Integrating　haptic　feedback　with　audio　and　video　not　only　expands　the　perceptual　dimensions　of　multimedia　applications　but　also　enhances　user　engagement　and　experience.　However,　higher　signal　sampling　rates　and　multi-degree-freedom　in　haptic　interaction　increase　data　significantly.　For　low-latency　and　reliable　transmission　of　haptic　signal　(i.e.　tactile　and　kinesthetic　signals),　efficient　haptic　coding　is　crucial.　Existing　algorithms　overlook　haptic　signal　characteristics,　leaving　room　for　improvement.　We　analyze　the　statistical　characteristics　of　kinesthetic　signals　in-depth.　Based　on　the　local　linear　characteristics　of　position　and　velocity　signals,　and　the　sparse　distribution　of　force　signal,　we　propose　an　improved　kinesthetic　coding　algorithm　by　combining　dead-zone　coding　with　segmented　linear　prediction.　Extensive　experiments　on　the　standard　datasets　of　the　IEEE　P1918.1.1　Haptic　Codecs　Task　Group　demonstrate　the　superior　performance　compared　to　state-of-the-art　methods,　achieving　a　more　than　halved　reduction　in　data　transmission　rates　with　high　signal-to-noise　ratios　and　structural　similarity.　©　1994-2012　IEEE.