A new hybrid algorithm for intelligent detection of sudden decline syndrome of date palm disease.

Date palm is an important domestic cash crop in most countries. Sudden Decline Syndrome (SDS) causes a huge loss to the crop both in quality and quantity. The literature reports the significance of early detection of disease towards preventive measures to improve the quality of the crop. The number of prevailing detection methods limits to consideration of a certain aspect of disease identification. This study proposes a new hybrid fuzzy fast multi-Otsu K-Means (FFMKO) algorithm integrating the date palm image enhancement, robust thresholding, and optimal clustering for significant disease identification. The algorithm adopts a multi-operator image resizing cost function based on image energy and the dominant color descriptor, the adaptive Fuzzy noise filter, and Otsu image thresholding combined with K-Means clustering enhancements. Besides, we validate the process with histogram equalization and threshold transformation towards enhanced color feature extraction of date palm images. The algorithm authenticates findings on a local dataset of 3293 date palm images and, on a benchmarked data set as well. It achieves an accuracy of 94.175% for successful detection of SDS that outperforms the existing similar algorithms. The impactful findings of this study assure the fast and authentic detection of the disease at an earlier stage to uplift the quality and quantity of the date palm and boost the agriculture-based economy.

A Machine Learning-Based Severity Prediction Tool for the Michigan Neuropathy Screening Instrument.

Diabetic sensorimotor polyneuropathy (DSPN) is a serious long-term complication of diabetes, which may lead to foot ulceration and amputation. Among the screening tools for DSPN, the Michigan neuropathy screening instrument (MNSI) is frequently deployed, but it lacks a straightforward rating of severity. A DSPN severity grading system has been built and simulated for the MNSI, utilizing longitudinal data captured over 19 years from the Epidemiology of Diabetes Interventions and Complications (EDIC) trial. Machine learning algorithms were used to establish the MNSI factors and patient outcomes to characterise the features with the best ability to detect DSPN severity. A nomogram based on multivariable logistic regression was designed, developed and validated. The extra tree model was applied to identify the top seven ranked MNSI features that identified DSPN, namely vibration perception (R), 10-gm filament, previous diabetic neuropathy, vibration perception (L), presence of callus, deformities and fissure. The nomogram's area under the curve (AUC) was 0.9421 and 0.946 for the internal and external datasets, respectively. The probability of DSPN was predicted from the nomogram and a DSPN severity grading system for MNSI was created using the probability score. An independent dataset was used to validate the model's performance. The patients were divided into four different severity levels, i.e., absent, mild, moderate, and severe, with cut-off values of 10.50, 12.70 and 15.00 for a DSPN probability of less than 50, 75 and 100%, respectively. We provide an easy-to-use, straightforward and reproducible approach to determine prognosis in patients with DSPN.

Nomogram-Based Chronic Kidney Disease Prediction Model for Type 1 Diabetes Mellitus Patients Using Routine Pathological Data.

Type 1 diabetes mellitus (T1DM) patients are a significant threat to chronic kidney disease (CKD) development during their life. However, there is always a high chance of delay in CKD detection because CKD can be asymptomatic, and T1DM patients bypass traditional CKD tests during their routine checkups. This study aims to develop and validate a prediction model and nomogram of CKD in T1DM patients using readily available routine checkup data for early CKD detection. This research utilized 1375 T1DM patients' sixteen years of longitudinal data from multi-center Epidemiology of Diabetes Interventions and Complications (EDIC) clinical trials conducted at 28 sites in the USA and Canada and considered 17 routinely available features. Three feature ranking algorithms, extreme gradient boosting (XGB), random forest (RF), and extremely randomized trees classifier (ERT), were applied to create three feature ranking lists, and logistic regression analyses were performed to develop CKD prediction models using these ranked feature lists to identify the best performing top-ranked features combination. Finally, the most significant features were selected to develop a multivariate logistic regression-based CKD prediction model for T1DM patients. This model was evaluated using sensitivity, specificity, accuracy, precision, and F1 score on train and test data. A nomogram of the final model was further generated for easy application in clinical practices. Hypertension, duration of diabetes, drinking habit, triglycerides, ACE inhibitors, low-density lipoprotein (LDL) cholesterol, age, and smoking habit were the top-8 features ranked by the XGB model and identified as the most important features for predicting CKD in T1DM patients. These eight features were selected to develop the final prediction model using multivariate logistic regression, which showed 90.04% and 88.59% accuracy in internal and test data validation. The proposed model showed excellent performance and can be used for CKD identification in T1DM patients during routine checkups.

An Automatic Premature Ventricular Contraction Recognition System Based on Imbalanced Dataset and Pre-Trained Residual Network Using Transfer Learning on ECG Signal.

The development of automatic monitoring and diagnosis systems for cardiac patients over the internet has been facilitated by recent advancements in wearable sensor devices from electrocardiographs (ECGs), which need the use of patient-specific approaches. Premature ventricular contraction (PVC) is a common chronic cardiovascular disease that can cause conditions that are potentially fatal. Therefore, for the diagnosis of likely heart failure, precise PVC detection from ECGs is crucial. In the clinical settings, cardiologists typically employ long-term ECGs as a tool to identify PVCs, where a cardiologist must put in a lot of time and effort to appropriately assess the long-term ECGs which is time consuming and cumbersome. By addressing these issues, we have investigated a deep learning method with a pre-trained deep residual network, ResNet-18, to identify PVCs automatically using transfer learning mechanism. Herein, features are extracted by the inner layers of the network automatically compared to hand-crafted feature extraction methods. Transfer learning mechanism handles the difficulties of required large volume of training data for a deep model. The pre-trained model is evaluated on the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) Arrhythmia and Institute of Cardiological Technics (INCART) datasets. First, we used the Pan-Tompkins algorithm to segment 44,103 normal and 6423 PVC beats, as well as 106,239 normal and 9987 PVC beats from the MIT-BIH Arrhythmia and IN-CART datasets, respectively. The pre-trained model employed the segmented beats as input after being converted into 2D (two-dimensional) images. The method is optimized with the using of weighted random samples, on-the-fly augmentation, Adam optimizer, and call back feature. The results from the proposed method demonstrate the satisfactory findings without the using of any complex pre-processing and feature extraction technique as well as design complexity of model. Using LOSOCV (leave one subject out cross-validation), the received accuracies on MIT-BIH and INCART are 99.93% and 99.77%, respectively, suppressing the state-of-the-art methods for PVC recognition on unseen data. This demonstrates the efficacy and generalizability of the proposed method on the imbalanced datasets. Due to the absence of device-specific (patient-specific) information at the evaluating stage on the target datasets in this study, the method might be used as a general approach to handle the situations in which ECG signals are obtained from different patients utilizing a variety of smart sensor devices.

Machine Learning-Based Epileptic Seizure Detection Methods Using Wavelet and EMD-Based Decomposition Techniques: A Review.

Epileptic seizures are temporary episodes of convulsions, where approximately 70 percent of the diagnosed population can successfully manage their condition with proper medication and lead a normal life. Over 50 million people worldwide are affected by some form of epileptic seizures, and their accurate detection can help millions in the proper management of this condition. Increasing research in machine learning has made a great impact on biomedical signal processing and especially in electroencephalogram (EEG) data analysis. The availability of various feature extraction techniques and classification methods makes it difficult to choose the most suitable combination for resource-efficient and correct detection. This paper intends to review the relevant studies of wavelet and empirical mode decomposition-based feature extraction techniques used for seizure detection in epileptic EEG data. The articles were chosen for review based on their Journal Citation Report, feature selection methods, and classifiers used. The high-dimensional EEG data falls under the category of '3N' biosignals-nonstationary, nonlinear, and noisy; hence, two popular classifiers, namely random forest and support vector machine, were taken for review, as they are capable of handling high-dimensional data and have a low risk of over-fitting. The main metrics used are sensitivity, specificity, and accuracy; hence, some papers reviewed were excluded due to insufficient metrics. To evaluate the overall performances of the reviewed papers, a simple mean value of all metrics was used. This review indicates that the system that used a Stockwell transform wavelet variant as a feature extractor and SVM classifiers led to a potentially better result.

Performance Analysis of Conventional Machine Learning Algorithms for Identification of Chronic Kidney Disease in Type 1 Diabetes Mellitus Patients.

Chronic kidney disease (CKD) is one of the severe side effects of type 1 diabetes mellitus (T1DM). However, the detection and diagnosis of CKD are often delayed because of its asymptomatic nature. In addition, patients often tend to bypass the traditional urine protein (urinary albumin)-based CKD detection test. Even though disease detection using machine learning (ML) is a well-established field of study, it is rarely used to diagnose CKD in T1DM patients. This research aimed to employ and evaluate several ML algorithms to develop models to quickly predict CKD in patients with T1DM using easily available routine checkup data. This study analyzed 16 years of data of 1375 T1DM patients, obtained from the Epidemiology of Diabetes Interventions and Complications (EDIC) clinical trials directed by the National Institute of Diabetes, Digestive, and Kidney Diseases, USA. Three data imputation techniques (RF, KNN, and MICE) and the SMOTETomek resampling technique were used to preprocess the primary dataset. Ten ML algorithms including logistic regression (LR), k-nearest neighbor (KNN), Gaussian naïve Bayes (GNB), support vector machine (SVM), stochastic gradient descent (SGD), decision tree (DT), gradient boosting (GB), random forest (RF), extreme gradient boosting (XGB), and light gradient-boosted machine (LightGBM) were applied to developed prediction models. Each model included 19 demographic, medical history, behavioral, and biochemical features, and every feature's effect was ranked using three feature ranking techniques (XGB, RF, and Extra Tree). Lastly, each model's ROC, sensitivity (recall), specificity, accuracy, precision, and F-1 score were estimated to find the best-performing model. The RF classifier model exhibited the best performance with 0.96 (±0.01) accuracy, 0.98 (±0.01) sensitivity, and 0.93 (±0.02) specificity. LightGBM performed second best and was quite close to RF with 0.95 (±0.06) accuracy. In addition to these two models, KNN, SVM, DT, GB, and XGB models also achieved more than 90% accuracy.

Force-Invariant Improved Feature Extraction Method for Upper-Limb Prostheses of Transradial Amputees.

A force-invariant feature extraction method derives identical information for all force levels. However, the physiology of muscles makes it hard to extract this unique information. In this context, we propose an improved force-invariant feature extraction method based on nonlinear transformation of the power spectral moments, changes in amplitude, and the signal amplitude along with spatial correlation coefficients between channels. Nonlinear transformation balances the forces and increases the margin among the gestures. Additionally, the correlation coefficient between channels evaluates the amount of spatial correlation; however, it does not evaluate the strength of the electromyogram signal. To evaluate the robustness of the proposed method, we use the electromyogram dataset containing nine transradial amputees. In this study, the performance is evaluated using three classifiers with six existing feature extraction methods. The proposed feature extraction method yields a higher pattern recognition performance, and significant improvements in accuracy, sensitivity, specificity, precision, and F1 score are found. In addition, the proposed method requires comparatively less computational time and memory, which makes it more robust than other well-known feature extraction methods.

An 8.72 µW Low-Noise and Wide Bandwidth FEE Design for High-Throughput Pixel-Strip (PS) Sensors.

The front-end electronics (FEE) of the Compact Muon Solenoid (CMS) is needed very low power consumption and higher readout bandwidth to match the low power requirement of its Short Strip application-specific integrated circuits (ASIC) (SSA) and to handle a large number of pileup events in the High-Luminosity Large Hadron Collider (LHC). A low-noise, wide bandwidth, and ultra-low power FEE for the pixel-strip sensor of the CMS has been designed and simulated in a 0.35 µm Complementary Metal Oxide Semiconductor (CMOS) process. The design comprises a Charge Sensitive Amplifier (CSA) and a fast Capacitor-Resistor-Resistor-Capacitor (CR-RC) pulse shaper (PS). A compact structure of the CSA circuit has been analyzed and designed for high throughput purposes. Analytical calculations were performed to achieve at least 998 MHz gain bandwidth, and then overcome pileup issue in the High-Luminosity LHC. The spice simulations prove that the circuit can achieve 88 dB dc-gain while exhibiting up to 1 GHz gain-bandwidth product (GBP). The stability of the design was guaranteed with an 82-degree phase margin while 214 ns optimal shaping time was extracted for low-power purposes. The robustness of the design against radiations was performed and the amplitude resolution of the proposed front-end was controlled at 1.87% FWHM (full width half maximum). The circuit has been designed to handle up to 280 fC input charge pulses with 2 pF maximum sensor capacitance. In good agreement with the analytical calculations, simulations outcomes were validated by post-layout simulations results, which provided a baseline gain of 546.56 mV/MeV and 920.66 mV/MeV, respectively, for the CSA and the shaping module while the ENC (Equivalent Noise Charge) of the device was controlled at 37.6 e- at 0 pF with a noise slope of 16.32 e-/pF. Moreover, the proposed circuit dissipates very low power which is only 8.72 µW from a 3.3 V supply and the compact layout occupied just 0.0205 mm2 die area.

Performance Analysis of Conventional Machine Learning Algorithms for Diabetic Sensorimotor Polyneuropathy Severity Classification.

BACKGROUND: Diabetic peripheral neuropathy (DSPN), a major form of diabetic neuropathy, is a complication that arises in long-term diabetic patients. Even though the application of machine learning (ML) in disease diagnosis is a very common and well-established field of research, its application in diabetic peripheral neuropathy (DSPN) diagnosis using composite scoring techniques like Michigan Neuropathy Screening Instrumentation (MNSI), is very limited in the existing literature. METHOD: In this study, the MNSI data were collected from the Epidemiology of Diabetes Interventions and Complications (EDIC) clinical trials. Two different datasets with different MNSI variable combinations based on the results from the eXtreme Gradient Boosting feature ranking technique were used to analyze the performance of eight different conventional ML algorithms. RESULTS: The random forest (RF) classifier outperformed other ML models for both datasets. However, all ML models showed almost perfect reliability based on Kappa statistics and a high correlation between the predicted output and actual class of the EDIC patients when all six MNSI variables were considered as inputs. CONCLUSIONS: This study suggests that the RF algorithm-based classifier using all MNSI variables can help to predict the DSPN severity which will help to enhance the medical facilities for diabetic patients.

A novel vehicle stationary detection utilizing map matching and IMU sensors.

Precise navigation is a vital need for many modern vehicular applications. The global positioning system (GPS) cannot provide continuous navigation information in urban areas. The widely used inertial navigation system (INS) can provide full vehicle state at high rates. However, the accuracy diverges quickly in low cost microelectromechanical systems (MEMS) based INS due to bias, drift, noise, and other errors. These errors can be corrected in a stationary state. But detecting stationary state is a challenging task. A novel stationary state detection technique from the variation of acceleration, heading, and pitch and roll of an attitude heading reference system (AHRS) built from the inertial measurement unit (IMU) sensors is proposed. Besides, the map matching (MM) algorithm detects the intersections where the vehicle is likely to stop. Combining these two results, the stationary state is detected with a smaller timing window of 3 s. A longer timing window of 5 s is used when the stationary state is detected only from the AHRS. The experimental results show that the stationary state is correctly identified and the position error is reduced to 90% and outperforms previously reported work. The proposed algorithm would help to reduce INS errors and enhance the performance of the navigation system.

Designing a ring-VCO for RFID transponders in 0.18 µm CMOS process.

In radio frequency identification (RFID) systems, performance degradation of phase locked loops (PLLs) mainly occurs due to high phase noise of voltage-controlled oscillators (VCOs). This paper proposes a low power, low phase noise ring-VCO developed for 2.42 GHz operated active RFID transponders compatible with IEEE 802.11 b/g, Bluetooth, and Zigbee protocols. For ease of integration and implementation of the module in tiny die area, a novel pseudodifferential delay cell based 3-stage ring oscillator has been introduced to fabricate the ring-VCO. In CMOS technology, 0.18 µm process is adopted for designing the circuit with 1.5 V power supply. The postlayout simulated results show that the proposed oscillator works in the tuning range of 0.5-2.54 GHz and dissipates 2.47 mW of power. It exhibits a phase noise of -126.62 dBc/Hz at 25 MHz offset from 2.42 GHz carrier frequency.