Accurate energy consumption prediction is crucial for optimizing the operation of electric commercial heavy-duty vehicles, e.g., route planning for charging. Moreover, understanding why certain predictions are cast is paramount for such a predictive model to gain user trust and be deployed in practice. Since commercial vehicles operate differently as transportation tasks, ambient, and drivers vary, a heterogeneous population is expected when building an AI system for forecasting energy consumption. The dependencies between the input features and the target values are expected to also differ across sub-populations. One well-known example of such a statistical phenomenon is the Simpson paradox. In this paper, we illustrate that such a setting poses a challenge for existing XAI methods that produce global feature statistics, e.g. LIME or SHAP, causing them to yield misleading results. We demonstrate a potential solution by training multiple regression models on subsets of data. It not only leads to superior regression performance but also more relevant and consistent LIME explanations. Given that the employed groupings correspond to relevant sub-populations, the associations between the input features and the target values are consistent within each cluster but different across clusters. Experiments on both synthetic and real-world datasets show that such splitting of a complex problem into simpler ones yields better regression performance and interpretability.

The development of delay-sensitive applications that require ultra high reliability created an additional challenge for wireless networks. This led to Ultra-Reliable Low-Latency Communications, as a use case that 5G and beyond 5G systems must support. However, supporting low latency communications requires the use of short codes, while attaining vanishing frame error probability (FEP) requires long codes. Thus, developing codes for the finite blocklength regime (FBR) achieving certain reliability requirements is necessary. This paper investigates the potential of Convolutional Neural Networks autoencoders (CNN-AE) in approaching the theoretical maximum achievable rate over a Gaussian channel for a range of signal-to-noise ratios at a fixed blocklength and target FEP, which is a different perspective compared to existing works that explore the use of CNNs from bit-error and symbol-error rate perspectives. We explain the studied CNN-AE architecture, evaluate it numerically, and compare it to the theoretical maximum achievable rate and the achievable rates of polar coded quadrature amplitude modulation (QAM), Reed-Muller coded QAM, multilevel polar coded modulation, and a TurboAE-MOD scheme from the literature. Numerical results show that the CNN-AE outperforms these benchmark schemes and approaches the theoretical maximum rate, demonstrating the capability of CNN-AEs in learning good codes for delay-constrained applications.

ISLAMABAD: A meeting on broadening of tax base was informed that the Federal Board of Revenue (FBR) has provided 14 million records of financial transactions of citizens to the National Database and Registration Authority (NADRA) to compute indicative income and tax liability of non-filers by use of artificial intelligence. The meeting was presided over by Adviser to the Prime Minister on Finance Shaukat Tarin on Monday. The FBR chairman and his team gave a detailed presentation on the progress on readiness for potential taxpayer outreach initiative to boost the revenue growth and resource mobilisation. The FBR chairman apprised the adviser that steps have been initiated for compilation of data, with the support of the NADRA, which would be available to potential and current taxpayers in a presentable and comprehensible manner through a web portal. According to Business Recorder, the 14 million financial records included property transactions, vehicle purchases, registration of cars with provincial excise departments, buying/selling of movable and immovable properties, utility bills, foreign travels, and other heavy expenditures.

Three years after his first interview, we catch up with Pivac to see how FBR has expanded its operation and chat about their latest commercial prototype, 'Hadrian X', as well as the future of the robotic construction industry. Mark Pivac is the primary inventor of FBR's automated bricklaying technology. He is an aeronautical and mechanical engineer with over 25 years' experience working on the development of high technology equipment ranging from lightweight aircraft to heavy off-road equipment. He has 20 years' experience working with pro/engineer 3D CAD software as well as high-level mathematics, including matrix mathematics, robot transformations and vector mathematics for machine motion. Mark has also worked extensively with design, commissioning and fault finding on servo controlled motion systems achieving very high dynamic performance.

HADRIAN X, a robot developed by Australian company FBR (formerly known as Fastbrick Robotics), has successfully completed its first full-scale test by building a 180 square metre house with three bedrooms and two bathrooms. Initially, Hadrian X was made to pass Factory Acceptance Testing (FAT), which focused on its ability to work with bricks of different sizes and cuts, building from a CAD model and building tall or "from slab to cap". Above: Hadrian X laying blocks to complete Factory Acceptance Testing (image courtesy of FBR). After completing the trial, Hadrian X completed its first full home structure in less than three days. The structure was verified by independent civil and structural engineers as having met the relevant building standards.