Abstract In recent years, contrastive language‐image pre‐training (CLIP) has gained popularity for processing 2D data. However, the application of cross‐modal transferable learning to 3D data remains a relatively unexplored area. In addition, high‐quality, labelled point cloud data for Mechanical, Electrical, and Plumbing (MEP) scenarios are in short supply. To address this issue, the authors introduce a novel object detection system that employs 3D point clouds and 2D camera images, as well as text descriptions as input, using image‐text matching knowledge to guide dense detection models for 3D point clouds in MEP environments. Specifically, the authors put forth the proposition of a language‐guided point cloud modelling (PCM) module, which leverages the shared image weights inherent in the CLIP backbone. This is done with the aim of generating pertinent category information for the target, thereby augmenting the efficacy of 3D point cloud target detection. After sufficient experiments, the proposed point cloud detection system with the PCM module is proven to have a comparable performance with current state‐of‐the‐art networks. The approach has 5.64% and 2.9% improvement in KITTI and SUN‐RGBD, respectively. In addition, the same good detection results are obtained in their proposed MEP scene dataset.

In rotating machinery fault diagnosis, domain adaptation (DA) transfer learning-based framework has been attracting great attentions to tackle the problem of inconsistent feature distribution and insufficient labeled fault feature data. However, most of the existing approaches mainly focus on either the cross-domain distribution alignment or manifold subspace learning, which faces two critical limitations: 1) it is hard to overcome the feature distortions when aligning the distribution in the original feature space and 2) subspace learning is insufficient to decrease the distribution divergence. To address the above limitations, this work proposes an intelligent fault diagnosis scheme based on supervised DA with manifold embedding and key features selection. It first applies maximal overlap discrete wavelet packet transform (MODWPT) to process the vibration signals and performs the statistical feature extraction. In order to ensure that the selected key features are conductive to domain adaption, the fault discriminative ability and domain invariance of the features are investigated based on the domain differences and Laplacian score. Then, it presents a new supervised domain adaption with manifold embedding for the distribution alignment in manifold subspace by taking the class information and neighboring relationships into account. Finally, an intra classifier is learned to predict the unlabeled target domain. The proposed fault diagnosis scheme is evaluated using a set of practical data sets of motor and bearing. The extensive experimental results demonstrate that it significantly outperforms the comparative models and achieves much more effective fault diagnosis under different working conditions.

Wireless sensor networks (WSNs) is a promising solution for disaster management because of its scalability and low cost operations. However, testing the effectiveness of WSNs in real-world disasters is time consuming, costly and in some cases even infeasible. In this paper, we propose a Disaster in Network Simulations (DiNS) framework based on OMNeT ++ to replicate a WSN deployed in a disaster in a simulated environment. DiNS allows researchers to observe how the disaster influences the sensor network and how the network can respond in return. A generic coupling interface is developed to support different disaster types. Moreover, we develop a verification tool for functional debugging and verification during new functions de-veloping of sensor nodes, and an optimization tool to support the mathematical optimization of the network operations in response to the disaster. The functionality of DiNS is demonstrated with a case study using wildfire disaster. It provides an easy way for validating and optimizing the disaster management with WSNs.

Achieving energy efficiency is always a primary concern for fog-architecture-based Internet of Things (IoT) applications. As the IoT devices are typically of small sizes and powered by battery energy, it is essential to address the energy consumption at all levels from the circuit to the system. Two of the promising solutions at circuit and system levels are approximate computing and energy-aware task allocation, respectively. However, the existing task allocation approaches are designed without considering the aspect of approximate computing. In this work, we fill this gap and aim to maximize the network lifetime subject to the accuracy requirements of the applications. By considering both the approximate computing and task allocation simultaneously, a nonlinear problem is obtained to allocate the tasks for the devices (fog nodes and IoT end devices) and to select the corresponding execution modes (tasks in approximate or exact modes). To efficiently solve this problem, a centralized algorithm is first proposed by transferring the above nonlinear problem as a linear programming (LP) problem. As executing the centralized algorithm is a challenge for the resource-limited IoT devices, this work further proposes an optimal distributed algorithm based on Dantzig-Wolfe decomposition to solve the problem of tasks distribution and execution modes selection. The centralized large-scaled LP problem is decomposed into small-scaled subproblems, which can be efficiently solved by each IoT device. The proposed algorithms are tested by extensive simulations. The results demonstrate that the distributed algorithm achieves the same results as the centralized algorithm, and both of them significantly outperform the previous approaches.

Ultra-low-power operation, as required by Internet of Things (IoT) systems, requires to address energy consumption at all levels from circuit to system. Two of the promising solutions at circuit and system levels are approximate computing and energy aware task allocation, respectively. However, the existing task allocation approaches are designed without considering the aspect of approximate computing. For the first time, this work proposes an optimal Task Allocation algorithm taking the Approximate Computing into account (TAAC) to fill this gap. The problem of tasks assignment and executing modes selection (approximate or exact modes of the tasks) can be efficiently solved by formulating it as a linear programming problem. The extensive simulation results show that the proposed TAAC algorithm significantly outperforms the previous approaches.

Prior approaches to the problem of visual discomfort prediction (VDP) for stereo/3D images are built for the uncompressed image. This paper presents a novel VDP method based on the compressed image by using multi-scale discrete cosine transform (MsDCT). Three types of visual discomfort features, including basic disparity intensity (BDI), disparity gradient energy (DGE) and disparity texture complexity (DTC), are extracted from two-dimensional (2-D) DCT coefficients. Additionally, a multi-scale transformation approach based on the different sizes of transform units is applied to obtain the multi-scale sub-features for each of the features. Then, through experimental comparison, a random forest regressor is chosen to fuse twenty-three sub-features to get the final objective prediction value of the S3D images. Experimental results conducted on two datasets show that the proposed method improves the prediction accuracy compared to those of recent S3D visual (dis)comfort predictors.

The Internet of Things (IoT) has been recognized as the next technological revolution. It faces two challenges: 1) how to achieve energy efficient communication for the battery constrained devices and 2) how to connect a very large number of devices to the Internet with low latency, high efficiency, and reliability. To address these problems, this paper proposes two methods based on Kalman filter (KF), termed as extensions of predicable KF (EPKF). They locally reduce the unnecessary transmission (access) of end devices to the network (Internet) utilizing the spatial and temporal correlations with low algorithmic overhead. Each transmitting device (TD) independently controls its transmission using the temporal correlation; and the receiving device (RD) exploits the spatial correlation among the TDs to further improve the reconstruction quality. The reconstruction problem in the RD is nonlinear. To reduce the computation complexity, an in-depth analysis of the local estimate error is conducted and the approximated linear solutions are thereupon obtained. They are fundamental methods applicable to any IoT monitored/controlled physical system that can be modeled as a linear state space representation. The pedestrian-position application is used as a case study to demonstrate the efficiency in the simulation. Remarkably, the EPKF methods using the linear combinations of the local estimates from multiple TDs reduce the transmission rate to 10%, while achieving the same reconstruction quality as using KF in the traditional manner.

Energy-aware workload distribution becomes crucial for extending the lifetime of wireless sensor networks (WSNs) in complex applications as those in Internet-of-Things or in-network DSP processing scenarios. Today static workload schedules are well understood, while dynamic schedules (i.e., with multiple partitions) remain unexplored. This paper models the dynamic scheduling by considering both the communication and computation energy consumption. It formulates a series of (integer) linear programming problems to characterize the optimal scheduling strategies. Surprisingly, even 2-partition scheduling can provide the maximum gains. Besides the interest to evaluate the optimality of on-line heuristics for dynamic scheduling, the reported off-line strategies can be immediately applied to WSN applications.

Energy efficiency is a primary concern for wireless sensor networks (WSNs). One of its most energy-intensive processes is the radio communication. This work uses a predictor combined with a Kalman filter (KF) to reduce the communication energy cost for cluster-based WSNs. The technique, called PKF, is suitable for typical WSN applications with adjustable data quality and tens of picojoule computation cost. However, it is challenging to precisely quantify its underlying process from a mathematical point of view. Through an in-depth mathematical analysis, we formulate the tradeoff between energy efficiency and reconstruction quality of PKF. One of our prominent results for that is the explicit expression for the covariance of the doubly truncated multivariate normal distribution; it improves the previous methods and has generality. The validity and accuracy of the analysis are verified with both artificial and real signals. The simulation results, using real temperature values, demonstrate the efficiency of PKF: without additional data degradation, it reduces the communication cost by more than 88%. Compared to previous works based on KF, PKF requires less computational effort while improving the reconstruction quality; compared with the techniques without KF, the advantages of PKF are even more significant. It reduces the transmission rate of them by at least 29%. Besides, it can be integrated into network level techniques to further extend the whole network lifetime.

Data compression using temporal and/or spatial correlations has been extensively studied to prolong the lifetime of wireless sensor networks (WSNs). In order to maximize the gain of these techniques, this work proposes an off-line altruistic compression-scheduling (ACS) scheme for cluster-based WSNs. It schedules when and how (i.e. without compression, with either of temporal and spatial compression, or with both of them) each sensor node executes compression techniques. The optimum scheduling solution to maximize the network lifetime is obtained by solving a linear program, whose computational complexity and runtime are efficiently reduced by a grouping and filtering algorithm. In addition, we propose a transmission power increment (TPI) method for WSNs with isolated nodes to improve the spatial compression possibilities. It can be used in ACS to further extend the lifetime of such networks. The efficiency of ACS is demonstrated by extensive simulation results using realistic models. It increases the network lifetime by a factor of 1.67 to 12.49 depending on different temporal correlations for typical WSNs. Compared with previous scheduling methods, it further extends the network lifetime with even less runtime. The combination of TPI and ACS significantly prolongs the lifetime of networks with isolated nodes.