A CMOS Current-Mode Vertical-Cavity-Semiconductor-Emitting-Laser Diode Driver for Short-Range LiDAR Sensors.

This paper presents a current-mode VCSEL driver (CMVD) implemented using 180 nm CMOS technology for application in short-range LiDAR sensors, in which current-steering logic is suggested to deliver modulation currents from 0.1 to 10 mApp and a bias current of 0.1 mA simultaneously to the VCSEL diode. For the simulations, the VCSEL diode is modeled with a 1.6 V forward-bias voltage and a 50 Ω series resistor. The post-layout simulations of the proposed CMVD clearly demonstrate large output pulses and eye-diagrams. Measurements of the CMVD demonstrate large output pulses, confirming the simulation results. The chip consumes a maximum of 11 mW from a 3.3 V supply, and the core occupies an area of 0.1 mm2.

Anti-Photoaging Effects of Upcycled Citrus junos Seed Anionic Peptides on Ultraviolet-Radiation-Induced Skin Aging in a Reconstructed Skin Model.

Side streams and byproducts of food are established sources of natural ingredients in cosmetics. In the present study, we obtained upcycled low-molecular-weight anionic peptides (LMAPs) using byproducts of the post-yuzu-juicing process by employing an enzyme derived from Bacillus sp. For the first time, we isolated anionic peptides less than 500 Da in molecular weight from Citrus junos TANAKA seeds via hydrolysis using this enzyme. The protective effect of LMAPs against UVR-induced photoaging was evaluated using a reconstructed skin tissue (RST) model and keratinocytes. The LMAPs protected the keratinocytes by scavenging intracellular reactive oxygen species and by reducing the levels of paracrine cytokines (IL-6 and TNF-α) in UVR (UVA 2 J/cm2 and UVB 15 mJ/cm2)-irradiated keratinocytes. Additionally, the increase in melanin synthesis and TRP-2 expression in RST caused by UVR was significantly inhibited by LMAP treatment. This treatment strongly induced the expression of filaggrin and laminin-5 in UVR-irradiated RST. It also increased type I collagen expression in the dermal region and in fibroblasts in vitro. These results suggest that a hydrolytic system using the enzyme derived from Bacillus sp. can be used for the commercial production of LMAPs from food byproducts and that these LMAPs can be effective ingredients for improving photoaging-induced skin diseases.

Optimization of Plant Growth Regulators for In Vitro Mass Propagation of a Disease-Free 'Shine Muscat' Grapevine Cultivar.

This study addresses the propagation challenges faced by 'Shine Muscat', a newly introduced premium grapevine cultivar in South Korea, where multiple viral infections pose considerable economic loss. The primary objective was to establish a robust in vitro propagation method for producing disease-free grapes and to identify effective plant growth regulators to facilitate large-scale mass cultivation. After experimentation, 2.0 µM 6-benzyladenine (BA) exhibited superior shoot formation in the Murashige and Skoog medium compared with kinetin and thidiazuron. Conversely, α-naphthaleneacetic acid (NAA) hindered shoot growth and induced callus formation, while indole-3-butyric acid (IBA) and indole-3-acetic acid (IAA) demonstrated favorable root formation, with IBA showing better results overall. Furthermore, inter simple sequence repeat analysis confirmed the genetic stability of in vitro-cultivated seedlings using 2.0 µM BA and 1.0 µM IBA, validating the suitability of the developed propagation method for generating disease-free 'Shine Muscat' grapes. These findings offer promising prospects for commercial grape cultivation, ensuring a consistent supply of healthy grapes in the market.

Deep brain stimulation of the anterior nuclei of the thalamus can alleviate seizure severity and induce hippocampal GABAergic neuronal changes in a pilocarpine-induced epileptic mouse brain.

Deep brain stimulation (DBS) of the anterior nucleus of the thalamus (ANT) has been widely used as an effective treatment for refractory temporal lobe epilepsy. Despite its promising clinical outcome, the exact mechanism of how ANT-DBS alleviates seizure severity has not been fully understood, especially at the cellular level. To assess effects of DBS, the present study examined electroencephalography (EEG) signals and locomotor behavior changes and conducted immunohistochemical analyses to examine changes in neuronal activity, number of neurons, and neurogenesis of inhibitory neurons in different hippocampal subregions. ANT-DBS alleviated seizure activity, abnormal locomotor behaviors, reduced theta-band, increased gamma-band EEG power in the interictal state, and increased the number of neurons in the dentate gyrus (DG). The number of parvalbumin- and somatostatin-expressing inhibitory neurons was recovered to the level in DG and CA1 of naïve mice. Notably, BrdU-positive inhibitory neurons were increased. In conclusion, ANT-DBS not only could reduce the number of seizures, but also could induce neuronal changes in the hippocampus, which is a key region involved in chronic epileptogenesis. Importantly, our results suggest that ANT-DBS may lead to hippocampal subregion-specific cellular recovery of GABAergic inhibitory neurons.

A Low-Cost Measurement Methodology for LiDAR Receiver Integrated Circuits.

This paper presents a test methodology to facilitate the measuring processes of LiDAR receiver ICs by avoiding the inherent walk error issue. In a typical LiDAR system, a costly laser diode driver emits narrow light pulses with fast rising edges, and the reflected pulses from targets enter an optical detector followed by an analog front-end (AFE) circuit. Then, the received signals pass through the cascaded amplifiers down to the time-to-digital converter (TDC) that can estimate the detection range. However, this relatively long signal journey leads to the significant decline of rising-edge slopes and the output pulse spreading, thus producing inherent walk errors in LiDAR receiver ICs. Compensation methods requiring complex algorithms and extra chip area have frequently been exploited to lessen the walk errors. In this paper, however, a simpler and lower-cost methodology is proposed to test LiDAR receiver ICs by employing a high-speed buffer and variable delay cells right before the TDC. With these circuits, both START and STOP pulses show very similar pulse shapes, thus effectively avoiding the walk error issue. Additionally, the time interval between two pulses is easily determined by varying the number of the delay cells. Test chips of the proposed receiver IC implemented in a 180-nm CMOS process successfully demonstrate easier and more accurate measurement results.

A CMOS Integrator-Based Clock-Free Time-to-Digital Converter for Home-Monitoring LiDAR Sensors.

This paper presents a nine-bit integrator-based time-to-digital converter (I-TDC) realized in a 180 nm CMOS technology for the applications of indoor home-monitoring light detection and ranging (LiDAR) sensors. The proposed I-TDC exploits a clock-free configuration so as to discard clock-related dynamic power consumption and some notorious issues such as skew, glitch, and synchronization. It consists of a one-dimensional (1D) flash TDC to generate coarse-control codes and an integrator with a peak detection and hold (PDH) circuit to produce fine-control codes. A thermometer-to-binary converter is added to the 1D flash TDC, yielding four-bit coarse codes so that the measured detection range can be represented by nine-bit digital codes in total. Test chips of the proposed I-TDC demonstrate the measured results of the 53 dB dynamic range, i.e., the maximum detection range of 33.6 m and the minimum range of 7.5 cm. The chip core occupies the area of 0.14 × 1.4 mm2, with the power dissipation of 1.6 mW from a single 1.2-V supply.

Enhanced Recognition of Amputated Wrist and Hand Movements by Deep Learning Method Using Multimodal Fusion of Electromyography and Electroencephalography.

Motion classification can be performed using biometric signals recorded by electroencephalography (EEG) or electromyography (EMG) with noninvasive surface electrodes for the control of prosthetic arms. However, current single-modal EEG and EMG based motion classification techniques are limited owing to the complexity and noise of EEG signals, and the electrode placement bias, and low-resolution of EMG signals. We herein propose a novel system of two-dimensional (2D) input image feature multimodal fusion based on an EEG/EMG-signal transfer learning (TL) paradigm for detection of hand movements in transforearm amputees. A feature extraction method in the frequency domain of the EEG and EMG signals was adopted to establish a 2D image. The input images were used for training on a model based on the convolutional neural network algorithm and TL, which requires 2D images as input data. For the purpose of data acquisition, five transforearm amputees and nine healthy controls were recruited. Compared with the conventional single-modal EEG signal trained models, the proposed multimodal fusion method significantly improved classification accuracy in both the control and patient groups. When the two signals were combined and used in the pretrained model for EEG TL, the classification accuracy increased by 4.18-4.35% in the control group, and by 2.51-3.00% in the patient group.

An Indoor-Monitoring LiDAR Sensor for Patients with Alzheimer Disease Residing in Long-Term Care Facilities.

This paper introduces an indoor-monitoring LiDAR sensor for patients with Alzheimer disease residing in long-term care facilities (LTCFs), and this sensor exploits an optoelectronic analog front-end (AFE) to detect light signals from targets by utilizing on-chip avalanche photodiodes (APDs) realized in a 180 nm CMOS process and a neural processing unit (NPU) used for motion detection and decisions, especially for incidents of falls occurring in LTCFs. The AFE consists of an on-chip CMOS P+/N-well APD, a linear-mode transimpedance amplifier, a post-amplifier, and a time-to-digital converter, whereas the NPU exploits network sparsity and approximate processing elements for low-power operation. This work provides a potential solution of low-cost, low-power, indoor-monitoring LiDAR sensors for patients with Alzheimer disease in LTCFs.

Empirical Bayes estimation of pairwise maximum entropy model for nonlinear brain state dynamics.

The pairwise maximum entropy model (pMEM) has recently gained widespread attention to exploring the nonlinear characteristics of brain state dynamics observed in resting-state functional magnetic resonance imaging (rsfMRI). Despite its unique advantageous features, the practical application of pMEM for individuals is limited as it requires a much larger sample than conventional rsfMRI scans. Thus, this study proposes an empirical Bayes estimation of individual pMEM using the variational expectation-maximization algorithm (VEM-MEM). The performance of the VEM-MEM is evaluated for several simulation setups with various sample sizes and network sizes. Unlike conventional maximum likelihood estimation procedures, the VEM-MEM can reliably estimate the individual model parameters, even with small samples, by effectively incorporating the group information as the prior. As a test case, the individual rsfMRI of children with attention deficit hyperactivity disorder (ADHD) is analyzed compared to that of typically developed children using the default mode network, executive control network, and salient network, obtained from the Healthy Brain Network database. We found that the nonlinear dynamic properties uniquely established on the pMEM differ for each group. Furthermore, pMEM parameters are more sensitive to group differences and are better associated with the behavior scores of ADHD compared to the Pearson correlation-based functional connectivity. The simulation and experimental results suggest that the proposed method can reliably estimate the individual pMEM and characterize the dynamic properties of individuals by utilizing empirical information of the group brain state dynamics.

A CMOS Optoelectronic Receiver IC with an On-Chip Avalanche Photodiode for Home-Monitoring LiDAR Sensors.

This paper presents an optoelectronic receiver (Rx) IC with an on-chip avalanche photodiode (APD) realized in a 0.18-µm CMOS process for the applications of home-monitoring light detection and ranging (LiDAR) sensors, where the on-chip CMOS P+/N-well APD was implemented to avoid the unwanted signal distortion from bondwires and electro-static discharge (ESD) protection diodes. Various circuit techniques are exploited in this work, such as the feedforward transimpedance amplifier for high gain, and a limiting amplifier with negative impedance compensation for wide bandwidth. Measured results demonstrate 93.4-dBΩ transimpedance gain, 790-MHz bandwidth, 12-pA/√Hz noise current spectral density, 6.74-µApp minimum detectable signal that corresponds to the maximum detection range of 10 m, and 56.5-mW power dissipation from a 1.8-V supply. This optoelectronic Rx IC provides a potential for a low-cost low-power solution in the applications of home-monitoring LiDAR sensors.

Thermal Ablation and High-Resolution Imaging Using a Back-to-Back (BTB) Dual-Mode Ultrasonic Transducer: In Vivo Results.

We present a back-to-back (BTB) structured, dual-mode ultrasonic device that incorporates a single-element 5.3 MHz transducer for high-intensity focused ultrasound (HIFU) treatment and a single-element 20.0 MHz transducer for high-resolution ultrasound imaging. Ultrasound image-guided surgical systems have been developed for lesion monitoring to ensure that ultrasonic treatment is correctly administered at the right locations. In this study, we developed a dual-element transducer composed of two elements that share the same housing but work independently with a BTB structure, enabling a mode change between therapy and imaging via 180-degree mechanical rotation. The optic fibers were embedded in the HIFU focal region of ex vivo chicken breasts and the temperature change was measured. Images were obtained in vivo mice before and after treatment and compared to identify the treated region. We successfully acquired B-mode and C-scan images that display the hyperechoic region indicating coagulation necrosis in the HIFU-treated volume up to a depth of 10 mm. The compact BTB dual-mode ultrasonic transducer may be used for subcutaneous thermal ablation and monitoring, minimally invasive surgery, and other clinical applications, all with ultrasound only.

An Update on the Role of Nrf2 in Respiratory Disease: Molecular Mechanisms and Therapeutic Approaches.

Nuclear factor erythroid 2-related factor (Nrf2) is a transcriptional activator of the cell protection gene that binds to the antioxidant response element (ARE). Therefore, Nrf2 protects cells and tissues from oxidative stress. Normally, Kelch-like ECH-associated protein 1 (Keap1) inhibits the activation of Nrf2 by binding to Nrf2 and contributes to Nrf2 break down by ubiquitin proteasomes. In moderate oxidative stress, Keap1 is inhibited, allowing Nrf2 to be translocated to the nucleus, which acts as an antioxidant. However, under unusually severe oxidative stress, the Keap1-Nrf2 mechanism becomes disrupted and results in cell and tissue damage. Oxide-containing atmospheric environment generally contributes to the development of respiratory diseases, possibly leading to the failure of the Keap1-Nrf2 pathway. Until now, several studies have identified changes in Keap1-Nrf2 signaling in models of respiratory diseases, such as acute respiratory distress syndrome (ARDS)/acute lung injury (ALI), chronic obstructive pulmonary disease (COPD), idiopathic pulmonary fibrosis (IPF), and asthma. These studies have confirmed that several Nrf2 activators can alleviate symptoms of respiratory diseases. Thus, this review describes how the expression of Keap1-Nrf2 functions in different respiratory diseases and explains the protective effects of reversing this expression.

Activation of Hair Cell Growth Factors by Linoleic Acid in Malva verticillata Seed.

Hair loss by excessive stress from work and lifestyle changes has become a growing concern, particularly among young individuals. However, most drugs for alopecia impose a plethora of side effects. We have found the powerful impact of Malva verticillata seed extracts on alleviating hair loss. This study further isolated effective chemicals in M. verticillata seed extracts by liquid silica gel column chromatography. Under the screening for the growth rate (%) of human follicles dermal papilla cells (HFDPCs), we identified linoleic acid (LA) and oleic acid in n-hexane of M. verticillate (MH)2 fraction. LA treatment activated Wnt/ß-catenin signaling and induced HFDPCs growth by increasing the expression of cell cycle proteins such as cyclin D1 and cyclin-dependent kinase 2. LA treatment also increased several growth factors, such as vascular endothelial growth factor, insulin-like growth factor-1, hepatocyte growth factor, and keratinocyte growth factor, in a dose-dependent manner. Besides, LA significantly inhibited Dickkopf-related protein expression (DKK-1), a primary alopecia signaling by dihydrotestosterone. Our findings suggest that LA treatment may alleviate a testosterone-induced signaling molecule and induces HFDPCs growth by activating Wnt/ß-catenin signaling.

Development of a nitinol-actuated surgical instrument for laparoscopic renal denervation: feasibility test in a swine survival model.

Purpose: In this study, we developed a novel nitinol-actuated surgical instrument to conduct laparoscopic renal denervation for the treatment of resistant hypertension. We investigated whether shape and temperature settings of nitinol specimens fit well into the design goals. Furthermore, we conducted a pilot study to validate the mechanical and physiological performance of nerve ablation without damaging the renal artery.Method: Tensile tests were performed to observe temperature-dependent thermomechanical properties and the original shape of nitinol specimens was set considering our design goal. We performed strain gage experiments to measure bending strain. We developed surgical instrument and operated laparoscopic renal denervation in a swine model. Subsequent impedance spectroscopy experiments were conducted to measure changes in impedance magnitudes during the operation and histological analyses were performed to visualize thermogenic damage to arteries and nerves.Results: Tensile testing showed that the shape memory effect begins above 37 °C. Measured strains on nitinol surfaces were 2.10% ± 0.769%, below the strain limit of 8%. Impedance spectroscopy experiments showed decreases in magnitude in all six trials. After operation of laparoscopic renal denervation following the protocol, renal arteries and nerves were harvested and thermogenic damage was observed in nerves but not arteries.Conclusion: We developed a novel nitinol-actuated surgical instrument with which to perform laparoscopic renal denervation. The feasibility of our device was verified using thermomechanical analyses of nitinol, and assessments of mechanical and physiological performance. Our device could be used in other laparoscopic procedures that require large degrees of freedom while restricting to trocar size.

Feasibility of Powered Intracapsular Tonsillectomy in Pediatric Patients with Tonsil Problem, Including Recurrent Tonsillitis: A Single Surgeon's Experience.

INTRODUCTION: Powered intracapsular tonsillectomy (PIT) is a technique that protects the tonsillar capsule by using a microdebrider, resulting in faster wound-healing and reduced suffering. Many studies have found PIT to be effective, particularly in pediatric patients with obstructive sleep apnea (OSA). However, previous studies have not included patients with a history of recurrent tonsillitis. OBJECTIVE: The aim of this study was to determine the efficacy of PIT in pediatric patients even with a history of recurrent tonsillitis, and therefore, we want to expand the indication for PIT and reveal its safety. METHODS: A total of 886 pediatric patients underwent PIT between February 2013 and March 2016. All patients rated their postoperative pain using a visual analog scale (VAS) and completed the Korean obstructive sleep apnea (KOSA)-18 questionnaire for assessment of their quality of life (QOL). There were 539 males and 347 females. Their mean age was 6.2 years (range 2-14 years). The majority (77.7%) underwent the operation for OSA, and the rest (22.3%) had a history of recurrent tonsillitis. To compare the efficacy of PIT with traditional tonsillectomy, we selected 191 patients who underwent extracapsular tonsillectomy (ECT), a conventional technique, during the same time period. The median follow-up period was 16.7 months. During the follow-up period, instances of delayed bleeding and recurrent pharyngitis were monitored. RESULTS: In comparison to the patients who underwent ECT, the PIT group showed significantly fewer cases of postoperative bleeding (p = 0.027). Thirteen patients in the PIT group (1.5%) visited the hospital during the follow-up period for pharyngitis, while 8 in the ECT group (4.2%) visited for pharyngitis. The mean postoperative pain score, as assessed by a VAS, was 4.6 ± 3.2, and pain improved within an average of 2.9 days after surgery in the PIT group. The mean KOSA-18 score for the QOL of the patients was 65.9 preoperatively and 35.6 postoperatively in the PIT group. CONCLUSIONS: Pediatric tonsillectomy using PIT is valid for reducing postoperative pain and improving the QOL of OSA patients. PIT is also effective and safe for patients with a history of recurrent tonsillitis.

Quantitative Analysis of EEG Power Spectrum and EMG Median Power Frequency Changes after Continuous Passive Motion Mirror Therapy System.

Robotic mirror therapy (MT), which allows movement of the affected limb, is proposed as a more effective method than conventional MT (CMT). To improve the rehabilitation effectiveness of post-stroke patients, we developed a sensory stimulation-based continuous passive motion (CPM)-MT system with two different operating protocols, that is, asynchronous and synchronous modes. To evaluate their effectiveness, we measured brain activation through relative and absolute power spectral density (PSD) changes of electroencephalogram (EEG) mu rhythm in three cases with CMT and CPM-MT with asynchronous and synchronous modes. We also monitored changes in muscle fatigue, which is one of the negative effects of the CPM device, based on median power frequency (MPF) and root mean square (RMS). Relative PSD was most suppressed when subjects used the CPM-MT system under synchronous control: 22.11%, 15.31%, and 16.48% on Cz, C3, and C4, respectively. The absolute average changes in MPF and RMS were 1.59% and 9.78%, respectively, with CPM-MT. Synchronous mode CPM-MT is the most effective method for brain activation, and muscle fatigue caused by the CPM-MT system was negligible. This study suggests the more effective combination rehabilitation system for MT by utilizing CPM and magnetic-based MT task to add action execution and sensory stimulation compared with CMT.

Caviar Extract and Its Constituent DHA Inhibits UVB-Irradiated Skin Aging by Inducing Adiponectin Production.

In this study, caviar (sturgeon eggs) was used to elucidate its roles in adiponectin production and skin anti-aging. Recently, caviar has been largely used not only as a nutritional food, but also in cosmetic products. In particular, it has been reported that docosahexaenoic acid (DHA), as one of the main phospholipid components of caviar extract, induces intracellular lipid accumulation and the expression of adiponectin in adipocytes. Although adipocytes are well known to be associated with the skin dermis by secreting various factors (e.g., adiponectin), the effects of caviar extract and DHA on the skin are not well studied. Here, we demonstrate the effects of caviar extract and DHA on adipocyte differentiation and adiponectin production, resulting in a preventive role in UV-irradiated skin aging. Caviar extract and DHA enhanced adipocyte differentiation and promoted the synthesis of transcription factors controlling adipocyte differentiation and adiponectin. In addition, the mRNA expression levels of matrix metalloproteinase-1 (MMP-1) were decreased in UVB-irradiated Hs68 fibroblasts that were cultured in conditioned medium from caviar extract or DHA-treated differentiated adipocytes. Taken together, these results indicate that caviar extract and DHA induce adipocyte differentiation and adiponectin production, thereby inhibiting UVB-induced premature skin aging via the suppression of MMP-1 production.

7,8-Dimethoxycoumarin stimulates melanogenesis via MAPKs mediated MITF upregulation.

Background: Melanin in the skin is the defense against the harmful UV radiation, which is considered as one of the major risk factors for skin cancer. The compound 7,8-dimethoxycoumarin (DMC, C11H10O4), a natural coumarin molecule present in several medicinal plants, possesses antioxidant and anti-inflammatory activities. However, the mechanism underlying its effects on melanogenesis in melanocytes is unclear. Therefore, we investigated the effect of DMC on melanogenesis activation in B16F10 melanoma cells. Methods: We examined the cytotoxic range of DMC on B16F10 melanoma cells and increased effects of melanogenesis, and intracellular tyrosinase activity. In addition, regulation mechanisms were assessed by Western blot analysis. Results: The results showed that DMC significantly increased melanin content and tyrosinase activity in the cells without being cytotoxic. Furthermore, DMC stimulated the expression of tyrosinase, TRP-1, TRP-2, and MITF thereby activating melanin production and Akt phosphorylation was increased in the Akt signaling pathway. on the contrary, interfering with the phosphorylation of ERK in the MAPKs pathway. Conclusions: These results suggest that DMC may serve as a candidate for potential melanin-producing activator and anti-gray hair applications.

A machine-learning approach to predict postprandial hypoglycemia.

BACKGROUND: For an effective artificial pancreas (AP) system and an improved therapeutic intervention with continuous glucose monitoring (CGM), predicting the occurrence of hypoglycemia accurately is very important. While there have been many studies reporting successful algorithms for predicting nocturnal hypoglycemia, predicting postprandial hypoglycemia still remains a challenge due to extreme glucose fluctuations that occur around mealtimes. The goal of this study is to evaluate the feasibility of easy-to-use, computationally efficient machine-learning algorithm to predict postprandial hypoglycemia with a unique feature set. METHODS: We use retrospective CGM datasets of 104 people who had experienced at least one hypoglycemia alert value during a three-day CGM session. The algorithms were developed based on four machine learning models with a unique data-driven feature set: a random forest (RF), a support vector machine using a linear function or a radial basis function, a K-nearest neighbor, and a logistic regression. With 5-fold cross-subject validation, the average performance of each model was calculated to compare and contrast their individual performance. The area under a receiver operating characteristic curve (AUC) and the F1 score were used as the main criterion for evaluating the performance. RESULTS: In predicting a hypoglycemia alert value with a 30-min prediction horizon, the RF model showed the best performance with the average AUC of 0.966, the average sensitivity of 89.6%, the average specificity of 91.3%, and the average F1 score of 0.543. In addition, the RF showed the better predictive performance for postprandial hypoglycemic events than other models. CONCLUSION: In conclusion, we showed that machine-learning algorithms have potential in predicting postprandial hypoglycemia, and the RF model could be a better candidate for the further development of postprandial hypoglycemia prediction algorithm to advance the CGM technology and the AP technology further.

Deep ECG-Respiration Network (DeepER Net) for Recognizing Mental Stress.

Unmanaged long-term mental stress in the workplace can lead to serious health problems and reduced productivity. To prevent this, it is important to recognize and relieve mental stress in a timely manner. Here, we propose a novel stress detection algorithm based on end-to-end deep learning using multiple physiological signals, such as electrocardiogram (ECG) and respiration (RESP) signal. To mimic workplace stress in our experiments, we used Stroop and math tasks as stressors, with each stressor being followed by a relaxation task. Herein, we recruited 18 subjects and measured both ECG and RESP signals using Zephyr BioHarness 3.0. After five-fold cross validation, the proposed network performed well, with an average accuracy of 83.9%, an average F1 score of 0.81, and an average area under the receiver operating characteristic (ROC) curve (AUC) of 0.92, demonstrating its superiority over conventional machine learning models. Furthermore, by visualizing the activation of the trained network's neurons, we found that they were activated by specific ECG and RESP patterns. In conclusion, we successfully validated the feasibility of end-to-end deep learning using multiple physiological signals for recognition of mental stress in the workplace. We believe that this is a promising approach that will help to improve the quality of life of people suffering from long-term work-related mental stress.