People suffering from Alzheimer's disease (AD) and their caregivers seek different approaches to cope with memory loss. Although AD patients want to live independently, they often need help from caregivers. In this situation, caregivers may attach notes on every single object or take out the contents of a drawer to make them visible before leaving the patient alone at home. This study reports preliminary results on an Ambient Assisted Living (AAL) real-time system, achieved through the Internet of Things (IoT) and Augmented Reality (AR) concepts, aimed at helping people suffering from AD. The system has two main sections: the smartphone or windows application allows caregivers to monitor patients' status at home and be notified if patients are at risk. The second part allows patients to use smart glasses to recognize QR codes in the environment and receive information related to tags in the form of audio, text, or three-dimensional image. This work presents preliminary results and investigates the possibility of implementing such a system.
In sequential decision-making scenarios i.e., mobile health recommendation systems revenue management contextual multi-armed bandit algorithms have garnered attention for their performance. But most of the existing algorithms are built on the assumption of a strictly parametric reward model mostly linear in nature. In this work we propose a new algorithm with a semi-parametric reward model with state-of-the-art complexity of upper bound on regret amongst existing semi-parametric algorithms. Our work expands the scope of another representative algorithm of state-of-the-art complexity with a similar reward model by proposing an algorithm built upon the same action filtering procedures but provides explicit action selection distribution for scenarios involving more than two arms at a particular time step while requiring fewer computations. We derive the said complexity of the upper bound on regret and present simulation results that affirm our methods superiority out of all prevalent semi-parametric bandit algorithms for cases involving over two arms.
In this paper, we examine the internet of things system which is dedicated for smart cities, smart factory, and connected cars, etc. To support such systems in wide area with low power consumption, energy harvesting technology without wired charging infrastructure is one of the important issues for longevity of networks. In consideration of the fact that the position and amount of energy charged for each device might be unbalanced according to the distribution of nodes and energy sources, the problem of maximizing the minimum throughput among all nodes becomes a NP-hard challenging issue. To overcome this complexity, we propose a machine learning based relaying topology algorithm with a novel backward-pass rate assessment method to present proper learning direction and an iterative balancing time slot allocation algorithm which can utilize the node with sufficient energy as the relay. To validate the proposed scheme, we conducted simulations on the system model we established, thus confirm that the proposed scheme is stable and superior to conventional schemes.
Control of the surface texture of steel strip during the galvanizing and temper rolling processes is essential to satisfy customer requirements and is conventionally measured post-production using a stylus. In-production laser reflection measurement is less consistent than physical measurement but enables real time adjustment of processing parameters to optimize product surface characteristics. We propose the use of machine learning to improve accuracy of the transformation from inline laser reflection measurements to a prediction of surface properties. In addition to accuracy, model evaluation speed is important for fast feedback control. The ROCKET model is one of the fastest state of the art models, however it can be sped up by utilizing a GPU. Our contribution is to implement the model in PyTorch for fast GPU kernel transforms and provide a soft version of the Proportion of Positive Values (PPV) nonlinear pooling function, allowing gradient flow. We perform timing and performance experiments comparing the implementations
Inferring chemical reaction networks (CRN) from time series data is a challenge encouraged by the growing availability of quantitative temporal data at the cellular level. This motivates the design of algorithms to infer the preponderant reactions between the molecular species observed in a given biochemical process, and help to build CRN model structure and kinetics. Existing ODE-based inference methods such as SINDy resort to least square regression combined with sparsity-enforcing penalization, such as Lasso. However, when the input time series are only available in wild type conditions in which all reactions are present, we observe that current methods fail to learn sparse models. Results: We present Reactmine, a CRN learning algorithm which enforces sparsity by inferring reactions in a sequential fashion within a search tree of bounded depth, ranking the inferred reaction candidates according to the variance of their kinetics, and re-optimizing the CRN kinetic parameters on the whole trace in a final pass to rank the inferred CRN candidates. We first evaluate its performance on simulation data from a benchmark of hidden CRNs, together with algorithmic hyperparameter sensitivity analyses, and then on two sets of real experimental data: one from protein fluorescence videomicroscopy of cell cycle and circadian clock markers, and one from biomedical measurements of systemic circadian biomarkers possibly acting on clock gene expression in peripheral organs. We show that Reactmine succeeds both on simulation data by retrieving hidden CRNs where SINDy fails, and on the two real datasets by inferring reactions in agreement with previous studies.
This paper studies a downlink system that combines orthogonal-time-frequency-space (OTFS) modulation and sparse code multiple access (SCMA) to support massive connectivity in high-mobility environments. We propose a cross-domain receiver for the considered OTFS-SCMA system which efficiently carries out OTFS symbol estimation and SCMA decoding in a joint manner. This is done by iteratively passing the extrinsic information between the time domain and the delay-Doppler (DD) domain via the corresponding unitary transformation to ensure the principal orthogonality of errors from each domain. We show that the proposed OTFS-SCMA detection algorithm exists at a fixed point in the state evolution when it converges. To further enhance the error performance of the proposed OTFS-SCMA system, we investigate the cooperation between downlink users to exploit the diversity gains and develop a distributed cooperative detection (DCD) algorithm with the aid of belief consensus. Our numerical results demonstrate the effectiveness and convergence of the proposed algorithm and show an increased spectral efficiency compared to the conventional OTFS transmission.
In this paper, we take a holistic approach to deal with the tradeoffs between energy use and comfort in commercial buildings. We developed a system called OCTOPUS, which employs a novel deep reinforcement learning (DRL) framework that uses a data-driven approach to find the optimal control sequences of all building's subsystems, including HVAC, lighting, blind and window systems. The DRL architecture includes a novel reward function that allows the framework to explore the tradeoffs between energy use and users' comfort, while at the same time enabling the solution of the high-dimensional control problem due to the interactions of four different building subsystems. In order to cope with OCTOPUS's data training requirements, we argue that calibrated simulations that match the target building operational points are the vehicle to generate enough data to be able to train our DRL framework to find the control solution for the target building. In our work, we trained OCTOPUS with 10-year weather data and a building model that is implemented in the EnergyPlus building simulator, which was calibrated using data from a real production building. Through extensive simulations, we demonstrate that OCTOPUS can achieve 14.26% and 8.1% energy savings compared with the state-of-the-art rule-based method in a LEED Gold Certified building and the latest DRL-based method available in the literature respectively, while maintaining human comfort within a desired range.
In this paper, we reduce the complexity of approximating the correlation clustering problem from $O(m\times\left( 2+ \alpha (G) \right)+n)$ to $O(m+n)$ for any given value of $\varepsilon$ for a complete signed graph with $n$ vertices and $m$ positive edges where $\alpha(G)$ is the arboricity of the graph. Our approach gives the same output as the original algorithm and makes it possible to implement the algorithm in a full dynamic setting where edge sign flipping and vertex addition/removal are allowed. Constructing this index costs $O(m)$ memory and $O(m\times\alpha(G))$ time. We also studied the structural properties of the non-agreement measure used in the approximation algorithm. The theoretical results are accompanied by a full set of experiments concerning seven real-world graphs. These results shows superiority of our index-based algorithm to the non-index one by a decrease of %34 in time on average.
Spiking Neural networks (SNN) have emerged as an attractive spatio-temporal computing paradigm for a wide range of low-power vision tasks. However, state-of-the-art (SOTA) SNN models either incur multiple time steps which hinder their deployment in real-time use cases or increase the training complexity significantly. To mitigate this concern, we present a training framework (from scratch) for one-time-step SNNs that uses a novel variant of the recently proposed Hoyer regularizer. We estimate the threshold of each SNN layer as the Hoyer extremum of a clipped version of its activation map, where the clipping threshold is trained using gradient descent with our Hoyer regularizer. This approach not only downscales the value of the trainable threshold, thereby emitting a large number of spikes for weight update with a limited number of iterations (due to only one time step) but also shifts the membrane potential values away from the threshold, thereby mitigating the effect of noise that can degrade the SNN accuracy. Our approach outperforms existing spiking, binary, and adder neural networks in terms of the accuracy-FLOPs trade-off for complex image recognition tasks. Downstream experiments on object detection also demonstrate the efficacy of our approach.
This paper studies the capacity region of asynchronous multiple access channel (MAC) with faster-thanNyquist (FTN) signaling. We first express the capacity region in the frequency domain. Next, we calculate an achievable rate region in time domain and prove that it is identical to the capacity region calculated in the frequency domain. Our analysis confirms that asynchronous transmission and FTN bring in significant gains.