Biblio
Diversity has been identified as one of the key dimensions of recommendation utility that should be considered besides the overall accuracy of the system. A common diversification approach is to rerank results produced by a baseline recommendation engine according to a diversification criterion. The intent-aware framework is one of the frameworks that has been proposed for recommendations diversification. It assumes existence of a set of aspects associated with items, which also represent user intentions, and the framework promotes diversity across the aspects to address user expectations more accurately. In this paper we consider item-based collaborative filtering and suggest that the traditional view of item similarity is lacking a user perspective. We argue that user preferences towards different aspects should be reflected in recommendations produced by the system. We incorporate the intent-aware framework into the item-based recommendation algorithm by injecting personalised intent-aware covariance into the item similarity measure, and explore the impact of such change on the performance of the algorithm. Our experiments show that the proposed method improves both accuracy and diversity of recommendations, offering better accuracy/diversity tradeoff than existing solutions.
Multi-Objective Recommender Systems (MO-RS) consider several objectives to produce useful recommendations. Besides accuracy, other important quality metrics include novelty and diversity of recommended lists of items. Previous research up to this point focused on naive combinations of objectives. In this paper, we present a new and adaptable strategy for prioritizing objectives focused on users' preferences. Our proposed strategy is based on meta-features, i.e., characteristics of the input data that are influential in the final recommendation. We conducted a series of experiments on three real-world datasets, from which we show that: (i) the use of meta-features leads to the improvement of the Pareto solution set in the search process; (ii) the strategy is effective at making choices according to the specificities of the users' preferences; and (iii) our approach outperforms state-of-the-art methods in MO-RS.
Successive interference cancellation (SIC) receiver is adopted by power domain non-orthogonal multiple access (NOMA) at the receiver side as the baseline receiver scheme taking the forthcoming expected mobile device evolution into account. Development technologies and advanced techniques are boldly being considered in order to achieve power saving in many networks, to reach sustainability and reliability in communication due to envisioned huge amount of data delivery. In this paper, we propose a novel scheme of NOMA-SIC for the sake of balancing the trade-off between system performance and complexity. In the proposed scheme, each SIC level is comprised by a matching filter (MF), a MF detector and a regenerator. In simulations, the proposed scheme demonstrates the best performance on power saving, of which energy efficiency increases with an increase in the number of NOMA device pairs.
Collaborative filtering (CF) has made it possible to build personalized recommendation models leveraging the collective data of large user groups, albeit with prescribed models that cannot easily leverage the existence of known behavioral models in particular settings. In this paper, we facilitate the combination of CF with existing behavioral models by introducing Bayesian Behavioral Collaborative Filtering (BBCF). BBCF works by embedding arbitrary (black-box) probabilistic models of human behavior in a latent variable Bayesian framework capable of collectively leveraging behavioral models trained on all users for personalized recommendation. There are three key advantages of BBCF compared to traditional CF and non-CF methods: (1) BBCF can leverage highly specialized behavioral models for specific CF use cases that may outperform existing generic models used in standard CF, (2) the behavioral models used in BBCF may offer enhanced intepretability and explainability compared to generic CF methods, and (3) compared to non-CF methods that would train a behavioral model per specific user and thus may suffer when individual user data is limited, BBCF leverages the data of all users thus enabling strong performance across the data availability spectrum including the near cold-start case. Experimentally, we compare BBCF to individual and global behavioral models as well as CF techniques; our evaluation domains span sequential and non-sequential tasks with a range of behavioral models for individual users, tasks, or goal-oriented behavior. Our results demonstrate that BBCF is competitive if not better than existing methods while still offering the interpretability and explainability benefits intrinsic to many behavioral models.
In-loop filtering is an important task in video coding, as it refines both the reconstructed signal for display and the pictures used for inter-prediction. In order to remove coding artifacts, machine learning based methods are assumed to be beneficial, as they utilize some prior knowledge on the characteristics of raw images. In this contribution, a dictionary learning / sparse coding based inloop filter and a frequency adaptation model based on the lp-ballenergy in the spectral domain is proposed. Thereby the dictionary is trained on raw data and the algorithms are controlled mainly by the parameter for the sparsity. The frequency adaption model results in further improvement of the sparse coding based loop filter. Experimental results show that the proposed method results in coding gains up to l-4.6 % at peak and -1.74 % on average against HEVC in a Random Access coding configuration.
This paper introduces a program for objective and subjective evaluation of speech quality. Using this environment, a lot of speech recordings and various indoor and outdoor noises were processed. As a subjective speech evaluation method, the Dynamic time warping (DTW) method was selected, with PARCOR coefficients being chosen as symptom vectors. For the filtration of the noise in the recording, adaptive filtering based on LMS and RLS algorithms was used and the performance of the adaptive filtering was assessed. Similarity ranged from 70% to 95% for both algorithms. In terms of signal to noise ratio, the RLS algorithm ranged from 36 dB to 42 dB, while the LMS algorithm only varied from 20 dB to 29 dB.
Active Noise Cancellation (ANC) is a classical area where noise in the environment is canceled by producing anti-noise signals near the human ears (e.g., in Bose's noise cancellation headphones). This paper brings IoT to active noise cancellation by combining wireless communication with acoustics. The core idea is to place an IoT device in the environment that listens to ambient sounds and forwards the sound over its wireless radio. Since wireless signals travel much faster than sound, our ear-device receives the sound in advance of its actual arrival. This serves as a glimpse into the future, that we call lookahead, and proves crucial for real-time noise cancellation, especially for unpredictable, wide-band sounds like music and speech. Using custom IoT hardware, as well as lookahead-aware cancellation algorithms, we demonstrate MUTE, a fully functional noise cancellation prototype that outperforms Bose's latest ANC headphone. Importantly, our design does not need to block the ear - the ear canal remains open, making it comfortable (and healthier) for continuous use.
This paper proposes a multi-channel linear prediction (MCLP) speech dereverberation algorithm based on QR-decomposition recursive least squares (QR-RLS) adaptive filter, which can avoid the possible instability caused by the RLS algorithm, and achieve same speech dereverberation performance as the prototype MCLP dereverberation algorithm based on RLS. This can be confirmed by the theoretical derivation and experiments. Thus, the proposed algorithm can be a good alternative for practical speech applications.
This paper presents the enhancement of speech signals in a noisy environment by using a Two-Sensor Fast Normalized Least Mean Square adaptive algorithm combined with the backward blind source separation structure. A comparative study with other competitive algorithms shows the superiority of the proposed algorithm in terms of various objective criteria such as the segmental signal to noise ratio (SegSNR), the cepstral distance (CD), the system mismatch (SM) and the segmental mean square error (SegMSE).
Route planner systems support commuters and city visitors in finding the best route between two arbitrary points. More advanced route planners integrate different transportation modes such as private transport, public transport, car- and bicycle sharing or walking and are able combine these to multi-modal routes. Nevertheless, state-of-the-art planner systems usually do not consider the users' personal preferences or the wisdom of the crowd when suggesting multi-modal routes. Including the knowledge and experience of locals who are familiar with local transport allows identification of alternative routes which are, for example, less crowded during peak hours. Collaborative filtering (CF) is a technique that allows recommending items such as multi-modal routes based on the ratings of users with similar preferences. In this paper, we introduce RouteMe, a mobile recommender system for personalized, multi-modal routes which combines CF with knowledge-based recommendations to increase the quality of route recommendations. We present our hybrid algorithm in detail and show how we integrate it in a working prototype. The results of a user study show that our prototype combining CF, knowledge-based and popular route recommendations outperforms state-of-the-art route planners.
Approximate Computing aims at trading off computational accuracy against improvements regarding performance, resource utilization and power consumption by making use of the capability of many applications to tolerate a certain loss of quality. A key issue is the dependency of the impact of approximation on the input data as well as user preferences and environmental conditions. In this context, we therefore investigate the concept of self-adaptive image processing that is able to autonomously adapt 2D-convolution filter operators of different accuracy degrees by means of partial reconfiguration on Field-Programmable-Gate-Arrays (FPGAs). Experimental evaluation shows that the dynamic system is able to better exploit a given error tolerance than any static approximation technique due to its responsiveness to changes in input data. Additionally, it provides a user control knob to select the desired output quality via the metric threshold at runtime.
This paper introduces an efficient and robust method that segments long motion capture data into distinct behaviors. The method is unsupervised, and is fully automatic. We first apply spectral clustering on motion affinity matrix to get a rough segmentation. We combined two statistical filters to remove the noises and get a good initial guess on the cut points as well as on the number of segments. Then, we analyzed joint usage information within each rough segment and recomputed an adaptive affinity matrix for the motion. Applying spectral clustering again on this adaptive affinity matrix produced a robust and accurate segmentation compared with the ground-truth. The experiments showed that the proposed approach outperformed the available methods on the CMU Mocap database.
Though the GNSS receiver baseband signal processing realizes more precise estimation by using Kalman Filter, traditional KF-based tracking loops estimate code phase and carrier frequency simultaneously by a single filter. In this case, the error of code phase estimate can affect the carrier frequency tracking loop, which is vulnerable than code tracking loop. This paper presents a tracking architecture based on dual filter. Filters can performing code locking and carrier tracking respectively, hence, the whole tracking loop ultimately avoid carrier tracking being subjected to code tracking errors. The control system is derived according to the mathematical expression of the Kalman system. Based on this model, the transfer function and equivalent noise bandwidth are derived in detail. As a result, the relationship between equivalent noise bandwidth and Kalman gain is presented. Owing to this relationship, the equivalent noise bandwidth for a well-designed tracking loop can adjust automatically with the change of environments. Finally, simulation and performance analysis for this novel architecture are presented. The simulation results show that dual Kalman filters can restrain phase noise more effectively than the loop filter of the classical GNSS tracking channel, therefore this whole system seems more suitable to working in harsh environments.
Visual Tracking methods based on particle filter framework uses frequently the state space information of the target object to calculate the observation model, However this often gives a poor estimate if unexpected motions happen, or under conditions of cluttered backgrounds illumination changes, because the model explores the state space without any additional information of current state. In order to avoid the tracking failure, we address in this paper, Particle filter based visual tracking, in which the target appearance model is represented through an adaptive conjunction of color histogram, and space based appearance combining with velocity parameters, then the appearance models is estimated using particles whose weights, are incrementally updated for dynamic adaptation of the cue parametrization.
Recommender systems are typically evaluated on their ability to provide items that satisfy the needs and interests of the end user. However, in many real world applications, users are not the only stakeholders involved. There may be a variety of individuals or organizations that benefit in different ways from the delivery of recommendations. In this paper, we re-define the recommender system as a multistakeholder environment in which different stakeholders are served by delivering recommendations, and we suggest a utility-based approach to evaluating recommendations in such an environment that is capable of distinguishing among the distributions of utility delivered to different stakeholders.
Long-term tracking is one of the most challenging problems in computer vision. During long-term tracking, the target object may suffer from scale changes, illumination changes, heavy occlusions, out-of-view, etc. Most existing tracking methods fail to handle object invisibility, supposing that the object is always visible throughout the image sequence. In this paper, a novel long-term tracking method is proposed, which mainly addresses the problem of object invisibility. We combine a correlation filter based tracker with an online classifier, aiming to estimate the object state and re-detect the object after its invisibility. In addition, an adaptive updating scheme is proposed for the appearance model of the object considering both visible and invisible situations. Quantitative and qualitative evaluations prove that our algorithm outperforms the state-of-the-art methods on the 20 benchmark sequences with object invisibility. Furthermore, the proposed algorithm achieves competitive performance with the state-of-the-art trackers on Object Tracking Benchmark which covers various challenging aspects in object tracking.
Information shared on Twitter is ever increasing and users-recipients are overwhelmed by the number of tweets they receive, many of which of no interest. Filters that estimate the interest of each incoming post can alleviate this problem, for example by allowing users to sort incoming posts by predicted interest (e.g., "top stories" vs. "most recent" in Facebook). Global and personal filters have been used to detect interesting posts in social networks. Global filters are trained on large collections of posts and reactions to posts (e.g., retweets), aiming to predict how interesting a post is for a broad audience. In contrast, personal filters are trained on posts received by a particular user and the reactions of the particular user. Personal filters can provide recommendations tailored to a particular user's interests, which may not coincide with the interests of the majority of users that global filters are trained to predict. On the other hand, global filters are typically trained on much larger datasets compared to personal filters. Hence, global filters may work better in practice, especially with new users, for which personal filters may have very few training instances ("cold start" problem). Following Uysal and Croft, we devised a hybrid approach that combines the strengths of both global and personal filters. As in global filters, we train a single system on a large, multi-user collection of tweets. Each tweet, however, is represented as a feature vector with a number of user-specific features.
We address the problem of object tracking in an underwater acoustic sensor network in which distributed nodes measure the strength of field generated by moving objects, encode the measurements into digital data packets, and transmit the packets to a fusion center in a random access manner. We allow for imperfect communication links, where information packets may be lost due to noise and collisions. The packets that are received correctly are used to estimate the objects' trajectories by employing an extended Kalman Filter, where provisions are made to accommodate a randomly changing number of obseravtions in each iteration. An adaptive rate control scheme is additionally applied to instruct the sensor nodes on how to adjust their transmission rate so as to improve the location estimation accuracy and the energy efficiency of the system. By focusing explicitly on the objects' locations, rather than working with a pre-specified grid of potential locations, we resolve the spatial quantization issues associated with sparse identification methods. Finally, we extend the method to address the possibility of objects entering and departing the observation area, thus improving the scalability of the system and relaxing the requirement for accurate knowledge of the objects' initial locations. Performance is analyzed in terms of the mean-squared localization error and the trade-offs imposed by the limited communication bandwidth.
This paper presents a quantitative study of adaptive filtering to cancel the EMG artifact from ECG signals. The proposed adaptive algorithm operates in real time; it adjusts its coefficients simultaneously with signals acquisition minimizing a cost function, the summation of weighted least square errors (LSE). The obtained results prove the success and the effectiveness of the proposed algorithm. The best ones were obtained for the forgetting factor equals to 0.99 and the regularization parameter equals to 0.02..
We present a gradient-based attack against SVM-based forensic techniques relying on high-dimensional SPAM features. As opposed to prior work, the attack works directly in the pixel domain even if the relationship between pixel values and SPAM features can not be inverted. The proposed method relies on the estimation of the gradient of the SVM output with respect to pixel values, however it departs from gradient descent methodology due to the necessity of preserving the integer nature of pixels and to reduce the effect of the attack on image quality. A fast algorithm to estimate the gradient is also introduced to reduce the complexity of the attack. We tested the proposed attack against SVM detection of histogram stretching, adaptive histogram equalization and median filtering. In all cases the attack succeeded in inducing a decision error with a very limited distortion, the PSNR between the original and the attacked images ranging from 50 to 70 dBs. The attack is also effective in the case of attacks with Limited Knowledge (LK) when the SVM used by the attacker is trained on a different dataset with respect to that used by the analyst.
Visual object tracking is challenging when the object appearances occur significant changes, such as scale change, background clutter, occlusion, and so on. In this paper, we crop different sizes of multiscale templates around object and input these multiscale templates into network to pretrain the network adaptive the size change of tracking object. Different from previous the tracking method based on deep convolutional neural network (CNN), we exploit deep Residual Network (ResNet) to offline train a multiscale object appearance model on the ImageNet, and then the features from pretrained network are transferred into tracking tasks. Meanwhile, the proposed method combines the multilayer convolutional features, it is robust to disturbance, scale change, and occlusion. In addition, we fuse multiscale search strategy into three kernelized correlation filter, which strengthens the ability of adaptive scale change of object. Unlike the previous methods, we directly learn object appearance change by integrating multiscale templates into the ResNet. We compared our method with other CNN-based or correlation filter tracking methods, the experimental results show that our tracking method is superior to the existing state-of-the-art tracking method on Object Tracking Benchmark (OTB-2015) and Visual Object Tracking Benchmark (VOT-2015).