Learning from Substitutable and Complementary Relations for Graph-based Sequential Product Recommendation

Sequential product recommendation, aiming at predicting the products that a target user will interact with soon, has become a hotspot topic. Most of the sequential recommendation models focus on learning from users’ interacted product sequences in a purely data-driven manner. However, they largely overlook the knowledgeable substitutable and complementary relations between products. To address this issue, we propose a novel Substitutable and Complementary Graph-based Sequential Product Recommendation model, namely, SCG-SPRe. The innovations of SCG-SPRe lie in its two main modules: (1) The module of interactive graph neural networks jointly encodes the high-order product correlations in the substitutable graph and the complementary graph into two types of relation-specific product representations. (2) The module of kernel-enhanced transformer networks adaptively fuses multiple temporal kernels to characterize the unique temporal patterns between a candidate product to be recommended and any interacted product in a target behavior sequence. Thanks to the seamless integration of the two modules, SCG-SPRe obtains candidate-dependent user representations for different candidate products to compute the corresponding ranking scores. We conduct extensive experiments on three public datasets, demonstrating SCG-SPRe is superior to competitive sequential recommendation baselines and validating the benefits of explicitly modeling the product-product relations.

In-sensor optoelectronic computing using electrostatically doped silicon

Complementary metal-oxide-semiconductor (CMOS) image sensors are a visual outpost of many machines that interact with the world. While they presently separate image capture in front-end silicon photodiode arrays from image processing in digital back-ends, efforts to process images within the photodiode array itself are rapidly emerging, in hopes of minimizing the data transfer between sensing and computing, and the associated overhead in energy and bandwidth. Electrical modulation, or programming, of photocurrents is requisite for such in-sensor computing, which was indeed demonstrated with electrostatically doped, but non-silicon, photodiodes. CMOS image sensors are currently incapable of in-sensor computing, as their chemically doped photodiodes cannot produce electrically tunable photocurrents. Here we report in-sensor computing with an array of electrostatically doped silicon p-i-n photodiodes, which is amenable to seamless integration with the rest of the CMOS image sensor electronics. This silicon-based approach could more rapidly bring in-sensor computing to the real world due to its compatibility with the mainstream CMOS electronics industry. Our wafer-scale production of thousands of silicon photodiodes using standard fabrication emphasizes this compatibility. We then demonstrate in-sensor processing of optical images using a variety of convolutional filters electrically programmed into a 3 × 3 network of these photodiodes.

Smart City (SC) Initiative and Urban Development in Rural Regions of Inland Norway

This study investigates the nature of the interconnection between Smart City (SC) and urban development initiatives. A case of Hamar city is used to identify how SC initiatives is used to combat some of the key challenges faced by a smaller city and non-metropolitan region. In contrast to metropolitan areas, the inland region with Hamar as its administrative centre is facing depopulation. A qualitative approach was applied including individual semi-structured and focus-group interviews. Despite an ambition of adopting SC and several SC projects that are up and running, the process is still at the early stages where many of its key stakeholders are unfamiliar with Hamar's SC initiatives. Poor integration between ICT systems also creates certain challenges. It concludes that better integration and marketing effort should be directed at educating the public about the purpose and goal of SC. Moreover, as technology evolves, it is important to be cautious about issues concerning privacy while ensuring seamless integration and communication between the systems in order to become a true ‘smart' effort.

Multi-HAPS Network Implementation within 3GPP’s NTN framework for 5G and beyond

High Altitude Platform Station (HAPS) is part of the 3GPP defined non-terrestrial network (NTN) infrastructure for 5G networks. Various technical studies by 3GPP have addressed NTN-based implementations and have significantly studied satellite-based scenarios. However, the study does not sufficiently address HAPS or multi-HAPS based scenarios specifically. Though HAPS, is captured under Unmanned Aerial Systems (UAS), it has unique operational realities that set it apart from other NTN platforms. For instance, HAPS come in different variants of fixed-wing, balloons and airships. This paper highlights the need for expanded studies specifically aimed at HAPS for more seamless integration. The work also analyses the Doppler effect associated with fixed-wing HAPS systems to further demonstrate how operational scenarios may differ for these platforms and the need for targeted studies. HAPS is expected to contribute significantly to the NTN-based implementations and may require more specialised considerations within the 3GPP NTN technical specification process, especially for 5G and beyond 5G (B5G) networks.

Effect of Environment-Related Cues on Auditory Distance Perception in the Context of Audio-Only Augmented Reality

Audio-only augmented reality consists of enhancing a real environment with virtual sound events. A seamless integration of the virtual events within the environment requires processing them with artificial spatialization and reverberation effects that simulate the acoustic properties of the room. However, in augmented reality, the visual and acoustic environment of the listener may not be fully mastered. This study aims to gain some insight into the acoustic cues (intensity and reverberation) that are used by the listener to form an auditory distance judgment, and to observe if these strategies can be influenced by the listener’s environment. To do so, we present a perceptual evaluation of two distance-rendering models informed by a measured Spatial Room Impulse Response. The choice of the rendering methods was made to design stimuli categories in which the availability and reproduction quality of acoustic cues are different. The proposed models have been evaluated in an online experiment gathering 108 participants who were asked to provide judgments of auditory distance about a stationary source. To evaluate the importance of environmental cues, participants had to describe the environment in which they were running the experiment, and more specifically the volume of the room and the distance to the wall they were facing. It could be shown that these context cues had a limited, but significant, influence on the perceived auditory distance.

Modular Piezoresistive Smart Textile for State Estimation of Cloths

Smart textiles have found numerous applications ranging from health monitoring to smart homes. Their main allure is their flexibility, which allows for seamless integration of sensing in everyday objects like clothing. The application domain also includes robotics; smart textiles have been used to improve human-robot interaction, to solve the problem of state estimation of soft robots, and for state estimation to enable learning of robotic manipulation of textiles. The latter application provides an alternative to computationally expensive vision-based pipelines and we believe it is the key to accelerate robotic learning of textile manipulation. Current smart textiles, however, maintain wired connections to external units, which impedes robotic manipulation, and lack modularity to facilitate state estimation of large cloths. In this work, we propose an open-source, fully wireless, highly flexible, light, and modular version of a piezoresistive smart textile. Its output stability was experimentally quantified and determined to be sufficient for classification tasks. Its functionality as a state sensor for larger cloths was also verified in a classification task where two of the smart textiles were sewn onto a piece of clothing of which three states are defined. The modular smart textile system was able to recognize these states with average per-class F1-scores ranging from 85.7 to 94.6% with a basic linear classifier.

TIAToolbox: An End-to-End Toolbox for Advanced Tissue Image Analytics

Computational Pathology (CPath) has seen rapid growth in recent years, driven by advanced deep learning (DL) algorithms. These algorithms typically share the same sequence of steps. However, due to the sheer size and complexity of handling large multi-gigapixel whole-slide images, there is no open-source software library that provides a generic end-to-end API for pathology image analysis using best practices for CPath. Most researchers have designed custom pipelines from the bottom-up, restricting the development of advanced CPath algorithms to specialist users. To help overcome this bottleneck, we present TIAToolbox, a Python toolbox designed to make CPath more accessible to new and advanced CPath scientists and pathologists alike. We provide a usable and adaptable library with efficient, cutting-edge and unit-tested tools for data loading, pre-processing, model inference, post-processing and visualization. This enables all kinds of users to easily build upon recent DL developments in the CPath literature. TIAToolbox provides a user-friendly modular API to enable seamless integration of advanced DL algorithms. We show with the help of examples how state-of-the-art DL algorithms can be streamlined using TIAToolbox.

AUTOMATION OF SHEET METAL COMBINATION DIE DESIGN PROCESS

This paper proposed a novel methodology for designing and manufacturing of sheet metal dies based on features of sheet parts. Also, combination is designed according to die cupping and punching features of sheet metal parts. The proposed approach is an attempt to make seamless integration of computer aided design with computer aided manufacturing. The features used in this study are taken from MusumiTM Catalogue as well as from various small and medium scale sheet metal industries. Work is divided into two phases. In the first phase, the relevant geometrical and topological data is extracted by reading STEP AP 203. In the second phase, a combine adjacency matrix and rule-based system is developed to recognize sheet metal features for die manufacturing. The system showed excellent performance for all types of features contained in the MusumiTM catalog and for different sheet metal industries. The proposed system for automated design of combination dies for sheet metal parts has been tested successfully for various types of industrial deep drawn parts. It reduces the die compoment design time from hours to minutes. selection of die components and drawings generated by the system were found to be reasonable and very similar to those actually used in the sheet metal industries for production of these typical components on combination dies.

Three-Layer PdO/CuWO4/CuO System for Hydrogen Gas Sensing with Reduced Humidity Interference

The growing hydrogen industry is stimulating an ongoing search for new materials not only for hydrogen production or storage but also for hydrogen sensing. These materials have to be sensitive to hydrogen, but additionally, their synthesis should be compatible with the microcircuit industry to enable seamless integration into various devices. In addition, the interference of air humidity remains an issue for hydrogen sensing materials. We approach these challenges using conventional reactive sputter deposition. Using three consequential processes, we synthesized multilayer structures. A basic two-layer system composed of a base layer of cupric oxide (CuO) overlayered with a nanostructured copper tungstate (CuWO4) exhibits higher sensitivity than individual materials. This is explained by the formation of microscopic heterojunctions. The addition of a third layer of palladium oxide (PdO) in forms of thin film and particles resulted in a reduction in humidity interference. As a result, a sensing three-layer system working at 150 °C with an equalized response in dry/humid air was developed.

The Importance of Subsurface Characterization and Monitoring During Development and Operation of Underground Gas Storage Facilities

Natural gas consumption is expected to grow significantly in coming decades in response to cleaner energy initiatives. Underground gas storage (UGS) will be key to addressing supply and demand dynamics for this transition to be successful. This technical paper will demonstrate the importance of an integrated subsurface characterization and monitoring approach not only for the construction of UGS, but also to guarantee safe and efficient operation over many decades. Key to long-term success of UGS is maximizing working capacity with respect to volume and pressure and maintaining well injection and withdrawal capabilities. Initial assessment steps involve determination of maximum storage capacity and an estimation of required cushion gas volumes. In similar manner to conventional field evaluation, we perform an integrated geological, geophysical, petrophysical and geomechanical characterization of the subsurface. However, for UGS facilities, the impact of cyclic variations of reservoir pressures on subsurface behavior and cap rock integrity also needs to be evaluated to determine safe operating limits at every point in time during the life of the UGS project. The holistic approach described above allows the operator to optimize the number of wells, well placement, completion design, etc. to ensure long-term safe and efficient operations. Furthermore, close integration of subsurface understanding with optimization of surface facilities, such as the compression system, is another critical component to ensure optimum UGS performance and deliverability. Moreover, another important task of the final phase of UGS facilities design involves enablement of sustainable operation through an asset integrity management plan. This phase is articulated around reservoir surveillance plans that monitor pressure, rock deformation and seismicity, in addition to regular wellbore inspection. Through close operations monitoring and the utilization of advanced data analytics, observations are compared to existing models for validation and operation optimization. Importantly we show that adapted monitoring programs provide critical long-term insight regarding the field response during successive cycles, leading to significant improvement in working gas capacity. A key consideration of this integrated UGS development strategy is based on the seamless integration of subsurface characterization, wellbore construction and well completions to ensure technical and commercial flexibility. The approach also emphasizes the integration with surface facilities design to ensure a true "Storage to Consumer" view for effective de-bottlenecking. Coupled with integrated subsurface integrity monitoring, this ensures a faster, cost efficient and safe response to the construction and operation of UGS facilities.