Research in the recognition of human activities of daily living has significantly improved using deep learning techniques. Traditional human activity recognition techniques often use handcrafted features from heuristic processes from single sensing modality. The development of deep learning techniques has addressed most of these problems by the automatic feature extraction from multimodal sensing devices to recognise activities accurately. In this paper, we propose a deep learning multi-channel architecture using a combination of convolutional neural network (CNN) and Bidirectional long short-term memory (BLSTM). The advantage of this model is that the CNN layers perform direct mapping and abstract representation of raw sensor inputs for feature extraction at different resolutions. The BLSTM layer takes full advantage of the forward and backward sequences to improve the extracted features for activity recognition significantly. We evaluate the proposed model on two publicly available datasets. The experimental results show that the proposed model performed considerably better than our baseline models and other models using the same datasets. It also demonstrates the suitability of the proposed model on multimodal sensing devices for enhanced human activity recognition.

Substrate-integrated waveguide (SIW) is a modern day (21st century) transmission line that has recently been developed. This technology has introduced new possibilities to the design of efficient circuits and components operating in the radio frequency (RF) and microwave frequency spectrum. Microstrip components are very good for low frequency applications but are ineffective at extreme frequencies, and involve rigorous fabrication concessions in the implementation of RF, microwave, and millimeter-wave components. This is due to wavelengths being short at higher frequencies. Waveguide devices, on the other hand, are ideal for higher frequency systems, but are very costly, hard to fabricate, and challenging to integrate with planar components in the neighborhood. SIW connects the gap that existed between conventional air-filled rectangular waveguide and planar transmission line technologies including the microstrip. This study explores the current advancements and new opportunities in SIW implementation of RF and microwave devices including filters, multiplexers (diplexers and triplexers), power dividers/combiners, antennas, and sensors for modern communication systems.

Owing to recent technological advancement, computers and other devices running several image editing applications can be further exploited for digital image processing operations. This paper evaluates various image processing techniques using matrix laboratory (MATLAB-based analytics). Compared to the conventional techniques, MATLAB gives several advantages for image processing. MATLAB-based technique provides easy debugging with extensive data analysis and visualization, easy implementation and algorithmic-testing without recompilation. Besides, MATLAB's computational codes can be enhanced and exploited to process and create simulations of both still and video images. Moreover, MATLAB codes are much concise compared to C++, thus making it easier for perusing and troubleshooting. MATLAB can handle errors prior to execution by proposing various ways to make the codes faster. The proposed technique enables advanced image processing operations such as image cropping/resizing, image denoising, blur removal, and image sharpening. The study aims at providing readers with the most recent MATLAB-based image processing application-tools. We also provide an empirical-based method using two-dimensional discrete cosine transform (2D-DCT) derived from its coefficients. Using the most recent algorithms running on MATLAB toolbox, we performed simulations to evaluate the performance of our proposed technique. The results largely present MATLAB as a veritable approach for image processing operations.

A Substrate integrated waveguide bandpass filter is presented with a novel CPW-to-SIW transition at both the input and output ports which also served as the input and output couplings into the filter. The CPW-to-SIW transition structures presented here exploited the step impedance between the 50 ohms input/output feedline and the transition to control the input/output couplings of the filter. The SIW filter is also shown to have very minimum milling or etching requirement which reduces the fabrication error. The proposed SIW filter has been validated experimentally and results presented. The results show that a simulated return loss of 15 dB and an initial measured return loss of 16 dB were achieved. An improved measured return loss of 22 dB was later achieved after some tuining adjustments were performed on the filter input and output couplings. A minimum insertion loss of 1.3 dB was also achieved across the band.

Folded-arms square open-loop resonator (FASOLR) is a variant of the conventional microstrip square open-loop resonator (SOLR) that facilitates further device size miniaturization by having the two arms of the conventional SOLR folded inwards. This paper highlights the benefits of this brand of compact SOLR by implementing a five-pole Chebyshev bandpass filter (BPF) using compact FASOLR. The test BPF is presented, with centre frequency of 2.2 GHz, fractional bandwidth of 10%, passband ripple of 0.04321 dB, and return loss of 20 dB. The design is implemented on a Rogers RT/Duroid 6010LM substrate with a dielectric constant of 10.7 and thickness of 1.27 mm. The filter device is manufactured and characterised, with the experimentation results being used to justify the simulation results. The presented measurement and electromagnetic (EM) simulation results demonstrate a good match. The EM simulation responses achieve a minimum insertion loss of 0.8 dB and a very good channel return loss of 22.6 dB. The measurement results, on the other hand, show a minimum insertion loss of 0.9 dB and a return loss of better than 19.2 dB. The filter component has a footprint of 36.08 mm by 6.74 mm (that is, 0.26 λg × 0.05 λg), with λg indicating the guided wavelength for the 50 Ohm microstrip line impedance at the centre frequency of the proposed fifth-order bandpass filter.