ACM Transactions on Internet Technology最新文献

The voice-based Internet of Multimedia Things (IoMT) is the combination of IoT interfaces and protocols with associated voice-related information, which enables advanced applications based on human-to-device interactions. An example is Automatic Speech Recognition (ASR) for live captioning and voice translation. Three major issues of ASR for IoMT are IoT development cost, speech recognition accuracy, and execution time complexity. For the first issue, most non-voice IoT applications are upgraded with the ASR feature through hard coding, which are error prone. For the second issue, recognition accuracy must be improved for ASR. For the third issue, many multimedia IoT services are real-time applications and, therefore, the ASR delay must be short.

This article elaborates on the above issues based on an IoT platform called VoiceTalk. We built the largest Taiwanese spoken corpus to train VoiceTalk ASR (VT-ASR) and show how the VT-ASR mechanism can be transparently integrated with existing IoT applications. We consider two performance measures for VoiceTalk: speech recognition accuracy and VT-ASR delay. For the acoustic tests of PAL-Labs, VT-ASR's accuracy is 96.47%, while Google's accuracy is 94.28%. We are the first to develop an analytic model to investigate the probability that the VT-ASR delay for the first speaker is complete before the second speaker starts talking. From the measurements and analytic modeling, we show that the VT-ASR delay is short enough to result in a very good user experience. Our solution has won several important government and commercial TV contracts in Taiwan. VT-ASR has demonstrated better Taiwanese Mandarin speech recognition accuracy than famous commercial products (including Google and Iflytek) in Formosa Speech Recognition Challenge 2018 (FSR-2018) and was the best among all participating ASR systems for Taiwanese recognition accuracy in FSR-2020.

Blockchain sharding splits a blockchain into several shards where consensus is reached at the shard level rather than over the entire blockchain. It improves transaction throughput and reduces the computational resources required of individual nodes. But a derivation of trustworthy consensus within a shard becomes an issue as the longest chain based mechanisms used in conventional blockchains can no longer be used. Instead, a vote-based consensus mechanism must be employed. However, existing vote-based Byzantine fault tolerance consensus protocols do not offer sufficient security guarantees for sharded blockchains. First, when used to support consensus where only one block is allowed at a time (binary consensus), these protocols are susceptible to progress-hindering attacks (i.e., unable to reach a consensus). Second, when used to support a stronger type of consensus where multiple concurrent blocks are allowed (strong consensus), their tolerance of adversary nodes is low. This article proposes a new consensus protocol to address all these issues. We call the new protocol MWPoW+, as its basic framework is based on the existing Multiple Winners Proof of Work (MWPoW) protocol but includes new mechanisms to address the issues mentioned previously. MWPoW+ is a vote-based protocol for strong consensus, asynchronous in consensus derivation but synchronous in communication. We prove that it can tolerate up to f < n/2 adversary nodes in a n-node system as if using a binary consensus protocol and does not suffer from progress-hindering attacks.

Computational Linguistics (CL) associated with the Internet of Multimedia Things (IoMT)-enabled multimedia computing applications brings several research challenges, such as real-time speech understanding, deep fake video detection, emotion recognition, home automation, and so on. Due to the emergence of machine translation, CL solutions have increased tremendously for different natural language processing (NLP) applications. Nowadays, NLP-enabled IoMT is essential for its success. Sarcasm detection, a recently emerging artificial intelligence (AI) and NLP task, aims at discovering sarcastic, ironic, and metaphoric information implied in texts that are generated in the IoMT. It has drawn much attention from the AI and IoMT research community. The advance of sarcasm detection and NLP techniques will provide a cost-effective, intelligent way to work together with machine devices and high-level human-to-device interactions. However, existing sarcasm detection approaches neglect the hidden stance behind texts, thus insufficient to exploit the full potential of the task. Indeed, the stance, i.e., whether the author of a text is in favor of, against, or neutral toward the proposition or target talked in the text, largely determines the text’s actual sarcasm orientation. To fill the gap, in this research, we propose a new task: stance-level sarcasm detection (SLSD), where the goal is to uncover the author’s latent stance and based on it to identify the sarcasm polarity expressed in the text. We then propose an integral framework, which consists of Bidirectional Encoder Representations from Transformers (BERT) and a novel stance-centered graph attention networks (SCGAT). Specifically, BERT is used to capture the sentence representation, and SCGAT is designed to capture the stance information on specific target. Extensive experiments are conducted on a Chinese sarcasm sentiment dataset we created and the SemEval-2018 Task 3 English sarcasm dataset. The experimental results prove the effectiveness of the SCGAT framework over state-of-the-art baselines by a large margin.

The proliferation of mobile networked devices has made it easier and faster than ever for people to obtain and share information. However, this occasionally results in the propagation of erroneous information, which may be difficult to distinguish from the truth. The widespread diffusion of such information can result in irrational and poor decision making on potentially important issues. In 2020, this coincided with the global outbreak of Coronavirus Disease (COVID-19), a highly contagious and deadly virus. The proliferation of misinformation about COVID-19 on social media has already been identified as an “infodemic” by the World Health Organization (WHO), posing significant challenges for global governments seeking to manage the pandemic. This has driven an urgent need for methods to automatically detect and identify such misinformation. The research uses multiple deep learning model frameworks to detect misinformation in Chinese and English, and compare them based on different text feature selections. The model learns the textual characteristics of each type of true and misinformation for subsequent true/false prediction. The long and short-term memory (LSTM) model, the gated recurrent unit (GRU) model, and the bidirectional long and short-term memory (BiLSTM) model were selected for fake news detection. BiLSTM produces the best detection result, with detection accuracy reaching 94% for short-sentence English texts, and 99% for long-sentence English texts, while the accuracy for Chinese texts was 82%.

Cyber-manufacturing Systems (CMS) have been growing in popularity. Transitioning from conventional manufacturing to an innovative paradigm that emphasizes innovation, automation, better customer service, and intelligent systems. A new manufacturing model can improve efficiency and productivity, and provide better customer service and response times. In addition, it may revolutionize the way products are produced, from design to completion. Thus, it is likely that this new manufacturing model will become increasingly popular shortly. By building new technologies on top of existing CMS, these systems ensure that data exchange and integration between decentralized systems are reliable and secure. Recently published case studies from industry and the literature support this claim. There are still some challenges to overcome, such as ensuring data reliability, but these can be overcome with further research and development. In summary, the use of CMS can revolutionize the manufacturing industry. This paper comprehensively analyses these systems and their potential applications and implications. The article gives an overview of the field and then explores the various aspects of CMS in greater detail. A taxonomy of the most common and current approaches to cyber-manufacturing systems is presented, including networked cyber-manufacturing systems, distributed cyber-manufacturing systems, cloud-based cyber-manufacturing systems, and cyber-physical systems (CPS). Furthermore, the paper identifies several popular open-source software and datasets and discusses how these resources can reduce barriers to CMS research. In addition, the paper identifies several important issues and research opportunities associated with CMS, including better integration between hardware and software, improved security and privacy protocols, communication protocols, and improved data management systems. The paper provides a comprehensive overview of current technology and valuable insights into the potential impact of the technology on society and industry.

Darknets are probes listening to traffic reaching IP addresses that host no services. Traffic reaching a darknet results from the actions of internet scanners, botnets and possibly misconfigured hosts. Such peculiar nature of the darknet traffic makes darknets a valuable instrument to discover malicious online activities, e.g., identifying coordinated actions performed by bots or scanners. However, the massive amount of packets and sources that darknets observe makes it hard to extract meaningful insights, calling for scalable tools to automatically identify and group sources that share similar behaviour.

We here present i-DarkVec, a methodology to learn meaningful representations of Darknet traffic. i-DarkVec leverages Natural Language Processing techniques (e.g., Word2Vec) to capture the co-occurrence patterns that emerge when scanners or bots launch coordinated actions. As in NLP problems, the embeddings learned with i-DarkVec enable several new machine learning tasks on the darknet traffic, such as identifying clusters of senders engaged in similar activities.

We extensively test i-DarkVec and explore its design space in a case study using real darknets. We show that with a proper definition of services, the learned embeddings can be used to (i) solve the classification problem to associate unknown sources’ IP addresses to the correct classes of coordinated actors, and (ii) automatically identify clusters of previously unknown sources performing similar attacks and scans, easing the security analyst’s job. i-DarkVec leverages a novel incremental embedding learning approach that is scalable and robust to traffic changes, making it applicable to dynamic and large-scale scenarios.

Cyber-Manufacturing combines industrial big data with intelligent analysis to find and understand the intangible problems in decision-making, which requires a systematic method to deal with rich signal data. With the development of spectral detection and photoelectric imaging technology, spectral blind deconvolution has achieved remarkable results. However, spectral processing is limited by one-dimensional signal, there is no available structural information with little training samples. Moreover, in most practical applications, it is feasible to collect unpaired noise and clean spectrum. This training method of unpaired learning is practical and valuable. Therefore, a two-stage deconvolution scheme combining self supervised learning and feature extraction is proposed in this paper, which generates two complementary paired sets through self supervised learning to extract the final deconvolution network. In addition, a new deconvolution network is designed for feature extraction. The spectrum is pre-trained through spectral feature extraction and noise estimation network to improve the training efficiency and meet the assumed noise characteristics. Experimental results show that this method is effective in dealing with different types of synthetic noise.