Institute of Software

The central building block of convolutional neural networks (CNNs) is the convolution operator, which enables networks to construct informative features by fusing both spatial and channel-wise information within local receptive fields at each layer. A broad range of prior research has investigated the spatial component of this relationship, seeking to strengthen the representational power of a CNN by enhancing the quality of spatial encodings throughout its feature hierarchy. In this work, we focus instead on the channel relationship and propose a novel architectural unit, which we term the "Squeeze-and-Excitation" (SE) block, that adaptively recalibrates channel-wise feature responses by explicitly modelling interdependencies between channels. We show that these blocks can be stacked together to form SENet architectures that generalise extremely effectively across different datasets. We further demonstrate that SE blocks bring significant improvements in performance for existing state-of-the-art CNNs at slight additional computational cost. Squeeze-and-Excitation Networks formed the foundation of our ILSVRC 2017 classification submission which won first place and reduced the top-5 error to 2.251 percent, surpassing the winning entry of 2016 by a relative improvement of ∼ 25 percent. Models and code are available at https://github.com/hujie-frank/SENet.

In 2008 we published the first set of guidelines for standardizing research in autophagy. Since then, research on this topic has continued to accelerate, and many new scientists have entered the field. Our knowledge base and relevant new technologies have also been expanding. Accordingly, it is important to update these guidelines for monitoring autophagy in different organisms. Various reviews have described the range of assays that have been used for this purpose. Nevertheless, there continues to be confusion regarding acceptable methods to measure autophagy, especially in multicellular eukaryotes. For example, a key point that needs to be emphasized is thatthere is a difference between measurements that monitor the numbers or volume of autophagic elements (e.g., autophagosomes or autolysosomes) at any stage of the autophagic process versus those that measure flux through the autophagy pathway (i.e., the completeprocess including the amount and rate of cargo sequestered and degraded). In particular, a block in macroautophagy that results in autophagosome accumulation must be differentiated from stimuli that increase autophagic activity, defined as increasedautophagy induction coupled with increased delivery to, and degradation within, lysosomes (inmost higher eukaryotes and some protists such as Dictyostelium) or the vacuole (in plants and fungi). In other words, it is especially important that investigators new to the field understand that the appearance of more autophagosomes does not necessarily equate with more autophagy. In fact, in manycases, autophagosomes accumulate because of a block in trafficking to lysosomes without a concomitant change in autophagosome biogenesis, whereas an increase in autolysosomes may reflect a reduction in degradative activity. It is worth emphasizing here that lysosomal digestion is a stage of autophagy and evaluating its competence is a crucial part of the evaluation of autophagic flux, or complete autophagy. Here, we present a set of guidelines for the selection and interpretation of methods for use by investigators who aim to examine macroautophagy and related processes, as well as forreviewers who need to provide realistic and reasonable critiques of papers that are focused on these processes. These guidelines are not meant to be a formulaic set of rules, because the appropriate assays depend in part on the question being asked and the system being used. In addition, we emphasize that no individual assay is guaranteed to be the most appropriate one in every situation, and we strongly recommend the use of multipleassays to monitor autophagy. Along these lines, because of the potential for pleiotropic effects due to blocking autophagy through genetic manipulation, it is imperative to target by gene knockout or RNA interference more than one autophagyrelated protein. In addition, some individual Atg proteins, or groups of proteins, are involved in other cellular pathways implying that not all Atg proteins can be used as a specific marker for an autophagic process. In these guidelines, we consider these various methods of assessing autophagy and what information can, or cannot, be obtained from them. Finally, by discussing the merits and limits of particular assays, we hope to encourage technical innovation in the field.

Compared to black-box neural networks, logic rules express explicit knowledge, can provide human-understandable explanations for reasoning processes, and have found their wide application in knowledge graphs and other downstream tasks. As extracting rules manually from large knowledge graphs is labour-intensive and often infeasible, automated rule learning has recently attracted significant interest, and a number of approaches to rule learning for knowledge graphs have been proposed. This survey aims to provide a review of approaches and a classification of state-of-the-art systems for learning first-order logic rules over knowledge graphs. A comparative analysis of various approaches to rule learning is conducted based on rule language biases, underlying methods, and evaluation metrics. The approaches we consider include inductive logic programming (ILP)-based, statistical path generalisation, and neuro-symbolic methods. Moreover, we highlight important and promising application scenarios of rule learning, such as rule-based knowledge graph completion, fact checking, and applications in other research areas.

Artificial intelligence (AI) coupled with promising machine learning (ML) techniques well known from computer science is broadly affecting many aspects of various fields including science and technology, industry, and even our day-to-day life. The ML techniques have been developed to analyze high-throughput data with a view to obtaining useful insights, categorizing, predicting, and making evidence-based decisions in novel ways, which will promote the growth of novel applications and fuel the sustainable booming of AI. This paper undertakes a comprehensive survey on the development and application of AI in different aspects of fundamental sciences, including information science, mathematics, medical science, materials science, geoscience, life science, physics, and chemistry. The challenges that each discipline of science meets, and the potentials of AI techniques to handle these challenges, are discussed in detail. Moreover, we shed light on new research trends entailing the integration of AI into each scientific discipline. The aim of this paper is to provide a broad research guideline on fundamental sciences with potential infusion of AI, to help motivate researchers to deeply understand the state-of-the-art applications of AI-based fundamental sciences, and thereby to help promote the continuous development of these fundamental sciences.

In this article, we revisit two popular convolutional neural networks in person re-identification (re-ID): verification and identification models. The two models have their respective advantages and limitations due to different loss functions. Here, we shed light on how to combine the two models to learn more discriminative pedestrian descriptors. Specifically, we propose a Siamese network that simultaneously computes the identification loss and verification loss. Given a pair of training images, the network predicts the identities of the two input images and whether they belong to the same identity. Our network learns a discriminative embedding and a similarity measurement at the same time, thus taking full usage of the re-ID annotations. Our method can be easily applied on different pretrained networks. Albeit simple, the learned embedding improves the state-of-the-art performance on two public person re-ID benchmarks. Further, we show that our architecture can also be applied to image retrieval. The code is available at https://github.com/layumi/2016_person_re-ID.

Specialized computational chemistry packages have permanently reshaped the landscape of chemical and materials science by providing tools to support and guide experimental efforts and for the prediction of atomistic and electronic properties. In this regard, electronic structure packages have played a special role by using first-principle-driven methodologies to model complex chemical and materials processes. Over the past few decades, the rapid development of computing technologies and the tremendous increase in computational power have offered a unique chance to study complex transformations using sophisticated and predictive many-body techniques that describe correlated behavior of electrons in molecular and condensed phase systems at different levels of theory. In enabling these simulations, novel parallel algorithms have been able to take advantage of computational resources to address the polynomial scaling of electronic structure methods. In this paper, we briefly review the NWChem computational chemistry suite, including its history, design principles, parallel tools, current capabilities, outreach, and outlook.

Relation classification is an important research arena in the field of natural language processing (NLP). In this paper, we present SDP-LSTM, a novel neural network to classify the relation of two entities in a sentence. Our neural architecture leverages the shortest dependency path (SDP) between two entities; multichannel recurrent neural networks, with long short term memory (LSTM) units, pick up heterogeneous information along the SDP. Our proposed model has several distinct features: (1) The shortest dependency paths retain most relevant information (to relation classification), while eliminating irrelevant words in the sentence. (2) The multichannel LSTM networks allow effective information integration from heterogeneous sources over the dependency paths. (3) A customized dropout strategy regularizes the neural network to alleviate overfitting. We test our model on the SemEval 2010 relation classification task, and achieve an F 1 -score of 83.7%, higher than competing methods in the literature.

Specialized computational chemistry packages have permanently reshaped the landscape of chemical and materials science by providing tools to support and guide experimental efforts and for the prediction of atomistic and electronic properties. In this regard, electronic structure packages have played a special role by using first-principle-driven methodologies to model complex chemical and materials processes. Over the past few decades, the rapid development of computing technologies and the tremendous increase in computational power have offered a unique chance to study complex transformations using sophisticated and predictive many-body techniques that describe correlated behavior of electrons in molecular and condensed phase systems at different levels of theory. In enabling these simulations, novel parallel algorithms have been able to take advantage of computational resources to address the polynomial scaling of electronic structure methods. In this paper, we briefly review the NWChem computational chemistry suite, including its history, design principles, parallel tools, current capabilities, outreach, and outlook.

This paper presents the design and implementation of RT-Fall, a real-time, contactless, low-cost yet accurate indoor fall detection system using the commodity WiFi devices. RT-Fall exploits the phase and amplitude of the fine-grained Channel State Information (CSI) accessible in commodity WiFi devices, and for the first time fulfills the goal of segmenting and detecting the falls automatically in real-time, which allows users to perform daily activities naturally and continuously without wearing any devices on the body. This work makes two key technical contributions. First, we find that the CSI phase difference over two antennas is a more sensitive base signal than amplitude for activity recognition, which can enable very reliable segmentation of fall and fall-like activities. Second, we discover the sharp power profile decline pattern of the fall in the time-frequency domain and further exploit the insight for new feature extraction and accurate fall segmentation/detection. Experimental results in four indoor scenarios demonstrate that RT-fall consistently outperforms the state-of-the-art approach WiFall with 14 percent higher sensitivity and 10 percent higher specificity on average.

How fake news goes viral via social media? How does its propagation pattern differ from real stories? In this paper, we attempt to address the problem of identifying rumors, i.e., fake information, out of microblog posts based on their propagation structure. We firstly model microblog posts diffusion with propagation trees, which provide valuable clues on how an original message is transmitted and developed over time. We then propose a kernel-based method called Propagation Tree Kernel, which captures high-order patterns differentiating different types of rumors by evaluating the similarities between their propagation tree structures. Experimental results on two real-world datasets demonstrate that the proposed kernel-based approach can detect rumors more quickly and accurately than state-ofthe-art rumor detection models.

Automatic rumor detection is technically very challenging. In this work, we try to learn discriminative features from tweets content by following their non-sequential propagation structure and generate more powerful representations for identifying different type of rumors. We propose two recursive neural models based on a bottom-up and a top-down tree-structured neural networks for rumor representation learning and classification, which naturally conform to the propagation layout of tweets. Results on two public Twitter datasets demonstrate that our recursive neural models 1) achieve much better performance than state-of-the-art approaches; 2) demonstrate superior capacity on detecting rumors at very early stage.

The massive data generated by the Internet of Things (IoT) are considered of high business value, and data mining algorithms can be applied to IoT to extract hidden information from data. In this paper, we give a systematic way to review data mining in knowledge view, technique view, and application view, including classification, clustering, association analysis, time series analysis and outlier analysis. And the latest application cases are also surveyed. As more and more devices connected to IoT, large volume of data should be analyzed, the latest algorithms should be modified to apply to big data. We reviewed these algorithms and discussed challenges and open research issues. At last a suggested big data mining system is proposed.

Matching images and sentences demands a fine understanding of both modalities. In this article, we propose a new system to discriminatively embed the image and text to a shared visual-textual space. In this field, most existing works apply the ranking loss to pull the positive image/text pairs close and push the negative pairs apart from each other. However, directly deploying the ranking loss on heterogeneous features (i.e., text and image features) is less effective, because it is hard to find appropriate triplets at the beginning. So the naive way of using the ranking loss may compromise the network from learning inter-modal relationship. To address this problem, we propose the instance loss, which explicitly considers the intra-modal data distribution. It is based on an unsupervised assumption that each image/text group can be viewed as a class. So the network can learn the fine granularity from every image/text group. The experiment shows that the instance loss offers better weight initialization for the ranking loss, so that more discriminative embeddings can be learned. Besides, existing works usually apply the off-the-shelf features, i.e., word2vec and fixed visual feature. So in a minor contribution, this article constructs an end-to-end dual-path convolutional network to learn the image and text representations. End-to-end learning allows the system to directly learn from the data and fully utilize the supervision. On two generic retrieval datasets (Flickr30k and MSCOCO), experiments demonstrate that our method yields competitive accuracy compared to state-of-the-art methods. Moreover, in language-based person retrieval, we improve the state of the art by a large margin. The code has been made publicly available.

Despite three decades of intensive research efforts, it remains an open question as to what is the underlying distribution of user-generated passwords. In this paper, we make a substantial step forward toward understanding this foundational question. By introducing a number of computational statistical techniques and based on 14 large-scale data sets, which consist of 113.3 million real-world passwords, we, for the first time, propose two Zipf-like models (i.e., PDF-Zipf and CDF-Zipf) to characterize the distribution of passwords. More specifically, our PDF-Zipf model can well fit the popular passwords and obtain a coefficient of determination larger than 0.97; our CDF-Zipf model can well fit the entire password data set, with the maximum cumulative distribution function (CDF) deviation between the empirical distribution and the fitted theoretical model being 0.49%~4.59% (on an average 1.85%). With the concrete knowledge of password distributions, we suggest a new metric for measuring the strength of password data sets. Extensive experimental results show the effectiveness and general applicability of the proposed Zipf-like models and security metric.

BACKGROUND: The plant microbiome is an integral part of the host and increasingly recognized as playing fundamental roles in plant growth and health. Increasing evidence indicates that plant rhizosphere recruits beneficial microbes to the plant to suppress soil-borne pathogens. However, the ecological processes that govern plant microbiome assembly and functions in the below- and aboveground compartments under pathogen invasion are not fully understood. Here, we studied the bacterial and fungal communities associated with 12 compartments (e.g., soils, roots, stems, and fruits) of chili pepper (Capsicum annuum L.) using amplicons (16S and ITS) and metagenomics approaches at the main pepper production sites in China and investigated how Fusarium wilt disease (FWD) affects the assembly, co-occurrence patterns, and ecological functions of plant-associated microbiomes. RESULTS: The amplicon data analyses revealed that FWD affected less on the microbiome of pepper reproductive organs (fruit) than vegetative organs (root and stem), with the strongest impact on the upper stem epidermis. Fungal intra-kingdom networks were less stable and their communities were more sensitive to FWD than the bacterial communities. The analysis of microbial interkingdom network further indicated that FWD destabilized the network and induced the ecological importance of fungal taxa. Although the diseased plants were more susceptible to colonization by other pathogenic fungi, their below- and aboveground compartments can also recruit potential beneficial bacteria. Some of the beneficial bacterial taxa enriched in the diseased plants were also identified as core taxa for plant microbiomes and hub taxa in networks. On the other hand, metagenomic analysis revealed significant enrichment of several functional genes involved in detoxification, biofilm formation, and plant-microbiome signaling pathways (i.e., chemotaxis) in the diseased plants. CONCLUSIONS: Together, we demonstrate that a diseased plant could recruit beneficial bacteria and mitigate the changes in reproductive organ microbiome to facilitate host or its offspring survival. The host plants may attract the beneficial microbes through the modulation of plant-microbiome signaling pathways. These findings significantly advance our understanding on plant-microbiome interactions and could provide fundamental and important data for harnessing the plant microbiome in sustainable agriculture. Video abstract.

Many researchers propose that, not only functional but also non-functional properties, also known as quality of service (QoS), should be taken into consideration when consumers select services. Consumers need to make prediction on quality of unused web services before selecting. Usually, this prediction is based on other consumers' experiences. Being aware of different QoS experiences of consumers, this paper proposes a collaborative filtering based approach to making similarity mining and prediction from consumers' experiences. Experimental results demonstrate that this approach can make significant improvement on the effectiveness of QoS prediction for web services.

Cloud Computing is becoming a well-known buzzword nowadays. Many companies, such as Amazon, Google, Microsoft and so on, accelerate their paces in developing Cloud Computing systems and enhancing their services to provide for a larger amount of users. However, security and privacy issues present a strong barrier for users to adapt into Cloud Computing systems. In this paper, we investigate several Cloud Computing system providers about their concerns on security and privacy issues. We find those concerns are not adequate and more should be added in terms of five aspects (i.e., availability, confidentiality, data integrity, control, audit) for security. Moreover, released acts on privacy are out of date to protect users' private information in the new environment (i.e., Cloud Computing system environment) since they are no longer applicable to the new relationship between users and providers, which contains three parties (i.e., Cloud service user, Cloud service provider/Cloud user, Cloud provider). Multi located data storage and services (i.e., applications) in the Cloud make privacy issues even worse. Hence, adapting released acts for new scenarios in the Cloud, it will result in more users to step into Cloud. We claim that the prosperity in Cloud Computing literature is to be coming after those security and privacy issues having be resolved.

With the development of sensor, wireless mobile communication, embedded system and cloud computing, the technologies of Internet of Things have been widely used in logistics, Smart Meter, public security, intelligent building and so on. Because of its huge market prospects, Internet of Things has been paid close attention by several governments all over the world, which is regarded as the third wave of information technology after Internet and mobile communication network. Bridging between wireless sensor networks with traditional communication networks or Internet, IOT Gateway plays an important role in IOT applications, which facilitates the seamless integration of wireless sensor networks and mobile communication networks or Internet, and the management and control with wireless sensor networks. In this paper, we proposed an IOT Gateway system based on Zigbee and GPRS protocols according to the typical IOT application scenarios and requirements from telecom operators, presented the data transmission between wireless sensor networks and mobile communication networks, protocol conversion of different sensor network protocols, and control functionalities for sensor networks, and finally gave an implementation of prototyping system and system validation.

Pre-trained large language models (LLMs) have recently emerged as a breakthrough technology in natural language processing and artificial intelligence, with the ability to handle large-scale datasets and exhibit remarkable performance across a wide range of tasks. Meanwhile, software testing is a crucial undertaking that serves as a cornerstone for ensuring the quality and reliability of software products. As the scope and complexity of software systems continue to grow, the need for more effective software testing techniques becomes increasingly urgent, making it an area ripe for innovative approaches such as the use of LLMs. This paper provides a comprehensive review of the utilization of LLMs in software testing. It analyzes 102 relevant studies that have used LLMs for software testing, from both the software testing and LLMs perspectives. The paper presents a detailed discussion of the software testing tasks for which LLMs are commonly used, among which test case preparation and program repair are the most representative. It also analyzes the commonly used LLMs, the types of prompt engineering that are employed, as well as the accompanied techniques with these LLMs. It also summarizes the key challenges and potential opportunities in this direction. This work can serve as a roadmap for future research in this area, highlighting potential avenues for exploration, and identifying gaps in our current understanding of the use of LLMs in software testing.

The past few years have witnessed the great potential of exploiting channel state information retrieved from commodity WiFi devices for respiration monitoring. However, existing approaches only work when the target is close to the WiFi transceivers and the performance degrades significantly when the target is far away. On the other hand, most home environments only have one WiFi access point and it may not be located in the same room as the target. This sensing range constraint greatly limits the application of the proposed approaches in real life. This paper presents FarSense--the first real-time system that can reliably monitor human respiration when the target is far away from the WiFi transceiver pair. FarSense works well even when one of the transceivers is located in another room, moving a big step towards real-life deployment. We propose two novel schemes to achieve this goal: (1) Instead of applying the raw CSI readings of individual antenna for sensing, we employ the ratio of CSI readings from two antennas, whose noise is mostly canceled out by the division operation to significantly increase the sensing range; (2) The division operation further enables us to utilize the phase information which is not usable with one single antenna for sensing. The orthogonal amplitude and phase are elaborately combined to address the "blind spots" issue and further increase the sensing range. Extensive experiments show that FarSense is able to accurately monitor human respiration even when the target is 8 meters away from the transceiver pair, increasing the sensing range by more than 100%.1 We believe this is the first system to enable through-wall respiration sensing with commodity WiFi devices and the proposed method could also benefit other sensing applications.