A machine-learning approach for stress detection using wearable sensors in free-living environments.

Stress is a psychological condition resulting from the body's response to challenging situations, which can negatively impact physical and mental health if experienced over prolonged periods. Early detection of stress is crucial to prevent chronic health problems. Wearable sensors offer an effective solution for continuous and real-time stress monitoring due to their non-intrusive nature and ability to monitor vital signs, e.g., heart rate and activity. Typically, most existing research has focused on data collected in controlled environments. Yet, our study aims to propose a machine learning-based approach for detecting stress in a free-living environment using wearable sensors. We utilized the SWEET dataset, which includes data from 240 subjects collected via electrocardiography (ECG), skin temperature (ST), and skin conductance (SC). We assessed four machine learning models, i.e., K-Nearest Neighbors (KNN), Support Vector Classification (SVC), Decision Tree (DT), Random Forest (RF), and XGBoost (XGB) in four different settings. This study evaluates the performance of various machine learning models for stress classification using the SWEET dataset. The analysis included two binary classification scenarios (with and without SMOTE) and two multi-class classification scenarios (with and without SMOTE). The Random Forest model demonstrated superior performance in the binary classification without SMOTE, achieving an accuracy of 98.29 % and an F1-score of 97.89 %. For binary classification with SMOTE, the K-Nearest Neighbors model performed best, with an accuracy of 95.70 % and an F1-score of 95.70 %. In the three-level classification without SMOTE, the Random Forest model again excelled, achieving an accuracy of 97.98 % and an F1-score of 97.22 %. For three-level classification with SMOTE, XGBoost showed the highest performance, with an accuracy and F1-score of 98.98 %. These results highlight the effectiveness of different models under various conditions, emphasizing the importance of model selection and preprocessing techniques in enhancing classification performance.

Design and optimization of broadband metamaterial absorber based on manganese for visible applications.

Metamaterial absorbers have been extensively researched due to their potential applications in photonics. This paper presents a highly efficient Broadband Metamaterial Absorber (BMA) based on a Manganese-Silica-Manganese three layer structure with a shaped pattern at the top layer. For maximum absorption efficiency, the geometrical parameters of the proposed absorber have been optimized based on Particle Swarm Optimization (PSO). The optimal structure with a thickness of 190 nm, can achieve more than 94% absorption spanning visible band (400-800) nm with 98.72% average absorption, and more than 90% absorption over the range from 365 to 888 nm. In the range from 447 to 717 nm, the design presented above 99% absorptivity, providing an ultra-wide bandwidth of 270 nm. The physical mechanism of absorption is illustrated through the exploration of the electric and magnetic field distributions. Additionally, the proposed structure maintains 85% absorption stability for wide incident angles up to 70° for both the TE and TM polarizations under oblique incidence. Further, the optimized absorber structure with excellent absorption capabilities makes it suitable for various applications, including optical sensors, thermal emitters, and color imaging applications.

A Rare Case of Primary Clear Cell Adenocarcinoma of the Urinary Bladder.

Adenocarcinoma is a rare form of urinary bladder cancer, comprising only 2% of cases, with various histological patterns and levels of differentiation. Among these, clear cell adenocarcinoma is the least common. Contrary to other subtypes, clear cell adenocarcinoma of the bladder has been shown to have a female predominance, and typically presents at the age of 60 after being incidentally discovered on radiological and urinary studies. However, signs and symptoms such as visible and non-visible hematuria, and signs and symptoms of urinary tract infection refractory to antibiotic treatment could occur and clue into the diagnosis. Although imaging can reveal and characterise the lesion, definitive diagnosis requires cystoscopy with biopsy. The treatment of adenocarcinoma of the bladder often requires surgical resection, with adjuvant chemotherapy being utilized in a subset of patients. We report a 79-year-old patient complaining of gross hematuria. Ultrasound was performed and showed a calcified mass at the dome of the urinary bladder, which was confirmed by computerized tomography of the abdomen and pelvis. Subsequent cystoscopy confirmed the diagnosis of clear-cell adenocarcinoma and the tumor was resected using a trans-urethral approach. Radical cystectomy with regional lymphadenectomy and adjuvant chemotherapy were used as the primary therapeutic modality.