Generalized referring image segmentation (RIS) aims to segment regions in an image described by a natural language expression, handling not only single-target but also no- and multi-target scenarios. Previous approaches have proposed new components that enable a conventional RIS model to handle these additional scenarios, such as a target presence prediction head for no-target scenarios and multiple mask candidates for multi-target cases. However, we observe that these methods predominantly rely on the conventional RIS backbone without fully integrating the additional components and thus still struggle in such general scenarios. To address this, we propose an effective framework specifically tailored to handle no-target and multi-target scenarios, incorporating both architectural and data-driven approaches. Our architecture employs a learnable query designed to understand both target presence and plurality. While this approach alone outperforms previous state-of-the-art methods with similar computational requirements, we further introduce a novel data augmentation strategy that enables our framework to surpass computationally intensive LMM-based approaches.

In the manufacturing industry, digital twins play a role as a key technology for optimizing the manufacturing environment, such as real-time monitoring of production sites, process optimization, and prediction. Implementing a digital twin involves various challenges, including communication protocols of heterogeneous manufacturing equipment, use of commercial simulators, and reusability of digital twin models. To address these challenges, this study proposes an interoperability-based digital twin simulation framework that connects physical assets such as robots and machines to a simulation platform using standardized digital twin technologies. The proposed framework utilizes standards such as IEC 63278 – Asset Administration Shell and IEC 62541 – OPC UA, which have been suggested for digital twin implementation, to link data from heterogeneous equipment and simulators, enabling the realization of digital twins. Furthermore, the framework allows for bidirectional interaction and system behavior verification by running simulations based on actual equipment data and predefined process flows. Finally, this paper presents the results of performing simulations by linking the proposed framework with a commercial simulator using standard technologies.

Offloading neural network inferences from resource-constrained mobile devices to an edge server over wireless networks is becoming more crucial as the neural networks get heavier. To this end, recent studies have tried to make this offloading process more efficient. However, the most fundamental question on extracting and offloading the minimal amount of necessary information that does not degrade the inference accuracy has remained unanswered. We call such an ideal offloading semantic offloading and propose N-epitomizer, a new offloading framework that enables semantic offloading, thus achieving more reliable and timely inferences in highly-fluctuated or even low-bandwidth wireless networks. To realize N-epitomizer, we design an autoencoder-based scalable encoder trained to extract the most informative data and scale its output size to meet the latency and accuracy requirements of inferences over a network. We also accelerate N-epitomizer by exploiting light-weight knowledge distillation for the encoder design and decoder slimming for the decoder design, reducing its overall computation time significantly. Moreover, we extend our N-epitomizer to support multiple DNNs by extracting and offloading the union of the essential information required for each DNN. Our evaluation shows that N-epitomizer achieves exceptionally high compression for images without compromising inference accuracy, which is 21$\times$, 77$\times$, and 192$\times$higher than JPEG compression, and 20$\times$, 55$\times$, and 86$\times$higher than the state-of-the-art DNN-aware image compression GRACE for semantic segmentation, depth estimation, and classification, respectively. Our results show N-epitomizer’s strong potential as the first semantic offloading system to guarantee end-to-end latency even under highly varying cellular networks.

In this paper, we conduct a measurement study on operational 5G networks deployed across different frequency bands (mmWave and sub-6GHz) and server locations (mobile edge and Internet cloud). Specifically, we assess 5G performance in both uplink and downlink across multiple operators’ networks. We then carry out extensive comparisons of transport-layer protocols using ten different algorithms in full-fledged 5G networks, including an edge computing environment. Finally, we evaluate representative mobile applications over the 5G network with and without edge servers. Our comprehensive measurements provide several insights that affect the experience of 5G users: (i) With a 5G edge server, existing TCP congestion control algorithms can achieve throughput up to 1.8Gbps with only a single flow. (ii) The maximum TCP receive buffer size, which is set by off-the-shelf 5G phones, can limit the throughput performance of 5G networks, which is not observed in 4G LTE-A networks. (iii) Despite significant latency gains in download-centric applications, the 5G edge service provides limited benefits to CPU-intensive tasks or those that use significant uplink bandwidth. To our knowledge, this is the first measurement-driven understanding of 5G edge computing “in the wild,” which can provide an answer to how edge computing would perform in real 5G networks.

In this paper, we present a new transportation mode recognition system for smartphones called DeepVehicleSense, which is widely applicable to mobile context-aware services. DeepVehicleSense aims at achieving three performance objectives: high accuracy, low latency, and low power consumption at once by exploiting sound characteristics captured from the built-in microphone while being on candidate transportations. To attain high energy efficiency, DeepVehicleSense adopts hierarchical accelerometer-based triggers that minimize the activation of the microphone of smartphones. Further, to achieve high accuracy and low latency, DeepVehicleSense makes use of non-linear filters that can best extract the transportation sound samples. For recognition of five different transportation modes, we design a deep learning based sound classifier using a novel deep neural network architecture with multiple branches. Our staged inference technique can significantly reduce runtime and energy consumption while maintaining high accuracy for the majority of samples. Through 263-hour datasets collected by seven different Android phone models, we demonstrate that DeepVehicleSense achieves the recognition accuracy of 97.44% with only sound samples of 2 seconds at the power consumption of 35.08 mW on average for all-day monitoring.

Group activity recognition is the task of understanding the activity conducted by a group of people as a whole in a multiperson video. Existing models for this task are often impractical in that they demand ground-truth bounding box labels of actors even in testing or rely on off-the-shelf object detectors. Motivated by this, we propose a novel model for group activity recognition that depends neither on bounding box labels nor on object detector. Our model based on Transformer localizes and encodes partial contexts of a group activity by leveraging the attention mechanism, and represents a video clip as a set of partial context embeddings. The embedding vectors are then aggregated to form a single group representation that reflects the entire context of an activity while capturing temporal evolution of each partial context. Our method achieves outstanding performance on two benchmarks, Volleyball and NBA datasets, surpassing not only the state of the art trained with the same level of supervision, but also some of existing models relying on stronger supervision.

Video conferencing applications have seen explosive growth both in the number of available applications and their use. However, there have been few studies on the detailed analysis of video conferencing applications with respect to network dynamics, yet understanding these dynamics is essential for network design and improving these applications. In this paper, we carry out an in-depth measurement and modeling study on the rate control algorithms used in six popular commercial video conferencing applications. Based on macroscopic behaviors commonly observed across these applications in our extensive measurements, we construct a unified architecture to model the rate control mechanisms of individual applications. We then reconstruct each application's rate control by inferring key parameters that closely follow its rate control and quality adaptation behaviors. To our knowledge, this is the first work that reverse-engineers rate control algorithms of popular video conferencing applications, which are often unknown or hidden as they are proprietary software. We confirm our analysis and models using an end-to-end testbed that can capture the dynamics of each application under a variety of network conditions. We also show how we can use these models to gain insights into the particular behaviors of an application in two practical scenarios.

The sixth generation of DOCSIS standard is currently under development for the provisioning of multi-Gbps services over cable networks. Building upon DOCSIS 3.1 (D3.1), DOCSIS 4.0 (D4) introduces several features including full-duplex transmission and extended-spectrum, which benefit from subcarrier-level OFDM modulation configurations to adapt to varying channel conditions. To exploit the full potential of D4, we propose a softwarized adaptive subcarrier modulation management framework. The optimization system consists of (i) a clustering mechanism that classifies CMs (Cable Modems) with a similar channel condition into the same group using a sparsified K-means algorithm and (ii) an efficient profile generation mechanism to balance achieved channel throughput and packet error rate within the same group. Then, we implement key elements of the softwarized system using a virtualized network function in our DOCSIS experimental testbed that enables the programmatic control of OFDM channels using D4 performance parameters. Our experimental results show that the proposed optimization function offers significant improvements in OFDM channel throughput over current industry management practices. Furthermore, we confirm via simulations that using a novel clustering algorithm for the classification of CM populations and a new bit-loading method measurably enhances channel performance in large-scale distributed deployment scenarios.

In this paper, we propose SPARCLE, a novel scheduling system offering network-aware polynomial-time task assignment and resource allocation algorithms for stream processing applications in dispersed computing networks. In particular, we address two major challenges. The first one concerns the assignment of both computation and transport tasks comprising a stream processing application to computing nodes and communication links of the network, respectively, to maximize the application's processing rate. The second one concerns the resource allocation of multiple stream processing applications to satisfy their requested QoS. Our experimental results on a real image stream processing application and extensive simulations show that SPARCLE can increase the application's processing rate by 9 times and 3 times, compared to the cloud computing case and state-of-the-art algorithms, respectively.

As video calls and personal broadcasting become popular, the demand for mobile live streaming over cellular uplink channels is growing fast. However, current live streaming solutions are known to suffer from frequent uplink throughput fluctuations causing unnecessary video stalls and quality drops. As a remedy to this problem, we propose PERCEIVE, a deep learning-based uplink throughput prediction framework. PERCEIVE exploits a 2-stage LSTM (Long Short Term Memory) design and makes throughput predictions for the next 100ms. Our extensive evaluations show that PERCEIVE, trained with LTE network traces from three major operators in the U.S., achieves high accuracy in the uplink throughput prediction with only 7.67% mean absolute error and outperforms existing prediction techniques. We integrate PERCEIVE with WebRTC, a popular video streaming platform from Google, as a rate adaptation module. Our implementation on the Android phone demonstrates that it can improve PSNR by up to 6dB (4x) over the default WebRTC while providing less streaming latency.

4G LTE networks across the world (e.g., United States, Europe, and South Korea) use the same mechanism to broadcast emergency alerts. These alerts include AMBER, severe weather alerts, and the (unblockable) Presidential Alert in the US. We demonstrate the ability to spoof these alerts by forcing any 4G phone in the area of our malicious cell tower to receive and display a fabricated message. This demonstration uses a commercially-available software-defined radio, an LTE base station, and our modifications to the open-source NextEPC and srsLTE libraries to send the Presidential Alert to phones volunteered from the audience.

This paper presents a fully distributed scheduling framework called CASTLE (Client-side Adaptive Scheduler That minimizes Load and Energy), which jointly optimizes the spectral efficiency of cellular networks and battery consumption of smart devices. To do so, we focus on scenarios when many smart devices compete for cellular resources in the same base station: spreading out transmissions over time so that only a few devices transmit at once improves both spectral efficiency and battery consumption. To this end, we devise two novel features in CASTLE. First, we explicitly consider inter-cell interference for accurate cellular load estimation. Based on our observations, we exploit the RSRQ (Reference Signal Received Quality) and SINR as features in a machine learning algorithm to accurately estimate the cellular load. Second, we propose a fully distributed scheduling algorithm that coordinates transmissions between clients based on the locally estimated load level at each client. Our formulation for minimizing battery consumption at each device leads to an optimized backoff-based algorithm that fits practical environments. To evaluate these features, we prototype a complete LTE system testbed consisting of mobile devices, eNodeBs, EPC (Evolved Packet Core) and application servers. Our comprehensive experimental results show that CASTLE's load estimation is up to 91% accurate, and that CASTLE achieves higher spectral efficiency with less battery consumption, compared to existing centralized scheduling algorithms as well as a distributed CSMA-like protocol. Furthermore, we develop a light-weight SDK that can expedite the deployment of CASTLE into smart devices and evaluate it in a commercial LTE network.

Modern cell phones are required to receive and display alerts via the Wireless Emergency Alert (WEA) program, under the mandate of the Warning, Alert, and Response Act of 2006. These alerts include AMBER alerts, severe weather alerts, and (unblockable) Presidential Alerts, intended to inform the public of imminent threats. Recently, a test Presidential Alert was sent to all capable phones in the United States, prompting concerns about how the underlying WEA protocol could be misused or attacked. In this paper, we investigate the details of this system, and develop and demonstrate the first practical spoofing attack on Presidential Alerts, using both commercially available hardware as well as modified open source software. Our attack can be performed using a commercially-available software defined radio, and our modifications to the open source NextEPC and srsLTE software libraries. We find that with only four malicious portable base stations of a single Watt of transmit power each, almost all of a 50,000-seat stadium can be attacked with a 90% success rate. The true impact of such an attack would of course depend on the density of cell phones in range; fake alerts in crowded cities or stadiums could potentially result in cascades of panic. Fixing this problem will require a large collaborative effort between carriers, government stakeholders, and cell phone manufacturers. To seed this effort, we also discuss several defenses to address this threat in both the short and long term.

We present the demonstration of a fully distributed scheduling framework called CASTLE (Client-side Adaptive Scheduler That minimizes Load and Energy) that jointly optimizes the spectral efficiency of cellular networks and battery consumption of smart devices. To do so, we focus on scenarios when many smart devices compete for cellular resources in the same base station: spreading out transmissions over time so that only a few devices transmit at once and improves both spectral efficiency and battery consumption. To this end, we devise two novel features in CASTLE. First, we explicitly consider inter-cell interference for accurate cellular load estimation in our machine learning algorithm. Second, we propose a fully distributed scheduling algorithm that coordinates transmissions between clients based on the locally estimated load level at each client. Our formulation for minimizing battery consumption at each device leads to an optimized back off-based algorithm that fits practical environments. Our comprehensive experimental results show that CASTLE's load estimation is up to 91 % accurate, and that CASTLE achieves higher spectral efficiency with less battery consumption, compared to existing centralized scheduling algorithms as well as a distributed CSMA-like protocol. Furthermore,we develop a light-weight SDK that can expedite the deployment of CASTLE into smart devices and evaluate it in a commercial LTE network.

Since the diagnosis of severe bufferbloat in mobile cellular networks, a number of low-latency congestion control algorithms have been proposed. However, due to the need for continuous bandwidth probing in dynamic cellular channels, existing mechanisms are designed to cyclically overload the network. As a result, it is inevitable that their latency deviates from the smallest possible level (i.e., minimum RTT). To tackle this problem, we propose a new low-latency congestion control, ExLL, which can adapt to dynamic cellular channels without overloading the network. To do so, we develop two novel techniques that run on the cellular receiver: 1) cellular bandwidth inference from the downlink packet reception pattern and 2) minimum RTT calibration from the inference on the uplink scheduling interval. Furthermore, we incorporate the control framework of FAST into ExLL's cellular specific inference techniques. Hence, ExLL can precisely control its congestion window to not overload the network unnecessarily. Our implementation of ExLL on Android smartphones demonstrates that ExLL reduces latency much closer to the minimum RTT compared to other low-latency congestion control algorithms in both static and dynamic channels of LTE networks.

There are several ways to improve the quality of experience (QoE) of mobile user equipments (UEs), among which latency reduction has been paid less attention compared to throughput enhancement. In this paper, we consider a new cellular network architecture that puts edge servers closer to UEs (e.g., nearby BS) and present a suitable rate control algorithm, so that we can achieve both lower controllable latency and better fairness without any throughput loss, compared to traditional rate control schemes such as TCP. In the proposal, BS decides the queue threshold to keep a desirable queue length and delivers congestion notification based on the queue differential to the edge server, so the edge server can adjust its rate to reflect wireless channel capacity while maintaining a target queueing delay at BS. Our scheme is beneficial due to (i) UE-agnostic approach and (ii) potential suitability to 5G network architecture under standardization by 3GPP. Via NS-3 simulation we demonstrate that our scheme outperforms popular TCP variants in terms of latency and fairness metrics in several network scenarios.

A new transportation mode recognition system for smartphones, VehicleSense that is widely applicable to mobile context-aware services is proposed. VehicleSense aims at achieving three performance objectives: high accuracy, low latency, and low power consumption at once by exploiting sound characteristics captured from the built-in microphone while being on candidate transportations. To attain high energy efficiency, VehicleSense adopts hierarchical accelerometer-based triggers that minimize the activation of the microphone of smartphones. Further, to attain high accuracy and low latency, VehicleSense makes use of non-linear filters that can best extract the transportation sound samples. Our 186-hour log of sound and accelerometer data collected by seven different Android smartphone models confirms that VehicleSense achieves the recognition accuracy of 98.2% with only 0.5 seconds of sound sampling at the power consumption of 26.1 mW on average for all day monitoring.

Reducing startup delay of video streaming is important for attracting more users. In LTE networks, even though available bandwidth has increased, behavior of TCP, which has a slow start phase and estimates available capacity based on packet loss event, increases the startup delay of video streaming. To solve this issue, we design a proxy-based TCP rate control (PTRC) scheme for achieving low startup delay of mobile video streaming by using the explicit radio related information from a base station (BS). We introduce a target queue length (Qtarget) as feedback information to a proxy, which represents a desired value at the BS. Here, the Qtarget is dynamically calculated by referring to average data rate of a radio link and backhaul delay. Then the proxy is informed of this Qtarget by an in-band signaling message from the BS, and controls its sending rate accordingly. Hence, the proposed PTRC scheme can boost up its transmission rates in the initial phase, and keep instant queue length at the BS close to the Qtarget. We verify that the proposed PTRC scheme achieves about 71.2% reduction of startup delay for mobile video streaming in LTE environment, compared to conventional schemes.

This paper proposes a new protocol called Optimal DCF (O-DCF). O-DCF modifies the rule of adapting CSMA parameters, such as backoff time and transmission length, based on a function of the demand-supply differential of link capacity captured by the local queue length. O-DCF is fully compatible with 802.11 hardware, so that it can be easily implemented only with a simple device driver update. O-DCF is inspired by the recent analytical studies proven to be optimal under assumptions, which often generates a big gap between theory and practice. O-DCF effectively bridges such a gap, which is implemented in off-the-shelf 802.11 chipset. Through extensive simulations and real experiments with a 16-node wireless network testbed, we evaluate the performance of O-DCF and show that it achieves near-optimality in terms of throughput and fairness and outperforms other competitive ones, such as 802.11 DCF, optimal CSMA, and DiffQ for various scenarios. Also, we consider the coexistence of O-DCF and 802.11 DCF and show that O-DCF fairly shares the medium with 802.11 via its parameter control.

As smartphones have become increasingly pervasive, large amount of mobile data traffic has started to overwhelm the networks. Surprisingly, according to [1], the main cause of network congestion in cellular networks today is not only the data traffic generated by smartphones, but also the underlying signaling from the smartphone applications such as push email, instant messaging, and social network services. Such signaling is inevitable as the service providers need to provide always connected service to users. Among multiple signaling burdens, we consider “keepalive” message that is widely used to make a persistent IP connection for most push services in order to keep Network Address Translation (NAT) tables refreshed. Keepalive messages not only overburden the cellular network due to accompanied signaling traffics, but also significantly reduce the battery life of smartphones. In this paper, we propose a method that makes the push service possible without a keepalive mechanism for NATted network system. When the application servers have data to send to some UE given that the UE's information such as IP address and port number is not available in the servers, they first request this information from the network instead of maintaining a persistent IP connection. Our proposal helps increasing the battery life of the smartphone and relieving the overhead of the network. Simulation results show that the proposed scheme can reduce both battery power consumption and signaling traffic of UE by more than about 30% and 20%, respectively, compared to the keepalive-based legacy mechanism.

This paper proposes a new wireless MAC protocol called Optimal DCF (O-DCF). O-DCF modifies the rule of adapting CSMA parameters, such as backoff time and transmission length, based on a function of the supply-demand differential captured by the local queue length. O-DCF is fully compatible with 802.11 hardware, so that it can be easily implemented only with a simple device driver update. O-DCF is inspired by the recent theoretical studies on queue-based CSMA for high throughput and fairness. O-DCF effectively bridges the gap between theory and practice, implemented and tested in an off-the-shelf 802.11 chipset. Through extensive simulations and real experiments with a 16-node wireless network testbed, we evaluate the performance of O-DCF and show that it outperforms other competitive ones, such as 802.11 DCF, optimal CSMA, and DiffQ for various scenarios.

By `optimal CSMA' we denote a promising approach to maximize throughput-based utility in wireless networks without message passing or synchronization among nodes. Despite the theoretical guarantees on the performance of these protocols, their evaluation in real networking scenarios has been preliminary. In this paper, we propose a methodical approach for the first comprehensive evaluation of optimal CSMA, via experimentation with a custom implementation. Example findings include; 1) hidden terminals with symmetric channels can drive the protocol to a state of extreme contention aggressiveness due to the low service received by flows. Since increasing aggressiveness does not mitigate collisions but actually aggravates them, optimal CSMA enters a positive-feedback loop eventually reaching a deadlock state of total flow starvation; 2) however, the use of RTS/CTS in such scenarios can reduce collisions to lower levels, restoring throughput and preventing an excessive contention aggressiveness by optimal CSMA flows; 3) in practical hidden terminal scenarios with physical layer capture optimal CSMA reduces the aggressiveness of dominant flows, but the contention window sizes used by such adaptation mechanism are not long enough to solve competing flows' starvation when carrier sensing fails; 4) topologies with a “flow-in-the-middle” yield starvation in traditional CSMA but fairness in optimal CSMA, because its contention aggressiveness adaptation creates frequent transmission opportunities for the central (otherwise starved) flow; 5) optimal CSMA excessively prioritizes links with low channel quality, due to queue-based control that does not otherwise incorporate channel conditions; 6) in its current design, optimal CSMA conflicts with window-based end-to-end congestion control, and leads to a efficiency-fairness tradeoff in TCP performance. This study deepens our understanding of optimal CSMA and the general adaptation philosophy behind its design, and the derived insights suggest enhancements to optimal CSMA theory.

A wireless mesh network (WMN) is being considered for commercial use in spite of several unaddressed issues. In this paper we focus on one of the most critical issues: the impact of ambient motion of entities like people on the channel characteristics and on the WMN performance. A human body in an electro-magnetic (EM) field acts as an scatterer that absorbs 60% of incident EM energy, thereby shadowing the receiver. This human body model along with the human mobility behavior gives rise to a black body (a group movement) effect that traps the incident EM wave with repetitive internal reflections. The black body theory is verified by simulating the WiSEMesh testbed in picoKAIST, a tool based on deterministic ray tube method. Experimental results show each link exhibiting a unique channel variation pattern in presence of the black body. Based on the pattern we provide several insights in WMN deployment and protocol design.