Microstructural Characterization of Thermomechanical and Heat-Affected Zones of an Inertia Friction Welded Astroloy

The behaviour of γ’ phase to thermal and mechanical effects during rapid heating of Astroloy, a powder metallurgy nickel-based superalloy has been investigated. The thermo-mechanical-affected zone (TMAZ) and heat-affected zone (HAZ) microstructures of an inertia friction welded (IFW) Astroloy were simulated using a Gleeble thermo-mechanical simulation system. Detailed microstructural examination of the simulated TMAZ and HAZ and those present in actual IFW specimens showed that γ’ particles persisted during rapid heating up to a temperature where the formation of liquid is thermodynamically favored and subsequently re-solidified eutectically. The result obtained showed that forging during the thermo-mechanical simulation significantly enhanced resistance to weld liquation cracking of the alloy. This is attributable to strain-induced rapid isothermal dissolution of the constitutional liquation products within 150 μm from the center of the forged sample. This was not observed in purely thermally simulated samples. The microstructure within the TMAZ of the as-welded alloy is similar to the microstructure in the forged Gleeble specimens.     

Physicochemical properties of the flour and starch from three Nigeria rice (<Emphasis Type="Italic">Oryza sativa</Emphasis> L.) varieties

Three varieties of Nigerian rice grains: CISADANE, OS₆ and NERICA 19 were processed to obtain flours and starches. They were evaluated for their proximate composition and physicochemical properties. The grain physical dimension measurements showed that the CISADANE was slender while OS₆ and NERICA 19 were bold and thick. The 1,000 grain weight was highest for CISADANE rice followed by OS₆ and NERICA 19. CISADANE had the highest protein and amylose contents. Protein contents in samples ranged as follows: 5.6–6.7, 5.2–6.9 and 0.2–0.9 % in brown rice, milled rice and the rice starches, respectively. The amylose content of CISADANE (27.7–36.5 %) and OS₆ (19.9–25.6 %) were high compared with NERICA 19 with negligible amylose. Swelling power and solubility generally increased with increasing temperatures (60–90 °C) for all the samples. Cooked CISADANE grain was hardest and OS₆ (Faro 11) rice was softest while the stickiness was highest in OS₆.     

A lightweight deep learning with feature weighting for activity recognition

With the development of deep learning, numerous models have been proposed for human activity recognition to achieve state-of-the-art recognition on wearable sensor data. Despite the improved accuracy achieved by previous deep learning models, activity recognition remains a challenge. This challenge is often attributed to the complexity of some specific activity patterns. Existing deep learning models proposed to address this have often recorded high overall recognition accuracy, while low recall and precision are often recorded on some individual activities due to the complexity of their patterns. Some existing models that have focused on tackling these issues are always bulky and complex. Since most embedded systems have resource constraints in terms of their processor, memory and battery capacity, it is paramount to propose efficient lightweight activity recognition models that require limited resources consumption, and still capable of achieving state-of-the-art recognition of activities, with high individual recall and precision. This research proposes a high performance, low footprint deep learning model with a squeeze and excitation block to address this challenge. The squeeze and excitation block consist of a global average-pooling layer and two fully connected layers, which were placed to extract the flattened features in the model, with best-fit reduction ratios in the squeeze and excitation block. The squeeze and excitation block served as channel-wise attention, which adjusted the weight of each channel to build more robust representations, which enabled our network to become more responsive to essential features while suppressing less important ones. By using the best-fit reduction ratio in the squeeze and excitation block, the parameters of the fully connected layer were reduced, which helped the model increase responsiveness to essential features. Experiments on three publicly available datasets (PAMAP2, WISDM, and UCI-HAR) showed that the proposed model outperformed existing state-of-the-art with fewer parameters and increased the recall and precision of some individual activities compared to the baseline, and the existing models.