Psychotherapy is crucial for managing cue-induced cravings. However, most research has focused on explicit drug cues that elicit intense cravings, and recreating such high-risk scenarios in practice can inadvertently heighten cravings afterward, making these approaches impractical or ethically problematic in real-world settings. To address this, we developed a cue-exposure technology probe system, VirtualCravingProbe, which integrates VR simulations with real-time biofeedback to enhance self-awareness in clinical drug psychotherapy. We conducted an exploratory study with twelve patients recovering from methamphetamine addiction using the VirtualCravingProbe system, generating design guidelines for future iterations of an integrated VR and biofeedback-assisted therapy tool. Results revealed qualitative evidence that real-time heart-rate monitoring in VR heightened patients’ awareness of triggers and their craving responses. These findings align with the CBT cognitive-triangle framework, which emphasizes the interplay of thoughts, emotions, and behaviors. Moreover, the system demonstrated potential to enrich patient–therapist dialogue and support the adoption of effective coping strategies.

Inflammation of the long head of the biceps tendon is a common cause of shoulder pain. Bicipital peritendinous effusion (BPE) is the most common biceps tendon abnormality and is related to various shoulder injuries. Physicians usually use ultrasound imaging to grade the inflammation severity of the long head of the biceps tendon. However, obtaining a clear and accurate ultrasound image is difficult for inexperienced attending physicians. To reduce physicians' workload and avoid errors, an automated BPE recognition system was developed in this article for classifying inflammation into the following categories-normal and mild, moderate, and severe. An ultrasound image serves as the input in the proposed system; the system determines whether the ultrasound image contains biceps. If the image depicts biceps, then the system predicts BPE severity. In this study, two crucial methods were used for solving problems associated with computer-aided detection. First, the faster regions with convolutional neural network (faster R-CNN) used to extract the region of interest (ROI) area identification to evaluate the influence of dataset scale and spatial image context on performance. Second, various CNN architectures were evaluated and explored. Model performance was analyzed by using various network configurations, parameters, and training sample sizes. The proposed system was used for three-class BPE classification and achieved 75% accuracy. The results obtained for the proposed system were determined to be comparable to those of other related state-of-the-art methods.

Airborne light detection and ranging (LiDAR) technology is an active remote sensing technique that produces a true orthophoto at a single wavelength. LiDAR is not as dependent on the weather as optical sensors, and LiDAR features have been widely applied for characterizing land cover classes of interest. Instead of using point-based features for classification, object-based LiDAR features were employed in this study. In addition, instead of directly mining a data set with large numerical attributes, a preprocessing step, known as data discretization, was applied before data mining. The results show that although original data are simplified, mining results are concise, more meaningful and easy-to-interpret. In this way, the accuracy of land cover classification can be further improved.

The information and communication technologies (ICT) integrate different types of wireless communication to provide IT-enabled services and applications. The great majority end devices are equipped with multiple network interfaces such as Wi-Fi and 4G. Our goal is to integrate the available network interfaces and technologies to enhance seamless communication efficiency and increase resources utilization. We proposed a heterogeneous network management algorithm which includes roaming and sharing functions. The roaming function provides the multiple network resources in physical and media access control layers. The sharing function supports multiple network resources allocation and the service handover process based on the Multipath TCP protocol. The simulation result also shows that the proposed scheme can increase the network bandwidth utilization effectively. The sharing system could be used in home, mobile and vehicular environments to realize ubiquitous social sharing networks.

A common scenario considered in recommender systems is to predict a user's preferences on unseen items based on his/her preferences on observed items. A major limitation of this scenario is that a user might be interested in different things each time when using the system, but there is no way to allow the user to actively alter or adjust the recommended results. To address this issue, we propose the idea of "query-based recommendation" that allows a user to specify his/her search intention while exploring new items, thereby incorporating the concept of information retrieval into recommendation systems. Moreover, the idea is more desirable when the user intention can be expressed in different ways. Take music recommendation as an example: the proposed system allows a user to explore new song tracks by specifying either a track, an album, or an artist. To enable such heterogeneous queries in a recommender system, we present a novel technique called "Heterogeneous Preference Embedding" to encode user preference and query intention into low-dimensional vector spaces. Then, with simple search methods or similarity calculations, we can use the encoded representation of queries to generate recommendations. This method is fairly flexible and it is easy to add other types of information when available. Evaluations on three music listening datasets confirm the effectiveness of the proposed method over the state-of-the-art matrix factorization and network embedding methods.

The cold start problem arises in various recommendation applications. In this paper, we propose a tensor factorization-based algorithm that exploits content features extracted from music audio to deal with the cold start problem for the emerging application next-song recommendation. Specifically, the new algorithm learns sequential behavior to predict the next song that a user would be interested in based on the last song the user just listened to. A unique characteristic of the algorithm is that it learns and updates the mapping between the audio feature space and the item latent space each time during the iterations of the factorization process. This way, the content features can be better exploited in forming the latent features for both users and items, leading to more effective solutions for cold-start recommendation. Evaluation on a large-scale music recommendation dataset shows that the recommendation result of the proposed algorithm exhibits not only higher accuracy but also better novelty and diversity, suggesting its applicability in helping a user explore new items in next-item recommendation. Our implementation is available at https://github.com/fearofchou/ALMM.

Evaluation is important to assess the performance of a computer system in fulfilling a certain user need. In the context of recommendation, researchers usually evaluate the performance of a recommender system by holding out a random subset of observed ratings and calculating the accuracy of the system in reproducing such ratings. This evaluation strategy, however, does not consider the fact that in a real-world setting we are actually given the observed ratings of the past and have to predict for the future. There might be new songs, which create the cold-start problem, and the users' musical preference might change over time. Moreover, the user satisfaction of a recommender system may be related to factors other than accuracy. In light of these observations, we propose in this paper a novel evaluation framework that uses various time-based data splitting methods and evaluation metrics to assess the performance of recommender systems. Using millions of listening records collected from a commercial music streaming service, we compare the performance of collaborative filtering (CF) and content-based (CB) models with low-level audio features and semantic audio descriptors. Our evaluation shows that the CB model with semantic descriptors obtains a better trade-off among accuracy, novelty, diversity, freshness and popularity, and can nicely deal with the cold-start problems of new songs.

The use of multisource data in remote sensing image classification has become increasingly popular. Although additional features incorporated could improve classification accuracy, the amount of relevant information may induce interclass confusion. Feature selection plays an important role in image analysis process. This study investigates feature space optimization in the use of multispectral UltraCAM xp imagery and full waveform Riegl LMS 680i lidar data. Meaningful features are based on similar spectral or spatial properties.

Singing voice plays an important role in the listening experience of music. In this paper, we propose to classify popular music by the timbre quality of the singing voice. Specifically, we adopt six singing voice timbre classes as the taxonomy and build a new data set, KKTIC, that contains the expert annotations of 387 Chinese popular songs. To build an automatic classifier, we resort to signal processing and machine learning techniques and extract a number of singing voice-related features such as vibrato and harmonic-to-noise ratio. We also propose the use of vocal segment detection and singing voice separation as preprocessing steps. Our evaluation identifies the relevant acoustic features and validates the importance of these preprocessing steps. The accuracy in timbre classification reaches 79.84% in a five-fold stratified cross validation.

The online repository of music tags provides a rich source of semantic descriptions useful for training emotion-based music classifier. However, the imbalance of the online tags affects the performance of emotion classification. In this paper, we present a novel data-sampling method that eliminates the imbalance but still takes the prior probability of each emotion class into account. In addition, a two-layer emotion classification structure is proposed to harness the genre information available in the online repository of music tags. We show that genre-based grouping as a precursor greatly improves the performance of emotion classification. On the average, the incorporation of online genre tags improves the performance of emotion classification by a factor of 55% over the conventional single-layer system. The performance of our algorithm for classifying 183 emotion classes reaches 0.36 in example-based f-score.

This paper presents a novel video-based human fall detection system that can detect a human fall in real-time with a high detection rate. This fall detection system is based on an ingenious combination of skeleton feature and human shape variation, which can efficiently distinguish “fall-down” activities from “fall-like” ones. The experimental results indicate that the proposed human fall detection system can achieve a high detection rate and low false alarm rate.

Genre and emotion have been applied to content-based music retrieval and organization; however, the intrinsic correlation between them has not been explored. In this paper we present a statistical association analysis to examine such intrinsic correlation and propose a two-layer scheme that exploits the correlation for emotion classification. Significant improvement of classification accuracy over the traditional single-layer scheme is obtained.

Clustering for better representation of the diversity of text or image search results has been studied extensively. In this paper, we extend this methodology to the novel domain of music search. We conduct empirical evaluation of different clustering algorithms, audio feature representations, and the incorporation of lyrics for music clustering. Our evaluation shows the fusion of audio and text features yields the best clustering accuracy.

In this paper, we present a multimodal approach to structure segmentation of music with applications to audio content analysis and music information retrieval. In particular, since lyrics contain rich information about the semantic structure of a song, our approach incorporates lyrics to overcome the existing difficulties associated with large acoustic variation in music. We further design a constrained clustering algorithm for music segmentation and evaluate its performance on commercial recordings. Experimental results show that our method can effectively detect the boundaries and the types of semantic structure of music segments.

In recent years, there has been a dramatic proliferation of research on information retrieval based on highly subjective concepts such as emotion, preference and aesthetic. Such retrieval methods are fascinating but challenging since it is difficult to built a general retrieval model that performs equally well to everyone. In this paper, we propose two novel methods, bag-of-users model and residual modeling, to accommodate the individual differences for emotion-based music retrieval. The proposed methods are intuitive and generally applicable to other information retrieval tasks that involve subjective perception. Evaluation result shows the effectiveness of the proposed methods.

As one of the most important mid-level features of music, chord contains rich information of harmonic structure that is useful for music information retrieval. In this paper, we present a chord recognition system based on the N-gram model. The system is time-efficient, and its accuracy is comparable to existing systems. We further propose a new method to construct chord features for music emotion classification and evaluate its performance on commercial song recordings. Experimental results demonstrate the advantage of using chord features for music classification and retrieval.

This technical demo presents a novel emotion-based music retrieval platform, called Mr. Emo, for organizing and browsing music collections. Unlike conventional approaches which quantize emotions into classes, Mr. Emo defines emotions by two continuous variables arousal and valence and employs regression algorithms to predict them. Associated with arousal and valence values (AV values), each music sample becomes a point in the arousal-valence emotion plane, so a user can easily retrieve music samples of certain emotion(s) by specifying a point or a trajectory in the emotion plane. Being content centric and functionally powerful, such emotion-based retrieval complements traditional keyword- or artist-based retrieval. The demo shows the effectiveness and novelty of music retrieval in the emotion plane.

Content-based retrieval has emerged in the face of content explosion as a promising approach to information access. In this paper, we focus on the challenging issue of recognizing the emotion content of music signals, or music emotion recognition (MER). Specifically, we formulate MER as a regression problem to predict the arousal and valence values (AV values) of each music sample directly. Associated with the AV values, each music sample becomes a point in the arousal-valence plane, so the users can efficiently retrieve the music sample by specifying a desired point in the emotion plane. Because no categorical taxonomy is used, the regression approach is free of the ambiguity inherent to conventional categorical approaches. To improve the performance, we apply principal component analysis to reduce the correlation between arousal and valence, and RReliefF to select important features. An extensive performance study is conducted to evaluate the accuracy of the regression approach for predicting AV values. The best performance evaluated in terms of theR2statistics reaches 58.3% for arousal and 28.1% for valence by employing support vector machine as the regressor. We also apply the regression approach to detect the emotion variation within a music selection and find the prediction accuracy superior to existing works. A group-wise MER scheme is also developed to address the subjectivity issue of emotion perception.

Typical music emotion classification (MEC) approaches categorize emotions and apply pattern recognition methods to train a classifier. However, categorized emotions are too ambiguous for efficient music retrieval. In this paper, we model emotions as continuous variables composed of arousal and valence values (AV values), and formulate MEC as a regression problem. The multiple linear regression, support vector regression, and AdaBoost.RT are adopted to evaluate the prediction accuracy. Since the regression approach is inherently continuous, it is free of the ambiguity problem existing in its categorical counterparts.

A force sensor with quartz crystal resonator has the characteristic that the resonance frequency changes by the external force, which achieves high sensitivity, high-speed response, and wide range measurement by a simple structure. Also it has the superior feature in the temperature and frequency stability. On the other hand, the quartz crystal resonator had been hardly applied to a dynamic force measurement because of low degree of mechanical characteristic, that is, it is weak to the impact, bend, and tension. The objective of this study is to construct the sensor mechanism that safely maintains the quartz crystal resonator for the external force with flat structure. We designed and analyzed a novel retention mechanism of the quartz crystal resonator for the flat structure. The proposed force sensor is flat, small, and sensitive enough to be applied to several usages such as medical treatment and dynamic contact force detection of human.

In this paper we describe novel magnetically driven polymeric microtool for non-intrusive and no contamination experiments on a chip. The composite is formed by suspending magnetite particles (Fe3O4) in polydimethylsiloxane (PDMS). In order to obtain precise and complicated pattern of micromagnetic tools, a photolithography techniques has been applied by making good use of thick KMPR-1050 photoresist as sacrificed mould. The surface of the produced micromagnetic tools is specially coated in order to suppress stiction in the biochip. The novelties of these tools are (1) fabrication of any 2D shape, (2) softness (harmless to cells), (3) no contact actuation (no stiction), 4. mass production with low cost. Here we have demonstrated that the mass-produced versatile micromagnetic tools such as stirrer and valve. The potential impact of this technology includes sample selection and separation, cell immobilization, genetic operation, tracking, mixing and reaction techniques into portable microfluidic labs-on-a-chip, culture systems and cell loading system.

We propose a hybrid learning algorithm for fuzzy neural network (FNN) systems, which combining the back-propagation and the genetic algorithms. Without any pre-training, the algorithm achieves high accuracy performance. Here, we make a breakthrough of the restriction of membership function to be some specific shape (e.g., triangular form, trapezoid form and shape of bell). The membership functions of the FNN are constructed by a group of line segment and then are fine tuned by genetic algorithm (GA) for achieving the mapping accuracy. The proposed training algorithm can be described as: (a) Firstly, we construct and train the FNN using the back-propagation algorithm to obtain membership functions and consequent weight vector. (b) Membership functions with a group of line segment by partitioning and sampling themselves are constructed. Thus we can represent membership functions in a string form-chromosome for genetic algorithm (GA). (c) Finally, for every partition point, we use the GA to search the optimal value and obtain the optimal membership functions. Simulation results show that the mapping capability of the FNN trained by the proposed method is much better. In addition, the application on the fuzzy rules reduction is presented to show the effectiveness of the approach.