Comparing and experimenting machine learning techniques for code smell detection

Several code smell detection tools have been developed providing different results, because smells can be subjectively interpreted, and hence detected, in different ways. In this paper, we perform the largest experiment of applying machine learning algorithms to code smells to the best of our knowledge. We experiment 16 different machine-learning algorithms on four code smells (Data Class, Large Class, Feature Envy, Long Method) and 74 software systems, with 1986 manually validated code smell samples. We found that all algorithms achieved high performances in the cross-validation data set, yet the highest performances were obtained by J48 and Random Forest, while the worst performance were achieved by support vector machines. However, the lower prevalence of code smells, i.e., imbalanced data, in the entire data set caused varying performances that need to be addressed in the future studies. We conclude that the application of machine learning to the detection of these code smells can provide high accuracy (>96 %), and only a hundred training examples are needed to reach at least 95 % accuracy.     

Maximum density of quantum information in a scalable CMOS implementation of the hybrid qubit architecture

Scalability from single-qubit operations to multi-qubit circuits for quantum information processing requires architecture-specific implementations. Semiconductor hybrid qubit architecture is a suitable candidate to realize large-scale quantum information processing, as it combines a universal set of logic gates with fast and all-electrical manipulation of qubits. We propose an implementation of hybrid qubits, based on Si metal-oxide-semiconductor (MOS) quantum dots, compatible with the CMOS industrial technological standards. We discuss the realization of multi-qubit circuits capable of fault-tolerant computation and quantum error correction, by evaluating the time and space resources needed for their implementation. As a result, the maximum density of quantum information is extracted from a circuit including eight logical qubits encoded by the [[7, 1, 3]] Steane code. The corresponding surface density of logical qubits is 2.6 Mqubit/cm\(^2\).     

Information diffusion in distributed OSN: The impact of trusted relationships

Distributed Online Social Networks (DOSN) are a valid alternative to OSN based on peer-to-peer communications. Without centralised data management, DOSN must provide the users with higher level of control over their personal information and privacy. Thus, users may wish to restrict their personal network to a limited set of peers, depending on the level of trust with them. This means that the effective social network (used for information exchange) may be a subset of the complete social network, and may present different structural patterns, which could limit information diffusion. In this paper, we estimate the capability of DOSN to diffuse content based on trust between social peers. To have a realistic representation of a OSN friendship graph, we consider a large-scale Facebook network, from which we estimate the trust level between friends. Then, we consider only social links above a certain threshold of trust, and we analyse the potential capability of the resulting graph to spread information through several structural indices. We test four possible thresholds, coinciding with the definition of personal social circles derived from sociology and anthropology. The results show that limiting the network to “active social contacts” leads to a graph with high network connectivity, where the nodes are still well-connected to each other, thus information can potentially cover a large number of nodes with respect to the original graph. On the other hand, the coverage drops for more restrictive assumptions. Nevertheless the re-insertion of a single excluded friend for each user is sufficient to obtain good coverage (i.e., always higher than 40 %) even in the most restricted graphs. We also analyse the potential capability of the network to spread information (i.e., network spreadability), studying the properties of the social paths between any pairs of users in the graph, which represent the effective channels traversed by information. The value of contact frequency between pairs of users determines a decay of trust along the path (the higher the contact frequency the lower the decay), and a consequent decay in the level of trustworthiness of information traversing the path. We show that selecting the link to re-insert in the network with probability proportional to its level of trust is the best re-insertion strategy, as it leads to the best connectivity/spreadability combination.     

Position‐Based Skinning for Soft Articulated Characters

In this paper, we introduce a two‐layered approach addressing the problem of creating believable mesh‐based skin deformation. For each frame, the skin is first deformed with a classic linear blend skinning approach, which usually leads to unsightly artefacts such as the well‐known candy‐wrapper effect and volume loss. Then we enforce some geometric constraints which displace the positions of the vertices to mimic the behaviour of the skin and achieve effects like volume preservation and jiggling. We allow the artist to control the amount of jiggling and the area of the skin affected by it. The geometric constraints are solved using a position‐based dynamics (PBDs) schema. We employ a graph colouring algorithm for parallelizing the computation of the constraints. Being based on PBDs guarantees efficiency and real‐time performances while enduring robustness and unconditional stability. We demonstrate the visual quality and the performance of our approach with a variety of skeleton‐driven soft body characters.     

Batch sequencing and cooperation

Game theoretic analysis of sequencing situations has been restricted to manufacturing systems which consist of machines that can process only one job at a time. However, in many manufacturing systems, operations are carried out by batch machines which can simultaneously process multiple jobs. This paper aims to extend the game theoretical approach to the cost allocation problems arising from sequencing situations on systems that consist of batch machines. To analyze the allocation problem at hand, it focusses on the existence of core elements, convexity, and the Shapley value.     

Energy efficient and reliable data delivery in urban sensing applications: A performance analysis

Urban sensing is an emerging application field for Wireless Sensor Networks (WSNs), where a number of static sensors is sparsely deployed in an urban area to collect environmental information. Data sensed by each sensor are, then, opportunistically transmitted to Mobile Nodes (MNs) that happen to be in contact. In the considered scenario, communications between MNs and sensors require paradigms with a minimal synchronization between devices, extremely fast and energy efficient, especially at the sensor side. To deal with the above issues, in [1] we proposed a hybrid protocol for data delivery from sensors to MNs, named Hybrid Adaptive Interleaved Data Protocol (HI). By combining Erasure Coding (EC) with an Automatic Repeat reQuest (ARQ) scheme, the proposed protocol maximizes the reliability of communications while minimizing the energy consumed by sensors. In this paper, we present an in-depth analysis of the HI performance. We provide an analytical evaluation by defining a flexible model to derive the probability of data delivery and exploiting it to investigate the performance over a wide range of parameters. Moreover, we perform an experimental study to evaluate the HI effectiveness on real sensor platforms. Specifically, we analyze the impact of resource constraints imposed by sensors on data delivery and provide a careful characterization of its actual consumption of resources.     

NetCluster: A clustering-based framework to analyze internet passive measurements data

Internet measured data collected via passive measurement are analyzed to obtain localization information on nodes by clustering (i.e., grouping together) nodes that exhibit similar network path properties. Since traditional clustering algorithms fail to correctly identify clusters of homogeneous nodes, we propose the NetCluster novel framework, suited to analyze Internet measurement datasets. We show that the proposed framework correctly analyzes synthetically generated traces. Finally, we apply it to real traces collected at the access link of Politecnico di Torino campus LAN and discuss the network characteristics as seen at the vantage point.     

Titans’ revenge: Detecting Zeus via its own flaws

Malware is one of the main threats to the Internet security in general, and to commercial transactions in particular. However, given the high level of sophistication reached by malware (e.g. usage of encrypted payload and obfuscation techniques), malware detection tools and techniques still call for effective and efficient solutions. In this paper, we address a specific, dreadful, and widely diffused financial malware: Zeus.The contributions of this paper are manifold: first, we propose a technique to break the encrypted malware communications, extracting the keystream used to encrypt such communications; second, we provide a generalization of the proposed keystream extraction technique. Further, we propose Cronus, an IDS that specifically targets Zeus malware. The implementation of Cronus has been experimentally tested on a production network, and its high quality performance and effectiveness are discussed. Finally, we highlight some principles underlying malware—and Zeus in particular—that could pave the way for further investigation in this field.