BACKGROUND/OBJECTIVES:Deep learning models for digital mammography sensor data are increasingly deployed across hospitals using different X-ray detector technologies and patient populations. Whether models trained on one sensor platform and population maintain accuracy when transferred to another has not been tested for the latest generation of mammography-specific foundation models under one controlled protocol. METHODS:We fine-tuned five backbone architectures (ResNet-50, DINOv2-B14, Rad-DINO, Mammo-CLIP B5, and Mammo-FM) on CBIS-DDSM (film-digitized, USA, n = 714 validation) with three seeds, ablated a density-aware focal loss across three auxiliary weights, and evaluated transfer to three external sensor cohorts: CMMD (full-field digital, China, n = 1032), DMID (mixed digital, India, n = 509), and MIAS (film-digitized, UK, n = 322). Significance used paired DeLong z-tests with Benjamini-Hochberg FDR correction; temperature scaling tested post hoc recalibration at all transfer targets. RESULTS:Within this single-source three-seed evaluation, ResNet-50 outperformed all four foundation models on CBIS-DDSM (AUC 0.867 vs. 0.847, 0.846, 0.813, and 0.703; all gaps p_adj < 0.05). The density-aware focal loss degraded both AUC and calibration at every weight tested. At transfer, every model lost 0.165 to 0.320 AUC points relative to in-distribution performance, with sensitivity at 95% specificity collapsing from 0.31 to 0.47 in-distribution to 0.11 to 0.22 across the three external targets. A per-seed Stouffer meta-analysis confirms that Mammo-CLIP B5 and Mammo-FM significantly outperformed ResNet-50 on DMID and Mammo-CLIP on CMMD, after BH-FDR; MIAS comparisons remained directional only. In the extremely dense subgroup (BI-RADS D4), Mammo-FM reached AUC 0.870 versus ResNet-50 at 0.842, a directional observation whose 95% CIs overlap heavily at the n = 140 sample size and which we do not interpret as a statistically supported advantage. CONCLUSIONS:In this single training-source, three-seed protocol, mammography-specific pretraining did not deliver the in-distribution AUC premium reported in the originating papers, and no architecture reached a level at which transfer deployment without local validation would be defensible. We frame these as observations specific to the present protocol rather than as broader conclusions about foundation models for mammography classification. The findings argue for sensor-stratified and population-stratified external validation and for local recalibration as practical prerequisites before clinical use. Code and weights are released under MIT license.

Accurate estimation of crack distance is critical for railway safety and structural health monitoring. This paper proposes a Skip-Feedback Neural Network (SFNN) for single-sensor acoustic emission (AE)-based crack distance estimation in railway rails. Unlike conventional multi-sensor or high-cost inspection systems, the proposed framework employs a single AE sensor together with entropy-based signal representations to capture distance-dependent crack characteristics under noisy operating conditions. The SFNN integrates learnable skip and feedback pathways to enhance feature reuse, stabilize gradient propagation, and improve robustness against signal attenuation. Experimental evaluation was performed using controlled pencil-lead break simulations at multiple crack-to-sensor distances, as well as field measurements at real crack locations validated by phased-array ultrasonic testing. Results demonstrate that the proposed SFNN consistently outperforms baseline neural-network models across different distance ranges. The proposed framework offers a cost-efficient, noise-resilient, and scalable solution for AE-based railway crack monitoring and future structural health-monitoring applications.

Monolithic zirconia restorations are frequently affected by the unnoticed growth of subcritical cracks, a failure process that is not captured by traditional imaging methods like radiographs and ultrasounds in sophisticated dental architectures. To address this evaluative inadequacy, this research introduces a hierarchical deep learning framework for microcrack detection and spatial localization. We promote a hierarchical deep learning system that integrates Acoustic Emission (AE) detection alongside signal processing. Raw AE signals utilized during dynamic loading are enhanced via Kalman filtering and Continuous Wavelet Transform (CWT) to construct high-fidelity time-frequency scalograms. The diagnostic pipeline operates in two stages: first, a hybrid CNN-BiGRU network with temporal attention fulfills zirconia component-level classification; second, a ResNet-18 backbone integrated with Bidirectional LSTM and Multi-Head Attention precisely localizes defects across five anatomical crown regions. This hierarchical design effectively captures the non-stationary, transient nature of fracture-induced stress waves. The framework achieved an F1-score of 99.00% and an AUC of 0.994, significantly outperforming conventional convolutional networks. By enabling predictive maintenance through early, non-invasive damage localization, this study demonstrates a promising laboratory framework for AE-based crack detection in zirconia dental structures and prosthetics and toward enhanced clinical reliability in digital dentistry.

Railway infrastructure security is contingent upon the prompt identification of structural anomalies within steel tracks. This research establishes a framework that merges acoustic emission (AE) sensing with advanced machine learning for prompt fracture identification and location. To improve the quality of Raw AE signals, they are first cleaned using Kalman filtering to tackle environmental disturbances and ambiguous readings. The characteristics that arise from entropy comprising approximate entropy, Shannon entropy, and dimensional entropy are derived to delineate the temporal patterns of fracture-induced emissions. Density-based spatial clustering of applications with noise (DBSCAN) is applied to remove outliers during preprocessing. Long short-term memory (LSTM) networks classify crack locations into three anatomical regions: rail head, web, and foot. Experimental validation with 3,000 labeled AE signals (1,000 per class) under laboratory conditions, the full pipeline that integrates Kalman filtering, entropy features, DBSCAN, and an LSTM classifier attains an accuracy of 98.83%. With an entropy-based variant, the accuracy drops to 96.67%, confirming the incremental value of temporal denoising and outlier rejection. While using mel-frequency cepstral coefficient (MFCC) baseline achieves 97.67% accuracy, a deep neural network (DNN) trained on Kalman-filtered, entropy-based, and DBSCAN-processed inputs reaches 96.33% accuracy, underscoring the advantages of temporal modeling for AE. A GRU using the same Kalman-filtered, entropy-based, and DBSCAN-processed inputs, achieves 97.67% accuracy, but trails the LSTM overall. When deployed on actual railway lines with a mobile inspection platform, the system maintained robust performance, correctly identifying 84.67% of cracks at 3 km/h and 80.67% at 5 km/h. The LSTM configuration consistently outperformed all alternative approaches, including the entropy-only variant, MFCC-based method, DNN classifier, and GRU model. This confirms the LSTM’s enhanced capability to capture the temporal dynamics of AE signals, establishing it as the most effective framework for AE-based crack localization in railway structural health monitoring.

Radio frequency interference (RFI) segmentation in Ku-band satellite communications remains challenging because of weak, non-stationary interference characteristics and the scarcity of pixel-level annotated empirical data. To address this limitation, this study proposes a synthetic-to-real deep learning framework in which four parameterized RFI morphologies—narrowband, broadband, impulsive, and frequency-varying—are superimposed onto empirical Ku-band spectrogram backgrounds acquired from a 12-m ground-station platform. A conditional Generative Adversarial Network (cGAN) is then employed for domain adaptation to reduce the synthetic-to-real gap by harmonizing the hybrid spectrograms with empirical thermal noise characteristics. The refined spectrograms and their exact binary masks are subsequently used to train a U-Net model for pixel-level segmentation. Quantitative evaluation on held-out empirical-background hybrid test data shows that the proposed framework achieves an Intersection over Union (IoU) of 0.849 and an F1-score of 0.918, outperforming traditional threshold-based methods and unrefined learning baselines. Additional qualitative validation on naturally observed empirical Ku-band RFI recordings further supports the practical applicability of the proposed framework beyond controlled hybrid test data. These results indicate that generative domain adaptation provides a practical and scalable alternative to manual labeling for automated RFI monitoring in operational Ku-band environments.

Sleep-related respiratory disturbances are difficult to monitor continuously outside specialized laboratories because conventional polysomnography is resource-intensive and intrusive. This study presents a contactless edge-AI engineering prototype for detecting controlled voluntary respiratory-motion suppression and motion artifacts using a 60 GHz frequency-modulated continuous-wave radar. The system integrates a 60 GHz radar front end, lightweight local preprocessing, an INT8 one-dimensional convolutional neural network deployed on the Analog Devices MAX78000 CNN accelerator (Analog Devices Thailand, Chon Buri, Thailand), and an event-driven Raspberry Pi Zero 2W gateway for alert transmission. Evaluation was performed using a controlled healthy-volunteer dataset consisting of normal breathing, voluntary breath-holding-induced respiratory suppression, and deliberate motion artifact. The final valid test set contained 270 technically valid 30 s windows balanced across the three classes. The INT8 model achieved an overall accuracy of 92.6% (95% confidence interval: 88.8–95.2%), with a macro-averaged precision, recall, and F1-score of 92.6%, 92.6%, and 92.5%, respectively. Active CNN inference on the MAX78000 consumed 0.152 ± 0.011 mJ and was completed in 5.20 ± 0.11 ms, corresponding to approximately 280-fold lower active inference energy than Python 3.14.6/TensorFlow Lite 2.21.0-based execution on the Raspberry Pi Zero 2W. These results demonstrate the feasibility of privacy-aware, low-power respiratory-pattern classification at the edge. However, the study should be interpreted strictly as an engineering proof-of-concept based on controlled voluntary breathing and movement tasks in healthy volunteers. It is not a clinically validated apnea or obstructive sleep apnea detection system and did not include polysomnography, oxygen saturation measurement, airflow sensing, sleep staging, or diagnosed patient cohorts.

Satellite communication systems experience significant signal degradation during rain events, a phenomenon that can be leveraged for meteorological applications. This study introduces a novel hybrid machine learning framework combining unsupervised clustering with cluster-specific supervised deep learning models to transform satellite signal attenuation into a predictive tool for rainfall prediction. Unlike conventional single-model approaches treating all atmospheric conditions uniformly, our methodology employs K-Means Clustering with the Elbow Method to identify four distinct atmospheric regimes based on Signal-to-Noise Ratio (SNR) patterns from a 12-m Ku-band satellite ground station at King Mongkut’s Institute of Technology Ladkrabang (KMITL), Bangkok, Thailand, combined with absolute pressure and hourly rainfall measurements. The dataset comprises 98,483 observations collected with 30-s temporal resolutions, providing comprehensive coverage of diverse tropical atmospheric conditions. The experimental platform integrates three subsystems: a receiver chain featuring a Low-Noise Block (LNB) converter and Software-Defined Radio (SDR) platform for real-time data acquisition; a control system with two-axis motorized pointing incorporating dual-encoder feedback; and a preprocessing workflow implementing data cleaning, K-Means Clustering (k = 4), Synthetic Minority Over-Sampling Technique (SMOTE) for balanced representation, and standardization. Specialized Long Short-Term Memory (LSTM) networks trained for each identified cluster enable capture of regime-specific temporal dynamics. Experimental validation demonstrates substantial performance improvements, with cluster-specific LSTM models achieving R2 values exceeding 0.92 across all atmospheric regimes. Comparative analysis confirms LSTM superiority over RNN and GRU. Classification performance evaluation reveals exceptional detection capabilities with Probability of Detection ranging from 0.75 to 0.99 and False Alarm Ratios below 0.23. This work presents a scalable approach to weather radar systems for tropical regions with limited ground-based infrastructure, particularly during rapid meteorological transitions characteristic of tropical climates.

This research presents an innovative transportation safety system integrating millimeter-wave radar sensing with artificial intelligence. Our approach employs the MR60BHA1 radar sensor mounted behind the driver's seat to non-intrusively monitor vital signs, combined with deep learning algorithms that analyze correlations between heart rate variability, respiratory patterns, body movements, and environmental factors. Trained on Thailand's first comprehensive driver fatigue database, our custom neural network architecture achieved 97.5% detection accuracy, significantly outperforming traditional single parameter monitoring approaches. The research contributes three key innovations: (1) a novel deep learning framework optimized for Thai driving conditions that correlates multiple radar-derived physiological parameters; (2) an adaptive feature extraction algorithm that identifies and weights the most significant fatigue indicators based on individual characteristics and local contexts; and (3) a comprehensive multiparameter database incorporating synchronized measurements calibrated for various Thai driving environments. This culturally adaptive monitoring technology establishes a new paradigm for intelligent transportation systems particularly suited for tropical regions.

Radio astronomy requires precise target localization and tracking to ensure accurate observations. Conventional regulation methodologies, encompassing PID controllers, frequently encounter difficulties due to orientation inaccuracies precipitated by mechanical limitations, environmental fluctuations, and electromagnetic interferences. To tackle these obstacles, this investigation presents a reinforcement learning (RL)-oriented framework for high-accuracy monitoring in radio telescopes. The suggested system amalgamates a localization control module, a receiver, and an RL tracking agent that functions in scanning and tracking stages. The agent optimizes its policy by maximizing the signal-to-noise ratio (SNR), a critical factor in astronomical measurements. The framework employs a reconditioned 12-m radio telescope at King Mongkut’s Institute of Technology Ladkrabang (KMITL), originally constructed as a satellite earth station antenna for telecommunications and was subsequently refurbished and adapted for radio astronomy research. It incorporates dual-axis servo regulation and high-definition encoders. Real-time SNR data and streaming are supported by a HamGeek ZedBoard with an AD9361 software-defined radio (SDR). The RL agent leverages the Proximal Policy Optimization (PPO) algorithm with a self-attention actor–critic model, while hyperparameters are tuned via Optuna. Experimental results indicate strong performance, successfully maintaining stable tracking of randomly moving, non-patterned targets for over 4 continuous hours without any external tracking assistance, while achieving an SNR improvement of up to 23.5% compared with programmed TLE-based tracking during live satellite experiments with Thaicom-4. The simplicity of the framework, combined with its adaptability and ability to learn directly from environmental feedback, highlights its suitability for next-generation astronomical techniques in radio telescope surveys, radio line observations, and time-domain astronomy. These findings underscore RL’s potential to enhance telescope tracking accuracy and scalability while reducing control system complexity for dynamic astronomical applications.

In the rapidly evolving domain of Unmanned Aerial Vehicles (UAVs), precise altitude estimation remains a significant challenge, particularly for lightweight UAVs. This research presents an innovative approach to enhance altitude estimation accuracy for UAVs weighing under 2 kg without cameras, utilizing advanced AI Deep Learning algorithms. The primary novelty of this study lies in its unique integration of unsupervised and supervised learning techniques. By synergistically combining K-Means Clustering with a multiple-input deep learning regression-based model (DL-KMA), we have achieved substantial improvements in altitude estimation accuracy. This methodology represents a significant advancement over conventional approaches in UAV technology. Our experimental design involved comprehensive field data collection across two distinct altitude environments, employing a high-precision Digital Laser Distance Meter as the reference standard (Class II). This rigorous approach facilitated a thorough evaluation of our model’s performance across varied terrains, ensuring robust and reliable results. The outcomes of our study are particularly noteworthy, with the model demonstrating remarkably low Mean Squared Error (MSE) values across all data clusters, ranging from 0.011 to 0.072. These results not only indicate significant improvements over traditional methods, but also establish a new benchmark in UAVs altitude estimation accuracy. A key innovation in our approach is the elimination of costly additional hardware such as Light Detection and Ranging (LiDAR), offering a cost-effective, software-based solution. This advancement has broad implications, enhancing the accessibility of advanced UAVs technology and expanding its potential applications across diverse sectors including precision agriculture, urban planning, and emergency response. This research represents a significant contribution to the integration of AI and UAVs technology, potentially unlocking new possibilities in UAVs applications. By enhancing the capabilities of lightweight UAVs, we are not merely improving a technical aspect, but revolutionizing the potential applications of UAVs across industries. Our work sets the stage for safer, more reliable, and precise UAVs operations, marking a pivotal moment in the evolution of aerial technology in an increasingly UAV-dependent world.

This work presents a novel approach utilizing continuous wavelet transform and deep learning for pattern recognition and classification of generated cracked signals. The research employs a smart sensing data acquisition system in a non-destructive manner, utilizing dual acoustic emission (AE) sensor to determine the specific cracked position at the crown surface. An AE data acquisition module is used to transform the AE signals captured by the AE sensor into.csv data, which is then subjected to denoising utilizing band stop and Bayesian filters to eliminate background noise. Subsequently, the denoised data are processed and classified using an algorithmic model called SqueezeNet, which facilitates the accurate localization of cracks in the Monolithic crown. For the purpose of training and validating the algorithmic model, the study uses AE signals produced by pencil lead breaking (PLB) at the incisal, labial, palatal, left, and right sides of the crown. In order to make it easier to identify the sources of AE signals resulting from PLB-induced AE events, wavelet transform (WT) is used to assess the location of the crown in respect to AE signals. AE signals are divided into two categories and the algorithm’s accuracy in classifying them is assessed during the training and testing stages. With a total accuracy of $\mathbf{9 6 . 5 \%}$, the deep learning-powered AE approach successfully detects flaws on the dental crown surfaces. The integration of a dual AE sensor with a SqueezeNet algorithm based on AE signals sets this study apart, offering an automated and efficient solution for early cracked detection in dental crowns for prototype clinical dental restorative crack identification.

The feasibility of utilizing the acoustic emission (AE) technique for the detection and classification of cracks within monolithic dental crown is assessed in this study, owing to its non-destructive nature which enables passive monitoring of structures. The AE signals captured are subjected to analysis to extract pertinent information regarding the source and location of the cracks. A novel approach is proposed, employing deep learning 1D convolutional neural networks (1D-CNNs) for the recognition and classification of the recorded cracked signals. The AE signals, obtained through a handmade AE data acquisition unit, are converted into .csv format and subjected to denoising using Bayesian methods to eliminate background noise. The signals are collected through the breakage of pencil lead (Vallen systeme) Hsu-Nielsen-Source 0.5 (ASTM E976) applied to each surface of the dental crown. Subsequently, the data signals are divided into training and testing groups following an $85 / 15$ split. The performance of the deep learning 1D-CNNs is evaluated based on Precision, Recall and total accuracy metrics. The applicated of automated deep learning in this study demonstrated significantly high overall accuracy ($98.67 \%$). The integration of handmade data acquisition with 1D-CNN crack detection proves to be an effective method for early screening. The novel method harnesses acoustic emission signals in 1D-CNNs, thereby enhancing the accuracy of clinical dental restorative crack identification and determining the onset time.

This research focuses on investigating glucose meters utilizing metamaterial microwave sensors. The metamaterial microwave sensor is designed with a strip line loaded with a complementary split ring. The sensor is designed to conduct Ansys high‐frequency structure simulator and uses conductor material coated on a hydrocarbon ceramic laminate (Roger RO4232) substrate, with a sweep frequency range of 1–6 GHz. The signal of the metamaterial microwave sensor depends on the change in glucose permittivity and conductivity when the glucose concentration changes. The research involves designing a simulation model to explore the impact of complementary split ring size on the sensor's response to changes in glucose permittivity. Additionally, experiments are conducted using the proposed sensor to measure glucose concentration in solution, aiming to analyze trends in sensor response to varying concentrations of glucose and evaluate its sensitivity to changes in glucose concentration. The experimental results indicate that the metamaterial microwave sensor is able to respond to variations in glucose level, a sensitivity of the proposed sensor is 0.0345 dB (mg dL−1)−1 in range of 0–110 mg dL−1 with R2 0.9628.

Monolithic zirconia (MZ) crowns are widely utilized in dental restorations, particularly for substantial tooth structure loss. Inspection, tactile, and radiographic examinations can be time-consuming and error-prone, which may delay diagnosis. Consequently, an objective, automatic, and reliable process is required for identifying dental crown defects. This study aimed to explore the potential of transforming acoustic emission (AE) signals to continuous wavelet transform (CWT), combined with Conventional Neural Network (CNN) to assist in crack detection. A new CNN image segmentation model, based on multi-class semantic segmentation using Inception-ResNet-v2, was developed. Real-time detection of AE signals under loads, which induce cracking, provided significant insights into crack formation in MZ crowns. Pencil lead breaking (PLB) was used to simulate crack propagation. The CWT and CNN models were used to automate the crack classification process. The Inception-ResNet-v2 architecture with transfer learning categorized the cracks in MZ crowns into five groups: labial, palatal, incisal, left, and right. After 2000 epochs, with a learning rate of 0.0001, the model achieved an accuracy of 99.4667%, demonstrating that deep learning significantly improved the localization of cracks in MZ crowns. This development can potentially aid dentists in clinical decision-making by facilitating the early detection and prevention of crack failures.

This research proposes augmenting cropped computed tomography (CT) slices with data attributes to enhance the performance of a deep-learning-based automatic left-femur segmentation scheme. The data attribute is the lying position for the left-femur model. In the study, the deep-learning-based automatic left-femur segmentation scheme was trained, validated, and tested using eight categories of CT input datasets for the left femur (F-I–F-VIII). The segmentation performance was assessed by Dice similarity coefficient (DSC) and intersection over union (IoU); and the similarity between the predicted 3D reconstruction images and ground-truth images was determined by spectral angle mapper (SAM) and structural similarity index measure (SSIM). The left-femur segmentation model achieved the highest DSC (88.25%) and IoU (80.85%) under category F-IV (using cropped and augmented CT input datasets with large feature coefficients), with an SAM and SSIM of 0.117–0.215 and 0.701–0.732. The novelty of this research lies in the use of attribute augmentation in medical image preprocessing to enhance the performance of the deep-learning-based automatic left-femur segmentation scheme.

This research proposes preprocessing techniques for computed tomography (CT) slices with the aim of improving the performance of a deep-learning segmentation model (U-Net model). The preprocessing techniques used in this study include window leveling, histogram equalization, Gaussian blurring, and cropping (incorporating mathematical morphology and histogram projection). The U-Net model is applied to three groups of input data sets (B-I to B-III) for training, validation, and testing. The segmentation performance is evaluated using metrics such as Dice similarity coefficient (DSC) and intersection over union (IoU). The trained U-Net model achieves the highest DSC (95.15%) and IoU (91.09%) under B-III dataset, utilizing cropped and enhanced CT input datasets. Window leveling, histogram equalization, Gaussian blurring, and cropping are identified as the optimal preprocessing techniques for bladder segmentation. This novel research applies diverse image processing techniques in medical image preprocessing to enhance the deep-learning U-Net model's segmentation performance.

This study introduces an innovation non-destructive approach employing dual-sensor acoustic emission (AE) techniques to detect and accurately locate cracks within monolith dental crowns, even when subjected to various load directions. Throughout the process, the AE sensor recorded AE signals that were subsequently converted into .csv data using an AE data acquisition module. Afterward, these digital records underwent denoising to eliminate background and contact-related disturbances. Subsequently, the noise-filtered data underwent processing and classification via a deep learning algorithmic model, enabling accurate localization of cracks within the dental crown. The study utilized AE signals generated by pencil lead breakage (PLB) at the labial, left, palatal, and right surfaces of dental crown for both training and testing of the algorithmic model. Initially, wavelet transform (WT) was employed to analyze and examine the dental crown's location in relation to AE signals. The approach was introduced to precisely identify the sources of AE signals originating from PLB-induced AE events. During the algorithm's training and testing phases, the AE signals were categorized into two groups, and the accuracy of their classification was evaluated. The deep learning-powered AE strategy successfully identified cracks within the dental crown. The total accuracy was 90.625%. This study's innovation resides in its utilization of a dual AE sensor combined with a deep learning algorithm based on AE signals. This combination effectively detects and precisely locates cracks within dental crowns. In contrast to current AE crack-localization methods that depend on human interpretation in radiographic examination, this approach offers an automated and more efficient solution.

This paper proposed to insert additional feature into input datasets (i.e., CT scans) for automatic femur segmentation model, U-Net, with respect to increase the accuracy of model performance. An additional feature is available reference information representing identity on each CT scans and has an effect on results of deep learning model training. In this experiment, choose the left-femur as the target organ, which is common organs-at-risk (OARs) for lower abdominal cancers. The automatic femur segmentation model training was separately executed through two different datasets, one cropped-dataset with additional feature and one original dimension dataset without additional feature. For additional feature, lying posture of patient when entered the CT scanner was selected. The performance results of both trained U-Net models were compered in order to observe the difference of effect. Evaluation results reported that the additional feature could increase an accuracy and precision including support prediction for the left-femur segmentation, with the Dice Similarity Coefficient (DSC) of 61.573% and Intersection Over Union (IoU) of 45.621%, respectively. Specifically, deep learning combining additional feature insertion on cropped-datasets was the novelty in this experiment to effectively segment the left femur.

This research proposes a multiple-input deep learning-driven ion-sensitive field-effect transistor (ISFET) scheme to predict the concentrations of carbaryl pesticide. In the study, the carbaryl concentrations are varied between 1 × 10−7–1 × 10−3 M, and the temperatures of solutions between 20–35 °C. To validate the multiple-input deep learning regression model, the proposed ISFET scheme is deployed onsite (a field test) to measure pesticide concentrations in the carbaryl-spiked vegetable extract. The advantage of this research lies in the use of a deep learning algorithm with an ISFET sensor to effectively predict the pesticide concentrations, in addition to improving the prediction accuracy. The results demonstrate the very high predictive ability of the proposed ISFET scheme, given an MSE, MAE, and R2 of 0.007%, 0.016%, and 0.992, respectively. The proposed multiple-input deep learning regression model with signal compensation is applicable to a wide range of solution temperatures which is convenient for onsite measurement. Essentially, the proposed multiple-input deep learning regression model could be adopted as an effective alternative to the conventional statistics-based regression to predict pesticide concentrations.