Human motion analysis using a smartphone-embedded accelerometer sensor provided important context for the identification of static, dynamic, and complex sequence of activities. Research in smartphone-based motion analysis are implemented for tasks, such as health status monitoring, fall detection and prevention, energy expenditure estimation, and emotion detection. However, current methods, in this regard, assume that the device is tightly attached to a pre-determined position and orientation, which might cause performance degradation in accelerometer data due to changing orientation. Therefore, it is challenging to accurately and automatically identify activity details as a result of the complexity and orientation inconsistencies of the smartphone. Furthermore, the current activity identification methods utilize conventional machine learning algorithms that are application dependent. Moreover, it is difficult to model the hierarchical and temporal dynamic nature of the current, complex, activity identification process. This paper aims to propose a deep stacked autoencoder algorithm, and orientation invariant features, for complex human activity identification. The proposed approach is made up of various stages. First, we computed the magnitude norm vector and rotation feature (pitch and roll angles) to augment the three-axis dimensions (3-D) of the accelerometer sensor. Second, we propose a deep stacked autoencoder based deep learning algorithm to automatically extract compact feature representation from the motion sensor data. The results show that the proposed integration of the deep learning algorithm, and orientation invariant features, can accurately recognize complex activity details using only smartphone accelerometer data. The proposed deep stacked autoencoder method achieved 97.13% identification accuracy compared to the conventional machine learning methods and the deep belief network algorithm. The results suggest the impact of the proposed method to improve a smartphone-based complex human activity identification framework.
Worldwide, the burden of cancer is drastically increasing over the past few years. Among all types of cancers in women, breast cancer (BrC) is the main cause of unnatural deaths. For early diagnosis, histopathology (Hp) imaging is a gold standard for positive and detailed (at tissue level) diagnosis of breast tumor (BrT) compared to mammogram images. A large number of studies used BrT Hp images to solve binary or multiclassification problems using high computational resources. However, classification models' performance may be compromised due to the high correlation among various types of BrT in Hp images, which raises the misclassification rate. Thus, this paper aims to develop a tree-based BrT multiclassification model via deep learning (DL) to extract discriminative features to solve the multiclassification problem with better performance using less computational resources. The main contributions of this work are to create an ensemble, tree-based DL model that is pre-trained on the BreakHis dataset, and implementation of a misclassification reduction algorithm. The ensemble, tree-based DL model, extracts discriminative BrT features from Hp images. The target dataset (i.e., Bioimaging challenge 2015 breast histology) is small in size; thus, to avoid overfitting of the proposed model, pretraining is performed on the BreakHis dataset. Whereas, misclassification reduction algorithm is implemented to enhance the performance of the classification model. The experimental results show that the proposed model outperformed the existing state-of-the-art baseline studies. The achieved classification accuracy is ranging from 87.50 % to 100 % for four subtypes of BrT. Thus, the proposed model can assist doctors as the second opinion in any healthcare centre.
Drug-drug interactions (DDIs) may result in the alteration of therapeutic response. Sometimes they may increase the untoward effects of many drugs. Hospitalized cardiac patients need more attention regarding drug-drug interactions due to complexity of their disease and therapeutic regimen. This research was performed to find out types, prevalence and association between various predictors of potential drug-drug interactions (pDDIs) in the Department of Cardiology and to report common interactions. This study was performed in the hospitalized cardiac patients at Ayub Teaching Hospital, Abbottabad, Pakistan. Patient charts of 2342 patients were assessed for pDDIs using Micromedex® Drug Information. Logistic regression was applied to find predictors of pDDIs. The main outcome measure in the study was the association of the potential drug-drug interactions with various factors such as age, gender, polypharmacy, and hospital stay of the patients. We identified 53 interacting-combinations that were present in total 5109 pDDIs with median number of 02 pDDIs per patient. Overall, 91.6% patients had at least one pDDI; 86.3% were having at least one major pDDI, and 84.5% patients had at least one moderate pDDI. Among 5109 identified pDDIs, most were of moderate (55%) or major severity (45%); established (24.2%), theoretical (18.8%) or probable (57%) type of scientific evidence. Top 10 common pDDIs included 3 major and 7 moderate interactions. Results obtained by multivariate logistic regression revealed a significant association of the occurrence of pDDIs in patient with age of 60 years or more (p
Full Heuslers alloys are a fascinating class of materials leading to many technological applications. These have been studied widely under ambient conditions. However, less attention been paid to study them under the effect of compression and strain. Here in this work Co2YZ (Y= Cr, Nb, Ta, V and Z = Al, Ga) Heusler alloys have been studied comprehensively under pressure variations. Calculated lattice constants are in reasonable agreement with the available data. It is determined that lattice constant deceases with the increase in tensile stress and increases by increasing pressure in reverse direction. Band profiles reveals the half metallic nature of the studied compounds. The bond length decreases while band gap increases in compressive strain. The compounds are found to be reflective in visible region, as characteristics of the metals. The magnetic moments reveal the half-mettalic ferromagnetic nature of the compounds.
A hormonal imbalance may disrupt the rigorously monitored cellular microenvironment by hampering the natural homeostatic mechanisms. The most common example of such hormonal glitch could be seen in obesity where the uprise in adipokine levels is in virtue of the expanding bulk of adipose tissue. Such aberrant endocrine signaling disrupts the regulation of cellular fate, rendering the cells to live in a tumor supportive microenvironment. Previously, it was believed that the adipokines support cancer proliferation and metastasis with no direct involvement in neoplastic transformations and tumorigenesis. However, the recent studies have reported discrete mechanisms that establish the direct involvement of adipokine signaling in tumorigenesis. Moreover, the individual adipokine profile of the patients has never been considered in the prognosis and staging of the disease. Hence, the present manuscript has focused on the reported extensive mechanisms that culminate the basis of poor prognosis and diminished survival rate in obese cancer patients.
Lack of proper infrastructure and the poor economic conditions of rural communities make them dependent on herbal medicines. Thus, there is a need to obtain and conserve the historic and traditional knowledge about the medicinal importance of different plants found in different areas of the world. In this regard, a field study was conducted to document the medicinal importance of local plants commonly used by the inhabitants of very old historic villages in Southern Punjab, Pakistan. In total, 58 plant species were explored, which belonged to 28 taxonomic families, as informed by 200 experienced respondents in the study area. The vernacular name, voucher number, plant parts used, and medicinal values were also documented for each species. Among the documented species, Poaceae remained the most predominant family, followed by Solanaceae and Asteraceae. The local communities were dependent on medicinal plants for daily curing of several ailments, including asthma, common cold, sore throat, fever, cardiovascular diseases, and digestive disorders. Among the reported species, leaves and the whole plant remained the most commonly utilized plant parts, while extracts (38.8%) and pastes (23.9%) were the most popular modes of utilization. Based on the ICF value, the highest value was accounted for wound healing (0.87), followed by skincare, nails, hair, and teeth disorders (0.85). The highest RFC value was represented by Acacia nilotica and Triticum aestivum (0.95 each), followed by Azadirachta indica (0.91). The highest UV was represented by Conyza canadensis and Cuscuta reflexa (0.58 each), followed by Xanthium strumarium (0.37). As far as FL was concerned, the highest value was recorded in the case of Azadirachta indica (93.4%) for blood purification and Acacia nilotica (91.1%) for sexual disorders. In conclusion, the local inhabitants primarily focus on medicinal plants for the treatment of different diseases in the very old historic villages of Southern Punjab, Pakistan. Moreover, there were various plants in the study area that have great ethnobotanical potential to treat various diseases, as revealed through different indices.