Nature-inspired heuristic paradigms for parameter estimation of control autoregressive moving average systems

Neural Computing and Applications - Aim of this research is to explore the strength of evolutionary and swarm intelligence techniques for parameter identification of control autoregressive moving...     

Numerical solution of doubly singular nonlinear systems using neural networks-based integrated intelligent computing

Neural Computing and Applications - In this paper, a bio-inspired computational intelligence technique is presented for solving nonlinear doubly singular system using artificial neural networks...     

Influence of pH and Temperature on Structural,Optical and Catalytical Investigations of CeO2-SiO2 Nanoparticles

Silicon - CeO2-SiO2 nanoparticles were synthesized by surfactant assisted via sol-gel process at variable pH 9, 10 and 11 by keeping constant temperature of...     

Microscopic brain tumor detection and classification using 3D CNN and feature selection architecture

Brain tumor is one of the most dreadful natures of cancer and caused a huge number of deaths among kids and adults from the past few years. According to WHO standard, the 700,000 humans are being with a brain tumor and around 86,000 are diagnosed since 2019. While the total number of deaths due to brain tumors is 16,830 since 2019 and the average survival rate is 35%. Therefore, automated techniques are needed to grade brain tumors precisely from MRI scans. In this work, a new deep learning‐based method is proposed for microscopic brain tumor detection and tumor type classification. A 3D convolutional neural network (CNN) architecture is designed at the first step to extract brain tumor and extracted tumors are passed to a pretrained CNN model for feature extraction. The extracted features are transferred to the correlation‐based selection method and as the output, the best features are selected. These selected features are validated through feed‐forward neural network for final classification. Three BraTS datasets 2015, 2017, and 2018 are utilized for experiments, validation, and accomplished an accuracy of 98.32, 96.97, and 92.67%, respectively. A comparison with existing techniques shows the proposed design yields comparable accuracy.     

Status of biodiesel research and development in Pakistan

Performance of biodiesel in engines is well established and biodiesel is currently adjudged as a low carbon fuel with the most potential of replacing fossil fuels. The fossil fuel sources are dwindling in Pakistan resulting in importation of about 8.1 million tonnes at approximately US$ 9.4 billion per annum. In the ambit of this justification, augmenting the energy scarce resources in Pakistan through intense harnessing of the varied biodiesel sources can adequately address the deficiency and can ensure energy security. Towards this end, the progress attained in biodiesel related researches in Pakistan are evaluated and presented with the view of highlighting ways of achieving the target set by the Government. A feedstock that drew less attention is spent triglycerides, and the little work reported by some organizations appeared promising. Now the onus is upon organizations such as the Alternative Energy Development Board and Pakistan State Oil to harness the research results from several indigenous Universities and develop a full-scale biodiesel economy in Pakistan.     

Promoting renewables in the energy sector of Tajikistan

Energy technology transfer can allow countries to move quickly to environmentally sound and sustainable practices. Integration of Renewable Energy Sources (RES) technologies in the energy sector of these countries can play a key role towards sustainability. The level of penetration of RES technologies remains seriously in arrears in Tajikistan, although the country has great RES potential. The aim of the paper is to look deeply into the most appropriate RES technology, which can be gradually introduced in the energy sector of Tajikistan and supported through demonstrations, business workshops, guides for installers with technical details and design proposals. The multi-dimensional methodology adopted included transparent decision support processes, using linguistic variables, taking into consideration the specific conditions prevailing in Tajikistan, as well as policy and technical proposal for the further development of the local market. Based on the results, the emphasis is laid on decentralized heat production, though the promotion of Solar Water Heaters, which seems to be an attractive energy option, with multiple benefits for the country.     

Thermophysical Properties of Platinum-Copper Alloys

Platinum and copper along with their alloys have been used in a broad range of applications including jewelry, coinage, electrical and electronic devices, and many others. Their thermophysical properties play an important role in casting processes and are required as input data for casting simulation. The focus of this work was to investigate these properties by different methods. Platinum, copper, and four platinum-copper alloys, namely, Pt96Cu04, Pt68Cu32, Pt50Cu50, and Pt25Cu75, were investigated within this work. The melting range and thermal expansion were measured at fem by differential scanning calorimetry and dilatometry, respectively. At TU Graz, wire-shaped samples were investigated by an ohmic pulse heating technique. This technique delivers thermophysical properties of electrically conducting materials far into the liquid phase. These measurements allow the calculation of specific heat capacity and the temperature dependencies of electrical resistivity, enthalpy, and density of these alloys in the solid and liquid phases. Thermal conductivity and thermal diffusivity as a function of temperature are estimated from resistivity data using the Wiedemann?CFranz law at the end of the solid phase and at the beginning of the liquid phase. The results are compared with the available literature values.     

An Efficient Internet Traffic Classification System Using Deep Learning for IoT

Internet of Things (IoT) defines a network of devices connected to the internet and sharing a massive amount of data between each other and a central location. These IoT devices are connected to a network therefore prone to attacks. Various management tasks and network operations such as security, intrusion detection, Quality-of-Service provisioning, performance monitoring, resource provisioning, and traffic engineering require traffic classification. Due to the ineffectiveness of traditional classification schemes, such as port-based and payload-based methods, researchers proposed machine learning-based traffic classification systems based on shallow neural networks. Furthermore, machine learning-based models incline to misclassify internet traffic due to improper feature selection. In this research, an efficient multilayer deep learning based classification system is presented to overcome these challenges that can classify internet traffic. To examine the performance of the proposed technique, Moore-dataset is used for training the classifier. The proposed scheme takes the pre-processed data and extracts the flow features using a deep neural network (DNN). In particular, the maximum entropy classifier is used to classify the internet traffic. The experimental results show that the proposed hybrid deep learning algorithm is effective and achieved high accuracy for internet traffic classification, i.e., 99.23%. Furthermore, the proposed algorithm achieved the highest accuracy compared to the support vector machine (SVM) based classification technique and k-nearest neighbours (KNNs) based classification technique.