With the rapid prevalence of smart mobile devices and the dramatic proliferation of location-based social networks (LBSNs), location-based recommendation has become an important means to help people discover attractive and interesting points of interest (POIs). However, the extreme sparsity of user-POI matrix and cold-start issue create severe challenges, causing CF-based methods to degrade significantly in their recommendation performance. Moreover, location-based recommendation requires spatiotemporal context awareness and dynamic tracking of the user's latest preferences in a real-time manner.
Hardened adder and carry logic is widely used in commercial FPGAs to improve the efficiency of arithmetic functions. There are many design choices and complexities associated with such hardening, including circuit design, FPGA architectural choices, and the CAD flow. There has been very little study, however, on these choices and hence we explore a number of possibilities for hard adder design. We also highlight optimizations during front-end elaboration that help ameliorate the restrictions placed on logic synthesis by hardened arithmetic. We show that hard adders and carry chains, when used for simple adders, increase performance by a factor of four or more, but on larger benchmark designs that contain arithmetic, improve overall performance by roughly 15%. We measure an average area increase of 5% for architectures with carry chains but believe that better logic synthesis should reduce this penalty. Interestingly, we show that adding dedicated inter-logic-block carry links or fast carry look-ahead hardened adders result in only minor delay improvements for complete designs.
Many natural language processing tasks solely rely on sparse dependencies between a few tokens in a sentence. Soft attention mechanisms show promising performance in modeling local/global dependencies by soft probabilities between every two tokens, but they are not effective and efficient when applied to long sentences. By contrast, hard attention mechanisms directly select a subset of tokens but are difficult and inefficient to train due to their combinatorial nature. In this paper, we integrate both soft and hard attention into one context fusion model, "reinforced self-attention (ReSA)", for the mutual benefit of each other. In ReSA, a hard attention trims a sequence for a soft self-attention to process, while the soft attention feeds reward signals back to facilitate the training of the hard one. For this purpose, we develop a novel hard attention called "reinforced sequence sampling (RSS)", selecting tokens in parallel and trained via policy gradient. Using two RSS modules, ReSA efficiently extracts the sparse dependencies between each pair of selected tokens. We finally propose an RNN/CNN-free sentence-encoding model, "reinforced self-attention network (ReSAN)", solely based on ReSA. It achieves state-of-the-art performance on both Stanford Natural Language Inference (SNLI) and Sentences Involving Compositional Knowledge (SICK) datasets.
Activity recognition is a core component of ubiquitous computing applications (e.g., fall detection of elder people) since many of such applications require an intelligent environment to infer what a person is doing or attempting to do. Unfortunately, the success of existing approaches on activity recognition relies heavily on people's involvement such as wearing battery-powered sensors, which might not be practical in real-world situations (e.g., people may forget to wear sensors). In this paper, we propose a device-free, real-time posture recognition technique using an array of pure passive RFID tags. In particular, posture recognition is treated as a machine learning problem where a series of probabilistic model is built via learning how the Received Signal Strength Indicator (RSSI) from the tag array is distributed when a person performs different postures. We also design a segmentation algorithm to divide the continuous, multidimensional RSSI data stream into a set of individual segments by analyzing the shape of the RSSI data. Our approach for posture recognition eliminates the need for the monitored subjects to wear any devices. To the best of our knowledge, this work is the first on device-free posture recognition using low cost, unobtrusive RFID technology. Our experimental studies demonstrate the feasibility of the proposed approach for posture recognition.
As brain dynamics fluctuate considerably across different subjects, it is challenging to design effective handcrafted features based on prior knowledge. Regarding this gap, this paper proposes a Graph-based Convolutional Recurrent Attention Model (G-CRAM) to explore EEG features across different subjects for movement intention recognition. A graph structure is first developed to embed the positioning information of EEG nodes, and then a convolutional recurrent attention model learns EEG features from both spatial and temporal dimensions and adaptively emphasizes on the most distinguishable temporal periods. The proposed approach is validated on two public movement intention EEG datasets. The results show that the GCRAM achieves superior performance to state-of-the-art methods regarding recognition accuracy and ROC-AUC. Furthermore, model interpreting studies reveal the learning process of different neural network components and demonstrate that the proposed model can extract detailed features efficiently.
To explore the clustered voltage balancing mechanism of the star-connected cascaded H-Bridge (SCHB) STATCOM, this paper analyzes the relationship between the active power and the control variables-modulation reference voltages in a dq frame through positive and negative sequence component decomposition. The derived relationship in the dq frame reveals that the negative sequence modulation reference voltage is capable of redistributing the active power among three phases and also the SCHB STATCOM features the clustered voltage self-stabilizing without any additional clustered voltage balancing control. To eliminate the differences of three clustered voltages, a new clustered voltage balancing control is proposed by regulating negative sequence modulation reference voltage in the dq frame. Its balancing mechanism is analyzed in detail and a simple implementation is presented as well. The effectiveness of the proposed control is verified by experimental results on a 400 V/15 kvar SCHB STATCOM.
The staggering amounts of content readily available to us via digital channels can often appear overwhelming. While much research has focused on aiding people at selecting relevant articles to read, only few approaches have been developed to assist readers in more efficiently reading an individual text. In this paper, we present HiText, a simple yet effective way of dynamically marking parts of a document in accordance with their salience. Rather than skimming a text by focusing on randomly chosen sentences, students and other readers can direct their attention to sentences determined to be important by our system. For this, we rely on a deep learning-based sentence ranking method. Our experiments show that this results in marked increases in user satisfaction and reading efficiency, as assessed using TOEFL-style reading comprehension tests.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
'/%3e%3c/defs%3e%3cpath fill='%23012169' d='M0 0h10080v5040H0z'/%3e%3cpath stroke='%23fff' stroke-width='.6' d='m0 0 6 3m0-3L0 3' clip-path='url(%23b)' transform='scale(840)'/%3e%3cpath stroke='%23e4002b' stroke-width='.4' d='m0 0 6 3m0-3L0 3' clip-path='url(%23c)' transform='scale(840)'/%3e%3cpath stroke='%23fff' stroke-width='840' d='M2520 0v2520M0 1260h5040'/%3e%3cpath stroke='%23e4002b' stroke-width='504' d='M2520 0v2520M0 1260h5040'/%3e%3cg fill='%23fff'%3e%3cuse xlink:href='%23d' x='2520' y='3780'/%3e%3cuse xlink:href='%23a' x='7560' y='4200'/%3e%3cuse xlink:href='%23a' x='6300' y='2205'/%3e%3cuse xlink:href='%23a' x='7560' y='840'/%3e%3cuse xlink:href='%23a' x='8680' y='1869'/%3e%3cuse xlink:href='%23e' x='8064' y='2730'/%3e%3c/g%3e%3c/svg%3e)
