Lane marking detection is fundamental for both advanced driving assistance systems and traffic surveillance systems. However, detecting lane is highly challenging when the visibility of a road lane marking is low, obscured or often invisible due to real-life challenging environment and adverse weather. Most of the lane detection methods suffer from four types of challenges: (i) light effects i.e. shadow, glare of light, reflection etc. created by different light sources like streetlamp, tunnel-light, sun, wet road etc.; (ii) Obscured visibility of eroded, blurred, dashed, colored and cracked lane caused by natural disasters and adverse weather (rain, snow etc.); (iii) lane marking occlusion by different objects from surroundings (wiper, vehicles etc.); and (iv) presence of confusing lane like lines inside the lane view e.g., guardrails, pavement marking, road divider etc. In this paper, we proposed a simple, real-time, and robust lane detection and tracking method to detect lane marking considering the abovementioned challenging conditions. In this method, we introduced three key technologies. First, we introduce a comprehensive intensity threshold range (CITR) to improve the performance of the canny operator in detecting different types of lane edges e.g., clear, low intensity, cracked, colored, eroded, or blurred lane edges. Second, we propose a two-step lane verification technique, the angle-based geometric constraint (AGC) and length-based geometric constraint (LGC) followed by Hough Transform, to verify the characteristics of lane marking and to prevent incorrect lane detection. Finally, we propose a novel lane tracking technique, to predict the lane position of the next frame by defining a range of horizontal lane position (RHLP) along the x axis which will be updated with respect to the lane position of previous frame. It can keep track of the lane position when either left or right or both lane markings are partially and fully invisible. To evaluate the performance of the proposed method we used the DSDLDE (Lee and Moon, 2018) and SLD (Borkar et al., 2009) dataset with $1080\times 1920$ and $480\times 720$ resolutions at 24 and 25 frames/sec respectively where the video frames containing different challenging scenarios. Experimental results show that the average detection rate is 97.55%, and the average processing time is 22.33 msec/frame, which outperforms the state-of-the-art method.

Surface electromyography (EMG) is one of the promising signals for the recognition of the intended hand movement of an amputee. Nevertheless, there are several barriers to its successful implementation in the advanced prosthetic hand. Subject-dependent EMG pattern recognition is one of them, which limits the use of a training model for a specific subject to others. So, this study aims to explore a subject invariant EMG pattern recognition method that is performed by extracting subject invariant features. To extract subject invariant features, we have created a feature space using a feature extraction method, and the dimensionality of the feature space is reduced by employing spectral regression discriminant analysis (SRDA). Finally, each SRDA feature is normalized using min-max normalization, which confines the scale of each SRDA feature from 0 to 1. The proposed subject invariant EMG pattern recognition method achieves the F1 score of 97.26%, 96.47%, 95.42%, and 93.71% with a linear discriminant analysis classifier (LDA) for an electrode array of 8×16, 8×8, 8×4, and 8×2, respectively. The achieved performances are almost equal to or sometimes better than those achieved in subject independent and subject-dependent EMG pattern recognition. Also, the proposed method is simple, classifier independent, time complexity free, and does not require any customization or fine-tuning of classifiers. So, the proposed subject invariant EMG pattern recognition method would be an option to overcome the training barrier for each subject without compromising the EMG pattern recognition performance.

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.

Background: Post-translational modification is one of the bio-molecular mechanisms in living organisms, which incorporate functional diversity in proteins as well as regulate cellular processes. Transformation of arginine residue to citrulline in protein is such a modification. Objective: Our objective is to identify citrullinated arginine residue sites quickly and accurately. Methods: In this study, a novel computational tool, abbreviated as predCitru-Site, has been developed to predict citrullination sites. This technique effectively has incorporated the sequencecoupling effect of surrounding amino acids of arginine residues as well as optimizes skewed training citrullination dataset for prediction quality improvement. The performance of predCitru- Site has been measured from the average of 5 complete runs of the 10-fold cross-validation test to comply with existing tools. Results and Conclusion: predCitru-Site has achieved 97.6% sensitivity, 98.9% specificity, and overall accuracy of 98.5%. With Matthew’s correlation coefficient of 0.967, it has also shown an area under the receiver operator characteristics curve of 0.997. Compared with existing tools, predCitru-Site significantly outperforms on the same benchmark dataset. It also shows significant improvement in the case of independent tests in all performance metrics (around 50% higher in AUC). These results suggest that our method is promising and can be used as a complementary technique for fast exploration of citrullination in arginine residue. A user-friendly web server has also been deployed at http://research.ru.ac.bd/predCitru-Site/ for the convenience of experimental scientists.

Variation in the electromyogram pattern recognition (EMG-PR) performance with the muscle contraction force is a key limitation of the available prosthetic hand. To alleviate this problem, we propose a scheme to realize electromyogram signal normalization across channels before feature extraction. The proposed signal normalization scheme is validated over a dataset of nine transradial amputees that includes three force levels with six hand gestures. Moreover, we employ three classifiers, namely, linear discriminant analysis (LDA), support vector machine (SVM) and k-nearest neighbour (KNN), to evaluate the EMG-PR performance. In addition to the signal normalization scheme, we perform nonlinear transformation of the features by using the logarithm function. Both schemes facilitate merging of the muscle activation patterns of different force levels. The experimental results indicate that the force invariant EMG-PR performance (F1 score of at least 3.24% to 4.34%) of the proposed schemes is significantly enhanced compared to that obtained in recent studies. Therefore, we recommend using these features along with the proposed signal normalization scheme and nonlinear transformation of the features to improve the force invariant EMG-PR performance. The proposed feature extraction method achieves the highest F1 score of 91.28%, 91.39% and 90.56% when using the LDA, SVM and KNN classifiers, respectively.