Electronic nose (E-nose) plays an important role in the detection of Chinese baijiu, which is an alcoholic beverage of high reputation. However, traditional e-nose data processing relies on manual selection of features with complicated preprocessing steps. The production process of baijiu with the same flavor is similar, but due to the limited number of sensors, it is not easy to quickly extract specific features with e-nose. To overcome this shortcoming, we propose a novel method based on Channel Attention Convolutional Neural Network (CA-CNN) for authenticity identification of Chinese baijiu. The underlying channel attention module analyzes the dependencies between channels and learning weights in order to improve the detection accuracy. In particular, we evaluated the comprehensive performance of the system by comparing it with traditional machine learning methods. The prediction accuracy of the CA-CNN (98.53%) is better than the back-propagation artificial neural network (BP-ANN) (90.83%), the support vector machine (SVM) (84.5%), and the random forest (RF) (86.867%). The experiment results show that the CA-CNN has reasonable reliability, stability and good prediction performance in the quality classification of Chinese baijiu. It provides an effective reference method for the standardization of baijiu quality inspection.

Odor descriptors are words used to express human olfactory perception. At a certain level, predicting the odor descriptor rating using an electronic nose(E-nose) equips the machine with the ability to perceive odors. In this paper, we propose a novel deep learning framework for predicting odor descriptor rating via E-nose signals. The proposed framework has multiple sibling neural networks, including a Convolutional LSTM(ConvLSTM) layer and a regression layer. The ConvLSTM layers are used to learn the spatiotemporal features from sensor signal. On the one hand, it effectively extracts the temporal features of the signal, and on the other hand, it makes good use of the sensor dependencies. The output of the regression layer corresponds to a combination of descriptors or single descriptors, depending on their similarity. The experiment results show that: i) the framework utilizing the spatiotemporal correlation of the E-nose signal is more effective than using the temporal or spatial model alone, and that ii) the combination of descriptors based on descriptors similarity can effectively improve the prediction accuracy. On the DREAM dataset, our proposed framework outperforms the state-of-the- art methods in odor descriptor rating prediction.

In this paper, a full-stack perspective that involves content coding, caching and recommendation is presented for wireless edge caching networks. Therein, content coding and recommendations are utilized to ensure the reliability of the network and to boost the gain of edge caching, respectively. Specifically, with a well-designed coding pattern, the concurrently occurred data corruptions of multiple access points (APs) can be successfully recovered. Whilst, the successful content retrieval is warranted with highly selective retrieval sets. Further, by offering personalized recommendations, the cache hitting at network edges can be promoted. On these grounds, a cache hit ratio maximization problem for reliability-aware wireless edge caching system is formulated, considering the successful content retrieval and repair, total repair cost requirements, cache capacity budget of each AP, and recommendation quality and quantity per user. To solve this intractable problem, a framework with two steps is developed, which leads to construction of a suitable coding schema with the minimum repair cost per content to satisfy the retrieval and repair criteria, thus achieving a stabilized optimal solution regarding the joint cache placement and recommendation decisions from a game-theoretical viewpoint. Finally, extensive numerical simulations are performed to confirm the superior performance of our devised algorithms compared with benchmark baselines.

In this paper, we explore the interplay between personalized bundle recommendation and cache decision on the performance of wireless edge caching networks. A revenue maximization perspective is provided. To this end, we first examine the quantitative impact of bundle recommendation on the content request probability of different users. We then specify the definition of system revenue, showing its dependence on bundle recommendation and caching policies. With that, a joint bundling, caching and recommendation decision problem is formulated to maximize the achievable system revenue, taking into account the constraints of user-distinguished recommendation quality, recommendation amount, and the cache capacity budget. To solve this non-tractable optimization problem, a divide-then-conquer methodology is adopted. Specifically, we first determine the bundle state per user, on which basis we perform the joint bundle recommendation and caching decision-making, wherein several bundling strategies with different time-complexity are devised. Last but not least, we provide detailed properties analysis for our proposed bundling and joint optimization algorithms. Comprehensive numerical simulations validate the performance enhancement of the designed solutions compared to extensive conventional single-item recommendation oriented benchmarks.

In recent years, more machine learning algorithms have been applied to odor classification. These odor classification algorithms usually assume that the training data sets are static. However, for some odor recognition tasks, new odor classes continually emerge. That is, the odor data sets are dynamically growing while both training samples and number of classes are increasing over time. Motivated by this concern, this paper proposes a deep nearest class mean (DNCM) model based on the deep learning framework and the nearest class mean method. The proposed model not only leverages deep neural network to extract deep features but also able to dynamically integrate new classes over time. In our experiments, the DNCM model was initially trained with 10 classes, then 25 new classes are integrated. Experiment results demonstrate that the proposed model is very efficient for incremental odor classification, especially for new classes with only a small number of training examples.

As satellite communications provide ubiquitous coverage, they play a key role in providing Internet connectivity in remote or marginalized areas, so as to enable the vision of a truly global connectivity of the Internet of Things (IoT). However, these areas often lack reliable electricity supply. Thus, this paper proposes a satellite internet access point powered by solar energy, so that a stable Internet connection can be provided. The access point provides Wi-Fi coverage so that sensors, IoT, and devices can connect to the access point using the Wi-Fi, a common wireless technology. Our design took some cost-saving measures to make it affordable and selected the components that require minimal maintenance operations. The satellite access point costs about USD $500, and can provide four days of Internet connectivity without solar energy.