due to its low cost, low complexity and ease of implementation. However, many factors affect the ranging performance of the ED-based methods, especially, non-line-of-sight (NLOS) condition and the integration interval. In this context, a new TOA estimation method is developed in this paper. Firstly, the received signal is denoised using a five-level wavelet decomposition, next, a double sliding window algorithm is applied to detect the change in the variance information of the received signal, the first path (FP) TOA is then calculated according to the first variance sharp increase. The simulation results using the CM1 and CM2 IEEE 802.15.4a channel models, prove that our proposed approach works effectively compared with the conventional ED-based methods.</span>

Capacitor Pre-Charge Method for Back-to-Back Seven-Level Hybrid Clamped Converter Without Extra Power Supply

Multilevel converters with floating capacitors generally require precharging to build up the voltage on floating capacitors and dc-link before the normal operation. In particular, precharge is challenging for converters with overvoltage concerns under initial zero capacitor voltages. As a promising topology, seven-level hybrid clamped (7L-HC) converters also require precharge of capacitors and shall avoid high voltage stress during the precharge. Considering the high cost of deploying extra dedicated precharge circuits in a medium voltage system, the precharging method without relying on dedicated power supplies is favored. In this article, specific switching states and their corresponding selection schemes are designed to precharge floating capacitors of back-to-back 7L-HC converters. In this process, the inrush current and voltage stress can always be limited in the safe range. This method only needs series and shunt resistors typically already exist in practical converter circuits, resulting in low cost and ease of implementation. The design method of the resistances is also provided. Both simulation and experimental results validate the feasibility of this method.

Improving User Environment Detection Using Context-Aware Multi-Task Deep Learning in Mobile Networks

Cognition of user behavior can make future mobile networks more intelligent and flexible. Knowledge about users’ habits can be used to personalize services and intelligently manage network resources. However, inferring this key information with a low-cost signaling implementation, and avoiding constant user interaction, is crucial for Mobile Network Operators (MNOs). With this motivation, this paper investigates the detection of the real-life mobile user environment using context-aware detection via multi-task learning (MTL). We propose models that are able to automatically detect up to eight distinct real-life user environments. We also improve the detection accuracy with the assistance of the mobility state profiling task. We associate both environment and mobility tasks because they correspond to the main attributes of user behavior and, additionally, both of them are correlated. Using MTL, the task of detecting environment corresponds to simultaneously answering the questions: “how and where mobile user consumes mobile services?”. We build models using real-life radio data which is already available in network. This data has been massively gathered from multiple diversified situations of mobile users. Simulation results support our claim to detect several environment classes in network infrastructure with improved UED accuracy.

An Artificial Intelligence Approach for Real-Time Tuning of Weighting Factors in FCS-MPC for Power Converters

In this article a finite control set model predictive control, is used to track a current reference in a power converter connected to an <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$RL$</tex-math></inline-formula> load. An artificial intelligence approach is presented for real-time determination of the weighting factor that regulates the average switching frequency, independently of the operating point. The article focuses on the design, training, and digital implementation of an artificial neural network (ANN) that can be developed in a low-cost control platform. It is presented a sampling and offline ANN training procedure, together with a low-cost hardware implementation based on integer quantization of the ANN. The abovementioned approach provides a standalone application, serving as a framework for the development of ANN applications for power-converters. The main advantage of the presented approach is that the ANN inference is executed in real time. In this way, the weighting factor is automatically updated in real-time, allowing the system to quickly adapt to any reference step changes, and consequently provide the desired behavior. Executing the setup in laboratory prototype confirmed the theoretical analysis and successful tracking of the reference frequency.

A Retail Object Classification Method Using Multiple Cameras for Vision-Based Unmanned Kiosks

Several unmanned retail stores have been introduced with the development of sensors, wireless communication, and computer vision technologies. A vision-based kiosk that is only equipped with a vision sensor has significant advantages such as compactness and low implementation cost. Using convolutional neural network (CNN)-based object detectors, the kiosk recognizes an object when a customer picks up a product. In retail object recognition, the key challenge is the limited number of detections and high interclass similarity. In this study, these challenges are addressed by utilizing the “view-specific” feature of an object; specifically, an object class is divided into multiple “view-based” subclasses, and the object detectors are trained using these data. Further, the “view-aware feature” is defined by aggregating subclass detection results from multiple cameras. A superclass classifier predicts a superclass by utilizing an informative subclass detection result that distinguishes the target object from other similar-looking objects. To verify the effectiveness of the proposed approach, a prototype of the vision-based unmanned kiosk system is implemented. Experimental results indicate that the proposed method outperforms the conventional method, even on a state-of-the-art detection network. The dataset used in this study has been subsequently provided in the IEEE DataPort for reproducibility.

Hybrid Wi-Fi and BLE Fingerprinting Dataset for Multi-Floor Indoor Environments with Different Layouts

Indoor positioning has garnered significant interest over the last decade due to the rapidly growing demand for location-based services. As a result, a multitude of techniques has been proposed to localize objects and devices in indoor environments. Wireless fingerprinting, which leverages machine learning, has emerged as one of the most popular positioning approaches due to its low implementation cost. The prevailing fingerprinting-based positioning mainly utilizes wireless fidelity (Wi-Fi) and Bluetooth low energy (BLE) signals. However, the RSS of Wi-Fi and BLE signals are very sensitive to the layout of the indoor environment. Thus, any change in the indoor layout could potentially lead to severe degradation in terms of localization performance. To foster the development of new positioning methods, several open-source location fingerprinting datasets have been made available to the research community. Unfortunately, none of these public datasets provides the received signal strength (RSS) measurements for indoor environments with different layouts. To fill this gap, this paper presents a new hybrid Wi-Fi and BLE fingerprinting dataset for multi-floor indoor environments with different layouts to facilitate the future development of new fingerprinting-based positioning systems that can provide adaptive positioning performance in dynamic indoor environments. Additionally, the effects of indoor layout change on the location fingerprint and localization performance are also investigated.

Universal Sensorless Open-Circuit Fault Detection and Isolation Method of Dual-Active-Bridge Converters With Low-Cost Diagnostic Circuit

As one of the promising power interfaces between the energy storage components and the dc link, dual active bridge (DAB) converters have gained extensive researches. Its reliability and healthy operation under one or even multiple unexpected open-circuit faulty conditions have become one of the main design challenges. Conventional fault detection (FD) and fault isolation (FI) methods exhibit obvious limitations in terms of detection speed, number of FD signatures, universality, accuracy, computational burden, and implementation cost due to the added sensors. To fill in this gap, this article presents a robust, fast, accurate, and low-cost FD and FI method for DAB converters, which is applicable under various operational conditions. The proposed method will adopt the differential switch node voltage between the primary and secondary bridge of DAB converters as the universal fault signature for complete FD and FI. The corresponding fault diagnostic circuit is simple, compact, low cost, and easy in implementation. This sensorless fault diagnostic technique can detect the switch open-circuit fault within a quarter of a switching cycle and realize the fault isolation accurately. A DAB prototype with a fault diagnostic circuit was designed, and main experimental results under various faulty conditions were provided to validate the advantages of the proposed method.

Unity Attractors Inspired Programmable Cellular Automata and Barnacles Swarm Optimization-Based Energy Efficient Data Communication for Securing IoT

Wireless Sensor Networks (WSNs) is the innovative technology that covers wide range of application that possesses high potential merits such as long-term operation, unmonitored network access, data transmission, and low implementation cost. In this context, Internet of Things (IoT) have evolved as an exciting paradigm with the rapid advancement of cellular mobile networks, near field communications and cloud computing. WSNs potentially interacts with the IoT devices based on the sensing features of web devices and communication technologies in sensors. At this juncture, IoT need to facilitate huge amount of data aggregation with security and disseminate it to the reliable path to make it reach the required base station. In this paper, Unity Attractors Inspired Programmable Cellular Automata and Barnacles Swarm Optimization-Based Energy Efficient Data Communication Mechanism (UAIPCA-BSO) is proposed for Securing data and estimate the optimal path through which it can be forwarded in the IoT environment. In specific, Unity Attractors Inspired Programmable Cellular Automata is adopted for guaranteeing security during the data transmission process. It also aids in determining the optimal path of data transmission based on the merits of Barnacles Swarm Optimization Algorithm (BSOA), such that data is made to reach the base station at the required destination in time. The simulation results of UAIPCA-BSO confirmed minimized end-to-end delay , accuracy and time taken for malicious node detection, compared to the baseline approaches used for comparison.

Finding Subsampling Index Sets for Kronecker Product of Unitary Matrices for Incoherent Tight Frames

Frames are recognized for their importance in many fields of communications, signal processing, quantum physics, and so on. In this paper, we design an incoherent tight frame by selecting some rows of a matrix that is the Kronecker product of Fourier and unitary matrices. The Kronecker-product-based frame allows its elements to have a small number of phases, regardless of the frame length, which is suitable for low-cost implementation. To obtain the Kronecker-product-based frame with low mutual coherence, we first derive an objective function by transforming the Gram matrix expression to compute the coherence. If the Hadamard matrix is employed as a unitary matrix, the objective function can be computed efficiently with low complexity. Then, we find a subsampling index set for the Kronecker-product-based frame by minimizing the objective function. In simulations, we show that the Kronecker-product-based frames can achieve similar mutual coherence to optimized harmonic frames of a large number of phases. We apply the frames to compressed sensing (CS) as the measurement matrices, where the Kronecker-product-based frames demonstrate reliable performance of sparse signal recovery.

Enabling Spectrally Resolved Single-Molecule Localization Microscopy at High Emitter Densities.

Single-molecule localization microscopy (SMLM) is a powerful super-resolution technique for elucidating structure and dynamics in the life- and material sciences. Simultaneously acquiring spectral information (spectrally resolved SMLM, sSMLM) has been hampered by several challenges: an increased complexity of the optical detection pathway, lower accessible emitter densities, and compromised spatio-spectral resolution. Here we present a single-component, low-cost implementation of sSMLM that addresses these challenges. Using a low-dispersion transmission grating positioned close to the image plane, the +1stdiffraction order is minimally elongated and is analyzed using existing single-molecule localization algorithms. The distance between the 0th and 1st order provides accurate information on the spectral properties of individual emitters. This method enables a 5-fold higher emitter density while discriminating between fluorophores whose peak emissions are less than 15 nm apart. Our approach can find widespread use in single-molecule applications that rely on distinguishing spectrally different fluorophores under low photon conditions.

Detector Processor for a 5G Base Station.

Nonlinear soft bit detection is essential for the uplink receivers of 5G base stations, especially for users around the cell edge. However, its throughput and computing complexity are always challenges for both research and industry. A low-cost and low-power parallel implementation of a soft-output detector based on sorted QR decomposition (SQRD) and the K-best breadth-first search algorithm is thus proposed to reduce computational complexity and latency. In addition, to save area and reduce latency, two improvement methods are used: (1) reduce the computing cost by saturating and truncating large values during PED computing and (2) reduce the sorting cost by using the binary bit sorting method for a reduced sample set with finite accuracy. Furthermore, a pipelined VLSI architecture is designed using 28-nm digital CMOS technology offered by Semiconductor Manufacturing International Corporation (SMIC). It can achieve a peak throughput of 6400 Mbps while consuming 153 K gates (including all flip-flops) for SMIC’s 28-nm technology and running at 800 MHz, a 32% cost reduction compared with the published reference design.

Fault estimation and fault tolerant control for interval type-2 Takagi–Sugeno fuzzy systems via membership-function-dependent approach

This paper investigates the fault estimation (FE)-based fault tolerant control (FTC) technique to achieve the desired control performance for the nonlinear systems suffering from uncertainties, external disturbance and actuator faults using the interval type-2 (IT2) Takagi–Sugeno (T–S) fuzzy model. In this work, an IT2 fuzzy observer is built to simultaneously estimate both the system states and actuator faults, upon which a fault tolerant controller is proposed to guarantee the asymptotical stability of the closed-loop system with a prescribed H_{infty } performance level. Considering the bidirectional robustness interactions between the observer and FTC system, an integrated design technique is developed to address observer and FTC units together in one step to realize the required robustness within the whole closed-loop FTC system. By utilizing Lyapunov stability theory combined with the matrix inequality convexification techniques, a membership-function-dependent (MFD) FTC strategy is proposed where the information of membership functions is taken into account in the analysis for relaxation of the stability conditions. Additionally, to offer greater design flexibility and lower implementation cost to the fault tolerant controller, the imperfect premise matching (IPM) scheme is adopted, such that the premise membership functions of the fault tolerant controller can be chosen differently from those of IT2 fuzzy model. Finally, simulation results are provided to validate the effectiveness of the proposed FTC strategy.

Data Privacy Preservation and Security in Smart Metering Systems

Smart meters (SMs) can play a key role in monitoring vital aspects of different applications such as smart grids (SG), alternative currents (AC) optimal power flows, adversarial training, time series data, etc. Several practical privacy implementations of SM have been made in the literature, but more studies and testing may be able to further improve efficiency and lower implementation costs. The major objectives of cyberattacks are the loss of data privacy on SM-based SG/power grid (PG) networks and threatening human life. As a result, losing data privacy is very expensive and gradually hurts the national economy. Consequently, employing an efficient trust model against cyberattacks is strictly desired. This paper presents a research pivot for researchers who are interested in security and privacy and shade light on the importance of the SM. We highlight the involved SMs’ features in several applications. Afterward, we focus on the SMs’ vulnerabilities. Then, we consider eleven trust models employed for SM security, which are among the common methodologies utilized for attaining and preserving the data privacy of the data observed by the SMs. Following that, we propose a comparison of the existing solutions for SMs’ data privacy. In addition, valuable recommendations are introduced for the interested scholars, taking into consideration the vital effect of SM protection on disaster management, whether on the level of human lives or the infrastructure level.

Enhanced Multilink Single-Radio Operation for the Next-Generation IEEE 802.11 BE Wi-Fi Systems

For the next-generation Wi-Fi systems, the Enhanced Multilink Single-Radio (EMLSR) operation has become a promising feature to improve the Wi-Fi system performance. The EMLSR enables dynamic switching among multiple bands with low-cost implementation and efficient power consumption. However, with realistic channelization of multiple links with 320 MHz bandwidth on 6 GHz and 160 MHz bandwidth on 5 GHz, the performance of EMLSR is jeopardized due to the crowded 5 GHz band with existing Wi-Fi systems. In addition, the unbalanced bandwidth configuration between an access point (AP) and stations (STAs) multilink devices (MLDs) may result in wasted secondary channels when STAs supporting smaller bandwidth stay on the primary channel only. We proposed the further enhanced EMLSR with a new MAC protocol and link selection mechanism, where a primary link (PL) is selected between AP and STA with the unbalanced Link/Band and one or multiple secondary links (SLs) with balanced Link/Band. The STA tunes the main radio on the PL and the scan radio to one of the SLs. The PL will be more prioritized than the SL based on the link selection algorithm to maximize the channel utilization. Compared with legacy EMLSR, the enhanced EMLSR can improve the utilization of the secondary channel. Even under heavy OBSS load on SL or both PL and SL, the further enhanced EMLSR can achieve 50% to 70% throughput gain.

Optimization of Planar Phased Arrays for Vehicles

Radar sensors are used for the detection of objects surrounding a vehicle to enable advanced driver assistance systems. Wide angle azimuth field-of-view (FOV) sensor having high angular resolution is beneficial, but presents challenges for low-cost implementation where element-to-element spacing may be larger than one-half wavelength. Irregular placement of array elements in a two-dimensional (2-D) array can achieve low-cost targets, but may generate large sidelobes if done without care. We introduce an optimization method to determine placement of array elements in a vehicular volumetric beam-scanning radar to minimize sidelobe power for typical automotive beam steering angles. Optimization with array constraints is realized using a gradient-based nonlinear programming technique. Optimization is accelerated by extending <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">uv</i> -projection planes beyond the unit circle. For a grating lobe-free scan area based on vehicular applications, the azimuth scanning FOV is increased by 11° bidirectionally to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\pm$</tex-math></inline-formula> 54° compared to a reference triangular grid array with 24 elements. The validity of an antenna design generated using the optimization method is established by a three-dimensional (3-D) electromagnetic wave simulation of a representative optimized array configuration.

Managing Autism Spectrum Disorder in the Face of Pandemic Using Internet-Based Parent-Mediated Interventions: A Systematic Review of Randomized Controlled Trials.

ASD is a neurodevelopmental disorder that is primarily treated with psychosocial intervention. However, it is costly and requires extensive resources to be effective. This inaccessibility is also further worsened by the ongoing COVID-19 pandemic, making the shift to a digital approach a sensible option. Among the available ASD therapies, parent-mediated interventions (PMIs) have a broad application and lower implementation cost. Hence, this systematic review aims to evaluate the potential that telehealth-based PMI holds and explore its feasibility throughout the COVID-19 pandemic. To build up this study, a systematic search through PubMed, Scopus, ProQuest, Wiley, and Cochrane was performed until 14 January 2021. Using the preferred Reporting Items for Systematic Review and Meta-Analysis guidelines, we ultimately included six studies in the review. Each study was evaluated utilizing the Cochrane Risk of Bias (ROB)-2 tool. Generally, parents’ outcomes (knowledge, satisfaction, and compliance) were higher in intervention group (E-learning) compared to control (standard treatment or wait-list). Children also showed some improvements in social skill, communication skill, and intelligence after receiving the treatment. In addition, coaching or therapist sessions were found to be crucial as adjuvant to support parents during the intervention. In conclusion, internet-based parent-mediated interventions are promising and recommended for managing ASD patients, in the face of pandemic. However, more variety in study locations is also needed, particularly in low- and middle-income countries, to tackle the knowledge and clinical application gap. Further research should be conducted with a uniform measurement tool to achieve the same perception and reliable pooled analysis.

A Deep Learning Framework for Automatic Sleep Apnea Classification Based on Empirical Mode Decomposition Derived from Single-Lead Electrocardiogram.

Background: Although polysomnography (PSG) is a gold standard tool for diagnosing sleep apnea (SA), it can reduce the patient’s sleep quality by the placement of several disturbing sensors and can only be interpreted by a highly trained sleep technician or scientist. In recent years, electrocardiogram (ECG)-derived respiration (EDR) and heart rate variability (HRV) have been used to automatically diagnose SA and reduce the drawbacks of PSG. Up to now, most of the proposed approaches focus on machine-learning (ML) algorithms and feature engineering, which require prior expert knowledge and experience. The present study proposes an SA detection algorithm to differentiate a normal and apnea event using a deep-learning (DL) framework based on 1D and 2D deep CNN with empirical mode decomposition (EMD) of a preprocessed ECG signal. The EMD is ideally suited to extract essential components which are characteristic of the underlying biological or physiological processes. In addition, the simple and compact architecture of 1D deep CNN, which only performs 1D convolutions, and pretrained 2D deep CNNs, are suitable for real-time and low-cost hardware implementation. Method: This study was validated using 7 h to nearly 10 h overnight ECG recordings from 33 subjects with an average apnea-hypopnea index (AHI) of 30.23/h originated from PhysioNet Apnea-ECG database (PAED). In preprocessing, the raw ECG signal was normalized and filtered using the FIR band pass filter. The preprocessed ECG signal was then decomposed using the empirical mode decomposition (EMD) technique to generate several features. Several important generated features were selected using neighborhood component analysis (NCA). Finally, deep learning algorithm based on 1D and 2D deep CNN were used to perform the classification of normal and apnea event. The synthetic minority oversampling technique (SMOTE) was also applied to evaluate the influence of the imbalanced data problem. Results: The segment-level classification performance had 93.8% accuracy with 94.9% sensitivity and 92.7% specificity based on 5-fold cross-validation (5fold-CV), meanwhile, the subject-level classification performance had 83.5% accuracy with 75.9% sensitivity and 88.7% specificity based on leave-one-subject-out cross-validation (LOSO-CV). Conclusion: A novel and robust SA detection algorithm based on the ECG decomposed signal using EMD and deep CNN was successfully developed in this study.