Sensor-based human activity recognition using fuzzified deep CNN architecture with λmax method

Purpose This work aims to develop a novel fuzzy associator rule-based fuzzified deep convolutional neural network (FDCNN) architecture for the classification of smartphone sensor-based human activity recognition. This work mainly focuses on fusing the λmax method for weight initialization, as a data normalization technique, to achieve high accuracy of classification. Design/methodology/approach The major contributions of this work are modeled as FDCNN architecture, which is initially fused with a fuzzy logic based data aggregator. This work significantly focuses on normalizing the University of California, Irvine data set’s statistical parameters before feeding that to convolutional neural network layers. This FDCNN model with λmax method is instrumental in ensuring the faster convergence with improved performance accuracy in sensor based human activity recognition. Impact analysis is carried out to validate the appropriateness of the results with hyper-parameter tuning on the proposed FDCNN model with λmax method. Findings The effectiveness of the proposed FDCNN model with λmax method was outperformed than state-of-the-art models and attained with overall accuracy of 97.89% with overall F1 score as 0.9795. Practical implications The proposed fuzzy associate rule layer (FAL) layer is responsible for feature association based on fuzzy rules and regulates the uncertainty in the sensor data because of signal inferences and noises. Also, the normalized data is subjectively grouped based on the FAL kernel structure weights assigned with the λmax method. Social implications Contributed a novel FDCNN architecture that can support those who are keen in advancing human activity recognition (HAR) recognition. Originality/value A novel FDCNN architecture is implemented with appropriate FAL kernel structures.

Effect of Holding Time on Populations of Microparticles in Spheroidal Graphite Irons

Non-metallic microparticles in spheroidal graphite irons are a product of the inoculation and the Mg-treatment of the liquid melt. Besides the influence on the mechanical properties of these iron–carbon–silicon alloys, they are also responsible for the nucleation and the morphology of the graphite phase. The present investigation is undertaken to study holding time effects of a (Ba, Ca, Al)–ferrosilicon (called Ba-inoculant) and (Ca, Al)–ferrosilicon (called Ca-inoculant) inoculants on the overall distribution of microparticles. Using the 2D to 3D conversions method, which is typically used for graphite nodules, the non-metallic microparticles’ statistical parameters, such as size distributions and number densities, are quantified. The total number of particles is similar after Mg-treatment and inoculation for Ca-inoculant but not for Ba-inoculated samples, which lose approximately 25 pct of microparticles after 1 minute of holding time. Iron treated with the Ca-inoculant loses about 37 pct of its nodules after 5 minutes, while the Ba-inoculated melts maintain their performance even after 10 minutes. Based on extrapolating the trend of the undercooling, Ba-inoculated samples would reach the uninoculated undercooling values in 48 minutes, while Ca-inoculated samples in only 11 minutes. By evaluating the size distributions of the non-metallic microparticles, the Ostwald ripening hypothesis or particle aggregation can be verified. The results suggest that sulfides are more critical for graphite nucleation since they can be correlated with the graphite number densities. However, due to the small difference in the microparticle population of the uninoculated sample with Ca-inoculated samples, other aspects of the fading mechanism need to be considered, such as transient metastable states, since the central hypothesis of loss of inclusions cannot alone explain the decrease in the nucleation frequency of graphite.

Competitive Adsorption of Copper, Zinc, and Chromium from Wastewater Using Corn-Cob Ash: Optimization Approach

Corn Cob ash was used in competitive adsorption of copper, zinc, and chromium from wastewater. The central composite design; a sub-set of response surface methodology was used to optimize the adsorption of the heavy metals. The result of the statistical parameters showed the coefficient of determination (R2) of 1.000, 0.999, and 1.000 for copper, zinc, and chromium respectively. The optimal conditions obtained for adsorbent dosage, initial concentration, temperature, contact time, and particle size were 13.20 mg, 79.72 mg/l, 34.95 °C, 40.38 min, and 1400 µm, respectively with the desirability of 1.000. The predicted and the actual values of metal removal obtained were 69.41%, 76.37%, as well as 70.44%, 72.50%, 77.90 % and 71.00% for copper, zinc, and chromium respectively. The ressult indicated a good conformity between the model predicted values and the actual values, thus having small errors of 3.09%, 1.53 % and 0.56 % for copper, zinc, and chromium respectively.

A Fatigue Reliability Assessment for Rail Tension Clamps Based on Field Measurement Data

Tension clamps play an important role in maintaining the track gauge by fixing the rails to the sleepers. Damage to the tension clamps was observed on an urban railway. The cause of the fracturing of the tension clamps was identified and reliability analyses on the fatigue failure of the tension clamps were performed. The stress ranges were estimated by measuring the strain at the locations where most of the fractures occurred during train operation. Afterward, a statistical model of the stress ranges was developed using the measured data. The statistical parameters of the stress ranges for the reliability analysis were estimated based on the field measurement data. The reliability indexes were calculated for the inner and outer rails and for the inside and outside track gauges of each rail. The variations of the reliability index for the years in service and the number of cycles were investigated. The results of the reliability analyses showed a consistency with the field observations.

A Robust Feature Extraction and Deep Learning Approach for Cancer Gene Prognosis

Mutated genes are one of the prominent factors in origination and spread of cancer disease. Here we have used Genomic signal processing methods to identify the patterns that differentiate cancer and non-cancerous genes. Furthermore, Deep learning algorithms were used to model a system that automatically predicts the cancer gene. Unlike the existing methods, two feature extraction modules are deployed to extract six attributes. Power Spectral Density based module was used to extract statistical parameters like Mean, Median, Standard deviation, Mean Deviation and Median Deviation. Adaptive Functional Link Network (AFLN) based filter module was used to extract Normalized Mean Square Error (NMSE). The uniqueness of this paper is identification of six input features that differentiates cancer genes. In this work artificial neural network is developed to predict cancer genes. Comparison is done on three sets of datasets with 6 attributes, 5 attributes and one attribute. We performed all the training and testing on the Tensorflow using the Keras library in Python using Google Colab. The developed approach proved its efficiency with 6 attributes attaining an accuracy of 98% for 150 epochs. The ANN model was also compared with existing work and attained a 10 fold cross validation accuracy of 96.26% with an increase of 1.2%.

Flexible and Integrative Psychiatric Care Based on a Global Treatment Budget: Comparing the Implementation in Germany and Poland

Background: The past decade has witnessed the establishment of flexible and integrative treatment (FIT) models in 55 German and Polish psychiatric catchment areas. FIT is based on a global treatment budget (GTB), which integrates funding of all acute psychiatric hospital services for a regional population. Prior research has identified 11 specific program components of FIT in Germany. In this paper we aim at assessing the applicability of these components to the Polish context and at comparatively analysing FIT implementation in Poland and Germany.Methods: Qualitative interviews about the applicability of the 11 FIT-specific components were conducted with the program managers of the Polish FIT models (n = 19). Semi-quantitative data on the FIT-specific components were then collected in 19 Polish and 10 German FIT models. We assessed the grading of each component, their overall degree of implementation and compared them between the two countries. In all study hospitals, structural and statistical parameters of service delivery were collected and compared.Results: The qualitative results showed that the German FIT-specific components are in principle applicable to the polish context. This allowed the comparative assessment of components grading and degree of implementation, which showed only subtle discrepancies between German and Polish FIT models. The little discrepancies point to specific aspects of care such as home treatment, peer support, and cooperation with non-clinical and social welfare institutions that should be further integrated in the components' definition.Conclusions: The specific program components of FIT as first defined from the German experience, serves as a powerful tool to measure, and evaluate implementation of integrated psychiatric care both within and between health systems.

MULTIPLE VACUUM SYRINGE BLOOD ASPIRATION PROCEDURE (MVSBAP): A NEW HORIZON OF RAKTAMOKSHANA PROCEDURE IN PANCHAKARMA THERAPY OF AYURVEDA

Panchakarma is a specialized branch of Ayurveda that primarily deals with the body's purification (Shodhana) of doshas. As we know, the word Panchakarma refers to five special therapeutic procedures like Vamana, Virechana, Vasti, Nasya and Raktamokshana. Raktamokshana is an effective bloodletting therapy. Classically it is described as of six types, i.e. (1) Shringa, (2) Jalauka, (3) Alabu, (4) Shiravedha, (5) Prachchhana and (6) Ghatiyantra. In the present study, a clinical trial has been done, especially in the disease of Gridhrasi, with particular reference to Sciatica by combining Parchchhana and Ghatiyantra, a modified form of Raktamokshana therapy, called Multiple Vacuum Syringe Blood Aspiration Procedure (MVSBAP). Sciatica is painful neuralgia of the Sciatic Nerve in which pain starts from the gluteal region and buttock and comes down through the back of thigh, knee, calf and outer border of the foot. Sixty patients were selected for the clinical trial using a simple random sampling method from the OPD and IPD of Government Ayurveda College and Hospital, Varanasi, Uttar Pradesh, India. Two groups are made like Group-A and Group-B, each consisting of 30 patients. Patients of Group-A are treated with only traditional Ayurvedic medicines, and patients of Group-B are treated with MVSBAP and traditional Ayurvedic medication. After one month of final treatment, assessment is done on statistical parameters, which show pretty better results in Group-B patients. The application of MVSBAP in the disease of Gridhrasi draws a new horizon to the ailing humanities.

Assessment of the level of pollution of water bodies of the Denezhkin kamen reserve by the Shemur field

Waste produced during the extraction of minerals can cause various environmental problems. One of which is polluting underground and surface waters. The purpose of the article is to assess the level of pollution of water bodies of the Denezhkin Kamen reserve by the Shemur ore field. To assess the level of pollution, individual and complex pollution indices, statistical parameters and the ʺQuartileʺ method for calculating emissions are used. An analysis of the geological structure of the territory and physical and geographical conditions of the area was carried out; the level of pollution was assessed; the main causes of pollution were determined; the main pollutants were identified. The waters flowing through the reserve are not polluted they are polluted near the reserve borders. Pollutants are carried downstream over long distances and get into the intakes of local settlements. In the Bannaya River basin, the pollution area is about 80 km; in the Olkhovka River basin, the pollution area is about 60 km. There is a dependence in the change in the concentration of pollutants on seasonality and weather conditions. The main pollutants are those that are contained in large quantities in the overburden rocks of the deposit. Additional studies are required using a sampling program, which was not available during the current studies.

Variation of the Descriptive Grain Size Distribution Along Cores From the Sebkha of Sidi El Hani, Eastern Tunisia

In this chapter, cores were the object of descriptive classifications of the grain size distribution, which were meant to describe the grain size continuous variability within cores and to correlate between them. The statistical treatment of the crude data was done on the basis of two different methods (the method of moments statistics and the method of inclusive graphic statistics) to compute statistical parameters of the grain size distribution such as mean and median. The correlations between cores were done on the basis of sand/silt/clay percentages. Even though it has given special care to test different methods of studying the grain size distribution, this study has not deviated from its primary purpose of investigating the filling of the playa; correlations between different cores were meant to infer their sedimentary dynamics.

Drainage System of Tegalsari Polder for Handling Flood and Tide in Tegal City Indonesia

Although in 2019 the local government of Tegal city Indonesia had constructed a retention basin at drainage system of Siwatu, Tegal Barat, Tegal city with a catchment area of 226 ha, the areas around the system still experienced flood and inundation. This study belonged to a descriptive qualitative research aimed to evaluate the performances of Siwatu drainage system and Tegalsari retention basin. Data of the study included field data and technical data from institutions. Based on the 15-year rainfall data (2014 – 2018) from Pemali - Comal PSDA Office, Central Java Province, Indonesia, the statistical parameters of Cs: 0.0027, Ck: 1.904, Sd: 15.91, Cv: 0.144 were obtained and so Gumbel method distribution was applied in the study, the return period rainfall of 10 years was 138 mm, the flood discharge for Qr.10 years was 9.63 m3/sec., the addition of long storage was 8×2,50×500 m, and the combination of pump addition was of 1 m3/sec. with the long storage of 8×2.00×500 m. By implementing one of the alternative choices, either flood or inundation could be resolved.