Instant delivery has become an essential service in daily life, requiring strict delivery timelines. However, traditional delivery methods that employ human couriers struggle to meet the soaring delivery demands due to labor shortages. While researchers have explored alternative solutions using ground vehicles (e.g., crowdsourced taxis) and Unmanned Aerial Vehicles (UAVs), their inherent limitations, such as constrained delivery detour for crowdsourced taxis and limited battery capacity of UAVs, greatly constrain their effectiveness. To address these challenges, this paper proposes a novel air-ground delivery paradigm that cooperatively integrates UAVs and crowdsourced taxis. First, UAV stations are strategically deployed based on delivery gaps between the delivery demands and taxis' delivery capacity, instead of delivery demands only; Then, a predictive UAV repositioning strategy is designed to bridge instantaneously dynamic delivery gaps. Thereafter, a transfer learning-based (TL-based) algorithm that mines the delivery knowledge of human couriers is designed to optimize the cooperative performance. This algorithm extracts behavioral insights from human couriers and transfers them to enhance the delivery capabilities of UAVs and taxis. Finally, parcel assignment is formulated as optimization problems aimed at maximizing total preferences of UAVs and taxis, and maximizing delivery number while minimizing cost, respectively. Evaluations on real-world datasets demonstrate that the proposed method delivers 27.4% more parcels, saves 19.2% delivery cost, and preserves 36.3% more of the travel experience of taxi passengers than the state-of-the-art (SOTA) air-ground cooperative approach for instant delivery.

Visual text generation, which aims to generate photo-realistic images with coherent and well-formed scene text being rendered, has attracted widespread attention. Although recent works have achieved promising performance, the limited flexibility and controllability hinder their practical applications. We observe that different from natural objects, visual text in real scenes often has an arbitrarily shaped structure with different granularities (i.e., character, word, or line). In this paper, we consider the modality gap between image and text, and propose a new separation and composition pipeline for flexible and controllable visual text generation from only text prompts. At the core of our framework is a novel Hierarchical and Directional Layout representation, i.e., HDLayout, which can model the sequential and multi-granularity nature of the visual text. Under this formulation, we are able to generate arbitrarily shaped visual text automatically. Extensive experiments demonstrate that our method outperforms several strong baselines in a variety of scenarios both qualitatively and quantitatively, yielding state-of-the-art performances on arbitrarily shaped visual text generation.

Industrial Internet of Things (IIoT) systems face major challenges in ensuring reliable, low-latency communication for time-sensitive tasks, especially under the limited resources. In this paper, we propose a short packet communication scheme in Non-Orthogonal Multiple Access (NOMA)-assisted IIoT system. Each device partitions its transmitted data into finite blocklength packets and transmits them to the base station (BS) via the NOMA method. Specifically, we minimize the total system delay by jointly optimizing the number of short packets transmitted by each device, the transmit power of each short packet, and the data volume of each short packet, while satisfying block error rate (BLER) constraints. Since the proposed optimization problem is non-convex, we adopt a hierarchical approach to obtain the optimal solution. In particular, we decompose the problem into a top problem of solving the number of short packets and a bottom problem of optimizing the transmit power and data volume of each packet. For the bottom problem, we convexify it by introducing new variables and applying the Successive Convex Approximation (SCA) method. For the top problem, we employ the Dream Optimization Algorithm (DOA) to handle the discrete variables and obtain a suboptimal solution. Simulation results demonstrate that our algorithm outperforms the genetic algorithm and Frequency Division Multiple Access (FDMA) transmission in terms of total system delay.

Deploying deep neural networks (DNNs) on resource-constrained Internet of Things (IoT) devices is challenging due to limited processing power, energy constraints, and stringent latency requirements. This article introduces a new method to split DNN tasks in IoT systems, focusing on saving power and reducing delays. We use Gaussian process regression (GPR) to predict how long tasks will take under different conditions. We also use a simple linear regression model to estimate how much power IoT devices use based on their CPU usage. These predictive models are integrated into a Bayesian optimization framework to determine the optimal DNN task partitioning point, balancing latency and energy efficiency. The system adjusts to changes in the network and device conditions, ensuring it works well in different situations. Experiments on a heterogeneous IoT testbed demonstrate that GPR accurately predicts execution latencies, and the linear regression model provides reliable power consumption estimates. The Bayesian optimization algorithm efficiently explores the tradeoff space, offering low power consumption and high latency satisfaction rates. Our code is shared for public usehttps://github.com/nucleusbiao/Time-Sensitive-and-Power-Efficient-DNN-Task-Partitioning.

Federated Learning (FL) has become a state-of-the-art technique for addressing data isolation and privacy problems. However, the traditional FL framework has limitations on lack of labeled data, adaptation to evolving environments and tasks, and insufficient generalization of the global model due to non-independent and identically distributed (non-IID) data. These issues suggest incorporating human knowledge and interaction into the FL workflow can be beneficial. Human-machine hybrid intelligence is an area that human abilities are considered to prompt the usability and robustness of the system by providing human domain knowledge. Combining FL and human-machine hybrid intelligence can fully utilize their benefits and complement each other perfectly. This article presents our vision of the next generation of FL, Human-Machine Hybrid Federated Learning, namely HIFL. And this work first defines the concept of HIFL and proposes three patterns of collaboration for HIFL: (1) local hybrid intelligence (LocalHIFL), (2) separate hybrid intelligence (SeparateHIFL), and (3) cross hybrid intelligence (CrossHIFL). In each pattern, we survey methodologies and techniques that are utilized to address specific problems that occurred after adding human-machine collaboration in FL process. Besides, we exhibit some potential application scenarios, and provide several open challenges and opportunities contained in HIFL. This survey intends to provide a high-level summarization for improving FL by combining human-machine hybrid intelligence, and to motivate interested readers to consider approaches for designing effective FL approaches and ways of intelligence fusion according to their requirements.

In the Industrial Internet of Things (IIoT), the latency-sensitive task can be efficiently performed based on real-time data collection, transmission, and computation. In this article, we thus propose a hybrid nonorthogonal multiple access-rate splitting multiple access (NOMA-RSMA) edge-cloud service computing framework for the IIoT consisting of end devices (EDs), edge servers (ESs), and cloud servers (CSs), in which the tasks are allowed to be computed at the EDs, the ESs, or a CS. When the task computation takes place at the ESs or the CS, tasks would be first compressed at EDs, and then be offloaded to the ESs via nonorthogonal multiple access (NOMA). After that, the ESs offload tasks to the CS via rate splitting multiple access (RSMA) if tasks are intended to be processed at the CS. Otherwise, the ESs perform computation locally. Specifically, under the delay constraints, we aim to minimize the total system energy consumption by jointly optimizing the transmit power of the EDs and the ESs, the transmission delays of each NOMA group and RSMA, the signal splitting ratio of the ESs, the computation power of the EDs, the ESs, and the CS, the compression delay, the offloading decisions of the EDs and the ESs. To address the formulated nonconvex problem, we employ a hierarchical decomposition approach to layer it into a top-level offloading decision problem and a bottom-level resource allocation problem. We design a block coordinate descent (BCD)-based method to solve the bottom-level problem. Additionally, we propose an algorithm based on deep reinforcement learning and online offloading (DROO) to obtain the suboptimal offloading decisions for EDs and ESs in the top-level problem. Numerical results validate the accuracy and effectiveness of our algorithms in terms of the total energy consumption, compared with three heuristic algorithms, i.e., the genetic algorithm, and the cross-entropy algorithm, the Deep Q-Network algorithm.

Cloud-based quantization is a key technique for deploying deep neural networks on resource-constrained devices. However, the growing number of heterogeneous devices has placed an increasing burden on the cloud server. It is necessary to handle the high costs of quantizing original models to multiple bitwidths on the cloud server. Therefore, we propose an efficient hierarchical quantization method (HQAQ), which transforms classical cloud-based quantization to two-phase quantization: cloud-edge post-training quantization and edge-device hybrid re-quantization. HQAQ first quantizes original models on the cloud server and distributes the quantized model to edge servers. Then the edge servers re-quantize the quantized model to respond to heterogeneous devices’ requests. To minimize the computational costs on edge servers, edge-device hybrid re-quantization integrates top-bitwidth quantization-aware training with cross-bitwidth quantization points transfer. Quantization points transfer employs clustering to discover the distribution of the quantization points with higher bit-width, which helps quantize the models of lower-bitwidth models. The experimental results on image classification and time series prediction tasks demonstrate that the proposed method improves communication efficiency while maintaining model performance.

Proximity graphs (PG) have gained increasing popularity as the state-of-the-art solutions to k -approximate nearest neighbor ( k -ANN) search on high-dimensional data, which serves as a fundamental function in various fields, e.g., retrieval-augmented generation. Although PG-based approaches have the best k -ANN search performance, their index construction cost is superlinear to the number of points. Such superlinear cost substantially limits their scalability in the era of big data. Hence, the goal of this paper is to accelerate the construction of PG-based methods without compromising their k -ANN search performance. To achieve this goal, two mainstream categories of PG are revisited: relative neighborhood graph (RNG) and navigable small world graph (NSWG). By revisiting their construction process, we find the issues of construction efficiency. To address these issues, we propose a new construction framework with a novel pruning strategy for edge selection, which accelerates RNG construction while keeping its k -ANN search performance. Then, we integrate this framework into NSWG construction to enhance both the construction efficiency and k -ANN search performance of NSWG. Extensive experiments are conducted to validate our construction framework for both RNG and NSWG, and that it significantly reduces the PG construction cost, achieving up to 5.6x speedup, while not compromising the k -ANN search performance.

The how-to vlog has gained popularity as a medium for learning practical skills, such as cooking and handcrafting. The sequencing process of these videos should meticulously integrate storytelling and cinematographic elements to ensure audience comprehension and engagement, posing a significant challenge for novice creators. Pioneer efforts have adhered to predefined editing rules or assembled clips based on textual logic, limiting their applicability across diverse educational scenarios and causing visual discontinuities. In contrast, we aim to extract rich cinematographic patterns from well-edited professional how-to vlogs to enhance shot assembly. To this end, we identify two crucial aspects influencing educational value: narrative continuity and scale transition. We model the shot assembly process as a task of selecting the next shot and devise a cinematographic-aware contrastive model to learn representations that distinguish between the good next shots against the bad ones. This method incorporates a two-stream cinematographic-aware encoding module for explicit factor encoding and a situation-adaptive attention-based integration module to accommodate varying assembly scenarios. Quantitative results from our novel professional user-generated vlogs dataset (proVlog-HowTo) clearly demonstrate the proposed method’s effectiveness. User study results further indicate its superiority in generating videos with narrative continuity and smooth transitions.

As device-free identity recognition (IR) gains popularity and the demand for the Internet of Things (IoT) continues to grow, a new-era IR system featuring multiple distributed recognition devices and edge servers faces two main challenges: model adaptability and balancing the personalization of devices with the generalization of the system. This research introducesFedHMIR, a federated framework designed to simultaneously address these challenges by harmonizing human-machine collaboration with personalization-generalization trade-offs. The proposed framework features a human-machine cooperative online internal update mechanism, leveraging reinforcement learning to maintain the adaptability of personalized local IR models. To counter overfitting and enhance the generalization of the overall IR system, an external update process incorporating a confidence index is introduced. Additionally, the framework employs asynchronous internal and external update procedures to effectively balance personalization and generalization between local and global models. Finally, extensive experiments on three diverse real-world datasets demonstrate the effectiveness and advantages ofFedHMIRcompared to state-of-the-art baselines.

The data compression based transmission has been envisioned as a promising solution to improve the data transmission efficiency with the limited radio resources in the future sixth-generation (6G) wireless networks. In this paper, we propose an integrated communication and computation resource allocation system for image transmission based on compressive sensing (CS), which consists of several camera devices and a base station (BS). The device side first compresses the images, after which the compressed images are transmitted using non-orthogonal multiple access (NOMA) transmission, and finally the BS restores the received compressed images. Due to the limited energy supply, the total system energy consumption is minimized by jointly optimizing the image sampling rate, the image data transmission power, the number of floating point operations per second (FLOPS), the time of image compression and the time of data transmission under the constraints of latency and the peak signal-to-noise ratio (PSNR). Due to the non-convexity of the proposed problem, after a series of equal substitutions we convexify the problem. Then, the Karush-Kuhn-Tucker (KKT) condition and the gradient descent method are used to obtain the optimal solution of the target problem. After simulation experiments, it is concluded that the proposed CS-based image transmission scheme effectively reduces the total energy consumption by a factor of 2.7 compared with frequency division multiple access (FDMA), and the total latency by 180% compared with the original image transmission.

With the growing demand for image transmission, there is a need for solutions that offer low energy consumption and low latency. In this paper, we present a novel relay-assisted system based on non-orthogonal multiple access (NOMA) and mobile edge computing (MEC). Our proposed system compresses images at the device end, decompresses them at either a relay or a cloud server (CS). The primary objective is to minimize system energy consumption under given task delay constraints. Considering that this is a non-convex optimization problem, we solve it by decomposing it into a continuous subproblem and a discrete subproblem. To solve the continuous subproblem, we convexify it by introducing new parameters and change variables to get the optimal the computing power of devices, relay and CS, sampling rate of devices, transmission power of devices and relay. To solve the discrete subproblem, we propose a cross-entropy (CE) algorithm to obtain the optimal decompression decision and subcarrier allocation decision. Simulation results demonstrate the accuracy and effectiveness of our algorithm in optimizing total energy consumption compared to the Linear Interactive and General Optimizer (LINGO) and frequency division multiple access (FDMA) methods.

Federated learning (FL) learns an optimal global model by aggregating local models trained on distributed data from different devices. Due to heterogeneous data distributions across devices, local models will be divergent, resulting in the global model’s performance degradation. Recent studies attempt to balance local models to obtain a global model that can adapt to each device. But they ignore a more challenging problem that redundant local models from devices will break the balance, resulting in the global model overfitting redundant local models. Therefore, we propose FedSmooth, a novel global aggregation algorithm. FedSmooth first identifies the redundant local models without sensitive local information (e.g., label distribution), then designs a smooth global aggregation to strengthen the effect of local models that can accelerate finding the optimal global model. Experimental results show that our method outperforms 4 SOTA baseline methods even if there is more redundancy.

Instant delivery has become a fundamental service in people's daily lives. Different from the traditional express service, the instant delivery has a strict shipping time constraint after being ordered. However, the labor shortage makes it challenging to realize efficient instant delivery. To tackle the problem, researchers have studied to introduce vehicles (i.e., taxis) or Unmanned Aerial Vehicles (UAVs or drones) into instant delivery tasks. Unfortunately, the delivery detour of taxis and the limited battery of UAVs make it hard to meet the rapidly increasing instant delivery demands. Under this circumstance, this paper proposes an air-ground cooperative instant delivery paradigm to maximize the delivery performance and meanwhile minimize the negative effects on the taxi passengers. Specifically, a data-driven delivery potential-demands-aware cooperative strategy is designed to improve the overall delivery performance of both UAVs and taxis as well as the taxi passengers' experience. The experimental results show that the proposed method improves the delivery number by 30.1% and 114.5% compared to the taxi-based and UAV-based instant delivery respectively, and shortens the delivery time by 35.7% compared to the taxi-based instant delivery.

Unmanned Aerial Vehicles (UAVs) are widely applied in smart city applications such as urban sensing and delivery, due to the UAVs’ agility, low cost and not being restricted by ground road conditions. However, the limited battery capacity becomes one of the biggest obstacles to the application of UAVs. To address this issue, this paper investigates an emergency response application, in which UAVs generally ride crowdsourced buses to save energy and respond to a stochastic emergency event (such as a traffic accident) when the event occurs. For the bus-based UAV response paradigm, a single UAV response process with the constraint of the bus mobility is first modeled. Subsequently, a data-driven UAV path planning algorithm is designed. Then two emergency response cases by multi-UAV are investigated. One case is irregular emergency response, whose objective is to maximize the temporal-spatial coverage of the urban area. The other case is predictable emergency response, which optimizes the response performance to these emergencies. Thereafter, the bus-stimulating problems for the two cases are formulated and solved. Finally, utilizing a real-world bus trajectory dataset generated by a large-scale bus fleet and a traffic event dataset, the emergency response performance of the bus-based UAV response paradigm is comprehensively evaluated. The results show that (1) with only 30 UAVs, 90% of Shenzhen city can be covered in the irregular emergency response case; (2) with only 50 UAVs, the average response delay to the emergencies is shorter than 1.5 minutes, which is 56% shorter than baselines, in the predictable emergencies response case.

Mobile edge computing has been a promising technology that enables diverse applications of computation-intensive yet latency-sensitive in marine Internet of Things networks. In this paper, we propose a framework of hierarchical computing offloading with the assistance of high altitude platforms (HAPs), and a hybrid transmission scheme of non-orthogonal multiple access (NOMA) and frequency division multiple access (FDMA) is designed for achieving efficient computation offloading. Specifically, the offshore sensing devices (SDs) initially perform computation offloading to the HAPs by forming NOMA groups, and the HAPs further offload partial workload to the onshore base station (BS) via FDMA. For efficient calculation, we aim to minimize the overall delay in completing all the workload processing of these SDs by jointly optimizing the durations of NOMA and FDMA transmission as well as the hierarchical computation offloading workload. Though the problem is in the form of non-convexity, we design an efficient SCA-based algorithm to tackle it. Finally, numerical results demonstrate the optimality and convergence of the proposed algorithm, as well as the performance gains of the proposed scheme.

Internet of Things (IoT) is one of the key applications of 5G, and the data transmission is the basis of IoT networks. In this paper, we investigate the data transmission scheme in non-orthogonal multiple access (NOMA) for IoT networks to minimize the transmission latency. In order to improve the communication efficiency between devices and the base station (BS) without more energy consumption, we deploy an energy harvesting (EH) relay node between devices and the BS for data transmitting and forwarding. Based on this networking model, we first aim at minimizing the transmission latency by jointly optimizing the transmit power of devices and the relay, forwarding ratios among devices, and forwarding time fraction when transmitting a fixed data bits from devices to the BS via the relay under the constraints of energy buffer and data buffer. Noted that the formulated problem is discrete-continuous mixed and non-convex, we apply the deep deterministic policy gradient (DDPG) algorithm in the framework of bisection searching to obtain the optimal solution. Specifically, the bisection searching is used to seek the possible transmission latency, and the DDPG is to check the feasibility of the chosen transmission latency. Finally, the effectiveness of the proposed model-data-driven algorithm is verified by comparing it with other benchmark algorithms, such as LINGO.

The lack of rich visual information affects the shopping experience of the visually impaired (VI), including identifying and selecting commodities. Recent studies on VI assistance have focused on commodity identification but neglected to provide fine-grained and intuitive pick-up guidance, which is not user-friendly enough. Therefore, we propose a user-driven shopping assistance system to improve the shopping experience for VI users. We first conduct an in-depth interview with VI, then implement a prototype shopping assistance system—MobiEye, with real-time video analysis. Further, we evaluate the prototype system and identify two directions to optimizing the existing system: (1) Improving the pick-up accuracy in dense placement; and (2) reducing the latency and communication overhead. To address these two problems, we design a new guidance strategy for dense placements and propose a mobile-edge cocomputing strategy with a motion predictor and a communication gate to filter the transmitted images. Finally, we invited VI participants to evaluate the effectiveness and efficiency of MobiEye. The experimental results show that MobiEye achieved a 13% improvement in pick-up success rate and a 12 s reduction in average pick-up time compared with other shopping assistance systems.

Air pollution seriously affects public health, while effective air quality prediction remains a challenging problem since the complex spatial-temporal couplings exist in multi-area monitoring data of the city. Current approaches rarely consider relative geographical locations when capturing spatial-temporal relations, instead the latent inter-dependencies (i.e., implicit spatial relations) of data as a replacement. However, such relations cannot necessarily reflect the diffusion of air pollutants in the real world, and genuine location-related information could be lost during the implicit relation learning process. In this article, we introduce a new concept, geospatial-temporal data, and propose a novel deep neural network architecture, CoupledGT, to learn the geospatial-temporal couplings within data for air quality prediction. Specifically, the asymmetric diffusion relation of air quality data between two areas is first explicitly represented by the newly developed planar Gaussian diffusion (PGD) equation. And then, a geospatial couplings diffuser (GCD) is designed to parameterize the PGD equation and learn multi-areas diffusion mutually affected geospatial couplings. Besides, the RNN is employed to capture temporal couplings of each area, and incorporated with GCD to learn both shared and unique characteristics of the geospatial-temporal data simultaneously, which empowers the generalization and efficiency of the model. Extensive experiments on two real-world datasets demonstrate our method is robust and outperforms existing baseline methods in air quality prediction tasks.

To meet the growing bike-sharing demands and make people’s travel convenient, the companies need to add new stations at locations where demands exceed supply. Before making reliable decisions on adding new stations, it is required to understand the spatial effects of new stations on the station network. In this paper, we study the deployment of the new station by estimating its varied causal effects on the demands of nearby stations, e.g., how does adding a new station (treatment) causally influence the demands (outcome) of nearby stations? When working with observational data, we should control hidden confounders, which cause spurious relations between treatments and outcomes. However, previous studies use historical data of the individual unit (e.g., the station’s historical demands) to approximate its hidden confounders, which cannot deal with the lack of historical data for new stations. And the conventional methods overlook the differences between units, which cannot be applied to our problem. To overcome the challenges, we propose a novel model (CausalSE) to estimate the varied effects of new stations on nearby stations, which uses the shared knowledge (i.e., similar traveling patterns among stations) to approximate hidden confounders. Experimental results on real-world datasets show that CausalSE outperforms 6 state-of-the-art methods.

Next mobile app recommendation aims to recommend the next app that a user is most likely to use based on the user’s app usage behaviors, which is beneficial for improving user experience, app pre-loading, and system optimization. However, existing works ignore the complex correlations between apps in the app usage sessions. In addition, they do not consider the dynamics of user interests over time. To address these concerns, we propose a novel model named dynamic usage graph network (DUGN) to recommend the next app that a user is most likely to use. To model the complex correlations among apps explicitly, we adopt the dynamic graph structure to learn the dynamics of user interests. Firstly, we extract user interests in each app usage graph by using the hierarchical graph attention mechanism. Secondly, we capture user interests evolving over time, and generate the dynamic user embeddings by modeling the temporal dependencies among multiple app usage graphs. Finally, we obtain the current user interests in the current app usage graph, fuse multiple user interests and generate comprehensive user embeddings for next mobile app recommendation. We conduct experiments on real-world datasets. The results show that our model outperforms the state-of-art recommendation methods.

Ubiquitous Internet of Things (IoT) sensors in the smart city generate various urban utility sequential data, such as electricity and water usage records, which are defined as multivariate utility time series (MUTS). Due to the complex behavior of human beings, MUTS contains more complicated relationships, which go beyond general multivariate time series (TS). Specifically, multifaceted temporal couplings exist in MUTS, including intra-/inter-TS, short-to-long term, evolving, and polarized (positive/negative) relationships. Existing multisequence predictors including the latest deep-learning methods either weaken short-to-long term representation or omit evolving and polarized couplings. This work focuses on MUTS sensory data representation and prediction and proposes a novel approach—CoupledMUTS for multifaceted temporal coupling relational learning. MUTS representation module generates multidimensional representations to reveal short-to-long temporal couplings in MUTS. Gated coupling units (GCUs) module learns evolving couplings by filtering weak positive/negative relations. And dual-stage fusion module integrates multifaceted temporal couplings in both intra-TS and inter-TS for prediction. Extensive experiments on two real-world utility data sets demonstrate that our method outperforms existing shallow and deep models in utility demand prediction.

With the growth of Internet of Things (IoT) devices, smart travel methods, such as sharing-bike and ride-hailing become popular commuting methods. With people’s growing needs and the rapid dynamics in a city environment, simply using a single travel demand for prediction may be insufficient. Alternatively, modeling multiple travel demands simultaneously can deepen our understanding toward the status of these potentially correlated demands and deploy the transportation in the city better. An important observation in this work is that multiple travel demands in a city often show common patterns, referred to as the shared mobility-aware knowledge. In addition, there are also unique patterns that characterize individual travel demand resulting in unique knowledge. To better leverage the shared and unique knowledge, we propose a novel framework (MultiST) to predict multiple spatial–temporal sequences (multiple travel demands) via two components that extract the shared and unique spatial–temporal dependencies, respectively. For the unique component, we use convolutional neural networks and gated recurrent units to embed unique knowledge. For the shared component, we design a recurrent Gaussian cell to extract temporal dependencies. Empirical results show that MultiST outperforms six state-of-the-art baseline methods and three variants of MultiST. We further visualize the temporal dependencies of the shared knowledge and discuss the practical implications.

The cross-domain recommender systems aim to alleviate the data sparsity problem in a target domain by transferring knowledge from a source domain. However, existing works ignore the latent information underlying the user-item interactions. In addition, they don’t explicitly model the intra-domain and cross-domain interactions. To address these concerns, we propose a novel model named cross-graph knowledge transfer network to improve the recommendation performance. To explicitly model intra-domain and cross-domain interactions, we utilize the graph structure to transfer knowledge across domains. Firstly, we design a neighbor sampling method to extract useful intra-domain and cross-domain interactions. Secondly, we aggregate multiple interactive information in each domain and generate intra-domain embeddings by using intra-domain attention mechanism. Thirdly, we fuse the information from two domains to generate effective user and item embeddings by using cross-domain attention mechanism. Finally, we feed user and item embeddings into the domain-specific prediction layers for personalized recommendation. We conduct experiments on real-world datasets. The results show that our model outperforms five state-of-art methods.

In e-commerce platforms, the online descriptive information of products shows significant impacts on the purchase behaviors. To attract potential buyers for product promotion, numerous workers are employed to write the impressive product descriptions. The hand-crafted product descriptions are less-efficient with great labor costs and huge time consumption. Meanwhile, the generated product descriptions do not take consideration into the customization and the diversity to meet users’ interests. To address these problems, we propose one generic framework, namely DeepDepict, to automatically generate the information-rich and personalized product descriptive information. Specifically, DeepDepict leverages the graph attention to retrieve the product-related knowledge from external knowledge base to enrich the diversity of products, constructs the personalized lexicon to capture the linguistic traits of individuals for the personalization of product descriptions, and utilizes multiple pointer-generator network to fuse heterogeneous data from multi-sources to generate informative and personalized product descriptions. We conduct intensive experiments on one public dataset. The experimental results show that DeepDepict outperforms existing solutions in terms of description diversity, BLEU, and personalized degree with significant margin gain, and is able to generate product descriptions with comprehensive knowledge and personalized linguistic traits.

In this paper, we propose a new single-image dehazing method for synthetic and real-world hazy images. Based on the color attenuation prior, this proposed dehazing method improves it in two aspects. First, we estimate the atmospheric light with the haze-lines prior, which is based on the observation that pixel values of a hazy image can be modeled as lines in the RGB color space that intersects at the air-light. Second, the dynamic scattering coefficient, which is an exponential function of image depth, is proposed to replace the constant scattering coefficient. Experimental results demonstrate that the dehazed image of proposed algorithm is clearer and more natural than that of the color attenuation prior. The proposed algorithm can effectively improve the effect of dehazing.

Navigation services using digital maps make people's travel much easier. However, these services often fail to provide specific routes to those destinations that lack micro data in digital maps, such as a small laundry store in a shopping area. In this paper, we propose CrowdNavi, a last mile navigation service in outdoor environments using crowdsourcing based on the guider-follower model. First, we collect trajectories of guiders and images of reference objects along trajectories. To guide followers by reference objects along the route, we design a Semantic Crowd Navigation model to generate fine-grained maps by integrating guiders' data. Second, we design two score functions to fulfill two main requirements and plan hints. Last, we provide context-aware navigation for followers based on the fine-grained map and detect deviation in real-time. Real world experiments conducted in three different areas show that our proposed system in combination with images of reference objects is efficient.

Pedestrians distracted by smartphones are easy to meet with various dangers when crossing or walking on the street, such as the obstacles on the sidewalk (e.g., temporary parking and road repairing). Existing works about pedestrian safety are mostly based on the sensing capabilities from a single device. The surrounding information that can be learned, however, is quite limited or incomplete. Therefore, in many cases the dangers cannot be detected and the pedestrians cannot be alerted. In this paper, a novel system called CrowdWatch is proposed, which leverages mobile crowd sensing and crowd intelligence aggregation to detect temporary obstacles and make effective alerts for distracted walkers. To detect obstacles, we first study the regular rules of pedestrians' avoidance behaviors from the aspects of turn-making and visual contexts. The Dempster-Shafer evidence theory is then used to fuse the behavior and visual contexts, and further calculate the confidence of obstacle existence. Afterwards, we leverage the features of pedestrians' traces to characterize an appropriate dangerous area, which is used to alert distracted walkers. The conducted experiments with 36 participants and different obstacle settings indicate that the crowd-intelligencebased obstacle detection method is effective and the accuracy of reminding attains 83.3%.

Grey system theory has been widely used to forecast the economic data that are often nonlinear, irregular, and nonstationary. Current forecasting models based on grey system theory could adapt to various economic time series data. However, these models ignored the importance of the model parameter optimization and the use of recent data, which lead to poor forecasting accuracy. In this article, we propose a novel forecasting model, called particle swarm optimization rolling grey model (PSO‐RGM(1,1)), based on a rolling mechanism GM with optimized parameters by using the particle swarm optimization algorithm. The simple model is shown to be very effective in forecasting the tertiary industry data sequences, which are short and noisy but regular in secular trend. The experimental results show that PSO‐RGM(1,1) outperforms other commonly used forecasting models on three real economic data sets. Our empirical study shows that PSO is found to be the best overall algorithm to optimize the parameter of RGM compared with other well‐known metaheuristics. Furthermore, we evaluated other variant PSOs and found that single particle PSO outperforms others overall in terms of prediction accuracy, convergence speed, and degree of certainty.