Autonomous vehicles (AVs) are gaining in popularity over the years as a viable cab service apps as well as for personal use. However, incidents of crashes involving AVs continue to occur, adversely affecting their prospects for widespread acceptance by both end users and regulatory authorities. While such cases are routinely investigated, in the absence of a human to testify on what caused the crash, one has to rely solely on available data. It is therefore imperative that the data logged by AVs is accessible to the concerned parties in a trustworthy manner. In this paper, we present AVChain—a novel framework for using a permissioned blockchain like HyperLedger Fabric (HLF) to record and share AV data comprised of sensors, actuators, maps, planning algorithms and machine learning models so that the data stays immutable even in the face of cross blaming among involved parties. Since the data volume is extremely large, we appropriately compress and down sample the same before storing in a distributed file system, namely, IPFS (Inter-Planetary File System). The hashes of such IPFS data called Content Ids (CIDs) are committed to the HLF network for making them tamper proof. The HLF ledger can later be queried to obtain the CIDs, which are then further used to retrieve and un-compress the original data from IPFS. Effectiveness and usability of AVChain is demonstrated by generating AV data from CARLA, which is a widely used open source AV simulator. For sharing AV data across organizations like sensor and actuator suppliers, map service providers, machine learning model developers and law enforcement authorities, the Weaver tool has been used to make multiple HLF networks interoperate. We have also developed a web application to demonstrate the working of AVChain. Results of an extensive set of experiments establish the efficacy of our approach.

Blockchain interoperability is increasingly recognized as the centerpiece for robust interactions among decentralized services. Blockchain ledgers are generally tamper-proof and thus enforce non-repudiation for transactions recorded within the same network. However, such a guarantee does not hold for cross blockchain transactions. When disruptions occur due to malicious activities or system failures within one blockchain network, foreign networks can take advantage by denying legitimate claims or mounting fraudulent liabilities against the defenseless network. In response, this paper introduces InterSnap, a novel blockchain snapshot archival methodology, for enabling auditability of cross blockchain transactions, enforcing non-repudiation. InterSnap introduces cross-chain transaction receipts that ensure their irrefutability. Snapshots of ledger data along with these receipts are utilized as non-repudiable proof of bilateral agreements among different networks. InterSnap enhances system resilience through a distributed snapshot generation process, need-based snapshot scheduling process, and archival storage and sharing via decentralized platforms. Through a prototype implementation based on Hyperledger Fabric, we conducted experiments using on-premise machines, AWS public cloud instances, as well as a private cloud infrastructure. We establish that InterSnap can recover from malicious attacks while preserving cross chain transaction receipts. Additionally, our proposed solution demonstrates adaptability to increasing loads while securely transferring snapshot archives with minimal overhead.

The concept of a decentralized web has been realized with the idea of Web 3.0 through interconnecting over multiple blockchain-based networks. However, blockchain incurs significant time and space overhead. This problem can be solved using snapshots that store the blockchain’s states compactly. But, the existing snapshot mechanism used in Hyperledger Fabric is limited to siloed operations on a single blockchain only. In this paper, we contribute towards overcoming this drawback by developing a novel mechanism for peer selection, snapshot archival, and cross-blockchain sharing of the snapshot. We extend the snapshot collection mechanism in Hyperledger Fabric to implement the above idea and test it over two blockchain networks emulating a decentralized web architecture.

Mobile devices with touch capabilities often utilize touchscreen keyboards. However, due to the lack of tactile feedback, users often have to switch their focus of attention between the keyboard area, where they must locate and click the correct keys, and the text area, where they must verify the typed output. This can impair user experience and performance. In this paper, we examine multimodal feedback and guidance signals that keep users' focus of attention in the keyboard area but also provide the kind of information users would normally receive in the text area. We evaluated whether combinations of multimodal signals could improve typing performance in a controlled experiment. One combination reduced keystrokes-per-character by 8% and correction backspaces by 28%.

This article introduces the systemic-structural activity (SSA) approach to modeling user performance on human-computer interaction tasks. The human operator's eye and computer mouse movements were analyzed, and their interrelationship was investigated in the framework of the SSA theory. A new method of eye movement interpretation is presented. Procedures for development of predictive design models of human performance are also suggested. These design models can be developed based on either purely analytical procedures or a combination of analytical procedures and abbreviated experimental studies. Developed models are task specific and are described in terms of human actions and operations, rather than in terms of the internal cognitive architecture. The design process is considered in terms of stages of the sequential refinement of designed models.