Image deformations caused by different steganographic methods are typically extremely small and highly similar, which makes their detection and identification to be a difficult task. Although recent steganalytic methods using deep learning have achieved high accuracy, they have been made to detect stego images to which specific steganographic methods have been applied. In this letter, a staganalytic method is proposed that uses hierarchical residual neural networks (ResNet), allowing detection (i.e. classification between stego and cover images) and identification of four spatial steganographic methods (i.e. LSB, PVD, WOW and S-UNIWARD). Experimental results show that using hierarchical ResNets achieves a classification rate of 79.71% in quinary classification, which is approximately 23% higher compared to using a plain convolutional neural network (CNN).

Incident ticket classification plays an important role in the complex system maintenance. However, low classification accuracy will result in high maintenance costs. To solve this issue, this paper proposes a fuzzy output support vector machine (FOSVM) based incident ticket classification approach, which can be implemented in the context of both two-class SVMs and multi-class SVMs such as one-versus-one and one-versus-rest. Our purpose is to solve the unclassifiable regions of multi-class SVMs to output reliable and robust results by more fine-grained analysis. Experiments on both benchmark data sets and real-world ticket data demonstrate that our method has better performance than commonly used multi-class SVM and fuzzy SVM methods.

Review rating prediction is an important problem in machine learning and data mining areas and has attracted much attention in recent years. Most existing methods for review rating prediction on Location-Based Social Networks only capture the semantics of texts, but ignore user information (social links, geolocations, etc.), which makes them less personalized and brings down the prediction accuracy. For example, a user's visit to a venue may be influenced by their friends' suggestions or the travel distance to the venue. To address this problem, we develop a review rating prediction framework named TSG by utilizing users' review Text, Social links and the Geolocation information with machine learning techniques. Experimental results demonstrate the effectiveness of the framework.

Transfer boosting, a branch of instance-based transfer learning, is a commonly adopted transfer learning method. However, currently popular transfer boosting methods focus on binary classification problems even though there are many multi-classification tasks in practice. In this paper, we developed a new algorithm called MultiTransferBoost on the basis of TransferBoost for multi-classification. MultiTransferBoost firstly separated the multi-classification problem into several orthogonal binary classification problems. During each iteration, MultiTransferBoost boosted weighted instances from different source domains while each instance's weight was assigned and updated by evaluating the difficulty of the instance being correctly classified and the “transferability” of the instance's corresponding source domain to the target. The updating process repeated until it reached the predefined training error or iteration number. The weight update factors, which were analyzed and adjusted to minimize the Hamming loss of the output coding, strengthened the connections among the sub binary problems during each iteration. Experimental results demonstrated that MultiTransferBoost had better classification performance and less computational burden than existing instance-based algorithms using the One-Against-One (OAO) strategy.

This paper considers the problem of contention resolution algorithm for multi-class with quality of service (QoS) constrained for wireless communication. Five different channel reservation schemes are proposed, namely, UNI+MLA, UNI+DS, UNI+DS+MLA, Partial UNI and Partial UNI+MLA schemes for multimedia traffic, all are extensions of our recently proposed UNI scheme for single-class traffic. The goal is to achieve the highest system performance and enable each traffic type to meet its QoS requirements. We evaluate the performance of each scheme by mathematical analysis. The numerical results show that our proposed schemes are effective in enabling each traffic type to achieve the best successful rate possible in this kind of environment. Finally when comparing between our proposed schemes and conventional technique in terms of both throughput performance and QoS requirements it is found that the UNI+MLA, UNI+DS+MLA and Partial UNI+MLA schemes are relatively efficient and suitable for practical applications.

The Erlang capacity of multi-service multi-access systems supporting several different radio access technologies was analyzed and compared according to two different operation methods: the separate and common operation methods, by simultaneously considering the link capacity limit per sector as well as channel element (CE) limit in a base station (BS). In a numerical example with GSM-like and WCDMA-like sub-systems, it is shown that we can get up to 60% Erlang capacity improvement through the common operation method using a near optimum so-called service-based user assignment scheme when there is no CE limit in BS. Even with the worst-case assignment scheme, we can still get about 15% capacity improvement over the separate operation method. However, a limited number of CEs in BS reduces the capacity gains of multi-service multi-access systems in both the common operation and separate operation. In order to fully extract the Erlang capacity of multi-service multi-access systems, an efficient method is needed in order to select a proper number of CE in BS while minimizing the equipment cost.

In the adaptive modulation and coding (AMC)-based orthogonal frequency division multiple access (OFDMA) system for broadband wireless service, a large number of users with short packets cause a serious capacity mismatch problem, which incurs resource under-utilization when the data rate of subchannel increases with a better channel condition. To handle the capacity mismatch problem, we propose an AMC-based subchannel multiplexing (ASM) scheme, which allows for sharing the same subchannel among the different simultaneous flows of the same user. Along with the ASM scheme, we also consider multi-class scheduling scheme, which employs the different packet scheduling algorithm for the different service class, e.g., packet loss rate-based (PLR) scheduling algorithm for real-time (RT) service and modified minimum bit rate-based (MMBR) scheduling algorithm for non-real-time (NRT) service. In the typical integrated service scenario with voice, video, and data traffic, we have shown that the proposed schemes significantly improve the overall system capacity.

The classification time required by conventional multi-class SVMs greatly increases as the number of pattern classes increases. This is due to the fact that the needed set of binary class SVMs gets quite large. In this paper, we propose a method to reduce the number of classes by using nearest neighbor rule (NNR) in the principle component analysis and linear discriminant analysis (PCA+LDA) feature subspace. The proposed method reduces the number of face classes by selecting a few classes closest to the test data projected in the PCA+LDA feature subspace. Results of experiment show that our proposed method has a lower error rate than nearest neighbor classification (NNC) method. Though our error rate is comparable to the conventional multi-class SVMs, the classification process of our method is much faster.

In this paper, we propose a Distributed Request based CDMA Reservation ALOHA protocol to support multi-class services, such as voice, data, and videophone services, efficiently in multi-rate transmission cellular systems. The proposed protocol introduces a frame structure composed of an access slot and an transmission slot and an adaptive access permission probability based on the estimated number of contending users for each service, in order to control MAI by limiting the access to slots. It can provide voice service without the voice packet dropping probability through the proposed code assignment scheme, unlike other CDMA/PRMA protocols. The code reservation is allowed for voice and videophone services. The low-rate data service basically uses the remaining codes among the codes reserved for the voice service, but it can also use the codes already assigned to voice calls during the their silent periods to utilize codes efficiently. On the other hand, the high-rate data service uses the codes reserved for itself and the remaining codes among the codes reserved for the videophone service. Using the analytic method based on the Markov-chain subsystem model for each service including the handoff calls in uplink cellular systems, we show that the proposed protocol can guarantee the constant GoS for the handoff calls even with a large number of contending users through the proposed code assignment scheme and the access permission probability. Also, we show that the data services are integrated efficiently on the multi-rate transmission environment.

Most of the QoS-based routing schemes proposed so far focus on improving the performance of individual service classes. In a multi-class network where high priority QoS traffic coexists with best-effort traffic, routing decision for QoS sessions will have an effect on lower ones. A mechanism that allows dynamic sharing of link resources among multiple classes of traffic is needed. In this paper we propose a multi-class routing algorithm based on inter-class sharing resources among multiple class of traffic. Our algorithm is based on the concept of "the virtual residual bandwidth," which is derived from the real residual bandwidth. The virtual residual bandwidth is greater than the residual bandwidth when the load of lower priority traffic is light, and smaller when the load of lower priority traffic is heavy. The idea of our approach is simple since the routing algorithm for individual traffic doesn't change, but the only change is the definition of the link cost. We demonstrate through some extensive simulations the effectiveness of our approach when the best effort distribution is uneven and when its load is heavy. Also better performance is noticed when using topology with large number of alternative paths.

We propose a call admission control (CAC) scheme for the reverse link of direct sequence-code division multiple access (DS-CDMA) systems with multi-class traffic, in which the admissibility of the set of requested channels is decided by checking the outage probability of the total composite power at a cell-site receiver. The reverse link capacities under various traffic conditions are evaluated. From numerical results, we see that the proposed scheme can utilize a given radio resource more effectively as compared with the existing scheme using constraints on the individual power levels.