This study aimed to determine the efficacy of a smartphone application named Quit with US among young adult smokers. An open-label, parallel, 2-group, randomized controlled trial with a 12-week follow-up was conducted between March and November 2020 among undergraduate students (18 to 24 years) in Chiang Mai Province, Thailand. A total of 273 participants were assigned by simple randomization procedure to the Quit with US intervention group (n = 137) or the control group (n = 136). 

All participants received pharmacists’ smoking cessation counseling at baseline and follow-ups. In addition, the intervention group’s participants were advised to use Quit with US. The baseline and 12-week follow-up assessments were conducted at a study unit, whereas other follow-ups were completed over the telephone. The primary abstinence outcome was the exhaled CO concentration level (≤6 ppm) verified 7-day point prevalence abstinence. At baseline, the participants’ mean (standard deviation) age was 21.06 (1.62) years. Most identified as daily smokers (57.9%, n = 158), consumed ≤10 cigarettes daily (89.4%, n = 244), and expressed low level of nicotine dependence as measured by Heaviness of Smoking Index score (86.1%, n = 235). Regarding intention-to-treat analyses, participants in the Quit with US intervention group achieved significantly greater smoking abstinence rate than those in the control group (58.4% (80/137) vs. 30.9% (42/136), risk ratio = 1.89, 95% confidence intervals = 1.42 to 2.52, p < 0.001). In conclusion, Quit with US integrated with pharmacists’ smoking cessation counseling significantly enhanced smoking abstinence rates among young adult light smokers consuming ≤ 10 cigarettes daily. 

In this study, linguistic variables in terms of triangular fuzzy numbers (TrFn) are used to manage such kind of rough information, then the rough approximations of the fuzzy hypersoft set (FHS-set) are characterized which are capable of handling such informational uncertainties. The FHS-set is more flexible as well as consistent as it tackles the limitation of fuzzy soft sets regarding categorizing parameters into their related sub-classes having their sub-parametric values. Based on these rough approximations, an algorithm is proposed for the optimal selection of suppliers by managing experts’ opinions and rough information collectively in the form of TrFn-based linguistic variables. To have a discrete decision, a signed distance method is employed to transform the TrFn-based opinions of experts into fuzzy grades. 
The proposed algorithm is corroborated with the help of a multi-criteria decision-making application to choose the best supplier for real estate builders. The beneficial facets of the put forward study are appraised through its structural comparison with few existing related approaches. The presented approach is consistent as it is capable to manage rough information and expert’s opinions about suppliers collectively by using rough approximations of FHS-set.
https://www.mdpi.com/2075-5309/12/7/940

The study proposes ReSVM, an approach combining deep features of ResNet-50 with the SVM classifier, for distraction detection of a driver. ReSVM is compared with six state-of-the-art approaches on four datasets, namely: State Farm Distracted Driver Detection, Boston University, DrivFace, and FT-UMT. Experiments demonstrate that ReSVM outperforms the existing approaches and achieves a classification accuracy as high as 95.5%. The study also compares ReSVM with its variants on the aforementioned datasets.

This research discusses machine learning algorithms, such as Gaussian Progress Regression (GPR), Support Vector Machine Regression (SVMR), Ensemble Learning (EL), and optimized GPR, SVMR, and EL, to predict the compressive strength of Lightweight Concrete (LWC). The simulation approaches of these trained models indicate that AI can provide accurate prediction models without undertaking extensive laboratory trials. Each model’s applicability and performance were rigorously reviewed and assessed. The findings revealed that the optimized GPR model (R = 0.9803) used in this study had the greatest accuracy. In addition, the optimized SVMR and GPR model showed good performance, with R-values 0.9777 and 0.9740, respectively. The proposed model is economic and efficient, and can be adopted by researchers and engineers to predict the compressive strength of LWC.

Manual diagnosis of crops diseases is not an easy process; thus, a computerized method is widely used. From a couple of years, advancements in the domain of machine learning, such as deep learning, have shown substantial success. However, they still faced some challenges such as similarity in disease symptoms and irrelevant features extraction. In this article, we proposed a new deep learning architecture with optimization algorithm for cucumber and potato leaf diseases recognition. The proposed architecture consists of five steps. In the first step, data augmentation is performed to increase the numbers of training samples. In the second step, pre-trained DarkNet19 deep model is opted and fine-tuned that later utilized for the training of fine-tuned model through transfer learning. Deep features are extracted from the global pooling layer in the next step that is refined using Improved Cuckoo search algorithm. The best selected features are finally classified using machine learning classifiers such as SVM, and named a few more for final classification results. The proposed architecture is tested using publicly available datasets–Cucumber National Dataset and Plant Village. The proposed architecture achieved an accuracy of 100.0%, 92.9%, and 99.2%, respectively. A comparison with recent techniques is also performed, revealing that the proposed method achieved improved accuracy while consuming less computational time.

https://www.techscience.com/cmc/v74n1/49776

we propose a novel computerised approach in this work using deep learning and featuring an ant colony optimisation (ACO) based selection. The proposed method consists of four fundamental steps: data augmentation to solve the imbalanced dataset, fine-tuned pre-trained deep learning models (NasNet Mobile and MobileNet-V2), the fusion of extracted deep features using matrix length, and finally, a selection of the best features using a hybrid ACO and a Neighbourhood Component Analysis (NCA). The best-selected features were eventually passed to many classifiers for final recognition. The experimental process involved an augmented dataset and achieved an average accuracy of 99.7%. Comparison with existing techniques showed that the proposed method was effective.